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>

14 files changed, 38 insertions, 29 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 475e1a738560..4acae248790c 100644
--- a/drivers/block/loop.c
+++ b/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);
 	}
 }
 
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index f6bafa9a68b9..153e2cdecb4d 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/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);
 }
 
 /*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 43cff01a5a67..01794cd2b6ca 100644
--- a/drivers/block/nbd.c
+++ b/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);
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 87b31f9ca362..82259242b9b5 100644
--- a/drivers/block/null_blk_main.c
+++ b/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;
 }
 
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 51569c199a6c..3a476dc1d14f 100644
--- a/drivers/block/skd_main.c
+++ b/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);
 		}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 9d21bf0f155e..741804bd8a14 100644
--- a/drivers/block/virtio_blk.c
+++ b/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)))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3b889ea950c2..3bb3dd8da9b0 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1655,7 +1655,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			BUG();
 		}
 
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 	}
 
 	rinfo->ring.rsp_cons = i;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index f60c02512121..5aec1cd09348 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -288,7 +288,8 @@ static void dm_complete_request(struct request *rq, blk_status_t error)
 	struct dm_rq_target_io *tio = tio_from_request(rq);
 
 	tio->error = error;
-	blk_mq_complete_request(rq);
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 
 /*
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 7896952de1ac..4791c82f8f7c 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1446,7 +1446,7 @@ static void mmc_blk_cqe_req_done(struct mmc_request *mrq)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 }
 
@@ -1926,7 +1926,7 @@ static void mmc_blk_hsq_req_done(struct mmc_request *mrq)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 }
 
@@ -1936,7 +1936,7 @@ void mmc_blk_mq_complete(struct request *req)
 
 	if (mq->use_cqe)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		mmc_blk_mq_complete_rq(mq, req);
 }
 
@@ -1988,7 +1988,7 @@ static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_mq_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 
 	mmc_blk_mq_dec_in_flight(mq, req);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2c5bc4fb702..6810c8812aed 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -304,7 +304,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
-	blk_mq_force_complete_rq(req);
+	blk_mq_complete_request(req);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c0f4226d3299..034613205701 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -481,7 +481,8 @@ static inline void nvme_end_request(struct request *req, __le16 status,
 	rq->result = result;
 	/* inject error when permitted by fault injection framework */
 	nvme_should_fail(req);
-	blk_mq_complete_request(req);
+	if (likely(!blk_should_fake_timeout(req->q)))
+		blk_mq_complete_request(req);
 }
 
 static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index cf87eb27879f..eb17fea8075c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2802,7 +2802,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr)
 			blk_update_request(req, BLK_STS_OK,
 					   blk_rq_bytes(req) - proc_bytes);
 			blk_mq_requeue_request(req, true);
-		} else {
+		} else if (likely(!blk_should_fake_timeout(req->q))) {
 			blk_mq_complete_request(req);
 		}
 	}
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index e01889394c84..a4f6f2e62b1d 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -256,7 +256,8 @@ static void scm_request_finish(struct scm_request *scmrq)
 	for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
 		error = blk_mq_rq_to_pdu(scmrq->request[i]);
 		*error = scmrq->error;
-		blk_mq_complete_request(scmrq->request[i]);
+		if (likely(!blk_should_fake_timeout(scmrq->request[i]->q)))
+			blk_mq_complete_request(scmrq->request[i]);
 	}
 
 	atomic_dec(&bdev->queued_reqs);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0ba7a65e7c8d..6ca91d09eca1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1589,18 +1589,12 @@ static blk_status_t scsi_mq_prep_fn(struct request *req)
 
 static void scsi_mq_done(struct scsi_cmnd *cmd)
 {
+	if (unlikely(blk_should_fake_timeout(cmd->request->q)))
+		return;
 	if (unlikely(test_and_set_bit(SCMD_STATE_COMPLETE, &cmd->state)))
 		return;
 	trace_scsi_dispatch_cmd_done(cmd);
-
-	/*
-	 * If the block layer didn't complete the request due to a timeout
-	 * injection, scsi must clear its internal completed state so that the
-	 * timeout handler will see it needs to escalate its own error
-	 * recovery.
-	 */
-	if (unlikely(!blk_mq_complete_request(cmd->request)))
-		clear_bit(SCMD_STATE_COMPLETE, &cmd->state);
+	blk_mq_complete_request(cmd->request);
 }
 
 static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)