[lkml]   [2010]   [Sep]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [RFC PATCH 1/2] perf_events: add support for per-cpu per-cgroup monitoring (v3)

On 09/10/2010 10:16 AM, Peter Zijlstra wrote:
> On Thu, 2010-09-09 at 23:41 +0200, Stephane Eranian wrote:
>>> alloc_percpu() is zalloc_percpu() in fact, memory is already cleared.
>> I remember thinking about this and trying to trace to the code down
>> to figure this out. But it is rather complicated. If alloc_percpu() always
>> clears the memory, then I think that calling is zalloc_percpu()
>> would be more helpful....

Maybe but at this point it might be a bit too late. The allocator has
been that way since the beginning.

> pcpu_populate_chunk() in mm/percpu-vm.c does indeed do that memset, the
> one in mm/percpu-km.c does not.
> It is not obviously clear to me the -km allocator does indeed result in
> zero filled memory.

Nice catch. Fortunately, the -km allocator isn't currently being used
in upstrea although it was enabled for linux-next a couple of days
ago. I'll fix it up.

Thank you.


 \ /
  Last update: 2010-09-10 10:45    [W:0.038 / U:1.124 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site