genirq, sched/isolation: Isolate from handling managed interrupts
The affinity of managed interrupts is completely handled in the kernel and
cannot be changed via the /proc/irq/* interfaces from user space. As the
kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent
vector exhaustion, it can happen that a managed interrupt whose affinity
mask contains both isolated and housekeeping CPUs is routed to an isolated
CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts
on the isolated CPU.
Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding
logic in the interrupt affinity selection code.
The subparameter indicates to the interrupt affinity selection logic that
it should try to avoid the above scenario.
This isolation is best effort and only effective if the automatically
assigned interrupt mask of a device queue contains isolated and
housekeeping CPUs. If housekeeping CPUs are online then such interrupts are
directed to the housekeeping CPU so that IO submitted on the housekeeping
CPU cannot disturb the isolated CPU.
If a queue's affinity mask contains only isolated CPUs then this parameter
has no effect on the interrupt routing decision, though interrupts are only
happening when tasks running on those isolated CPUs submit IO. IO submitted
on housekeeping CPUs has no influence on those queues.
If the affinity mask contains both housekeeping and isolated CPUs, but none
of the contained housekeeping CPUs is online, then the interrupt is also
routed to an isolated CPU. Interrupts are only delivered when one of the
isolated CPUs in the affinity mask submits IO. If one of the contained
housekeeping CPUs comes online, the CPU hotplug logic migrates the
interrupt automatically back to the upcoming housekeeping CPU. Depending on
the type of interrupt controller, this can require that at least one
interrupt is delivered to the isolated CPU in order to complete the
migration.
[ tglx: Removed unused parameter, added and edited comments/documentation
and rephrased the changelog so it contains more details. ]
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b6c53ab..818b280 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,6 +18,7 @@
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
+#include <linux/sched/isolation.h>
#include <uapi/linux/sched/types.h>
#include <linux/task_work.h>
@@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
if (!chip || !chip->irq_set_affinity)
return -EINVAL;
- ret = chip->irq_set_affinity(data, mask, force);
+ /*
+ * If this is a managed interrupt and housekeeping is enabled on
+ * it check whether the requested affinity mask intersects with
+ * a housekeeping CPU. If so, then remove the isolated CPUs from
+ * the mask and just keep the housekeeping CPU(s). This prevents
+ * the affinity setter from routing the interrupt to an isolated
+ * CPU to avoid that I/O submitted from a housekeeping CPU causes
+ * interrupts on an isolated one.
+ *
+ * If the masks do not intersect or include online CPU(s) then
+ * keep the requested mask. The isolated target CPUs are only
+ * receiving interrupts when the I/O operation was submitted
+ * directly from them.
+ *
+ * If all housekeeping CPUs in the affinity mask are offline, the
+ * interrupt will be migrated by the CPU hotplug code once a
+ * housekeeping CPU which belongs to the affinity mask comes
+ * online.
+ */
+ if (irqd_affinity_is_managed(data) &&
+ housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+ const struct cpumask *hk_mask, *prog_mask;
+
+ static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
+ static struct cpumask tmp_mask;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+
+ raw_spin_lock(&tmp_mask_lock);
+ cpumask_and(&tmp_mask, mask, hk_mask);
+ if (!cpumask_intersects(&tmp_mask, cpu_online_mask))
+ prog_mask = mask;
+ else
+ prog_mask = &tmp_mask;
+ ret = chip->irq_set_affinity(data, prog_mask, force);
+ raw_spin_unlock(&tmp_mask_lock);
+ } else {
+ ret = chip->irq_set_affinity(data, mask, force);
+ }
switch (ret) {
case IRQ_SET_MASK_OK:
case IRQ_SET_MASK_OK_DONE: