[patch v3 31/36] x86/apic: Provide cpu_primary_thread mask

Kirill A. Shutemov kirill at shutemov.name
Mon May 29 17:54:28 PDT 2023


On Mon, May 29, 2023 at 11:31:29PM +0300, Kirill A. Shutemov wrote:
> On Mon, May 29, 2023 at 09:27:13PM +0200, Thomas Gleixner wrote:
> > On Mon, May 29 2023 at 05:39, Kirill A. Shutemov wrote:
> > > On Sat, May 27, 2023 at 03:40:02PM +0200, Thomas Gleixner wrote:
> > > But it gets broken again on "x86/smpboot: Implement a bit spinlock to
> > > protect the realmode stack" with
> > >
> > > [    0.554079] .... node  #0, CPUs:        #1  #2
> > > [    0.738071] Callback from call_rcu_tasks() invoked.
> > > [   10.562065] CPU2 failed to report alive state
> > > [   10.566337]   #3
> > > [   20.570066] CPU3 failed to report alive state
> > > [   20.574268]   #4
> > > ...
> > >
> > > Notably CPU1 is missing from "failed to report" list. So CPU1 takes the
> > > lock fine, but seems never unlocks it.
> > >
> > > Maybe trampoline_lock(%rip) in head_64.S somehow is not the same as
> > > &tr_lock in trampoline_64.S. I donno.
> > 
> > It's definitely the same in the regular startup (16bit mode), but TDX
> > starts up via:
> > 
> > trampoline_start64
> >   trampoline_compat
> >     LOAD_REALMODE_ESP <- lock
> > 
> > That place cannot work with that LOAD_REALMODE_ESP macro. The untested
> > below should cure it.
> 
> Yep, works for me.
> 
> Aaand the next patch that breaks TDX boot is... <drum roll>
> 
> 	x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it
> 
> Disabling parallel bringup helps. I didn't look closer yet. If you have
> an idea let me know.

Okay, it crashes around .Lread_apicid due to touching MSRs that trigger #VE.

Looks like the patch had no intention to enable parallel bringup on TDX.

+        * Intel-TDX has a secure RDMSR hypercall, but that needs to be
+        * implemented seperately in the low level startup ASM code.

But CC_ATTR_GUEST_STATE_ENCRYPT that used to filter it out is
SEV-ES-specific thingy and doesn't cover TDX. I don't think we have an
attribute that fits nicely here.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov



More information about the linux-riscv mailing list