On Thu, Jul 20, 2023 at 09:38:51PM -0700, Joe Perches wrote:
> On Thu, 2023-07-20 at 20:56 -0700, Paul E. McKenney wrote:
>
> >
> > > That works much better, thank you! I will update the patch on my
> > > next rebase.
> >
> > As shown below. Is this what you had in mind?
> []
> > commit 496aa3821b40459b107f4bbc14ca867daad21fb6
> > Author: Paul E. McKenney <paulmck@xxxxxxxxxx>
> > Date: Thu Jul 6 11:48:07 2023 -0700
> >
> > checkpatch: Complain about unexpected uses of RCU Tasks Trace
> >
> > RCU Tasks Trace is quite specialized, having been created specifically
> > for sleepable BPF programs. Because it allows general blocking within
> > readers, any new use of RCU Tasks Trace must take current use cases into
> > account. Therefore, update checkpatch.pl to complain about use of any of
> > the RCU Tasks Trace API members outside of BPF and outside of RCU itself.
> []
> > diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
> []
> > @@ -7457,6 +7457,30 @@ sub process {
> > }
> > }
> >
> > +# Complain about RCU Tasks Trace used outside of BPF (and of course, RCU).
> > + our $rcu_trace_funcs = qr{(?x:
> > + rcu_read_lock_trace |
> > + rcu_read_lock_trace_held |
> > + rcu_read_unlock_trace |
> > + call_rcu_tasks_trace |
> > + synchronize_rcu_tasks_trace |
> > + rcu_barrier_tasks_trace |
> > + rcu_request_urgent_qs_task
> > + )};
> > + our $rcu_trace_paths = qr{(?x:
> > + kernel/bpf/ |
> > + include/linux/bpf |
> > + net/bpf/ |
> > + kernel/rcu/ |
> > + include/linux/rcu
> > + )};
> > + if ($line =~ /\b$rcu_trace_funcs\s*\(/) {
> > + if ($realfile !~ m@^$rcu_trace_paths@) {
> > + WARN("RCU_TASKS_TRACE",
> > + "use of RCU tasks trace is incorrect outside BPF or core RCU code\n" . $herecurr);
>
> Exactly yes.
>
> (though I still suggest a capture group to show the function like below)
>
> if ($line =~ /\b($rcu_trace_funcs)\s*\(/ &&
> $realfile !~ m{^$rcu_trace_paths}) {
> WARN("RCU_TASKS_TRACE",
> "use of RCU task trace '$1' is incorrect outside BPF or core RCU code\n" . $herecurr);
> }
That does seem to work!
I will fold this change in on my next rebase.
Thanx, Paul
