Messages in this thread | | | Date | Wed, 29 Nov 2017 16:26:31 +0100 | From | Peter Zijlstra <> | Subject | Re: [PATCH] x86/mm/kaiser: Flush the correct ASID in __native_flush_tlb_single() |
| |
On Wed, Nov 29, 2017 at 07:21:23AM -0800, Dave Hansen wrote: > Yes, that works. Also, as I think about it, INVLPG is a safer > (bug-resistant) instruction to use too. INVPCID _can_ get the current > (kernel) ASID wrong, as we saw. But INVLPG always uses the current one > and can't be wrong about flushing the *current* ASID. > > I think Andy measured it to be faster than INVPCID too. > > So, maybe we should just remove INVPCID's use entirely.
With my patches the below invpcid_flush_one() is the only remaining user (not counting flush_tlb_global).
I know Andy hates on INVPCID, but I could not convince myself that doing a full user invalidate makes sense for flush_tlb_single(), then again maybe it does, the patch is trivial after this.
> > arch/x86/include/asm/tlbflush.h | 23 +++++++---------------- > > 1 file changed, 7 insertions(+), 16 deletions(-) > > > > diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h > > index 481d5094559e..9587722162ee 100644 > > --- a/arch/x86/include/asm/tlbflush.h > > +++ b/arch/x86/include/asm/tlbflush.h > > @@ -438,29 +438,20 @@ static inline void __native_flush_tlb_single(unsigned long addr) > > { > > u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); > > > > + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); > > + > > + if (!kaiser_enabled) > > + return; > > + > > /* > > * Some platforms #GP if we call invpcid(type=1/2) before > > * CR4.PCIDE=1. Just call invpcid in the case we are called > > * early. > > */ > > + if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) > > flush_user_asid(loaded_mm_asid); > > + else > > invpcid_flush_one(user_asid(loaded_mm_asid), addr); > > }
| |