[PATCH v13 7/8] genirq/affinity: Restrict managed IRQ affinity to housekeeping CPUs

[Aaron Tomlin <atomlin@atomlin.com>]

At present, the managed interrupt spreading algorithm distributes vectors
across all available CPUs within a given node or system. On systems
employing CPU isolation (e.g., "isolcpus=io_queue"), this behaviour
defeats the primary purpose of isolation by routing hardware interrupts
(such as NVMe completion queues) directly to isolated cores.

Update irq_create_affinity_masks() to respect the housekeeping CPU mask.
By passing the HK_TYPE_IO_QUEUE mask directly to the topological
distribution function (group_mask_cpus_evenly()), we ensure that managed
interrupts are kept strictly off isolated CPUs.

This patch additionally addresses the architectural constraints of
restricted vector distribution:

    1. Vector Limits: Updated irq_calc_affinity_vectors() to bound the
       maximum number of allocated vectors to the weight of the
       housekeeping mask. This prevents drivers from wasting memory on
       dead hardware queues that cannot be routed to isolated CPUs.

    2. Multi-set Alignment: When isolation constraints result in fewer
       available masks than requested vectors for a given set, the
       remaining vector slots are padded with irq_default_affinity. The
       loop correctly advances by the requested vector count (this_vecs)
       to prevent shifting and corrupting the 1:1 hardware queue mapping
       for subsequent sets.

    3. Zero Overhead: The housekeeping mask is conditionally assigned via
       a direct pointer, completely avoiding temporary mask allocations
       (e.g., alloc_cpumask_var) and bitwise operations when CPU
       isolation is disabled. This guarantees zero performance or memory
       overhead for standard configurations.

Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
 kernel/irq/affinity.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 78f2418a8925..1d39dce685c7 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/group_cpus.h>
+#include <linux/sched/isolation.h>
 
 static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
 {
@@ -25,8 +26,10 @@ static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
 struct irq_affinity_desc *
 irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
 {
-	unsigned int affvecs, curvec, usedvecs, i;
+	unsigned int affvecs, curvec, usedvecs, i, j;
 	struct irq_affinity_desc *masks = NULL;
+	const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+	bool hk_enabled = housekeeping_enabled(HK_TYPE_IO_QUEUE);
 
 	/*
 	 * Determine the number of vectors which need interrupt affinities
@@ -70,19 +73,29 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
 	 */
 	for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
 		unsigned int nr_masks, this_vecs = affd->set_size[i];
-		struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
+		struct cpumask *result;
+		const struct cpumask *mask;
 
+		if (hk_enabled)
+			mask = hk_mask;
+		else
+			mask = cpu_possible_mask;
+
+		result = group_mask_cpus_evenly(this_vecs, mask,
+						&nr_masks);
 		if (!result) {
 			kfree(masks);
 			return NULL;
 		}
-
-		for (int j = 0; j < nr_masks; j++)
+		for (j = 0; j < nr_masks; j++)
 			cpumask_copy(&masks[curvec + j].mask, &result[j]);
+		for (j = nr_masks; j < this_vecs; j++)
+			cpumask_copy(&masks[curvec + j].mask, irq_default_affinity);
+
 		kfree(result);
 
-		curvec += nr_masks;
-		usedvecs += nr_masks;
+		curvec += this_vecs;
+		usedvecs += this_vecs;
 	}
 
 	/* Fill out vectors at the end that don't need affinity */
@@ -115,10 +128,14 @@ unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
 	if (resv > minvec)
 		return 0;
 
-	if (affd->calc_sets)
+	if (affd->calc_sets) {
 		set_vecs = maxvec - resv;
-	else
-		set_vecs = cpumask_weight(cpu_possible_mask);
+	} else {
+		if (housekeeping_enabled(HK_TYPE_IO_QUEUE))
+			set_vecs = cpumask_weight(housekeeping_cpumask(HK_TYPE_IO_QUEUE));
+		else
+			set_vecs = cpumask_weight(cpu_possible_mask);
+	}
 
 	return resv + min(set_vecs, maxvec - resv);
 }
-- 
2.51.0