lkml.org 
[lkml]   [2014]   [Mar]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: perf_fuzzer compiled for x32 causes reboot
From
Date
The bottom line is that if we want hard numbers we probably have to measure.

Hoisting the cr2 read is a no-brainer, might even help performance...

On March 1, 2014 1:50:42 AM PST, Borislav Petkov <bp@alien8.de> wrote:
>On Sat, Mar 01, 2014 at 10:16:50AM +0100, Ingo Molnar wrote:
>>
>> * Steven Rostedt <rostedt@goodmis.org> wrote:
>>
>> > > Also, this function is called a _LOT_ under certain workloads, I
>> > > don't know how cheap a CR2 read is, but it had better be really
>> > > cheap.
>> >
>> > That's a HPA question.
>>
>> We read CR2 in the page fault hot path, so it's on the top of CPU
>> architects' minds and it's reasonably optimized. A couple of cycles
>> IIRC, but would be nice to hear actual numbers.
>
>Yeah, we were discussing this last night on IRC.
>
>And hpa actually meant that the optimization potential was there but no
>one did do it, except maybe Transmeta. :-)
>
>So the expensive thing is writing to CR2 because it is a serializing
>instruction. In fact, all writes to control registers except CR8 are
>serializing.
>
>The reading from CR2 should be cheaper but not as cheap as a normal
>MOV %reg %reg is. On AMD, MOV %reg, %cr2 is done with microcode so
>definitely at least a couple of cycles and I'd guess it is not a
>trivial
>MOV on Intel too.
>
>Maybe a way to hide this cost is the OoO, as hpa suggested, depending
>on
>how much parallelism that particular code region can offer (serializing
>instructions close by).

--
Sent from my mobile phone. Please pardon brevity and lack of formatting.


\
 
 \ /
  Last update: 2014-03-01 18:41    [W:0.235 / U:0.044 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site