Messages in this thread | | | Date | Sun, 02 Nov 2008 17:50:49 +0100 | From | Helge Deller <> | Subject | Re: [PATCH 1/1] USBHID: correct start/stop cycle |
| |
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
| |