block/mq: don't complete requests via IPI

The IPI runs in hardirq context and there are sleeping locks. This patch
moves the completion into a workqueue.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

4 files changed, 25 insertions, 0 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 1ed2f55793a0d0..485dea101a3f6d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -125,6 +125,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 
 	INIT_LIST_HEAD(&rq->queuelist);
 	INIT_LIST_HEAD(&rq->timeout_list);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
 	rq->cpu = -1;
 	rq->q = q;
 	rq->__sector = (sector_t) -1;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 33ceddfd81a221..798e9d8a3541a8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -196,6 +196,9 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->resid_len = 0;
 	rq->sense = NULL;
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+	INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
 
@@ -325,6 +328,17 @@ void blk_mq_end_request(struct request *rq, int error)
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+void __blk_mq_complete_request_remote_work(struct work_struct *work)
+{
+	struct request *rq = container_of(work, struct request, work);
+
+	rq->q->softirq_done_fn(rq);
+}
+
+#else
+
 static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
@@ -332,6 +346,8 @@ static void __blk_mq_complete_request_remote(void *data)
 	rq->q->softirq_done_fn(rq);
 }
 
+#endif
+
 static void blk_mq_ipi_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
@@ -348,10 +364,14 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 		shared = cpus_share_cache(cpu, ctx->cpu);
 
 	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+		schedule_work_on(ctx->cpu, &rq->work);
+#else
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
 		smp_call_function_single_async(ctx->cpu, &rq->csd);
+#endif
 	} else {
 		rq->q->softirq_done_fn(rq);
 	}
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index daf17d70aeca92..463df89542556f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -212,6 +212,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
+void __blk_mq_complete_request_remote_work(struct work_struct *work);
 
 int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c70e3588a48c72..460be1e1453514 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -89,6 +89,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
+		struct work_struct work;
 		unsigned long fifo_time;
 	};