Re: [PATCH v1 2/2] perf auxtrace: Optimize barriers with load-acquire and store-release

[Leo Yan]

On Tue, Jun 01, 2021 at 12:45:16PM +0300, Adrian Hunter wrote:
> On 1/06/21 12:17 pm, Peter Zijlstra wrote:
> > On Tue, Jun 01, 2021 at 12:07:31PM +0300, Adrian Hunter wrote:
> >> __sync_xxx_compare_and_swap is out-of-date now. This page:
> >>
> >> https://gcc.gnu.org/onlinedocs/gcc/_005f_005fsync-Builtins.html#g_t_005f_005fsync-Builtins
> >>
> >> recommends '__atomic' builtins instead.
> > 
> > perf doesn't seem to use that.
> 
> I guess we could drop support for the compat case; add validation:
> 
> "Error, 32-bit perf cannot record AUX area traces from a 64-bit kernel.
> Please use a 64-bit version of perf instead."

Not sure what's a good method to detect the compat case.  I can think
out to use below conditions to check the compat case:

  if ((sizeof(unsigned long) == 4) &&
      (machine__is(machine, "x86_64") || machine__is(machine, "arm64") ||
       machine__is(machine, "aarch64")))  {

       pr_warn("Error, 32-bit perf cannot record from a 64-bit kernel.\n"
               "Please use a 64-bit version of perf instead.\n");
       return -ENOTSUP;
  }

Just want to check if any better to detect compat case in perf?

Thanks for suggestions,
Leo

> >> Since atomics are needed only for the "compat" case (i.e. 32-bit perf with 64-bit kernel)
> >> you could try to find an elegant way to check for a 64-bit kernel, and avoid the atomics
> >> for a 32-bit perf with 32-bit kernel.
> > 
> > Most 32bit archs cannot do 64bit atomics. I suppose the only reason this
> > doesn't explode is because the aux stuff isn't supported on many
> > architectures?
> > 
> 
> Yes but presumably the race itself is unlikely since the upper byte changes only once every 4GiB.
>