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

Smooth Cong Wang's bug fix into 'net-next'.  Basically put
the bulk of the tcf_block_put() logic from 'net' into
tcf_block_put_ext(), but after the offload unbind.

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 25 insertions, 36 deletions

diff --git a/net/ife/ife.c b/net/ife/ife.c
index f360341c72eb..7d1ec76e7f43 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -137,6 +137,6 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval)
 EXPORT_SYMBOL_GPL(ife_tlv_meta_encode);
 
 MODULE_AUTHOR("Jamal Hadi Salim <jhs@mojatatu.com>");
-MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>");
+MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
 MODULE_DESCRIPTION("Inter-FE LFB action");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a69a34f57330..a85e8a282d17 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2132,6 +2132,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb->ip_summed = skb->ip_summed;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
+	tcp_highest_sack_replace(sk, skb, nskb);
 
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
@@ -2735,7 +2736,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 		else if (!skb_shift(skb, next_skb, next_skb_size))
 			return false;
 	}
-	tcp_highest_sack_combine(sk, next_skb, skb);
+	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	if (next_skb->ip_summed == CHECKSUM_PARTIAL)
 		skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cfa374c8b54c..69b8cdb43aa2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3349,6 +3349,7 @@ static void addrconf_permanent_addr(struct net_device *dev)
 		if ((ifp->flags & IFA_F_PERMANENT) &&
 		    fixup_permanent_addr(idev, ifp) < 0) {
 			write_unlock_bh(&idev->lock);
+			in6_ifa_hold(ifp);
 			ipv6_del_addr(ifp);
 			write_lock_bh(&idev->lock);
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 535db8319769..5f5c78b632d0 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -641,6 +641,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	u32 tunnel_id, peer_tunnel_id;
 	u32 session_id, peer_session_id;
 	bool drop_refcnt = false;
+	bool drop_tunnel = false;
 	int ver = 2;
 	int fd;
 
@@ -709,7 +710,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (tunnel_id == 0)
 		goto end;
 
-	tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
+	tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id);
+	if (tunnel)
+		drop_tunnel = true;
 
 	/* Special case: create tunnel context if session_id and
 	 * peer_session_id is 0. Otherwise look up tunnel using supplied
@@ -837,6 +840,8 @@ out_no_ppp:
 end:
 	if (drop_refcnt)
 		l2tp_session_dec_refcount(session);
+	if (drop_tunnel)
+		l2tp_tunnel_dec_refcount(tunnel);
 	release_sock(sk);
 
 	return error;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 3a6ad0f438dc..64f95624f219 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -296,6 +296,6 @@ static void __exit psample_module_exit(void)
 module_init(psample_module_init);
 module_exit(psample_module_exit);
 
-MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>");
+MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
 MODULE_DESCRIPTION("netlink channel for packet sampling");
 MODULE_LICENSE("GPL v2");
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index a9f9a2ccc664..8b5abcd2f32f 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -271,6 +271,6 @@ static void __exit sample_cleanup_module(void)
 module_init(sample_init_module);
 module_exit(sample_cleanup_module);
 
-MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>");
+MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
 MODULE_DESCRIPTION("Packet sampling action");
 MODULE_LICENSE("GPL v2");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d9d54b367d23..2c03fcbc7188 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -322,8 +322,8 @@ static void tcf_block_put_final(struct work_struct *work)
 	struct tcf_block *block = container_of(work, struct tcf_block, work);
 	struct tcf_chain *chain, *tmp;
 
-	/* At this point, all the chains should have refcnt == 1. */
 	rtnl_lock();
+	/* Only chain 0 should be still here. */
 	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
 		tcf_chain_put(chain);
 	rtnl_unlock();
@@ -331,44 +331,24 @@ static void tcf_block_put_final(struct work_struct *work)
 }
 
 /* XXX: Standalone actions are not allowed to jump to any chain, and bound
- * actions should be all removed after flushing. However, filters are destroyed
- * in RCU callbacks, we have to hold the chains first, otherwise we would
- * always race with RCU callbacks on this list without proper locking.
+ * actions should be all removed after flushing. However, filters are now
+ * destroyed in tc filter workqueue with RTNL lock, they can not race here.
  */
-static void tcf_block_put_deferred(struct work_struct *work)
-{
-	struct tcf_block *block = container_of(work, struct tcf_block, work);
-	struct tcf_chain *chain;
-
-	rtnl_lock();
-	/* Hold a refcnt for all chains, except 0, in case they are gone. */
-	list_for_each_entry(chain, &block->chain_list, list)
-		if (chain->index)
-			tcf_chain_hold(chain);
-
-	/* No race on the list, because no chain could be destroyed. */
-	list_for_each_entry(chain, &block->chain_list, list)
-		tcf_chain_flush(chain);
-
-	INIT_WORK(&block->work, tcf_block_put_final);
-	/* Wait for RCU callbacks to release the reference count and make
-	 * sure their works have been queued before this.
-	 */
-	rcu_barrier();
-	tcf_queue_work(&block->work);
-	rtnl_unlock();
-}
-
 void tcf_block_put_ext(struct tcf_block *block,
 		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
 		       struct tcf_block_ext_info *ei)
 {
+	struct tcf_chain *chain, *tmp;
+
 	if (!block)
 		return;
 
 	tcf_block_offload_unbind(block, q, ei);
 
-	INIT_WORK(&block->work, tcf_block_put_deferred);
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_flush(chain);
+
+	INIT_WORK(&block->work, tcf_block_put_final);
 	/* Wait for existing RCU callbacks to cool down, make sure their works
 	 * have been queued before this. We can not flush pending works here
 	 * because we are holding the RTNL lock.
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 31a2e6d34dba..73ad8c8ef344 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -105,6 +105,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 		if (xfrm_offload(skb)) {
 			x->type_offload->encap(x, skb);
 		} else {
+			/* Inner headers are invalid now. */
+			skb->encapsulation = 0;
+
 			err = x->type->output(x, skb);
 			if (err == -EINPROGRESS)
 				goto out;
@@ -208,7 +211,6 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 	int err;
 
 	secpath_reset(skb);
-	skb->encapsulation = 0;
 
 	if (xfrm_dev_offload_ok(skb, x)) {
 		struct sec_path *sp;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b669c624a1ec..f02b1743b239 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2075,7 +2075,6 @@ make_dummy_bundle:
 	xdst->num_xfrms = num_xfrms;
 	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 
-	dst_hold(&xdst->u.dst);
 	return xdst;
 
 inc_error:
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 12213477cd3a..1f5cee2269af 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2069,6 +2069,7 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
 	if (err >= 0) {
 		xfrm_sk_policy_insert(sk, err, pol);
 		xfrm_pol_put(pol);
+		__sk_dst_reset(sk);
 		err = 0;
 	}