On Mon, Feb 5, 2024 at 10:54 AM Jan Kara <jack@xxxxxxx> wrote: > > On Fri 02-02-24 13:25:20, Sedat Dilek wrote: > > On Fri, Feb 2, 2024 at 1:12 PM Jan Kara <jack@xxxxxxx> wrote: > > > > > > On Fri 26-01-24 21:08:28, Kent Overstreet wrote: > > > > *_lock_nested() is fundamentally broken; lockdep needs to check lock > > > > ordering, but we cannot device a total ordering on an unbounded number > > > > of elements with only a few subclasses. > > > > > > > > the replacement is to define lock ordering with a proper comparison > > > > function. > > > > > > > > fs/pipe.c was already doing everything correctly otherwise, nothing > > > > much changes here. > > > > > > > > Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx> > > > > Cc: Christian Brauner <brauner@xxxxxxxxxx> > > > > Cc: Jan Kara <jack@xxxxxxx> > > > > Signed-off-by: Kent Overstreet <kent.overstreet@xxxxxxxxx> > > > > > > I had to digest for a while what this new lockdep lock ordering feature is > > > about. I have one pending question - what is the motivation of this > > > conversion of pipe code? AFAIU we don't have any problems with lockdep > > > annotations on pipe->mutex because there are always only two subclasses? > > > > > > Honza > > > > Hi, > > > > "Numbers talk - Bullshit walks." (Linus Torvalds) > > > > In things of pipes - I normally benchmark like this (example): > > > > root# cat /dev/sdc | pipebench > /dev/null > > > > Do you have numbers for your patch-series? > > Sedat AFAIU this patch is not about performance at all but rather about > lockdep instrumentation... But maybe I'm missing your point? > Sorry, I missed the point, Jan. -Sedat-
