Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

27 files changed, 165 insertions, 143 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index f19e0989a5a..fe17b8016bc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3836,6 +3836,7 @@ NETWORKING DRIVERS
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6.git
 S:	Odd Fixes
 F:	drivers/net/
 F:	include/linux/if_*
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index f36defa3776..57d965b7f52 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -808,6 +808,7 @@ static int btmrvl_sdio_host_to_card(struct btmrvl_private *priv,
 
 exit:
 	sdio_release_host(card->func);
+	kfree(tmpbuf);
 
 	return ret;
 }
diff --git a/drivers/net/ax88796.c b/drivers/net/ax88796.c
index 62d9c9cc567..1dd4403247c 100644
--- a/drivers/net/ax88796.c
+++ b/drivers/net/ax88796.c
@@ -921,7 +921,7 @@ static int ax_probe(struct platform_device *pdev)
  		size = (res->end - res->start) + 1;
 
 		ax->mem2 = request_mem_region(res->start, size, pdev->name);
-		if (ax->mem == NULL) {
+		if (ax->mem2 == NULL) {
 			dev_err(&pdev->dev, "cannot reserve registers\n");
 			ret = -ENXIO;
 			goto exit_mem1;
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 4cf9b7962af..04820590374 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -2080,6 +2080,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 			 struct sge_fl *fl, int len, int complete)
 {
 	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
+	struct port_info *pi = netdev_priv(qs->netdev);
 	struct sk_buff *skb = NULL;
 	struct cpl_rx_pkt *cpl;
 	struct skb_frag_struct *rx_frag;
@@ -2117,11 +2118,18 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 
 	if (!nr_frags) {
 		offset = 2 + sizeof(struct cpl_rx_pkt);
-		qs->lro_va = sd->pg_chunk.va + 2;
-	}
-	len -= offset;
+		cpl = qs->lro_va = sd->pg_chunk.va + 2;
 
-	prefetch(qs->lro_va);
+		if ((pi->rx_offload & T3_RX_CSUM) &&
+		     cpl->csum_valid && cpl->csum == htons(0xffff)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++;
+		} else
+			skb->ip_summed = CHECKSUM_NONE;
+	} else
+		cpl = qs->lro_va;
+
+	len -= offset;
 
 	rx_frag += nr_frags;
 	rx_frag->page = sd->pg_chunk.page;
@@ -2137,12 +2145,8 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 		return;
 
 	skb_record_rx_queue(skb, qs - &adap->sge.qs[0]);
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	cpl = qs->lro_va;
 
 	if (unlikely(cpl->vlan_valid)) {
-		struct net_device *dev = qs->netdev;
-		struct port_info *pi = netdev_priv(dev);
 		struct vlan_group *grp = pi->vlan_grp;
 
 		if (likely(grp != NULL)) {
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 0a064ce3eb4..83cd0d7417d 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -421,6 +421,8 @@ static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector)
 			msixbm = E1000_EICR_RX_QUEUE0 << rx_queue;
 		if (tx_queue > IGB_N0_QUEUE)
 			msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue;
+		if (!adapter->msix_entries && msix_vector == 0)
+			msixbm |= E1000_EIMS_OTHER;
 		array_wr32(E1000_MSIXBM(0), msix_vector, msixbm);
 		q_vector->eims_value = msixbm;
 		break;
@@ -877,7 +879,6 @@ static int igb_request_irq(struct igb_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct pci_dev *pdev = adapter->pdev;
-	struct e1000_hw *hw = &adapter->hw;
 	int err = 0;
 
 	if (adapter->msix_entries) {
@@ -909,20 +910,7 @@ static int igb_request_irq(struct igb_adapter *adapter)
 		igb_setup_all_tx_resources(adapter);
 		igb_setup_all_rx_resources(adapter);
 	} else {
-		switch (hw->mac.type) {
-		case e1000_82575:
-			wr32(E1000_MSIXBM(0),
-			     (E1000_EICR_RX_QUEUE0 |
-			      E1000_EICR_TX_QUEUE0 |
-			      E1000_EIMS_OTHER));
-			break;
-		case e1000_82580:
-		case e1000_82576:
-			wr32(E1000_IVAR0, E1000_IVAR_VALID);
-			break;
-		default:
-			break;
-		}
+		igb_assign_vector(adapter->q_vector[0], 0);
 	}
 
