Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

13 files changed, 76 insertions, 106 deletions

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index 7819a9f..d55051a 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -352,7 +352,7 @@ static void __exit dsa_loop_exit(void)
 
 	mdio_driver_unregister(&dsa_loop_drv);
 	for (i = 0; i < NUM_FIXED_PHYS; i++)
-		if (phydevs[i])
+		if (!IS_ERR(phydevs[i]))
 			fixed_phy_unregister(phydevs[i]);
 }
 module_exit(dsa_loop_exit);
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 6fdcd24..fc59e07 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;
@@ -108,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
-{
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
-}
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
+	atomic_set(&nf->mem, 0);
 }
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
@@ -140,31 +130,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_sum_positive(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/include/net/route.h b/include/net/route.h
index cb0a76d..1b09a93 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -189,10 +189,11 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 
 	rcu_read_lock();
 	err = ip_route_input_noref(skb, dst, src, tos, devin);
-	if (!err)
+	if (!err) {
 		skb_dst_force_safe(skb);
-	if (!skb_dst(skb))
-		err = -EINVAL;
+		if (!skb_dst(skb))
+			err = -EINVAL;
+	}
 	rcu_read_unlock();
 
 	return err;
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 30d875d..f85b08b 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 96e95e8..af74d04 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -234,10 +234,8 @@ evict_again:
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9a8cfac..46408c2 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -844,8 +844,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -871,13 +869,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 986d4ca..b263bf3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e1da5b8..846012e 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -714,19 +714,13 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 90165a6..ee485df 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -329,13 +329,21 @@ static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
 	struct hlist_head *g_head;
 	struct hlist_head *head;
 	struct l2tp_net *pn;
+	int err;
 
 	head = l2tp_session_id_hash(tunnel, session->session_id);
 
 	write_lock_bh(&tunnel->hlist_lock);
+	if (!tunnel->acpt_newsess) {
+		err = -ENODEV;
+		goto err_tlock;
+	}
+
 	hlist_for_each_entry(session_walk, head, hlist)
-		if (session_walk->session_id == session->session_id)
-			goto exist;
+		if (session_walk->session_id == session->session_id) {
+			err = -EEXIST;
+			goto err_tlock;
+		}
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		pn = l2tp_pernet(tunnel->l2tp_net);
@@ -343,12 +351,21 @@ static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
 						session->session_id);
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
+
 		hlist_for_each_entry(session_walk, g_head, global_hlist)
-			if (session_walk->session_id == session->session_id)
-				goto exist_glob;
+			if (session_walk->session_id == session->session_id) {
+				err = -EEXIST;
+				goto err_tlock_pnlock;
+			}
 
+		l2tp_tunnel_inc_refcount(tunnel);
+		sock_hold(tunnel->sock);
 		hlist_add_head_rcu(&session->global_hlist, g_head);
+
 		spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+	} else {
+		l2tp_tunnel_inc_refcount(tunnel);
+		sock_hold(tunnel->sock);
 	}
 
 	hlist_add_head(&session->hlist, head);
@@ -356,12 +373,12 @@ static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
 
 	return 0;
 
-exist_glob:
+err_tlock_pnlock:
 	spin_unlock_bh(&pn->l2tp_session_hlist_lock);
-exist:
+err_tlock:
 	write_unlock_bh(&tunnel->hlist_lock);
 
-	return -EEXIST;
+	return err;
 }
 
 /* Lookup a tunnel by id
@@ -1251,7 +1268,6 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	/* Remove hooks into tunnel socket */
 	sk->sk_destruct = tunnel->old_sk_destruct;
 	sk->sk_user_data = NULL;
-	tunnel->sock = NULL;
 
 	/* Remove the tunnel struct from the tunnel list */
 	pn = l2tp_pernet(tunnel->l2tp_net);
@@ -1261,6 +1277,8 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	atomic_dec(&l2tp_tunnel_count);
 
 	l2tp_tunnel_closeall(tunnel);
+
+	tunnel->sock = NULL;
 	l2tp_tunnel_dec_refcount(tunnel);
 
