bpf, sched: Remove unneeded rcu_read_lock() around BPF program invocation

The rcu_read_lock() call in cls_bpf and act_bpf are redundant: on the TX
side, there's already a call to rcu_read_lock_bh() in __dev_queue_xmit(),
and on RX there's a covering rcu_read_lock() in
netif_receive_skb{,_list}_internal().

With the previous patches we also amended the lockdep checks in the map
code to not require any particular RCU flavour, so we can just get rid of
the rcu_read_lock()s.
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210624160609.292325-7-toke@redhat.com

net/sched/act_bpf.c

@@ -43,7 +43,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
 	tcf_lastuse_update(&prog->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb);
 
-	rcu_read_lock();
 	filter = rcu_dereference(prog->filter);
 	if (at_ingress) {
 		__skb_push(skb, skb->mac_len);
@@ -56,7 +55,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
 	}
 	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
 		skb_orphan(skb);
-	rcu_read_unlock();
 
 	/* A BPF program may overwrite the default action opcode.
 	 * Similarly as in cls_bpf, if filter_res == -1 we use the

net/sched/cls_bpf.c

@@ -85,8 +85,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_bpf_prog *prog;
 	int ret = -1;
 
-	/* Needed here for accessing maps. */
-	rcu_read_lock();
 	list_for_each_entry_rcu(prog, &head->plist, link) {
 		int filter_res;
 
@@ -131,7 +129,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		break;
 	}
-	rcu_read_unlock();
 
 	return ret;
 }