Re: [PATCH 4.14 088/157] irqchip/gic-v3-its: Dont bind LPI to unavailable NUMA node
From: Greg Kroah-Hartman
Date: Mon Jul 02 2018 - 04:34:47 EST
On Mon, Jul 02, 2018 at 08:44:05AM +0100, Marc Zyngier wrote:
> On 01/07/18 17:22, Greg Kroah-Hartman wrote:
> > 4.14-stable review patch. If anyone has any objections, please let me know.
> >
> > ------------------
> >
> > From: Yang Yingliang <yangyingliang@xxxxxxxxxx>
> >
> > commit c1797b11a09c8323c92b074fd48b89a936c991d0 upstream.
> >
> > On a NUMA system, if an ITS is local to an offline node, the ITS driver may
> > pick an offline CPU to bind the LPI. In this case, pick an online CPU (and
> > the first one will do).
> >
> > But on some systems, binding an LPI to non-local node CPU may cause
> > deadlock (see Cavium erratum 23144). In this case, just fail the activate
> > and return an error code.
> >
> > Signed-off-by: Yang Yingliang <yangyingliang@xxxxxxxxxx>
> > Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
> > Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> > Cc: Jason Cooper <jason@xxxxxxxxxxxxxx>
> > Cc: Alexandre Belloni <alexandre.belloni@xxxxxxxxxxx>
> > Cc: Sumit Garg <sumit.garg@xxxxxxxxxx>
> > Cc: stable@xxxxxxxxxxxxxxx
> > Link: https://lkml.kernel.org/r/20180622095254.5906-5-marc.zyngier@xxxxxxx
> > Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> >
> > ---
> > drivers/irqchip/irq-gic-v3-its.c | 9 ++++++++-
> > 1 file changed, 8 insertions(+), 1 deletion(-)
> >
> > --- a/drivers/irqchip/irq-gic-v3-its.c
> > +++ b/drivers/irqchip/irq-gic-v3-its.c
> > @@ -2221,7 +2221,14 @@ static void its_irq_domain_activate(stru
> > cpu_mask = cpumask_of_node(its_dev->its->numa_node);
> >
> > /* Bind the LPI to the first possible CPU */
> > - cpu = cpumask_first(cpu_mask);
> > + cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
> > + if (cpu >= nr_cpu_ids) {
> > + if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
> > + return -EINVAL;
>
> As reported by the kbuild robot, you need to drop the return value here
> (the prototype was changed post 4.14). A WARN_ON() could be useful to
> detect the case though.
Thanks, now done (the return change, not WARN_ON, those are just
ignored). I've pushed out a -rc2 with that fix in it.
greg k-h