On Wed, Mar 10, 2021 at 04:03:31PM -0800, Doug Smythies wrote: > Hi Yu, > > I am just resending your e-mail, adjusting the "To:" list to > include the 3 others that have submitted similar patches. > Thanks for adding the authors. I'll combine their patch with their credits and send to Len for pulling.
thanks, Chenyu > ... Doug > > On Mon, Mar 8, 2021 at 8:11 AM Chen Yu <yu.c.c...@intel.com> wrote: > > > > Hi, > > On Mon, Mar 08, 2021 at 07:37:07AM -0800, Doug Smythies wrote: > > > On Mon, Mar 8, 2021 at 5:50 AM youling257 <youling...@gmail.com> wrote: > > > > > > > > this cause turbostat not work on amd cpu. > > > > > > > > root@localhost:~# /turbostat > > > > turbostat version 20.09.30 - Len Brown <l...@kernel.org> > > > > CPUID(0): AuthenticAMD 0xd CPUID levels; 0x8000001f xlevels; > > > > family:model:stepping 0x17:18:1 (23:24:1) > > > > > > There are already two fixes for this in the queue. > > > https://marc.info/?l=linux-pm&m=161382097503925&w=2 > > > https://marc.info/?l=linux-pm&m=161141701219263&w=2 > > Thanks for reporting and pointing this out. I assume these two patches are > > both fixing the > > same issue? It looks like these two patches should be merged into one: > > 1. Bingsong's patch access MSR_PKG_ENERGY_STAT only when RAPL_AMD_F17H is > > set, > > which is consistent with the original context. > > 2. Bas Nieuwenhuizen's patch also fixes the issue in idx_valid() > > in case RAPL_PKG was not set but with RAPL_AMD_F17H set. > > > > thanks, > > Chenyu
