net: sched: don't release block->lock when dumping chains

Function tc_dump_chain() obtains and releases block->lock on each iteration
of its inner loop that dumps all chains on block. Outputting chain template
info is fast operation so locking/unlocking mutex multiple times is an
overhead when lock is highly contested. Modify tc_dump_chain() to only
obtain block->lock once and dump all chains without releasing it.

Signed-off-by: Vlad Buslov <[e-mail]>
Suggested-by: Cong Wang <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

net/sched/cls_api.c

···
 /* called with RTNL */
 static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct tcf_chain *chain, *chain_prev;
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
 	struct Qdisc *q = NULL;
 	struct tcf_block *block;
 	struct tcmsg *tcm = nlmsg_data(cb->nlh);
+	struct tcf_chain *chain;
 	long index_start;
 	long index;
 	u32 parent;
···
 	index_start = cb->args[0];
 	index = 0;
 
-	for (chain = __tcf_get_next_chain(block, NULL);
-	     chain;
-	     chain_prev = chain,
-		     chain = __tcf_get_next_chain(block, chain),
-		     tcf_chain_put(chain_prev)) {
+	mutex_lock(&block->lock);
+	list_for_each_entry(chain, &block->chain_list, list) {
 		if ((tca[TCA_CHAIN] &&
 		     nla_get_u32(tca[TCA_CHAIN]) != chain->index))
 			continue;
···
 			index++;
 			continue;
 		}
+		if (tcf_chain_held_by_acts_only(chain))
+			continue;
 		err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv,
 					 chain->index, net, skb, block,
 					 NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					 RTM_NEWCHAIN);
-		if (err <= 0) {
-			tcf_chain_put(chain);
+		if (err <= 0)
 			break;
-		}
 		index++;
 	}
+	mutex_unlock(&block->lock);
 
 	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
 		tcf_block_refcnt_put(block, true);