Re: [PATCH 1/1] USBHID: correct start/stop cycle

[Helge Deller <deller@gmx.de>]

Jiri Slaby wrote:
> Helge Deller napsal(a):
>> Jiri Slaby wrote:
>>> On 11/02/2008 12:02 AM, Jiri Kosina wrote:
>>>> On Sat, 1 Nov 2008, Jiri Slaby wrote:
>>>>
>>>>> `stop' left out usbhid->urb* pointers and so the next `start' thought
>>>>> it needs to allocate nothing and used the memory pointers previously
>>>>> pointed to. This led to memory corruption and device malfunction.
>>> [...]
>>>> could you please verify whether this patch fixes the corruption you
>>>> were experiencing?
>>> btw. this is not expected to fix that, but if it does, the better ;).
>> I tried the patch and sadly it didn't fixed the parisc bug.
> 
> Could you bisect it?

I fully bisected it, and the final "buggy" patch seems to have been 
Denys Vlasenko's patch: cb8f488c33539f096580e202f5438a809195008f
(see 
http://github.com/jonsmirl/digispeaker/commit/cb8f488c33539f096580e202f5438a809195008f)
Denys: Any reason you removed "!prev" in front of "expand_stack" ? It 
seems wrong to remove the prev-check, else it would crash in 
expand_upwards(in the CONFIG_STACK_GROWSUP case).
This is parisc architecture (stack grows up, big-endian).

Sadly reverting just this patch, didn't fixed the bugzilla bug either: 
http://bugzilla.kernel.org/show_bug.cgi?id=11913
I think I need to redo all of my bisecting again... sigh...

Helge