Re: [RFC] Cpu-hotplug: Using the Process Freezer (try2)

[Andrew Morton <akpm@linux-foundation.org>]

On Tue, 3 Apr 2007 21:34:28 +0200
"Rafael J. Wysocki" <rjw@sisk.pl> wrote:

> > However, the hunk
> > 
> > @@ -1393,7 +1394,9 @@ long do_fork(unsigned long clone_flags,
> > 		tracehook_report_clone_complete(clone_flags, nr, p);
> > 
> > 		if (clone_flags & CLONE_VFORK) {
> > +			freezer_do_not_count();
> > 			wait_for_completion(&vfork);
> > +			freezer_count();
> > 			tracehook_report_vfork_done(p, nr);
> > 		}
> > 	} else {
> > 
> > Seems to be missing in the latest -mm's.
> 
> Good catch!
> 
> > Rafael / Andrew, 
> > 	Any reasons for leaving this hunk out?
> 
> No, absolutely not.  It's needed.
> 
> Moreover, freezer-fix-vfork-problem.patch from the broken-out -rc5-mm3
> contains it, so some other patch must have reverted this change.
> 
> [looks]
> 
> Ah, it's utrace-prep-2.patch .  Andrew?

urgh, I screwed up, sorry.

utrace-prep-2 reverts a bit of the underlying tree so that the utrace
patches (which are against mainline) don't throw a tremendous reject which
has to be fixed each time I pull Roland's tree.  I'm supposed to reapply
that change after the utrace patches but forgot.

--- a/kernel/fork.c~undo-utrace-prep-2
+++ a/kernel/fork.c
@@ -1387,7 +1387,9 @@ long do_fork(unsigned long clone_flags,
 			tracehook_report_clone_complete(clone_flags, nr, p);
 
 		if (clone_flags & CLONE_VFORK) {
+			freezer_do_not_count();
 			wait_for_completion(&vfork);
+			freezer_count();
 			if (likely(is_user))
 				tracehook_report_vfork_done(p, nr);
 		}
_