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

Conflicts:
	arch/s390/net/bpf_jit_comp.c
	drivers/net/ethernet/ti/netcp_ethss.c
	net/bridge/br_multicast.c
	net/ipv4/ip_fragment.c

All four conflicts were cases of simple overlapping
changes.

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

9 files changed, 71 insertions, 60 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 1d59e50ce8b7..34a308573f4b 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1026,14 +1026,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 
 	neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	if (neigh) {
-		read_lock_bh(&neigh->lock);
-		memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
-		r->arp_flags = arp_state_to_flags(neigh);
-		read_unlock_bh(&neigh->lock);
-		r->arp_ha.sa_family = dev->type;
-		strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+		if (!(neigh->nud_state & NUD_NOARP)) {
+			read_lock_bh(&neigh->lock);
+			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			r->arp_flags = arp_state_to_flags(neigh);
+			read_unlock_bh(&neigh->lock);
+			r->arp_ha.sa_family = dev->type;
+			strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+			err = 0;
+		}
 		neigh_release(neigh);
-		err = 0;
 	}
 	return err;
 }
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e813196c91c7..2d9cb1748f81 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		queue_delayed_work(system_power_efficient_wq,
 				&check_lifetime_work, 0);
 		rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
-		blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
 	}
 	return 0;
 }
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed60b03..9c02920725db 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@ struct fib_alias {
 	u8			fa_state;
 	u8			fa_slen;
 	u32			tb_id;
+	s16			fa_default;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 65e00399a9a6..558e196bae0f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1297,23 +1297,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 }
 
 /* Must be invoked inside of an RCU protected region.  */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 {
 	struct fib_info *fi = NULL, *last_resort = NULL;
 	struct hlist_head *fa_head = res->fa_head;
 	struct fib_table *tb = res->table;
+	u8 slen = 32 - res->prefixlen;
 	int order = -1, last_idx = -1;
-	struct fib_alias *fa;
+	struct fib_alias *fa, *fa1 = NULL;
+	u32 last_prio = res->fi->fib_priority;
+	u8 last_tos = 0;
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
+		if (fa->fa_slen != slen)
+			continue;
+		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+			continue;
+		if (fa->tb_id != tb->tb_id)
+			continue;
+		if (next_fi->fib_priority > last_prio &&
+		    fa->fa_tos == last_tos) {
+			if (last_tos)
+				continue;
+			break;
+		}
+		if (next_fi->fib_flags & RTNH_F_DEAD)
+			continue;
+		last_tos = fa->fa_tos;
+		last_prio = next_fi->fib_priority;
+
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-
-		if (next_fi->fib_priority > res->fi->fib_priority)
-			break;
 		if (!next_fi->fib_nh[0].nh_gw ||
 		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
 			continue;
@@ -1323,10 +1340,11 @@ void fib_select_default(struct fib_result *res)
 		if (!fi) {
 			if (next_fi != res->fi)
 				break;
+			fa1 = fa;
 		} else if (!fib_detect_death(fi, order, &last_resort,
-					     &last_idx, tb->tb_default)) {
+					     &last_idx, fa1->fa_default)) {
 			fib_result_assign(res, fi);
-			tb->tb_default = order;
+			fa1->fa_default = order;
 			goto out;
 		}
 		fi = next_fi;
@@ -1334,20 +1352,21 @@ void fib_select_default(struct fib_result *res)
 	}
 
 	if (order <= 0 || !fi) {
-		tb->tb_default = -1;
+		if (fa1)
+			fa1->fa_default = -1;
 		goto out;
 	}
 
 	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
+			      fa1->fa_default)) {
 		fib_result_assign(res, fi);
-		tb->tb_default = order;
+		fa1->fa_default = order;
 		goto out;
 	}
 
 	if (last_idx >= 0)
 		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
+	fa1->fa_default = last_idx;
 out:
 	return;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d32612e3c6..37c4bb89a708 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 			new_fa->fa_slen = fa->fa_slen;
 			new_fa->tb_id = tb->tb_id;
+			new_fa->fa_default = -1;
 
 			err = switchdev_fib_ipv4_add(key, plen, fi,
 						     new_fa->fa_tos,
@@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->fa_state = 0;
 	new_fa->fa_slen = slen;
 	new_fa->tb_id = tb->tb_id;
+	new_fa->fa_default = -1;
 
 	/* (Optionally) offload fib entry to switch hardware. */
 	err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1791,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 }
@@ -1862,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 
@@ -1990,7 +1988,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
 		return NULL;
 
 	tb->tb_id = id;
-	tb->tb_default = -1;
 	tb->tb_num_default = 0;
 	tb->tb_data = (alias ? alias->__data : tb->__data);
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5e346a082e5f..d0a7c0319e3d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -131,34 +131,22 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
 	unsigned int evicted = 0;
 	HLIST_HEAD(expired);
 
-evict_again:
 	spin_lock(&hb->chain_lock);
 
 	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
 		if (!inet_fragq_should_evict(fq))
 			continue;
 