 	if (adapter->flags & IGB_FLAG_HAS_MSI) {
@@ -1140,6 +1128,8 @@ int igb_up(struct igb_adapter *adapter)
 	}
 	if (adapter->msix_entries)
 		igb_configure_msix(adapter);
+	else
+		igb_assign_vector(adapter->q_vector[0], 0);
 
 	/* Clear any pending interrupts. */
 	rd32(E1000_ICR);
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index ba1ba0c5efd..63d449807d9 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -11,6 +11,8 @@ struct nf_conntrack_ecache;
 struct netns_ct {
 	atomic_t		count;
 	unsigned int		expect_count;
+	unsigned int		htable_size;
+	struct kmem_cache	*nf_conntrack_cachep;
 	struct hlist_nulls_head	*hash;
 	struct hlist_head	*expect_hash;
 	struct hlist_nulls_head	unconfirmed;
@@ -28,5 +30,6 @@ struct netns_ct {
 #endif
 	int			hash_vmalloc;
 	int			expect_vmalloc;
+	char			*slabname;
 };
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2eb3814d625..9a4b8b71407 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -40,6 +40,7 @@ struct netns_ipv4 {
 	struct xt_table		*iptable_security;
 	struct xt_table		*nat_table;
 	struct hlist_head	*nat_bysource;
+	unsigned int		nat_htable_size;
 	int			nat_vmalloced;
 #endif
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b7c4224f4e7..b10e3cdb08f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -377,6 +377,9 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8
 
 	if (acl->state == BT_CONNECTED &&
 			(sco->state == BT_OPEN || sco->state == BT_CLOSED)) {
+		acl->power_save = 1;
+		hci_conn_enter_active_mode(acl);
+
 		if (lmp_esco_capable(hdev))
 			hci_setup_sync(sco, acl->handle);
 		else
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 28517bad796..592da5c909c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1699,6 +1699,7 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu
 		break;
 
 	case 0x1c:	/* SCO interval rejected */
+	case 0x1a:	/* Unsupported Remote Feature */
 	case 0x1f:	/* Unspecified error */
 		if (conn->out && conn->attempt < 2) {
 			conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 6cf526d06e2..fc6ec1e7265 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -703,29 +703,9 @@ static void hidp_close(struct hid_device *hid)
 static int hidp_parse(struct hid_device *hid)
 {
 	struct hidp_session *session = hid->driver_data;
-	struct hidp_connadd_req *req = session->req;
-	unsigned char *buf;
-	int ret;
-
-	buf = kmalloc(req->rd_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, req->rd_data, req->rd_size)) {
-		kfree(buf);
-		return -EFAULT;
-	}
-
-	ret = hid_parse_report(session->hid, buf, req->rd_size);
-
-	kfree(buf);
-
-	if (ret)
-		return ret;
-
-	session->req = NULL;
 
-	return 0;
+	return hid_parse_report(session->hid, session->rd_data,
+			session->rd_size);
 }
 
 static int hidp_start(struct hid_device *hid)
@@ -770,12 +750,24 @@ static int hidp_setup_hid(struct hidp_session *session,
 	bdaddr_t src, dst;
 	int err;
 
