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

[ Upstream commit efbf78973978b0d25af59bc26c8013a942af6e64 ]

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 0 insertions, 1 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index becf86aa4ac6..d6ec5a5a6782 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -280,7 +280,6 @@ 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)