Re: [PATCH 1/4] x86/coco: Add a new CC attribute to unify cache flush during kexec

[Huang, Kai]

On Wed, 2024-02-28 at 10:54 +0800, Dave Young wrote:
> On Fri, 23 Feb 2024 at 18:41, Dave Young <dyoung@xxxxxxxxxx> wrote:
> > 
> > On Wed, 21 Feb 2024 at 17:33, Borislav Petkov <bp@xxxxxxxxx> wrote:
> > > 
> > > On Tue, Feb 20, 2024 at 04:30:13PM -0600, Tom Lendacky wrote:
> > > > I believe the issues were that different Intel systems would hang or reset
> > > > and it was bisected to that commit that added the WBINVD. It was a while
> > > > ago, but I remember that they were similar to what the 1f5e7eb7868e commit
> > > > ended up fixing, which was debugged because sometimes the WBINVD was still
> > > > occasionally issued resulting in the following patch
> > > > 
> > > >   9b040453d444 ("x86/smp: Dont access non-existing CPUID leaf")
> > > > 
> > > > It just means that if we go to an unconditional WBINVD, then we need to be
> > > > careful.
> > > 
> > > Let's try it.
> > > 
> > > Dave, do you remember what issues
> > > 
> > >   f23d74f6c66c ("x86/mm: Rework wbinvd, hlt operation in stop_this_cpu()")
> > > 
> > > fixed?
> > 
> > It should be a kexec reboot failure describe in below thread:
> > https://lore.kernel.org/lkml/20180117072123.GA1866@xxxxxxxxxxxxxxxxxxxxxxxxxx/
> > 
> > > 
> > > If so, can you try the below diff ontop of latest tip/master to see if
> > > those issues would reappear?
> > 
> > It was reproduced on an old laptop (Thinkpad t440s or t480s, I can not
> > remember), but I have replaced them with a new different one.  I tried
> > the latest tip-master with the if condition commented out, kexec
> > reboot works fine.
> > 
> > Let me try to find an old laptop to see if I can do more tests, will
> > get back later next week.
> 
> Update: tested on an old laptop as well,  I did not find any problems
> with unconditional native_wbinvd(), kexec and kdump works fine.
> 
> 

Hi DaveY,

Thanks for getting back and I appreciate your help.

Hi Boris/DaveH,

Based on this I'll change to do unconditional WBINVD during kexec() for in
stop_this_cpu() and relocate_kernel().  Please let me know if you have any
comments.

Thanks all!