+	session->rd_data = kzalloc(req->rd_size, GFP_KERNEL);
+	if (!session->rd_data)
+		return -ENOMEM;
+
+	if (copy_from_user(session->rd_data, req->rd_data, req->rd_size)) {
+		err = -EFAULT;
+		goto fault;
+	}
+	session->rd_size = req->rd_size;
+
 	hid = hid_allocate_device();
-	if (IS_ERR(hid))
-		return PTR_ERR(hid);
+	if (IS_ERR(hid)) {
+		err = PTR_ERR(hid);
+		goto fault;
+	}
 
 	session->hid = hid;
-	session->req = req;
+
 	hid->driver_data = session;
 
 	baswap(&src, &bt_sk(session->ctrl_sock->sk)->src);
@@ -806,6 +798,10 @@ failed:
 	hid_destroy_device(hid);
 	session->hid = NULL;
 
+fault:
+	kfree(session->rd_data);
+	session->rd_data = NULL;
+
 	return err;
 }
 
@@ -900,6 +896,9 @@ unlink:
 		session->hid = NULL;
 	}
 
+	kfree(session->rd_data);
+	session->rd_data = NULL;
+
 purge:
 	skb_queue_purge(&session->ctrl_transmit);
 	skb_queue_purge(&session->intr_transmit);
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index faf3d74c358..a4e215d50c1 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -154,7 +154,9 @@ struct hidp_session {
 	struct sk_buff_head ctrl_transmit;
 	struct sk_buff_head intr_transmit;
 
-	struct hidp_connadd_req *req;
+	/* Report descriptor */
+	__u8 *rd_data;
+	uint rd_size;
 };
 
 static inline void hidp_schedule(struct hidp_session *session)
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index fc5ee3296e2..89f4a59eb82 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -252,7 +252,6 @@ static void rfcomm_session_timeout(unsigned long arg)
 	BT_DBG("session %p state %ld", s, s->state);
 
 	set_bit(RFCOMM_TIMED_OUT, &s->flags);
-	rfcomm_session_put(s);
 	rfcomm_schedule(RFCOMM_SCHED_TIMEO);
 }
 
@@ -1151,7 +1150,11 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci)
 			break;
 
 		case BT_DISCONN:
-			rfcomm_session_put(s);
+			/* When socket is closed and we are not RFCOMM
+			 * initiator rfcomm_process_rx already calls
+			 * rfcomm_session_put() */
+			if (s->sock->sk->sk_state != BT_CLOSED)
+				rfcomm_session_put(s);
 			break;
 		}
 	}
@@ -1920,6 +1923,7 @@ static inline void rfcomm_process_sessions(void)
 		if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) {
 			s->state = BT_DISCONN;
 			rfcomm_send_disc(s, 0);
+			rfcomm_session_put(s);
 			continue;
 		}
 
diff --git a/net/core/dst.c b/net/core/dst.c
index 57bc4d5b8d0..cb1b3488b73 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <net/net_namespace.h>
+#include <linux/sched.h>
 
 #include <net/dst.h>
 
@@ -79,6 +80,7 @@ loop:
 	while ((dst = next) != NULL) {
 		next = dst->next;
 		prefetch(&next->next);
+		cond_resched();
 		if (likely(atomic_read(&dst->__refcnt))) {
 			last->next = dst;
 			last = dst;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index de0c2c72642..2e692afdc55 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3524,6 +3524,7 @@ static int pktgen_thread_worker(void *arg)
 			wait_event_interruptible_timeout(t->queue,
 							 t->control != 0,
 							 HZ/10);
+			try_to_freeze();
 			continue;
 		}
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 06632762ba5..90203e1b918 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -925,10 +925,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
 	if (t && !IS_ERR(t)) {
 		struct arpt_getinfo info;
 		const struct xt_table_info *private = t->private;
-
 #ifdef CONFIG_COMPAT
+		struct xt_table_info tmp;
+
 		if (compat) {
-			struct xt_table_info tmp;
 			ret = compat_table_info(private, &tmp);
 			xt_compat_flush_offsets(NFPROTO_ARP);
 			private = &tmp;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 572330a552e..3ce53cf13d5 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1132,10 +1132,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
 	if (t && !IS_ERR(t)) {
 		struct ipt_getinfo info;
 		const struct xt_table_info *private = t->private;
-
 #ifdef CONFIG_COMPAT
+		struct xt_table_info tmp;
+
 		if (compat) {
-			struct xt_table_info tmp;
 			ret = compat_table_info(private, &tmp);
 			xt_compat_flush_offsets(AF_INET);
 			private = &tmp;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index d171b123a65..d1ea38a7c49 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -210,7 +210,7 @@ static ctl_table ip_ct_sysctl_table[] = {
 	},
 	{
 		.procname	= "ip_conntrack_buckets",
-		.data		= &nf_conntrack_htable_size,
+		.data		= &init_net.ct.htable_size,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 8668a3defda..2fb7b76da94 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -32,7 +32,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	struct hlist_nulls_node *n;
 
