Re: [Qestion] Softlockup when send IPI to other CPUs

[Catalin Marinas]

Hi  Shijith,

On Thu, Jan 24, 2019 at 07:00:42AM +0000, Shijith Thotton wrote:
> On 01/23/2019 11:45 PM, Catalin Marinas wrote:
> > diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
> > index 30695a868107..5c9073bace83 100644
> > --- a/arch/arm64/mm/flush.c
> > +++ b/arch/arm64/mm/flush.c
> > @@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, unsigned long len)
> >   		__clean_dcache_area_pou(kaddr, len);
> >   		__flush_icache_all();
> >   	} else {
> > -		flush_icache_range(addr, addr + len);
> > +		/*
> > +		 * Don't issue kick_all_cpus_sync() after I-cache invalidation
> > +		 * for user mappings.
> > +		 */
> > +		__flush_icache_range(addr, addr + len);
> >   	}
> >   }
> 
> We also faced similar issue with LTP test migrate_pages03 in past and this patch 
> fixes the issue.
> 
> http://lists.infradead.org/pipermail/linux-arm-kernel/2019-January/623574.html

Thanks for confirming. I presume I can add your tested-by.

-- 
Catalin