Merge branch 'master' of /repos/git/net-next-2.6

Conflicts:
	include/net/netfilter/xt_rateest.h
	net/bridge/br_netfilter.c
	net/netfilter/nf_conntrack_core.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

7 files changed, 79 insertions, 31 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 972378f..23b25f8 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -26,6 +26,11 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+static void tcf_common_free_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct tcf_common, tcfc_rcu));
+}
+
 void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 {
 	unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
@@ -38,7 +43,11 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 			write_unlock_bh(hinfo->lock);
 			gen_kill_estimator(&p->tcfc_bstats,
 					   &p->tcfc_rate_est);
-			kfree(p);
+			/*
+			 * gen_estimator est_timer() might access p->tcfc_lock
+			 * or bstats, wait a RCU grace period before freeing p
+			 */
+			call_rcu(&p->tcfc_rcu, tcf_common_free_rcu);
 			return;
 		}
 	}
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index d885ba3..5709494 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -159,6 +159,9 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
 			iph->daddr = new_addr;
 
 		csum_replace4(&iph->check, addr, new_addr);
+	} else if ((iph->frag_off & htons(IP_OFFSET)) ||
+		   iph->protocol != IPPROTO_ICMP) {
+		goto out;
 	}
 
 	ihl = iph->ihl * 4;
@@ -247,6 +250,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
 		break;
 	}
 
+out:
 	return action;
 
 drop:
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index fdbd0b7..a0593c9 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -125,16 +125,15 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a,
 {
 	struct tcf_pedit *p = a->priv;
 	int i, munged = 0;
-	u8 *pptr;
+	unsigned int off;
 
-	if (!(skb->tc_verd & TC_OK2MUNGE)) {
-		/* should we set skb->cloned? */
+	if (skb_cloned(skb)) {
 		if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
 			return p->tcf_action;
 		}
 	}
 
-	pptr = skb_network_header(skb);
+	off = skb_network_offset(skb);
 
 	spin_lock(&p->tcf_lock);
 
@@ -144,17 +143,17 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a,
 		struct tc_pedit_key *tkey = p->tcfp_keys;
 
 		for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
-			u32 *ptr;
+			u32 *ptr, _data;
 			int offset = tkey->off;
 
 			if (tkey->offmask) {
-				if (skb->len > tkey->at) {
-					 char *j = pptr + tkey->at;
-					 offset += ((*j & tkey->offmask) >>
-						   tkey->shift);
-				} else {
+				char *d, _d;
+
+				d = skb_header_pointer(skb, off + tkey->at, 1,
+						       &_d);
+				if (!d)
 					goto bad;
-				}
+				offset += (*d & tkey->offmask) >> tkey->shift;
 			}
 
 			if (offset % 4) {
@@ -169,9 +168,13 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a,
 				goto bad;
 			}
 
-			ptr = (u32 *)(pptr+offset);
+			ptr = skb_header_pointer(skb, off + offset, 4, &_data);
+			if (!ptr)
+				goto bad;
 			/* just do it, baby */
 			*ptr = ((*ptr & tkey->mask) ^ tkey->val);
+			if (ptr == &_data)
+				skb_store_bits(skb, off + offset, ptr, 4);
 			munged++;
 		}
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 654f73d..537a487 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -97,6 +97,11 @@ nla_put_failure:
 	goto done;
 }
 
+static void tcf_police_free_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct tcf_police, tcf_rcu));
+}
+
 static void tcf_police_destroy(struct tcf_police *p)
 {
 	unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK);
@@ -113,7 +118,11 @@ static void tcf_police_destroy(struct tcf_police *p)
 				qdisc_put_rtab(p->tcfp_R_tab);
 			if (p->tcfp_P_tab)
 				qdisc_put_rtab(p->tcfp_P_tab);
-			kfree(p);
+			/*
+			 * gen_estimator est_timer() might access p->tcf_lock
+			 * or bstats, wait a RCU grace period before freeing p
+			 */
+			call_rcu(&p->tcf_rcu, tcf_police_free_rcu);
 			return;
 		}
 	}
@@ -397,6 +406,7 @@ static void __exit
 police_cleanup_module(void)
 {
 	tcf_unregister_action(&act_police_ops);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s (tcf_police_free_rcu) */
 }
 
 module_init(police_init_module);
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 9627542..4f52214 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -98,11 +98,11 @@ static int u32_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_re
 {
 	struct {
 		struct tc_u_knode *knode;
-		u8		  *ptr;
+		unsigned int	  off;
 	} stack[TC_U32_MAXDEPTH];
 
