Re: [RFC PATCH v2 0/3] x86/mm/tlb: Defer TLB flushes with PTI

[Dave Hansen]

On 8/23/19 3:52 PM, Nadav Amit wrote:
> n_pages		concurrent	+deferred-pti		change
> -------		----------	-------------		------
>  1		2119		1986 			-6.7%
>  10		6791		5417 			 -20%
> 
> Please let me know if I missed something that affects security or
> performance.

Hi Nadav,

Is this in a VM or on bare metal?  Could you also share the bare
/proc/cpuinfo for one of the CPU threads?  I want to make sure that any
oddities in the stepping or microcode are known.