We know this WARN_ON is harmless and in reality it may be trigged,
so convert it to printk() and dump_stack() for avoiding to confuse
people.
Also add comment about two releated races here.
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Stefan Haberland <sth@xxxxxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: "jianchao.wang" <jianchao.w.wang@xxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 69e73b4e32f3..480fc7623a5e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1391,9 +1391,27 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
/*
* We should be running this queue from one of the CPUs that
* are mapped to it.
+ *
+ * There are at least two related races now between setting
+ * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
+ * __blk_mq_run_hw_queue():
+ *
+ * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
+ * but later it becomes online, then this warning is harmless
+ * at all
+ *
+ * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
+ * but later it becomes offline, then the warning can't be
+ * triggered, and we depend on blk-mq timeout handler to
+ * handle dispatched requests to this hctx
*/
- WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
- cpu_online(hctx->next_cpu));
+ if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+ cpu_online(hctx->next_cpu)) {
+ printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
+ raw_smp_processor_id(),
+ cpumask_empty(hctx->cpumask) ? "inactive": "active");
+ dump_stack();
+ }
/*
* We can't run the queue inline with ints disabled. Ensure that
--
2.9.5
