[patch 27/30] xen/events: Only force affinity mask for percpu interrupts

[Thomas Gleixner <tglx@xxxxxxxxxxxxx>]

All event channel setups bind the interrupt on CPU0 or the target CPU for
percpu interrupts and overwrite the affinity mask with the corresponding
cpumask. That does not make sense.

The XEN implementation of irqchip::irq_set_affinity() already picks a
single target CPU out of the affinity mask and the actual target is stored
in the effective CPU mask, so destroying the user chosen affinity mask
which might contain more than one CPU is wrong.

Change the implementation so that the channel is bound to CPU0 at the XEN
level and leave the affinity mask alone. At startup of the interrupt
affinity will be assigned out of the affinity mask and the XEN binding will
be updated. Only keep the enforcement for real percpu interrupts.

On resume the overwrite is not required either because info->cpu and the
affinity mask are still the same as at the time of suspend. Same for
rebind_evtchn_irq().

This also prepares for proper interrupt spreading.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx>
Cc: xen-devel@xxxxxxxxxxxxxxxxxxxx
---
 drivers/xen/events/events_base.c |   42 ++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 14 deletions(-)

--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -433,15 +433,20 @@ static bool pirq_needs_eoi_flag(unsigned
        return info->u.pirq.flags & PIRQ_NEEDS_EOI;
 }
 
-static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu)
+static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
+                              bool force_affinity)
 {
        int irq = get_evtchn_to_irq(evtchn);
        struct irq_info *info = info_for_irq(irq);
 
        BUG_ON(irq == -1);
-#ifdef CONFIG_SMP
-       cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
-#endif
+
+       if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
+               cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
+               cpumask_copy(irq_get_effective_affinity_mask(irq),
+                            cpumask_of(cpu));
+       }
+
        xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
 
        info->cpu = cpu;
@@ -788,7 +793,7 @@ static unsigned int __startup_pirq(unsig
                goto err;
 
        info->evtchn = evtchn;
-       bind_evtchn_to_cpu(evtchn, 0);
+       bind_evtchn_to_cpu(evtchn, 0, false);
 
        rc = xen_evtchn_port_setup(evtchn);
        if (rc)
@@ -1107,8 +1112,8 @@ static int bind_evtchn_to_irq_chip(evtch
                        irq = ret;
                        goto out;
                }
-               /* New interdomain events are bound to VCPU 0. */
-               bind_evtchn_to_cpu(evtchn, 0);
+               /* New interdomain events are initially bound to VCPU 0. */
+               bind_evtchn_to_cpu(evtchn, 0, false);
        } else {
                struct irq_info *info = info_for_irq(irq);
                WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
@@ -1156,7 +1161,11 @@ static int bind_ipi_to_irq(unsigned int
                        irq = ret;
                        goto out;
                }
-               bind_evtchn_to_cpu(evtchn, cpu);
+               /*
+                * Force the affinity mask to the target CPU so proc shows
+                * the correct target.
+                */
+               bind_evtchn_to_cpu(evtchn, cpu, true);
        } else {
                struct irq_info *info = info_for_irq(irq);
                WARN_ON(info == NULL || info->type != IRQT_IPI);
@@ -1269,7 +1278,11 @@ int bind_virq_to_irq(unsigned int virq,
                        goto out;
                }
 
-               bind_evtchn_to_cpu(evtchn, cpu);
+               /*
+                * Force the affinity mask for percpu interrupts so proc
+                * shows the correct target.
+                */
+               bind_evtchn_to_cpu(evtchn, cpu, percpu);
        } else {
                struct irq_info *info = info_for_irq(irq);
                WARN_ON(info == NULL || info->type != IRQT_VIRQ);
@@ -1634,8 +1647,7 @@ void rebind_evtchn_irq(evtchn_port_t evt
 
        mutex_unlock(&irq_mapping_update_lock);
 
-        bind_evtchn_to_cpu(evtchn, info->cpu);
-       irq_set_affinity(irq, cpumask_of(info->cpu));
+       bind_evtchn_to_cpu(evtchn, info->cpu, false);
 
        /* Unmask the event channel. */
        enable_irq(irq);
@@ -1669,7 +1681,7 @@ static int xen_rebind_evtchn_to_cpu(evtc
         * it, but don't do the xenlinux-level rebind in that case.
         */
        if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
-               bind_evtchn_to_cpu(evtchn, tcpu);
+               bind_evtchn_to_cpu(evtchn, tcpu, false);
 
        if (!masked)
                unmask_evtchn(evtchn);
@@ -1798,7 +1810,8 @@ static void restore_cpu_virqs(unsigned i
 
                /* Record the new mapping. */
                (void)xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
-               bind_evtchn_to_cpu(evtchn, cpu);
+               /* The affinity mask is still valid */
+               bind_evtchn_to_cpu(evtchn, cpu, false);
        }
 }
 
@@ -1823,7 +1836,8 @@ static void restore_cpu_ipis(unsigned in
 
                /* Record the new mapping. */
                (void)xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
-               bind_evtchn_to_cpu(evtchn, cpu);
+               /* The affinity mask is still valid */
+               bind_evtchn_to_cpu(evtchn, cpu, false);
        }
 }