 	for (st->bucket = 0;
-	     st->bucket < nf_conntrack_htable_size;
+	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(net->ct.hash[st->bucket].first);
 		if (!is_a_nulls(n))
@@ -50,7 +50,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	head = rcu_dereference(head->next);
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= nf_conntrack_htable_size)
+			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
 		head = rcu_dereference(net->ct.hash[st->bucket].first);
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index fe1a64479dd..26066a2327a 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -35,9 +35,6 @@ static DEFINE_SPINLOCK(nf_nat_lock);
 
 static struct nf_conntrack_l3proto *l3proto __read_mostly;
 
-/* Calculated at init based on memory size */
-static unsigned int nf_nat_htable_size __read_mostly;
-
 #define MAX_IP_NAT_PROTO 256
 static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]
 						__read_mostly;
@@ -72,7 +69,7 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put);
 
 /* We keep an extra hash for each conntrack, for fast searching. */
 static inline unsigned int
-hash_by_src(const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple)
 {
 	unsigned int hash;
 
@@ -80,7 +77,7 @@ hash_by_src(const struct nf_conntrack_tuple *tuple)
 	hash = jhash_3words((__force u32)tuple->src.u3.ip,
 			    (__force u32)tuple->src.u.all,
 			    tuple->dst.protonum, 0);
-	return ((u64)hash * nf_nat_htable_size) >> 32;
+	return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
 }
 
 /* Is this tuple already taken? (not by us) */
@@ -147,7 +144,7 @@ find_appropriate_src(struct net *net,
 		     struct nf_conntrack_tuple *result,
 		     const struct nf_nat_range *range)
 {
-	unsigned int h = hash_by_src(tuple);
+	unsigned int h = hash_by_src(net, tuple);
 	const struct nf_conn_nat *nat;
 	const struct nf_conn *ct;
 	const struct hlist_node *n;
@@ -330,7 +327,7 @@ nf_nat_setup_info(struct nf_conn *ct,
 	if (have_to_hash) {
 		unsigned int srchash;
 
-		srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+		srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 		spin_lock_bh(&nf_nat_lock);
 		/* nf_conntrack_alter_reply might re-allocate exntension aera */
 		nat = nfct_nat(ct);
@@ -679,8 +676,10 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
 
 static int __net_init nf_nat_net_init(struct net *net)
 {
-	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size,
-						      &net->ipv4.nat_vmalloced, 0);
+	/* Leave them the same for the moment. */
+	net->ipv4.nat_htable_size = net->ct.htable_size;
+	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size,
+						       &net->ipv4.nat_vmalloced, 0);
 	if (!net->ipv4.nat_bysource)
 		return -ENOMEM;
 	return 0;
@@ -703,7 +702,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 	nf_ct_iterate_cleanup(net, &clean_nat, NULL);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced,
-			     nf_nat_htable_size);
+			     net->ipv4.nat_htable_size);
 }
 
 static struct pernet_operations nf_nat_net_ops = {
@@ -724,9 +723,6 @@ static int __init nf_nat_init(void)
 		return ret;
 	}
 
