Messages in this thread | | | Date | Mon, 27 Jul 2020 21:41:14 -0700 | From | Ricardo Neri <> | Subject | Re: [PATCH 4/4] x86/cpu: Use SERIALIZE in sync_core() when available |
| |
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
| |