Hi Marc,
On Tue, Oct 22, 2024 at 9:03 AM Marc Zyngier <maz@xxxxxxxxxx> wrote:
>
> On Mon, 21 Oct 2024 05:22:15 +0100,
> Yu Zhao <yuzhao@xxxxxxxxxx> wrote:
> >
> > GIC v3 and later support SGI broadcast, i.e., the mode that routes
> > interrupts to all PEs in the system excluding the local CPU.
> >
> > Supporting this mode can avoid looping through all the remote CPUs
> > when broadcasting SGIs, especially for systems with 200+ CPUs. The
> > performance improvement can be measured with the rest of this series
> > booted with "hugetlb_free_vmemmap=on irqchip.gicv3_pseudo_nmi=1":
> >
> > cd /sys/kernel/mm/hugepages/
> > echo 600 >hugepages-1048576kB/nr_hugepages
> > echo 2048kB >hugepages-1048576kB/demote_size
> > perf record -g -- bash -c "echo 600 >hugepages-1048576kB/demote"
> >
> > gic_ipi_send_mask() bash sys time
> > Before: 38.14% 0m10.513s
> > After: 0.20% 0m5.132s
> >
> > Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
> > ---
> > drivers/irqchip/irq-gic-v3.c | 20 +++++++++++++++++++-
> > 1 file changed, 19 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
> > index ce87205e3e82..42c39385e1b9 100644
> > --- a/drivers/irqchip/irq-gic-v3.c
> > +++ b/drivers/irqchip/irq-gic-v3.c
> > @@ -1394,9 +1394,20 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
> > gic_write_sgi1r(val);
> > }
> >
> > +static void gic_broadcast_sgi(unsigned int irq)
> > +{
> > + u64 val;
> > +
> > + val = BIT(ICC_SGI1R_IRQ_ROUTING_MODE_BIT) | (irq << ICC_SGI1R_SGI_ID_SHIFT);
>
> As picked up by the test bot, please fix the 32bit build.
Will do.
> > +
> > + pr_devel("CPU %d: broadcasting SGI %u\n", smp_processor_id(), irq);
> > + gic_write_sgi1r(val);
> > +}
> > +
> > static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
> > {
> > int cpu;
> > + cpumask_t broadcast;
> >
> > if (WARN_ON(d->hwirq >= 16))
> > return;
> > @@ -1407,6 +1418,13 @@ static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
> > */
> > dsb(ishst);
> >
> > + cpumask_copy(&broadcast, cpu_present_mask);
>
> Why cpu_present_mask? I'd expect that cpu_online_mask should be the
> correct mask to use -- we don't IPI offline CPUs, in general.
This is exactly because "we don't IPI offline CPUs, in general",
assuming "we" means the kernel, not GIC.
My interpretation of what the GIC spec says ("0b1: Interrupts routed
to all PEs in the system, excluding self") is that it broadcasts IPIs to
"cpu_present_mask" (minus the local one). So if the kernel uses
"cpu_online_mask" here, GIC would send IPIs to offline CPUs
(cpu_present_mask ^ cpu_online_mask), which I don't know whether it's
a defined behavior.
But if you actually meant GIC doesn't IPI offline CPUs, then yes, here
the kernel should use "cpu_online_mask".
> > + cpumask_clear_cpu(smp_processor_id(), &broadcast);
> > + if (cpumask_equal(&broadcast, mask)) {
> > + gic_broadcast_sgi(d->hwirq);
> > + goto done;
> > + }
>
> So the (valid) case where you would IPI *everyone* is not handled as a
> fast path? That seems a missed opportunity.
You are right: it should handle that case.
> This also seem an like expensive way to do it. How about something
> like:
>
> int mcnt = cpumask_weight(mask);
> int ocnt = cpumask_weight(cpu_online_mask);
> if (mcnt == ocnt) {
> /* Broadcast to all CPUs including self */
Does the comment mean the following two steps?
1. Broadcasting to everyone else.
2. Sending to self.
My understanding of the "Interrupt Routing Mode" is that it can't
broadcast to all CPUs including self, and therefore we need the above
two steps, which still can be a lot faster. Is my understanding
correct?
> } else if (mcnt == (ocnt - 1) &&
> !cpumask_test_cpu(smp_processor_id(), mask)) {
> /* Broadcast to all but self */
> }
>
> which avoids the copy+update_full compare.
Thank you.
