net_sched: get rid of rcu_barrier() in tcf_block_put_ext()

Both Eric and Paolo noticed the rcu_barrier() we use in
tcf_block_put_ext() could be a performance bottleneck when
we have a lot of tc classes.

Paolo provided the following to demonstrate the issue:

tc qdisc add dev lo root htb
for I in `seq 1 1000`; do
        tc class add dev lo parent 1: classid 1:$I htb rate 100kbit
        tc qdisc add dev lo parent 1:$I handle $((I + 1)): htb
        for J in `seq 1 10`; do
                tc filter add dev lo parent $((I + 1)): u32 match ip src 1.1.1.$J
        done
done
time tc qdisc del dev root

real    0m54.764s
user    0m0.023s
sys     0m0.000s

The rcu_barrier() there is to ensure we free the block after all chains
are gone, that is, to queue tcf_block_put_final() at the tail of workqueue.
We can achieve this ordering requirement by refcnt'ing tcf block instead,
that is, the tcf block is freed only when the last chain in this block is
gone. This also simplifies the code.

Paolo reported after this patch we get:

real    0m0.017s
user    0m0.000s
sys     0m0.017s

Tested-by: Paolo Abeni <pabeni@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 65d0d25f2648f645bad707c348cbb6454ef75cd5..02e7ad8b8dad85bb8e83eaeeac977658323764de 100644 (file)
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -278,7 +278,6 @@ struct tcf_block {
        struct net *net;
        struct Qdisc *q;
        struct list_head cb_list;
-       struct work_struct work;
 };
 
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ddcf04b4ab43732c001869f70d63ea193768ebc3..d51051dd8f7d72e9cc7efd4bd6de9768f595b4a4 100644 (file)
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -218,8 +218,12 @@ static void tcf_chain_flush(struct tcf_chain *chain)
 
 static void tcf_chain_destroy(struct tcf_chain *chain)
 {
+       struct tcf_block *block = chain->block;
+
        list_del(&chain->list);
        kfree(chain);
+       if (list_empty(&block->chain_list))
+               kfree(block);
 }
 
 static void tcf_chain_hold(struct tcf_chain *chain)
@@ -330,27 +334,13 @@ int tcf_block_get(struct tcf_block **p_block,
 }
 EXPORT_SYMBOL(tcf_block_get);
 
-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;
-
-       rtnl_lock();
-
-       /* At this point, all the chains should have refcnt == 1. */
-       list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
-               tcf_chain_put(chain);
-       rtnl_unlock();
-       kfree(block);
-}
-
 /* XXX: Standalone actions are not allowed to jump to any chain, and bound
  * actions should be all removed after flushing.
  */
 void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
                       struct tcf_block_ext_info *ei)
 {
-       struct tcf_chain *chain;
+       struct tcf_chain *chain, *tmp;
 
        /* Hold a refcnt for all chains, except 0, so that they don't disappear
         * while we are iterating.
@@ -364,13 +354,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
        tcf_block_offload_unbind(block, q, ei);
 
-       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.
+       /* At this point, all the chains should have refcnt >= 1. Block will be
+        * freed after all chains are gone.
         */
-       rcu_barrier();
-       tcf_queue_work(&block->work);
+       list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+               tcf_chain_put(chain);
 }
 EXPORT_SYMBOL(tcf_block_put_ext);