-	/* Leave them the same for the moment. */
-	nf_nat_htable_size = nf_conntrack_htable_size;
-
 	ret = register_pernet_subsys(&nf_nat_net_ops);
 	if (ret < 0)
 		goto cleanup_extend;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 480d7f8c980..8a7e0f52e17 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1164,10 +1164,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
 	if (t && !IS_ERR(t)) {
 		struct ip6t_getinfo info;
 		const struct xt_table_info *private = t->private;
-
 #ifdef CONFIG_COMPAT
+		struct xt_table_info tmp;
+
 		if (compat) {
-			struct xt_table_info tmp;
 			ret = compat_table_info(private, &tmp);
 			xt_compat_flush_offsets(AF_INET6);
 			private = &tmp;
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 156020d138b..6b3602de359 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -698,15 +698,18 @@ dev_irnet_ioctl(
 
       /* Query PPP channel and unit number */
     case PPPIOCGCHAN:
+      lock_kernel();
       if(ap->ppp_open && !put_user(ppp_channel_index(&ap->chan),
 						(int __user *)argp))
 	err = 0;
+      unlock_kernel();
       break;
     case PPPIOCGUNIT:
       lock_kernel();
       if(ap->ppp_open && !put_user(ppp_unit_number(&ap->chan),
 						(int __user *)argp))
-      err = 0;
+        err = 0;
+      unlock_kernel();
       break;
 
       /* All these ioctls can be passed both directly and from ppp_generic,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0e98c3282d4..4d79e3c1616 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -30,6 +30,7 @@
 #include <linux/netdevice.h>
 #include <linux/socket.h>
 #include <linux/mm.h>
+#include <linux/nsproxy.h>
 #include <linux/rculist_nulls.h>
 
 #include <net/netfilter/nf_conntrack.h>
@@ -63,8 +64,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_max);
 struct nf_conn nf_conntrack_untracked __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_untracked);
 
-static struct kmem_cache *nf_conntrack_cachep __read_mostly;
-
 static int nf_conntrack_hash_rnd_initted;
 static unsigned int nf_conntrack_hash_rnd;
 
@@ -86,9 +85,10 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
 	return ((u64)h * size) >> 32;
 }
 
-static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
+static inline u_int32_t hash_conntrack(const struct net *net,
+				       const struct nf_conntrack_tuple *tuple)
 {
-	return __hash_conntrack(tuple, nf_conntrack_htable_size,
+	return __hash_conntrack(tuple, net->ct.htable_size,
 				nf_conntrack_hash_rnd);
 }
 
@@ -296,7 +296,7 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
-	unsigned int hash = hash_conntrack(tuple);
+	unsigned int hash = hash_conntrack(net, tuple);
 
 	/* Disable BHs the entire time since we normally need to disable them
 	 * at least once for the stats anyway.
@@ -366,10 +366,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 
 void nf_conntrack_hash_insert(struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
 	unsigned int hash, repl_hash;
 
-	hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-	repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+	hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+	repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 
 	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 }
@@ -397,8 +398,8 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
 		return NF_ACCEPT;
 
-	hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-	repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+	hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+	repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 
 	/* We're not in hash table, and we refuse to set up related
 	   connections for unconfirmed conns.  But packet copies and
@@ -468,7 +469,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 	struct net *net = nf_ct_net(ignored_conntrack);
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
-	unsigned int hash = hash_conntrack(tuple);
+	unsigned int hash = hash_conntrack(net, tuple);
 
 	/* Disable BHs the entire time since we need to disable them at
 	 * least once for the stats anyway.
@@ -503,7 +504,7 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 	int dropped = 0;
 
 	rcu_read_lock();
-	for (i = 0; i < nf_conntrack_htable_size; i++) {
+	for (i = 0; i < net->ct.htable_size; i++) {
 		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
 					 hnnode) {
 			tmp = nf_ct_tuplehash_to_ctrack(h);
@@ -523,7 +524,7 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 		if (cnt >= NF_CT_EVICTION_RANGE)
 			break;
 
-		hash = (hash + 1) % nf_conntrack_htable_size;
+		hash = (hash + 1) % net->ct.htable_size;
 	}
 	rcu_read_unlock();
 
