[PATCH v8 11/12] blk-mq: prevent offlining hk CPUs with associated online isolated CPUs

[Daniel Wagner]

When isolcpus=io_queue is enabled, and the last housekeeping CPU for a
given hctx goes offline, there would be no CPU left to handle I/O. To
prevent I/O stalls, prevent offlining housekeeping CPUs that are still
serving isolated CPUs.

When isolcpus=io_queue is enabled and the last housekeeping CPU
for a given hctx goes offline, no CPU would be left to handle I/O.
To prevent I/O stalls, disallow offlining housekeeping CPUs that are
still serving isolated CPUs.

Reviewed-by: Aaron Tomlin <atomlin at atomlin.com>
Reviewed-by: Hannes Reinecke <hare at suse.de>
Signed-off-by: Daniel Wagner <wagi at kernel.org>
---
 block/blk-mq.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ba3a4b77f5786e5372adce53e4fff5aa2ace24aa..d48be77919e671a81077f7042103699a80959664 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3683,6 +3683,43 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	return data.has_rq;
 }
 
+static bool blk_mq_hctx_can_offline_hk_cpu(struct blk_mq_hw_ctx *hctx,
+					   unsigned int this_cpu)
+{
+	const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+
+	for (int i = 0; i < hctx->nr_ctx; i++) {
+		struct blk_mq_ctx *ctx = hctx->ctxs[i];
+
+		if (ctx->cpu == this_cpu)
+			continue;
+
+		/*
+		 * Check if this context has at least one online
+		 * housekeeping CPU; in this case the hardware context is
+		 * usable.
+		 */
+		if (cpumask_test_cpu(ctx->cpu, hk_mask) &&
+		    cpu_online(ctx->cpu))
+			break;
+
+		/*
+		 * The context doesn't have any online housekeeping CPUs,
+		 * but there might be an online isolated CPU mapped to
+		 * it.
+		 */
+		if (cpu_is_offline(ctx->cpu))
+			continue;
+
+		pr_warn("%s: trying to offline hctx%d but there is still an online isolcpu CPU %d mapped to it\n",
+			hctx->queue->disk->disk_name,
+			hctx->queue_num, ctx->cpu);
+		return false;
+	}
+
+	return true;
+}
+
 static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
 		unsigned int this_cpu)
 {
@@ -3714,6 +3751,11 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
+	if (housekeeping_enabled(HK_TYPE_IO_QUEUE)) {
+		if (!blk_mq_hctx_can_offline_hk_cpu(hctx, cpu))
+			return -EINVAL;
+	}
+
 	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
 		return 0;
 

-- 
2.51.0