Re: [PATCH] tools/liblockdep: Fix debug_check thinko in mutex destroy

[Sasha Levin <sasha.levin@oracle.com>]

On 12/14/2014 09:21 AM, Kirill Smelkov wrote:
> On Mon, Dec 08, 2014 at 09:59:54AM -0500, Sasha Levin wrote:
>> > On 12/08/2014 06:07 AM, Kirill Smelkov wrote:
>>> > > In mutex destroy code currently we pass to debug_check_no_locks_freed()
>>> > > 
>>> > >     [mem_from, mem_end)
>>> > > 
>>> > > address region. But debug_check_no_locks_freed() accepts
>>> > > 
>>> > >     mem_from, mem_*len*
>>> > > 
>>> > > i.e. second parameter is region length, not end address. And it was
>>> > > always so, starting from 2006 (fbb9ce95 "lockdep: core").
>>> > > 
>>> > > Fix it, or else on a mutex destroy we wrongly check
>>> > > much-wider-than-mutex region and can find not-yet-released other locks
>>> > > there and wrongly report BUGs on them.
>> > 
>> > Great catch, thanks!
> Thanks, where is this patch is/will-be applied?
> 
> I mean I could not find it neither in
> 
>     git://git.kernel.org/pub/scm/linux/kernel/git/sashal/linux.git
> 
> nor anywhere in linux-next nor in Linus's tree.

I'll send it to Ingo once v3.19-rc1 is out.


Thanks,
Sasha