blk-mq: turn WARN_ON in __blk_mq_run_hw_queue into printk

[ Upstream commit 7df938fbc4ee641e70e05002ac67c24b19e86e74 ]

We know this WARN_ON is harmless and in reality it may be trigged,
so convert it to printk() and dump_stack() to avoid to confusing
people.

Also add comment about two releated races here.

Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Stefan Haberland <sth@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "jianchao.wang" <jianchao.w.wang@oracle.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6f89966..007f966 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1143,9 +1143,27 @@ 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