On Fri, 9 May 2025 14:53:38 -0700
Andrii Nakryiko <[email protected]> wrote:

> > @@ -224,6 +224,10 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, 
> > bool user,
> >         struct perf_callchain_entry_ctx ctx;
> >         int rctx, start_entry_idx;
> >
> > +       /* crosstask is not supported for user stacks */
> > +       if (crosstask && user)
> > +               return NULL;  
> 
> I think get_perf_callchain() supports requesting both user and kernel
> stack traces, and if it's crosstask, you can still get kernel (but not
> user) stack, if I'm reading the code correctly.
> 
> So by just returning NULL early you will change this behavior, no?

Basically you are saying that one could ask for a kernel/user stack trace
with crosstask enabled and still just get the kernel trace?

If this is the case, then I think it may be best to remove patches 15-18
from this series and work on them in the "perf specific" series, as this
doesn't have anything to do with the unwind infrastructure itself.

Actually, patch 14 doesn't either, so I may move that one too (and keep the
acks to it).

Thanks,

-- Steve


> 
> > +
> >         entry = get_callchain_entry(&rctx);
> >         if (!entry)
> >                 return NULL;

Reply via email to