 	struct tc_u_hnode *ht = (struct tc_u_hnode*)tp->root;
-	u8 *ptr = skb_network_header(skb);
+	unsigned int off = skb_network_offset(skb);
 	struct tc_u_knode *n;
 	int sdepth = 0;
 	int off2 = 0;
@@ -134,8 +134,14 @@ next_knode:
 #endif
 
 		for (i = n->sel.nkeys; i>0; i--, key++) {
-
-			if ((*(__be32*)(ptr+key->off+(off2&key->offmask))^key->val)&key->mask) {
+			unsigned int toff;
+			__be32 *data, _data;
+
+			toff = off + key->off + (off2 & key->offmask);
+			data = skb_header_pointer(skb, toff, 4, &_data);
+			if (!data)
+				goto out;
+			if ((*data ^ key->val) & key->mask) {
 				n = n->next;
 				goto next_knode;
 			}
@@ -174,29 +180,45 @@ check_terminal:
 		if (sdepth >= TC_U32_MAXDEPTH)
 			goto deadloop;
 		stack[sdepth].knode = n;
-		stack[sdepth].ptr = ptr;
+		stack[sdepth].off = off;
 		sdepth++;
 
 		ht = n->ht_down;
 		sel = 0;
-		if (ht->divisor)
-			sel = ht->divisor&u32_hash_fold(*(__be32*)(ptr+n->sel.hoff), &n->sel,n->fshift);
-
+		if (ht->divisor) {
+			__be32 *data, _data;
+
+			data = skb_header_pointer(skb, off + n->sel.hoff, 4,
+						  &_data);
+			if (!data)
+				goto out;
+			sel = ht->divisor & u32_hash_fold(*data, &n->sel,
+							  n->fshift);
+		}
 		if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT)))
 			goto next_ht;
 
 		if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) {
 			off2 = n->sel.off + 3;
-			if (n->sel.flags&TC_U32_VAROFFSET)
-				off2 += ntohs(n->sel.offmask & *(__be16*)(ptr+n->sel.offoff)) >>n->sel.offshift;
+			if (n->sel.flags & TC_U32_VAROFFSET) {
+				__be16 *data, _data;
+
+				data = skb_header_pointer(skb,
+							  off + n->sel.offoff,
+							  2, &_data);
+				if (!data)
+					goto out;
+				off2 += ntohs(n->sel.offmask & *data) >>
+					n->sel.offshift;
+			}
 			off2 &= ~3;
 		}
 		if (n->sel.flags&TC_U32_EAT) {
-			ptr += off2;
+			off += off2;
 			off2 = 0;
 		}
 
-		if (ptr < skb_tail_pointer(skb))
+		if (off < skb->len)
 			goto next_ht;
 	}
 
@@ -204,9 +226,10 @@ check_terminal:
 	if (sdepth--) {
 		n = stack[sdepth].knode;
 		ht = n->ht_up;
-		ptr = stack[sdepth].ptr;
+		off = stack[sdepth].off;
 		goto check_terminal;
 	}
+out:
 	return -1;
 
 deadloop:
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index bd1892f..d20fcd2 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -205,7 +205,7 @@ void __qdisc_run(struct Qdisc *q)
 		}
 	}
 
-	clear_bit(__QDISC_STATE_RUNNING, &q->state);
+	qdisc_run_end(q);
 }
 
 unsigned long dev_trans_start(struct net_device *dev)
@@ -561,6 +561,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 
 	INIT_LIST_HEAD(&sch->list);
 	skb_queue_head_init(&sch->q);
+	spin_lock_init(&sch->busylock);
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
@@ -797,7 +798,7 @@ static bool some_qdisc_is_busy(struct net_device *dev)
 
 		spin_lock_bh(root_lock);
 
-		val = (test_bit(__QDISC_STATE_RUNNING, &q->state) ||
+		val = (qdisc_is_running(q) ||
 		       test_bit(__QDISC_STATE_SCHED, &q->state));
 
 		spin_unlock_bh(root_lock);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0b52b8d..4be8d04 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1550,7 +1550,6 @@ static const struct Qdisc_class_ops htb_class_ops = {
 };
 
 static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
-	.next		=	NULL,
 	.cl_ops		=	&htb_class_ops,
 	.id		=	"htb",
 	.priv_size	=	sizeof(struct htb_sched),
@@ -1561,7 +1560,6 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
 	.init		=	htb_init,
 	.reset		=	htb_reset,
 	.destroy	=	htb_destroy,
-	.change		=	NULL /* htb_change */,
 	.dump		=	htb_dump,
 	.owner		=	THIS_MODULE,
 };