Messages in this thread | | | Date | Wed, 12 Apr 2023 14:50:01 +0100 | From | Conor Dooley <> | Subject | Re: [PATCH v2 1/3] cacheinfo: Check sib_leaf in cache_leaves_are_shared() |
| |
On Wed, Apr 12, 2023 at 03:20:19PM +0200, Pierre Gondois wrote: > > On Wed, Apr 12, 2023 at 02:34:11PM +0200, Pierre Gondois wrote:
> > Another silly question: > > For two caches of level M & N; M != N; M, N > 1 should they be detected > > as shared in the absence of any information in DT/ACPI? > > The comment (to me) reads as if they should not, but it is rather vague. > > I think they should. The naming of cache_leaves_are_shared() might be > misleading. The function is more trying to find out if 2 cache leaves struct > are representing the same cache. So maybe renaming the function to > cache_leaves_identical() might be better?
Nah, I don't think this is really the fault of anything other than the !DT && !ACPI situation. I'm just trying to make sure I understand the intended behaviour in that scenario, that's all.
> If there is no DT/ACPI, it is not possible to identify whether 2 cache leaves > are representing the same cache. The desired behaviour is just: > - If this_leaf or sib_leaf is a L1 cache, then the caches are not identical > (or shared if we use this wording)
> So the meaning of cache_leaves_identical() is a bit bent for this > configuration.
Fair enough. [unhandled content-type:application/pgp-signature] | |