@@ -557,7 +558,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 
 	if (nf_conntrack_max &&
 	    unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
-		unsigned int hash = hash_conntrack(orig);
+		unsigned int hash = hash_conntrack(net, orig);
 		if (!early_drop(net, hash)) {
 			atomic_dec(&net->ct.count);
 			if (net_ratelimit())
@@ -572,7 +573,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 	 * Do not use kmem_cache_zalloc(), as this cache uses
 	 * SLAB_DESTROY_BY_RCU.
 	 */
-	ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
+	ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp);
 	if (ct == NULL) {
 		pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
 		atomic_dec(&net->ct.count);
@@ -611,7 +612,7 @@ void nf_conntrack_free(struct nf_conn *ct)
 	nf_ct_ext_destroy(ct);
 	atomic_dec(&net->ct.count);
 	nf_ct_ext_free(ct);
-	kmem_cache_free(nf_conntrack_cachep, ct);
+	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_free);
 
@@ -1014,7 +1015,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 	struct hlist_nulls_node *n;
 
 	spin_lock_bh(&nf_conntrack_lock);
-	for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
+	for (; *bucket < net->ct.htable_size; (*bucket)++) {
 		hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (iter(ct, data))
@@ -1113,9 +1114,12 @@ static void nf_ct_release_dying_list(struct net *net)
 
 static void nf_conntrack_cleanup_init_net(void)
 {
+	/* wait until all references to nf_conntrack_untracked are dropped */
+	while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1)
+		schedule();
+
 	nf_conntrack_helper_fini();
 	nf_conntrack_proto_fini();
-	kmem_cache_destroy(nf_conntrack_cachep);
 }
 
 static void nf_conntrack_cleanup_net(struct net *net)
@@ -1127,15 +1131,14 @@ static void nf_conntrack_cleanup_net(struct net *net)
 		schedule();
 		goto i_see_dead_people;
 	}
-	/* wait until all references to nf_conntrack_untracked are dropped */
-	while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1)
-		schedule();
 
 	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     nf_conntrack_htable_size);
+			     net->ct.htable_size);
 	nf_conntrack_ecache_fini(net);
 	nf_conntrack_acct_fini(net);
 	nf_conntrack_expect_fini(net);
+	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
+	kfree(net->ct.slabname);
 	free_percpu(net->ct.stat);
 }
 
@@ -1190,10 +1193,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 {
 	int i, bucket, vmalloced, old_vmalloced;
 	unsigned int hashsize, old_size;
-	int rnd;
 	struct hlist_nulls_head *hash, *old_hash;
 	struct nf_conntrack_tuple_hash *h;
 
+	if (current->nsproxy->net_ns != &init_net)
+		return -EOPNOTSUPP;
+
 	/* On boot, we can set this without any fancy locking. */
 	if (!nf_conntrack_htable_size)
 		return param_set_uint(val, kp);
@@ -1206,33 +1211,29 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hash)
 		return -ENOMEM;
 
-	/* We have to rehahs for the new table anyway, so we also can
-	 * use a newrandom seed */
-	get_random_bytes(&rnd, sizeof(rnd));
-
 	/* Lookups in the old hash might happen in parallel, which means we
 	 * might get false negatives during connection lookup. New connections
 	 * created because of a false negative won't make it into the hash
 	 * though since that required taking the lock.
 	 */
 	spin_lock_bh(&nf_conntrack_lock);
-	for (i = 0; i < nf_conntrack_htable_size; i++) {
+	for (i = 0; i < init_net.ct.htable_size; i++) {
 		while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
 			h = hlist_nulls_entry(init_net.ct.hash[i].first,
 					struct nf_conntrack_tuple_hash, hnnode);
 			hlist_nulls_del_rcu(&h->hnnode);
-			bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
+			bucket = __hash_conntrack(&h->tuple, hashsize,
+						  nf_conntrack_hash_rnd);
 			hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
 		}
 	}
-	old_size = nf_conntrack_htable_size;
+	old_size = init_net.ct.htable_size;
 	old_vmalloced = init_net.ct.hash_vmalloc;
 	old_hash = init_net.ct.hash;
 
