[RFC PATCH v1] blk-mq: isolate CPUs from hctx

[Costa Shulyupin <costa.shul@redhat.com>]

The housekeeping CPU masks, set up by the "isolcpus" and "nohz_full"
boot command line options, are used at boot time to exclude selected
CPUs from running some kernel housekeeping subsystems to minimize
disturbance to latency sensitive userspace applications such as DPDK.
This options can only be changed with a reboot. This is a problem for
containerized workloads running on OpenShift/Kubernetes where a
mix of low latency and "normal" workloads can be created/destroyed
dynamically and the number of CPUs allocated to each workload is often
not known at boot time.

Cgroups allow configuring isolated_cpus at runtime.
However, blk-mq may still use managed interrupts on the
newly isolated CPUs.

Rebuild hctx->cpumask considering isolated CPUs to avoid
managed interrupts on those CPUs and reclaim non-isolated ones.

The patch is based on
isolation: Exclude dynamically isolated CPUs from housekeeping masks:
https://lore.kernel.org/lkml/20240821142312.236970-1-longman@redhat.com/

Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
 block/blk-mq.c         | 30 ++++++++++++++++++++++++++++++
 include/linux/blk-mq.h |  1 +
 kernel/cgroup/cpuset.c |  2 ++
 3 files changed, 33 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 12ee37986331..d5786b953d17 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4145,6 +4145,36 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	}
 }
 
+/**
+ * blk_mq_isolate_cpus() - rebuild hctx->cpumask considering isolated CPUs
+ * to avoid managed interrupts on those CPUs.
+ */
+
+void blk_mq_isolate_cpus(const struct cpumask *isolcpus)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct request_queue *q = bdev_get_queue(dev_to_bdev(dev));
+		struct blk_mq_hw_ctx *hctx;
+		unsigned long i;
+
+		if (!queue_is_mq(q))
+			continue;
+
+		blk_mq_map_swqueue(q);
+		/*
+		 * Postcondition:
+		 * cpumask must not intersect with isolated CPUs.
+		 */
+		queue_for_each_hw_ctx(q, hctx, i)
+			WARN_ON_ONCE(cpumask_intersects(hctx->cpumask, isolcpus));
+	}
+	class_dev_iter_exit(&iter);
+}
+
 /*
  * Caller needs to ensure that we're either frozen/quiesced, or that
  * the queue isn't live yet.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2035fad3131f..a1f57b5ad46d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -924,6 +924,7 @@ void blk_freeze_queue_start_non_owner(struct request_queue *q);
 
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
+void blk_mq_isolate_cpus(const struct cpumask *isolcpus);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5066397899c9..cad17f3f3315 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -41,6 +41,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/blk-mq.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)    "%s:%d: %s " fmt, __FILE__, __LINE__, __func__
@@ -1317,6 +1318,7 @@ static void update_isolation_cpumasks(bool isolcpus_updated)
 		return;
 	ret = housekeeping_exlude_isolcpus(isolated_cpus, HOUSEKEEPING_FLAGS);
 	WARN_ON_ONCE((ret < 0) && (ret != -EOPNOTSUPP));
+	blk_mq_isolate_cpus(isolated_cpus);
 }
 
 /**
-- 
2.47.0