mmc: block: Add blk-mq support

Define and use a blk-mq queue. Discards and flushes are processed
synchronously, but reads and writes asynchronously. In order to support
slow DMA unmapping, DMA unmapping is not done until after the next request
is started. That means the request is not completed until then. If there is
no next request then the completion is done by queued work.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Linus Walleij <linus.walleij@linaro.org>

drivers/mmc/core/block.c

@@ -1220,6 +1220,14 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+static void mmc_blk_end_request(struct request *req, blk_status_t error)
+{
+	if (req->mq_ctx)
+		blk_mq_end_request(req, error);
+	else
+		blk_end_request_all(req, error);
+}
+
 /*
  * The non-block commands come back from the block layer after it queued it and
  * processed it with all other requests and then they get issued in this
@@ -1281,7 +1289,7 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req)
 		break;
 	}
 	mq_rq->drv_op_result = ret;
-	blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
+	mmc_blk_end_request(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
@@ -1324,7 +1332,7 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 	else
 		mmc_blk_reset_success(md, type);
 fail:
-	blk_end_request(req, status, blk_rq_bytes(req));
+	mmc_blk_end_request(req, status);
 }
 
 static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
@@ -1394,7 +1402,7 @@ static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
 	if (!err)
 		mmc_blk_reset_success(md, type);
 out:
-	blk_end_request(req, status, blk_rq_bytes(req));
+	mmc_blk_end_request(req, status);
 }
 
 static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
@@ -1404,7 +1412,7 @@ static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
 	int ret = 0;
 
 	ret = mmc_flush_cache(card);
-	blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
+	mmc_blk_end_request(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 /*
@@ -1481,11 +1489,9 @@ static void mmc_blk_eval_resp_error(struct mmc_blk_request *brq)
 	}
 }
 
-static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
-					     struct mmc_async_req *areq)
+static enum mmc_blk_status __mmc_blk_err_check(struct mmc_card *card,
+					       struct mmc_queue_req *mq_mrq)
 {
-	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
-						    areq);
 	struct mmc_blk_request *brq = &mq_mrq->brq;
 	struct request *req = mmc_queue_req_to_req(mq_mrq);
 	int need_retune = card->host->need_retune;
@@ -1591,6 +1597,15 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
 	return MMC_BLK_SUCCESS;
 }
 
+static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
+					     struct mmc_async_req *areq)
+{
+	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
+						    areq);
+
+	return __mmc_blk_err_check(card, mq_mrq);
+}
+
 static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 			      int disable_multi, bool *do_rel_wr_p,
 			      bool *do_data_tag_p)
@@ -1783,6 +1798,477 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	mqrq->areq.err_check = mmc_blk_err_check;
 }
 
