Re: [PATCH 4/4] x86/cpu: Use SERIALIZE in sync_core() when available

[Ricardo Neri <ricardo.neri-calderon@linux.intel.com>]

On Mon, Jul 27, 2020 at 03:30:20PM +0200, peterz@infradead.org wrote:
> On Mon, Jul 27, 2020 at 03:05:36PM +0200, peterz@infradead.org wrote:
> > Yeah, I'm not sure.. the 'funny' thing is that typically call
> > sync_core() from an IPI anyway. And the synchronous broadcast IPI is by
> > far the most expensive part of that.
> > 
> > Something like this...
> > 
> > diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
> > index 20e07feb4064..528e049ee1d9 100644
> > --- a/arch/x86/kernel/alternative.c
> > +++ b/arch/x86/kernel/alternative.c
> > @@ -989,12 +989,13 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
> >  
> >  static void do_sync_core(void *info)
> >  {
> > -	sync_core();
> > +	/* IRET implies sync_core() */
> >  }
> >  
> >  void text_poke_sync(void)
> >  {
> >  	on_each_cpu(do_sync_core, NULL, 1);
> > +	sync_core();
> >  }
> >  
> >  struct text_poke_loc {
> 
> So 'people' have wanted to optimize this for NOHZ_FULL and I suppose
> virt as well.
> 
> IFF VMENTER is serializing, I suppose we can simply do something like:
> 
> bool text_poke_cond(int cpu, void *info)
> {
> 	/*
> 	 * If we observe the vCPU is preempted, it will do VMENTER
> 	 * no point in sending an IPI to SERIALIZE.
> 	 */
> 	return !vcpu_is_preempted(cpu);
> }
> 
> void text_poke_sync(void)
> {
> 	smp_call_function_many_cond(cpu_possible_mask,
> 				    do_sync_core, NULL, 1, text_poke_cond);
> 	sync_core();
> }
> 
> The 'same' for NOHZ_FULL, except we need to cmpxchg a value such that
> if the cmpxchg() succeeds we know the CPU is in userspace and will
> SERIALIZE on the next entry. Much like kvm_flush_tlb_others().
> 
> 
> Anyway, that's all hand-wavey.. I'll let someone that cares about those
> things write actual patches :-)

I think I got a little lost here. If I understand correctly, there are
two alternatives to implement support for serialize better:

  a) alternative(IRET_TO_SELF, SERIALIZE, X86_FEATURE_SERIALIZE); or
  b) asm volatile("1:.byte 0xf, 0x1, 0xe8;2:" _ASM_EXTABLE(1b:2b)

a) would be the traditional and simpler solution. b) would rely on
causing an #UD and getting an IRET on existing hardware b) would need some
more optimization work when handling the exception and a few reworks on
the poke patching code.

Which option should I focus on? Which option would be more desirable/better?

Thanks and BR,
Ricardo