 	/* Call the original destructor */
@@ -1285,6 +1303,7 @@ void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
 		  tunnel->name);
 
 	write_lock_bh(&tunnel->hlist_lock);
+	tunnel->acpt_newsess = false;
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 again:
 		hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
@@ -1581,6 +1600,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	tunnel->magic = L2TP_TUNNEL_MAGIC;
 	sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
 	rwlock_init(&tunnel->hlist_lock);
+	tunnel->acpt_newsess = true;
 
 	/* The net we belong to */
 	tunnel->l2tp_net = net;
@@ -1829,11 +1849,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 			return ERR_PTR(err);
 		}
 
-		l2tp_tunnel_inc_refcount(tunnel);
-
-		/* Ensure tunnel socket isn't deleted */
-		sock_hold(tunnel->sock);
-
 		/* Ignore management session in session count value */
 		if (session->session_id != 0)
 			atomic_inc(&l2tp_session_count);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9101297..a305e0c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -162,6 +162,10 @@ struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
+	bool			acpt_newsess;	/* Indicates whether this
+						 * tunnel accepts new sessions.
+						 * Protected by hlist_lock.
+						 */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
 						/* hashed list of sessions,
 						 * hashed by id */
@@ -197,7 +201,9 @@ struct l2tp_tunnel {
 };
 
 struct l2tp_nl_cmd_ops {
-	int (*session_create)(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg);
+	int (*session_create)(struct net *net, struct l2tp_tunnel *tunnel,
+			      u32 session_id, u32 peer_session_id,
+			      struct l2tp_session_cfg *cfg);
 	int (*session_delete)(struct l2tp_session *session);
 };
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 4de2ec9..87da9ef 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -262,24 +262,19 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 	dev->needed_headroom += session->hdr_len;
 }
 
-static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
+			   u32 session_id, u32 peer_session_id,
+			   struct l2tp_session_cfg *cfg)
 {
 	unsigned char name_assign_type;
 	struct net_device *dev;
 	char name[IFNAMSIZ];
-	struct l2tp_tunnel *tunnel;
 	struct l2tp_session *session;
 	struct l2tp_eth *priv;
 	struct l2tp_eth_sess *spriv;
 	int rc;
 	struct l2tp_eth_net *pn;
 
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (!tunnel) {
-		rc = -ENODEV;
-		goto out;
-	}
-
 	if (cfg->ifname) {
 		strlcpy(name, cfg->ifname, IFNAMSIZ);
 		name_assign_type = NET_NAME_USER;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 57427d4..7135f46 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -643,10 +643,10 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		break;
 	}
 
-	ret = -EPROTONOSUPPORT;
-	if (l2tp_nl_cmd_ops[cfg.pw_type]->session_create)
-		ret = (*l2tp_nl_cmd_ops[cfg.pw_type]->session_create)(net, tunnel_id,
-			session_id, peer_session_id, &cfg);
+	ret = l2tp_nl_cmd_ops[cfg.pw_type]->session_create(net, tunnel,
+							   session_id,
+							   peer_session_id,
+							   &cfg);
 
 	if (ret >= 0) {
 		session = l2tp_session_get(net, tunnel, session_id, false);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index f0edb72..50e3ee9 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -788,25 +788,20 @@ end:
 
 #ifdef CONFIG_L2TP_V3
 
-/* Called when creating sessions via the netlink interface.
- */
-static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+/* Called when creating sessions via the netlink interface. */
+static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
+				   u32 session_id, u32 peer_session_id,
+				   struct l2tp_session_cfg *cfg)
 {
 	int error;
-	struct l2tp_tunnel *tunnel;
 	struct l2tp_session *session;
 	struct pppol2tp_session *ps;
 
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-
-	/* Error if we can't find the tunnel */
-	error = -ENOENT;
-	if (tunnel == NULL)
-		goto out;
-
 	/* Error if tunnel socket is not prepped */
-	if (tunnel->sock == NULL)
+	if (!tunnel->sock) {
+		error = -ENOENT;
 		goto out;
+	}
 
 	/* Default MTU values. */
 	if (cfg->mtu == 0)