diff mbox series

[v4,9/9] blk-mq: issue warning when offlining hctx with online isolcpus

Message ID 20241217-isolcpus-io-queues-v4-9-5d355fbb1e14@kernel.org
State New
Headers show
Series [v4,1/9] lib/group_cpus: let group_cpu_evenly return number of groups | expand

Commit Message

Daniel Wagner Dec. 17, 2024, 6:29 p.m. UTC
When we offlining a hardware context which also serves isolcpus mapped
to it, any IO issued by the isolcpus will stall as there is nothing
which handles the interrupts etc.

This configuration/setup is not supported at this point thus just issue
a warning.

Signed-off-by: Daniel Wagner <wagi@kernel.org>
---
 block/blk-mq.c | 43 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/block/blk-mq.c b/block/blk-mq.c
index de15c0c76f874a2a863b05a23e0f3dba20cb6488..f9af0f5dd6aac8da855777acf2ffc61128f15a74 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3619,6 +3619,45 @@  static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	return data.has_rq;
 }
 
+static void blk_mq_hctx_check_isolcpus_online(struct blk_mq_hw_ctx *hctx, unsigned int cpu)
+{
+	const struct cpumask *hk_mask;
+	int i;
+
+	if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ))
+		return;
+
+	hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
+
+	for (i = 0; i < hctx->nr_ctx; i++) {
+		struct blk_mq_ctx *ctx = hctx->ctxs[i];
+
+		if (ctx->cpu == 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: offlining hctx%d but there is still an online isolcpu CPU %d mapped to it, IO stalls expected\n",
+			hctx->queue->disk->disk_name,
+			hctx->queue_num, ctx->cpu);
+	}
+}
+
 static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
 		unsigned int this_cpu)
 {
@@ -3638,8 +3677,10 @@  static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
 			continue;
 
 		/* this hctx has at least one online CPU */
-		if (this_cpu != cpu)
+		if (this_cpu != cpu) {
+			blk_mq_hctx_check_isolcpus_online(hctx, this_cpu);
 			return true;
+		}
 	}
 
 	return false;