On Fri, Jan 06, 2023 at 03:33:27PM -0700, Jens Axboe wrote: > On 1/3/23 9:21?AM, Greg KH wrote: > > On Tue, Jan 03, 2023 at 08:57:57AM -0700, Jens Axboe wrote: > >> On 1/3/23 8:54?AM, Greg KH wrote: > >>> On Tue, Jan 03, 2023 at 10:37:22AM +0000, Russell King (Oracle) wrote: > >>>> Hi Greg, > >>>> > >>>> Probably not a good idea to pick this up just yet - there's been a > >>>> report of a performance regression due to this patch. > >>> > >>> There is? It's been in the tree since 5.11 which is quite old. So I > >>> think we can keep it for now and if a fix is found I will be glad to > >>> backport it to 5.10 as well. > >> > >> Just waiting on testing, came in the other day. Here's the thread: > >> > >> https://lore.kernel.org/lkml/7ecb8f3c-2aeb-a905-0d4a-aa768b9649b5@xxxxxxxxxx/ > > > > Thanks for the link, I'll watch out for that. > > This is now upstream as: > > commit 191f8453fc99a537ea78b727acea739782378b0d > Author: Jens Axboe <axboe@xxxxxxxxx> > Date: Wed Jan 4 07:48:37 2023 -0700 > > ARM: renumber bits related to _TIF_WORK_MASK > > and marked for stable, so it can go to 5.10/5.15-stable. Thanks, now queued up! greg k-h