75 lines
3.1 KiB
Diff
75 lines
3.1 KiB
Diff
|
|
References: bsc#1214718
|
|
|
|
# Commit 817d1cd627be668c358d038f0fadbf7d24d417d3
|
|
# Date 2024-06-18 15:14:49 +0200
|
|
# Author Roger Pau Monné <roger.pau@citrix.com>
|
|
# Committer Jan Beulich <jbeulich@suse.com>
|
|
x86/irq: deal with old_cpu_mask for interrupts in movement in fixup_irqs()
|
|
|
|
Given the current logic it's possible for ->arch.old_cpu_mask to get out of
|
|
sync: if a CPU set in old_cpu_mask is offlined and then onlined
|
|
again without old_cpu_mask having been updated the data in the mask will no
|
|
longer be accurate, as when brought back online the CPU will no longer have
|
|
old_vector configured to handle the old interrupt source.
|
|
|
|
If there's an interrupt movement in progress, and the to be offlined CPU (which
|
|
is the call context) is in the old_cpu_mask, clear it and update the mask, so
|
|
it doesn't contain stale data.
|
|
|
|
Note that when the system is going down fixup_irqs() will be called by
|
|
smp_send_stop() from CPU 0 with a mask with only CPU 0 on it, effectively
|
|
asking to move all interrupts to the current caller (CPU 0) which is the only
|
|
CPU to remain online. In that case we don't care to migrate interrupts that
|
|
are in the process of being moved, as it's likely we won't be able to move all
|
|
interrupts to CPU 0 due to vector shortage anyway.
|
|
|
|
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
|
|
Reviewed-by: Jan Beulich <jbeulich@suse.com>
|
|
|
|
--- a/xen/arch/x86/irq.c
|
|
+++ b/xen/arch/x86/irq.c
|
|
@@ -2539,7 +2539,7 @@ void fixup_irqs(const cpumask_t *mask, b
|
|
for ( irq = 0; irq < nr_irqs; irq++ )
|
|
{
|
|
bool break_affinity = false, set_affinity = true;
|
|
- unsigned int vector;
|
|
+ unsigned int vector, cpu = smp_processor_id();
|
|
cpumask_t *affinity = this_cpu(scratch_cpumask);
|
|
|
|
if ( irq == 2 )
|
|
@@ -2582,6 +2582,33 @@ void fixup_irqs(const cpumask_t *mask, b
|
|
affinity);
|
|
}
|
|
|
|
+ if ( desc->arch.move_in_progress &&
|
|
+ /*
|
|
+ * Only attempt to adjust the mask if the current CPU is going
|
|
+ * offline, otherwise the whole system is going down and leaving
|
|
+ * stale data in the masks is fine.
|
|
+ */
|
|
+ !cpu_online(cpu) &&
|
|
+ cpumask_test_cpu(cpu, desc->arch.old_cpu_mask) )
|
|
+ {
|
|
+ /*
|
|
+ * This CPU is going offline, remove it from ->arch.old_cpu_mask
|
|
+ * and possibly release the old vector if the old mask becomes
|
|
+ * empty.
|
|
+ *
|
|
+ * Note cleaning ->arch.old_cpu_mask is required if the CPU is
|
|
+ * brought offline and then online again, as when re-onlined the
|
|
+ * per-cpu vector table will no longer have ->arch.old_vector
|
|
+ * setup, and hence ->arch.old_cpu_mask would be stale.
|
|
+ */
|
|
+ cpumask_clear_cpu(cpu, desc->arch.old_cpu_mask);
|
|
+ if ( cpumask_empty(desc->arch.old_cpu_mask) )
|
|
+ {
|
|
+ desc->arch.move_in_progress = 0;
|
|
+ release_old_vec(desc);
|
|
+ }
|
|
+ }
|
|
+
|
|
/*
|
|
* Avoid shuffling the interrupt around as long as current target CPUs
|
|
* are a subset of the input mask. What fixup_irqs() cares about is
|