blk-mq: move failure injection out of blk_mq_complete_request

Move the call to blk_should_fake_timeout out of blk_mq_complete_request
and into the drivers, skipping call sites that are obvious error
handlers, and remove the now superflous blk_mq_force_complete_rq helper.
This ensures we don't keep injecting errors into completions that just
terminate the Linux request after the hardware has been reset or the
command has been aborted.

Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Christoph Hellwig

block/blk-mq.c

@@ -655,16 +655,13 @@ static void __blk_mq_complete_request_remote(void *data)
 }
 
 /**
- * blk_mq_force_complete_rq() - Force complete the request, bypassing any error
- * 				injection that could drop the completion.
- * @rq: Request to be force completed
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
  *
- * Drivers should use blk_mq_complete_request() to complete requests in their
- * normal IO path. For timeout error recovery, drivers may call this forced
- * completion routine after they've reclaimed timed out requests to bypass
- * potentially subsequent fake timeouts.
- */
-void blk_mq_force_complete_rq(struct request *rq)
+ * Description:
+ *	Complete a request by scheduling the ->complete_rq operation.
+ **/
+void blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
@@ -702,7 +699,7 @@ void blk_mq_force_complete_rq(struct request *rq)
 	}
 	put_cpu();
 }
-EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq);
+EXPORT_SYMBOL(blk_mq_complete_request);
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
 	__releases(hctx->srcu)
@@ -724,23 +721,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
 		*srcu_idx = srcu_read_lock(hctx->srcu);
 }
 
-/**
- * blk_mq_complete_request - end I/O on a request
- * @rq:		the request being processed
- *
- * Description:
- *	Ends all I/O on a request. It does not handle partial completions.
- *	The actual completion happens out-of-order, through a IPI handler.
- **/
-bool blk_mq_complete_request(struct request *rq)
-{
-	if (unlikely(blk_should_fake_timeout(rq->q)))
-		return false;
-	blk_mq_force_complete_rq(rq);
-	return true;
-}
-EXPORT_SYMBOL(blk_mq_complete_request);
-
 /**
  * blk_mq_start_request - Start processing a request
  * @rq: Pointer to request to be started

block/blk-timeout.c

@@ -20,13 +20,11 @@ static int __init setup_fail_io_timeout(char *str)
 }
 __setup("fail_io_timeout=", setup_fail_io_timeout);
 
-int blk_should_fake_timeout(struct request_queue *q)
+bool __blk_should_fake_timeout(struct request_queue *q)
 {
-	if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
-		return 0;
-
 	return should_fail(&fail_io_timeout, 1);
 }
+EXPORT_SYMBOL_GPL(__blk_should_fake_timeout);
 
 static int __init fail_io_timeout_debugfs(void)
 {

block/blk.h

@@ -223,18 +223,9 @@ ssize_t part_fail_show(struct device *dev, struct device_attribute *attr,
 		char *buf);
 ssize_t part_fail_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count);
-
-#ifdef CONFIG_FAIL_IO_TIMEOUT
-int blk_should_fake_timeout(struct request_queue *);
 ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
-#else
-static inline int blk_should_fake_timeout(struct request_queue *q)
-{
-	return 0;
-}
-#endif
 
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs);

block/bsg-lib.c

@@ -181,9 +181,12 @@ EXPORT_SYMBOL_GPL(bsg_job_get);
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len)
 {
+	struct request *rq = blk_mq_rq_from_pdu(job);
+
 	job->result = result;
 	job->reply_payload_rcv_len = reply_payload_rcv_len;
-	blk_mq_complete_request(blk_mq_rq_from_pdu(job));
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 EXPORT_SYMBOL_GPL(bsg_job_done);
 

drivers/block/loop.c

@@ -509,7 +509,8 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
-	blk_mq_complete_request(rq);
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -2048,7 +2049,8 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 			cmd->ret = ret;
 		else
 			cmd->ret = ret ? -EIO : 0;
-		blk_mq_complete_request(rq);
+		if (likely(!blk_should_fake_timeout(rq->q)))
+			blk_mq_complete_request(rq);
 	}
 }
 

drivers/block/mtip32xx/mtip32xx.c

@@ -492,7 +492,8 @@ static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status)
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 
 	cmd->status = status;
-	blk_mq_complete_request(req);
+	if (likely(!blk_should_fake_timeout(req->q)))
+		blk_mq_complete_request(req);
 }
 
 /*

drivers/block/nbd.c

@@ -784,6 +784,7 @@ static void recv_work(struct work_struct *work)
 	struct nbd_device *nbd = args->nbd;
 	struct nbd_config *config = nbd->config;
 	struct nbd_cmd *cmd;
+	struct request *rq;
 
 	while (1) {
 		cmd = nbd_read_stat(nbd, args->index);
@@ -796,7 +797,9 @@ static void recv_work(struct work_struct *work)
 			break;
 		}
 
-		blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
+		rq = blk_mq_rq_from_pdu(cmd);
+		if (likely(!blk_should_fake_timeout(rq->q)))
+			blk_mq_complete_request(rq);
 	}
 	atomic_dec(&config->recv_threads);
 	wake_up(&config->recv_wq);

drivers/block/null_blk_main.c

@@ -1283,7 +1283,8 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	case NULL_IRQ_SOFTIRQ:
 		switch (cmd->nq->dev->queue_mode) {
 		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
+			if (likely(!blk_should_fake_timeout(cmd->rq->q)))
+				blk_mq_complete_request(cmd->rq);
 			break;
 		case NULL_Q_BIO:
 			/*
@@ -1423,7 +1424,7 @@ static bool should_requeue_request(struct request *rq)
 static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
 {
 	pr_info("rq %p timed out\n", rq);
-	blk_mq_force_complete_rq(rq);
+	blk_mq_complete_request(rq);
 	return BLK_EH_DONE;
 }
 

drivers/block/skd_main.c

@@ -1417,7 +1417,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 	case SKD_CHECK_STATUS_REPORT_GOOD:
 	case SKD_CHECK_STATUS_REPORT_SMART_ALERT:
 		skreq->status = BLK_STS_OK;
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 		break;
 
 	case SKD_CHECK_STATUS_BUSY_IMMINENT:
@@ -1440,7 +1441,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 	case SKD_CHECK_STATUS_REPORT_ERROR:
 	default:
 		skreq->status = BLK_STS_IOERR;
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 		break;
 	}
 }
@@ -1560,7 +1562,8 @@ static int skd_isr_completion_posted(struct skd_device *skdev,
 		 */
 		if (likely(cmp_status == SAM_STAT_GOOD)) {
 			skreq->status = BLK_STS_OK;
-			blk_mq_complete_request(rq);
+			if (likely(!blk_should_fake_timeout(rq->q)))
+				blk_mq_complete_request(rq);
 		} else {
 			skd_resolve_req_exception(skdev, skreq, rq);
 		}

drivers/block/virtio_blk.c

@@ -171,7 +171,8 @@ static void virtblk_done(struct virtqueue *vq)
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
 			struct request *req = blk_mq_rq_from_pdu(vbr);
 
-			blk_mq_complete_request(req);
+			if (likely(!blk_should_fake_timeout(req->q)))
+				blk_mq_complete_request(req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))