diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ade4e6ec23e03acdaa4277cebfbbf059ff23df45..765e4274ba7155092ccc833352a1dbeebfabe3af 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1933,9 +1933,31 @@
<cpu number> begins at 0 and the maximum value is
"number of CPUs in system - 1".
- The format of <cpu-list> is described above.
-
+ managed_irq
+
+ Isolate from being targeted by managed interrupts
+ which have an interrupt mask containing isolated
+ CPUs. The affinity of managed interrupts is
+ handled by the kernel and cannot be changed via
+ the /proc/irq/* interfaces.
+
+ 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 delivered when tasks running on those
+ isolated CPUs submit IO. IO submitted on
+ housekeeping CPUs has no influence on those
+ queues.
+ The format of <cpu-list> is described above.
iucv= [HW,NET]
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 6c8512d3be88e4d1d34cbfa861fdbc3094ee925b..0fbcbacd1b2900bae38fd90f7aea73c04f06572d 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -13,6 +13,7 @@ enum hk_flags {
HK_FLAG_TICK = (1 << 4),
HK_FLAG_DOMAIN = (1 << 5),
HK_FLAG_WQ = (1 << 6),
+ HK_FLAG_MANAGED_IRQ = (1 << 7),
};
#ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 6c7ca2e983a595ff561396e3d3b9400072426c56..02236b13b359974e95a2e3ca4ec3f0cadfd0962a 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -12,6 +12,7 @@
#include <linux/interrupt.h>
#include <linux/ratelimit.h>
#include <linux/irq.h>
+#include <linux/sched/isolation.h>
#include "internals.h"
@@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void)
}
}
+static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
+{
+ const struct cpumask *hk_mask;
+
+ if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+ return false;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+ if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
+ return false;
+
+ return cpumask_test_cpu(cpu, hk_mask);
+}
+
static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
{
struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
/*
* If the interrupt can only be directed to a single target
* CPU then it is already assigned to a CPU in the affinity
- * mask. No point in trying to move it around.
+ * mask. No point in trying to move it around unless the
+ * isolation mechanism requests to move it to an upcoming
+ * housekeeping CPU.
*/
- if (!irqd_is_single_target(data))
+ if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
irq_set_affinity_locked(data, affinity, false);
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b6c53ab053d2ff332d4a7d49a9c6211a1447173e..818b2802d3e79f8a8d358f212b957f7298fe5318 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:
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9fcb2a695a41289fe490c64a0656300a74fefb99..008d6ac2342b7536fff293b2ce7054cf9d9cfc98 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
continue;
}
+ if (!strncmp(str, "managed_irq,", 12)) {
+ str += 12;
+ flags |= HK_FLAG_MANAGED_IRQ;
+ continue;
+ }
+
pr_warn("isolcpus: Error, unknown flag\n");
return 0;
}