-	nf_conntrack_htable_size = hashsize;
+	init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
 	init_net.ct.hash_vmalloc = vmalloced;
 	init_net.ct.hash = hash;
-	nf_conntrack_hash_rnd = rnd;
 	spin_unlock_bh(&nf_conntrack_lock);
 
 	nf_ct_free_hashtable(old_hash, old_vmalloced, old_size);
@@ -1271,15 +1272,6 @@ static int nf_conntrack_init_init_net(void)
 	       NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
 	       nf_conntrack_max);
 
-	nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
-						sizeof(struct nf_conn),
-						0, SLAB_DESTROY_BY_RCU, NULL);
-	if (!nf_conntrack_cachep) {
-		printk(KERN_ERR "Unable to create nf_conn slab cache\n");
-		ret = -ENOMEM;
-		goto err_cache;
-	}
-
 	ret = nf_conntrack_proto_init();
 	if (ret < 0)
 		goto err_proto;
@@ -1288,13 +1280,19 @@ static int nf_conntrack_init_init_net(void)
 	if (ret < 0)
 		goto err_helper;
 
+	/* Set up fake conntrack: to never be deleted, not in any hashes */
+#ifdef CONFIG_NET_NS
+	nf_conntrack_untracked.ct_net = &init_net;
+#endif
+	atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
+	/*  - and look it like as a confirmed connection */
+	set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
+
 	return 0;
 
 err_helper:
 	nf_conntrack_proto_fini();
 err_proto:
-	kmem_cache_destroy(nf_conntrack_cachep);
-err_cache:
 	return ret;
 }
 
@@ -1316,7 +1314,24 @@ static int nf_conntrack_init_net(struct net *net)
 		ret = -ENOMEM;
 		goto err_stat;
 	}
-	net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size,
+
+	net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
+	if (!net->ct.slabname) {
+		ret = -ENOMEM;
+		goto err_slabname;
+	}
+
+	net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
+							sizeof(struct nf_conn), 0,
+							SLAB_DESTROY_BY_RCU, NULL);
+	if (!net->ct.nf_conntrack_cachep) {
+		printk(KERN_ERR "Unable to create nf_conn slab cache\n");
+		ret = -ENOMEM;
+		goto err_cache;
+	}
+
+	net->ct.htable_size = nf_conntrack_htable_size;
+	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size,
 					     &net->ct.hash_vmalloc, 1);
 	if (!net->ct.hash) {
 		ret = -ENOMEM;
@@ -1333,15 +1348,6 @@ static int nf_conntrack_init_net(struct net *net)
 	if (ret < 0)
 		goto err_ecache;
 
-	/* Set up fake conntrack:
-	    - to never be deleted, not in any hashes */
-#ifdef CONFIG_NET_NS
-	nf_conntrack_untracked.ct_net = &init_net;
-#endif
-	atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
-	/*  - and look it like as a confirmed connection */
-	set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
-
 	return 0;
 
 err_ecache:
@@ -1350,8 +1356,12 @@ err_acct:
 	nf_conntrack_expect_fini(net);
 err_expect:
 	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     nf_conntrack_htable_size);
+			     net->ct.htable_size);
 err_hash:
+	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
+err_cache:
+	kfree(net->ct.slabname);
+err_slabname:
 	free_percpu(net->ct.stat);
 err_stat:
 	return ret;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index fdf5d2a1d9b..2f25ff61098 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -569,7 +569,7 @@ static void exp_proc_remove(struct net *net)
 #endif /* CONFIG_PROC_FS */
 }
 
