On Fri, Mar 21, 2014 at 01:09:48PM +0200, Jani Nikula wrote: > On Fri, 21 Mar 2014, Daniel Vetter <daniel@xxxxxxxx> wrote: > > On Fri, Mar 21, 2014 at 07:51:58AM +0000, Chris Wilson wrote: > >> On Fri, Mar 21, 2014 at 07:40:56AM +0000, Chris Wilson wrote: > >> > On non-LLC platforms, when changing the cache level of an object, we may > >> > need to unbind it show that prefetching across page boundaries does not > >> s/show/so/ > >> > cross into a different memory domain. This requires us to unbind > >> > conflicting vma, but we did so was iterating over the objects vma in an > >> s/was// > >> > unsafe manner (as the list was being modified as we iterated). > >> > >> Coffee will kick in in about 5 minutes. > > > > Fixed and applied, thanks for the patch. > > Given the regression was introduced in v3.12 I thought this would've > been fixes & cc: stable. Oops, thanks for catching this. cc: stable added. My Linus weather forcast tells me that -fixes is closed for 3.14 already, so dinq is good enough. -Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/intel-gfx
