nvme-tcp: Fix warning with CONFIG_DEBUG_PREEMPT

We shouldn't call smp_processor_id() in a preemptible context, but this is advisory at best, so instead call __smp_processor_id(). Fixes: db5ad6b ("nvme-tcp: try to send request in queue_rq context") Reported-by: Or Gerlitz <[email protected]> Reported-by: Yi Zhang <[email protected]> Signed-off-by: Sagi Grimberg <[email protected]> Signed-off-by: Christoph Hellwig <[email protected]>
fracktal · Jan 14, 2021 · ada8317 · ada8317
1 parent 7a84665
commit ada8317
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
@@ -286,7 +286,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 * directly, otherwise queue io_work. Also, only do that if we
 	 * are on the same cpu, so we don't introduce contention.
 	 */
-	if (queue->io_cpu == smp_processor_id() &&
+	if (queue->io_cpu == __smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
 		queue->more_requests = !last;
 		nvme_tcp_send_all(queue);