-module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0600);
+module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);
 
 int nf_conntrack_expect_init(struct net *net)
 {
@@ -577,7 +577,7 @@ int nf_conntrack_expect_init(struct net *net)
 
 	if (net_eq(net, &init_net)) {
 		if (!nf_ct_expect_hsize) {
-			nf_ct_expect_hsize = nf_conntrack_htable_size / 256;
+			nf_ct_expect_hsize = net->ct.htable_size / 256;
 			if (!nf_ct_expect_hsize)
 				nf_ct_expect_hsize = 1;
 		}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 65c2a7bc3af..4b1a56bd074 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -192,7 +192,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 	/* Get rid of expecteds, set helpers to NULL. */
 	hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode)
 		unhelp(h, me);
-	for (i = 0; i < nf_conntrack_htable_size; i++) {
+	for (i = 0; i < net->ct.htable_size; i++) {
 		hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
 			unhelp(h, me);
 	}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 42f21c01a93..0ffe689dfe9 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -594,7 +594,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	last = (struct nf_conn *)cb->args[1];
-	for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
+	for (; cb->args[0] < init_net.ct.htable_size; cb->args[0]++) {
 restart:
 		hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]],
 					 hnnode) {
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 028aba667ef..e310f1561bb 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -51,7 +51,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	struct hlist_nulls_node *n;
 
 	for (st->bucket = 0;
-	     st->bucket < nf_conntrack_htable_size;
+	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(net->ct.hash[st->bucket].first);
 		if (!is_a_nulls(n))
@@ -69,7 +69,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	head = rcu_dereference(head->next);
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= nf_conntrack_htable_size)
+			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
 		head = rcu_dereference(net->ct.hash[st->bucket].first);
@@ -355,7 +355,7 @@ static ctl_table nf_ct_sysctl_table[] = {
 	},
 	{
 		.procname       = "nf_conntrack_buckets",
-		.data           = &nf_conntrack_htable_size,
+		.data           = &init_net.ct.htable_size,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0444,
 		.proc_handler   = proc_dointvec,
@@ -421,6 +421,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 		goto out_kmemdup;
 
 	table[1].data = &net->ct.count;
+	table[2].data = &net->ct.htable_size;
 	table[3].data = &net->ct.sysctl_checksum;
 	table[4].data = &net->ct.sysctl_log_invalid;
 
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 929218a4762..21f9c7678aa 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -433,7 +433,7 @@ config NET_ACT_POLICE
 	  module.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called police.
+	  module will be called act_police.
 
 config NET_ACT_GACT
         tristate "Generic actions"
@@ -443,7 +443,7 @@ config NET_ACT_GACT
 	  accepting packets.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called gact.
+	  module will be called act_gact.
 
 config GACT_PROB
         bool "Probability support"
@@ -459,7 +459,7 @@ config NET_ACT_MIRRED
 	  other devices.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called mirred.
+	  module will be called act_mirred.
 
 config NET_ACT_IPT
         tristate "IPtables targets"
@@ -469,7 +469,7 @@ config NET_ACT_IPT
 	  classification.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called ipt.
+	  module will be called act_ipt.
 
 config NET_ACT_NAT
         tristate "Stateless NAT"
@@ -479,7 +479,7 @@ config NET_ACT_NAT
 	  netfilter for NAT unless you know what you are doing.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called nat.
+	  module will be called act_nat.
 
 config NET_ACT_PEDIT
         tristate "Packet Editing"
@@ -488,7 +488,7 @@ config NET_ACT_PEDIT
 	  Say Y here if you want to mangle the content of packets.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called pedit.
+	  module will be called act_pedit.
 
 config NET_ACT_SIMP
         tristate "Simple Example (Debug)"
@@ -502,7 +502,7 @@ config NET_ACT_SIMP
 	  If unsure, say N.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called simple.
+	  module will be called act_simple.
 
 config NET_ACT_SKBEDIT
         tristate "SKB Editing"
@@ -513,7 +513,7 @@ config NET_ACT_SKBEDIT
 	  If unsure, say N.
 
 	  To compile this code as a module, choose M here: the
-	  module will be called skbedit.
+	  module will be called act_skbedit.
 
 config NET_CLS_IND
 	bool "Incoming device classification"