Hi Will, On 4/9/20 2:26 PM, Will Deacon wrote: > Hi Vincenzo, > > Sorry, I was on holiday when you posted this and it slipped through the > cracks. > No issue at all. Thank you for getting back to me. > On Mon, Mar 16, 2020 at 03:37:23PM +0000, Vincenzo Frascino wrote: >>> On Fri, Mar 13, 2020 at 03:43:40PM +0000, Vincenzo Frascino wrote: >>>> The vDSO library should only include the necessary headers required for >>>> a userspace library (UAPI and a minimal set of kernel headers). To make >>>> this possible it is necessary to isolate from the kernel headers the >>>> common parts that are strictly necessary to build the library. >>>> >>>> Introduce asm/vdso/arch_timer.h to contain all the arm64 specific >>>> code. This allows to replace the second isb() in __arch_get_hw_counter() >>>> with a fake dependent stack read of the counter which improves the vdso >>>> library peformances of ~4.5%. Below the results of vdsotest [1] ran for >>>> 100 iterations. >>> >>> The subject seems to imply a non-functional change but as you read, it >>> gets a lot more complicated. Could you keep the functional change >>> separate from the header clean-up, maybe submit it as an independent >>> patch? And it shouldn't go in without Will's ack ;). >>> >> >> It is fine by me. I will repost the series with the required fixes and without >> this patch. This will give to me enough time to address Mark's comments as well >> and to Will to have a proper look. > > Please can you post whatever is left at -rc1? I'll have a look then, but > let's stick to just moving code around rather than randomly changing it > at the same time, ok? > Sure, I will try to re-post it by -rc1 and take on board your comments. > Thanks, > > Will > -- Regards, Vincenzo