-		if (!del_timer(&fq->timer)) {
-			/* q expiring right now thus increment its refcount so
-			 * it won't be freed under us and wait until the timer
-			 * has finished executing then destroy it
-			 */
-			atomic_inc(&fq->refcnt);
-			spin_unlock(&hb->chain_lock);
-			del_timer_sync(&fq->timer);
-			inet_frag_put(fq, f);
-			goto evict_again;
-		}
+		if (!del_timer(&fq->timer))
+			continue;
 
-		fq->flags |= INET_FRAG_EVICTED;
-		hlist_del(&fq->list);
-		hlist_add_head(&fq->list, &expired);
+		hlist_add_head(&fq->list_evictor, &expired);
 		++evicted;
 	}
 
 	spin_unlock(&hb->chain_lock);
 
-	hlist_for_each_entry_safe(fq, n, &expired, list)
+	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
 		f->frag_expire((unsigned long) fq);
 
 	return evicted;
@@ -240,18 +228,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	int i;
 
 	nf->low_thresh = 0;
-	local_bh_disable();
 
 evict_again:
+	local_bh_disable();
 	seq = read_seqbegin(&f->rnd_seqlock);
 
 	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
 		inet_evict_bucket(f, &f->hash[i]);
 
-	if (read_seqretry(&f->rnd_seqlock, seq))
-		goto evict_again;
-
 	local_bh_enable();
+	cond_resched();
+
+	if (read_seqretry(&f->rnd_seqlock, seq) ||
+	    percpu_counter_sum(&nf->mem))
+		goto evict_again;
 
 	percpu_counter_destroy(&nf->mem);
 }
@@ -284,8 +274,8 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
 	struct inet_frag_bucket *hb;
 
 	hb = get_frag_bucket_locked(fq, f);
-	if (!(fq->flags & INET_FRAG_EVICTED))
-		hlist_del(&fq->list);
+	hlist_del(&fq->list);
+	fq->flags |= INET_FRAG_COMPLETE;
 	spin_unlock(&hb->chain_lock);
 }
 
@@ -297,7 +287,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
 		fq_unlink(fq, f);
 		atomic_dec(&fq->refcnt);
-		fq->flags |= INET_FRAG_COMPLETE;
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
@@ -330,11 +319,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 		fp = xp;
 	}
 	sum = sum_truesize + f->qsize;
-	sub_frag_mem_limit(q, sum);
 
 	if (f->destructor)
 		f->destructor(q);
 	kmem_cache_free(f->frags_cachep, q);
+
+	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
@@ -390,7 +380,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	q->net = nf;
 	f->constructor(q, arg);
-	add_frag_mem_limit(q, f->qsize);
+	add_frag_mem_limit(nf, f->qsize);
 
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index f44bccc42494..d96722ae8979 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg)
 	ipq_kill(qp);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
-	if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+	if (!inet_frag_evicting(&qp->q)) {
 		struct sk_buff *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
@@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp)
 		kfree_skb(fp);
 		fp = xp;
 	} while (fp);
-	sub_frag_mem_limit(&qp->q, sum_truesize);
+	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
@@ -455,7 +455,7 @@ found:
 				qp->q.fragments = next;
 
 			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(&qp->q, free_it->truesize);
+			sub_frag_mem_limit(qp->q.net, free_it->truesize);
 			kfree_skb(free_it);
 		}
 	}
@@ -479,7 +479,7 @@ found:
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
-	add_frag_mem_limit(&qp->q, skb->truesize);
+	add_frag_mem_limit(qp->q.net, skb->truesize);
 	if (offset == 0)
 		qp->q.flags |= INET_FRAG_FIRST_IN;
 
@@ -586,7 +586,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		add_frag_mem_limit(&qp->q, clone->truesize);
+		add_frag_mem_limit(qp->q.net, clone->truesize);
 	}
 
 	skb_shinfo(head)->frag_list = head->next;
@@ -601,7 +601,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
 	}
-	sub_frag_mem_limit(&qp->q, head->truesize);
+	sub_frag_mem_limit(qp->q.net, head->truesize);
 
 	head->next = NULL;
 	head->dev = dev;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 11096396ef4a..908f7ef2f12a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2194,7 +2194,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	if (!res.prefixlen &&
 	    res.table->tb_num_default > 1 &&
 	    res.type == RTN_UNICAST && !fl4->flowi4_oif)
-		fib_select_default(&res);
+		fib_select_default(fl4, &res);
 
 	if (!fl4->saddr)
 		fl4->saddr = FIB_RES_PREFSRC(net, res);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7f4056785acc..45534a5ab430 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
-			sk_wait_data(sk, &timeo);
+			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
 				break;
@@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct task_struct *user_recv = NULL;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 
 		/* Next get a buffer. */
 
+		last = skb_peek_tail(&sk->sk_receive_queue);
 		skb_queue_walk(&sk->sk_receive_queue, skb) {
+			last = skb;
 			/* Now that we have two receive queues this
 			 * shouldn't happen.
 			 */
@@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
 			lock_sock(sk);
-		} else
-			sk_wait_data(sk, &timeo);
+		} else {
+			sk_wait_data(sk, &timeo, last);
+		}
 
 		if (user_recv) {
 			int chunk;