[PATCH v2 5/5] powerpc: Remove -mno-sched-epilog

Segher Boessenkool segher at kernel.crashing.org
Sat Sep 15 07:18:46 AEST 2018


On Sat, Sep 15, 2018 at 06:43:05AM +1000, Nicholas Piggin wrote:
> On Fri, 14 Sep 2018 11:03:38 -0700
> Nick Desaulniers <ndesaulniers at google.com> wrote:
> 
> > On Thu, Sep 13, 2018 at 9:07 PM Joel Stanley <joel at jms.id.au> wrote:
> > > Last time this was proposed there was an issue reported:
> > >
> > >  https://lists.ozlabs.org/pipermail/linuxppc-dev/2014-September/121214.html  
> > 
> > Heh, did PASemi sell boxes? Interesting, I'll have to read up on my history.
> > 
> > On Thu, Sep 13, 2018 at 10:06 PM Nicholas Piggin <npiggin at gmail.com> wrote:
> > > I don't think we can remove it completely because up to at least 4.6
> > > maybe 4.8 has problems.
> > >
> > > I have a few patches lying around I started looking at this... I'll
> > > send them.  
> > 
> > Yeah, it's too bad the link above doesn't mention gcc version.
> > 
> > The gcc bugreport mentions fixing the bug in
> > 7563dc64585324f443f5ac107eb6d89ee813a2d2, not sure how to check what
> > release version of gcc that is? (Do they tag releases?)
> 
> I'm not sure, that's not in my gcc tree AFAIKS.

This is a git hash in the kernel tree.

> > Nick, do you have a test case or more context about this still being
> > an issue in gcc 4.8? (maybe I should wait for your patch series?)
> 
> Sorry I forgot to cc you. This has links to some of the sched
> epilog bugs.
> 
> https://marc.info/?l=linuxppc-embedded&m=153690223909654&w=2

PR44199 was backported to 4.4 and PR52828 is fixed in 4.8.


Segher


More information about the Linuxppc-dev mailing list