On Tue, Aug 6, 2024 at 7:05 AM Oliver Sang <oliver.sang@xxxxxxxxx> wrote: > > hi, Linus, > > On Mon, Aug 05, 2024 at 12:33:58PM -0700, Linus Torvalds wrote: > > On Mon, 5 Aug 2024 at 11:55, Linus Torvalds > > <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote: > > > > > > So please consider this a "maybe something like this" patch, but that > > > 'arch_unmap()' really is pretty nasty > > > > Actually, the whole powerpc vdso code confused me. It's not the vvar > > thing that wants this close thing, it's the other ones that have the > > remap thing. > > > > .. and there were two of those error cases that needed to reset the > > vdso pointer. > > > > That all shows just how carefully I was reading this code. > > > > New version - still untested, but now I've read through it one more > > time - attached. > > we tested this version by applying it directly upon 8be7258aad, but seems it > have little impact to performance. still similar regression if comparing to > ff388fe5c4. Hi, I've just sent out a patch set[1] that should alleviate (or hopefully totally fix) these performance regressions. It'd be great if you could test it. For everyone: Apologies if you're in the CC list and I didn't CC you, but I tried to keep my patch set's CC list relatively short and clean (and I focused on the active participants). Everyone's comments are very welcome. [1]: https://lore.kernel.org/all/20240806212808.1885309-1-pedro.falcato@xxxxxxxxx/ -- Pedro