+#define MMC_MAX_RETRIES		5
+#define MMC_NO_RETRIES		(MMC_MAX_RETRIES + 1)
+
+#define MMC_READ_SINGLE_RETRIES	2
+
+/* Single sector read during recovery */
+static void mmc_blk_read_single(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	blk_status_t error = BLK_STS_OK;
+	int retries = 0;
+
+	do {
+		u32 status;
+		int err;
+
+		mmc_blk_rw_rq_prep(mqrq, card, 1, mq);
+
+		mmc_wait_for_req(host, mrq);
+
+		err = mmc_send_status(card, &status);
+		if (err)
+			goto error_exit;
+
+		if (!mmc_host_is_spi(host) &&
+		    R1_CURRENT_STATE(status) != R1_STATE_TRAN) {
+			u32 stop_status = 0;
+			bool gen_err = false;
+
+			err = send_stop(card,
+					DIV_ROUND_UP(mrq->data->timeout_ns,
+						     1000000),
+					req, &gen_err, &stop_status);
+			if (err)
+				goto error_exit;
+		}
+
+		if (mrq->cmd->error && retries++ < MMC_READ_SINGLE_RETRIES)
+			continue;
+
+		retries = 0;
+
+		if (mrq->cmd->error ||
+		    mrq->data->error ||
+		    (!mmc_host_is_spi(host) &&
+		     (mrq->cmd->resp[0] & CMD_ERRORS || status & CMD_ERRORS)))
+			error = BLK_STS_IOERR;
+		else
+			error = BLK_STS_OK;
+
+	} while (blk_update_request(req, error, 512));
+
+	return;
+
+error_exit:
+	mrq->data->bytes_xfered = 0;
+	blk_update_request(req, BLK_STS_IOERR, 512);
+	/* Let it try the remaining request again */
+	if (mqrq->retries > MMC_MAX_RETRIES - 1)
+		mqrq->retries = MMC_MAX_RETRIES - 1;
+}
+
+static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
+{
+	int type = rq_data_dir(req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct mmc_blk_data *md = mq->blkdata;
+	struct mmc_card *card = mq->card;
+	static enum mmc_blk_status status;
+
+	brq->retune_retry_done = mqrq->retries;
+
+	status = __mmc_blk_err_check(card, mqrq);
+
+	mmc_retune_release(card->host);
+
+	/*
+	 * Requests are completed by mmc_blk_mq_complete_rq() which sets simple
+	 * policy:
+	 * 1. A request that has transferred at least some data is considered
+	 * successful and will be requeued if there is remaining data to
+	 * transfer.
+	 * 2. Otherwise the number of retries is incremented and the request
+	 * will be requeued if there are remaining retries.
+	 * 3. Otherwise the request will be errored out.
+	 * That means mmc_blk_mq_complete_rq() is controlled by bytes_xfered and
+	 * mqrq->retries. So there are only 4 possible actions here:
+	 *	1. do not accept the bytes_xfered value i.e. set it to zero
+	 *	2. change mqrq->retries to determine the number of retries
+	 *	3. try to reset the card
+	 *	4. read one sector at a time
+	 */
+	switch (status) {
+	case MMC_BLK_SUCCESS:
+	case MMC_BLK_PARTIAL:
+		/* Reset success, and accept bytes_xfered */
+		mmc_blk_reset_success(md, type);
+		break;
+	case MMC_BLK_CMD_ERR:
+		/*
+		 * For SD cards, get bytes written, but do not accept
+		 * bytes_xfered if that fails. For MMC cards accept
+		 * bytes_xfered. Then try to reset. If reset fails then
+		 * error out the remaining request, otherwise retry
+		 * once (N.B mmc_blk_reset() will not succeed twice in a
+		 * row).
+		 */
+		if (mmc_card_sd(card)) {
+			u32 blocks;
+			int err;
+
+			err = mmc_sd_num_wr_blocks(card, &blocks);
+			if (err)
+				brq->data.bytes_xfered = 0;
+			else
+				brq->data.bytes_xfered = blocks << 9;
+		}
+		if (mmc_blk_reset(md, card->host, type))
+			mqrq->retries = MMC_NO_RETRIES;
+		else
+			mqrq->retries = MMC_MAX_RETRIES - 1;
+		break;
+	case MMC_BLK_RETRY:
+		/*
+		 * Do not accept bytes_xfered, but retry up to 5 times,
+		 * otherwise same as abort.
+		 */
+		brq->data.bytes_xfered = 0;
+		if (mqrq->retries < MMC_MAX_RETRIES)
+			break;
+		/* Fall through */
+	case MMC_BLK_ABORT:
+		/*
+		 * Do not accept bytes_xfered, but try to reset. If
+		 * reset succeeds, try once more, otherwise error out
+		 * the request.
+		 */
+		brq->data.bytes_xfered = 0;
+		if (mmc_blk_reset(md, card->host, type))
+			mqrq->retries = MMC_NO_RETRIES;
+		else
+			mqrq->retries = MMC_MAX_RETRIES - 1;
+		break;
+	case MMC_BLK_DATA_ERR: {
+		int err;
+
+		/*
+		 * Do not accept bytes_xfered, but try to reset. If
+		 * reset succeeds, try once more. If reset fails with
+		 * ENODEV which means the partition is wrong, then error
+		 * out the request. Otherwise attempt to read one sector
+		 * at a time.
+		 */
+		brq->data.bytes_xfered = 0;
+		err = mmc_blk_reset(md, card->host, type);
+		if (!err) {
+			mqrq->retries = MMC_MAX_RETRIES - 1;
+			break;
+		}
+		if (err == -ENODEV) {
+			mqrq->retries = MMC_NO_RETRIES;
+			break;
+		}
+		/* Fall through */
+	}
+	case MMC_BLK_ECC_ERR:
+		/*
+		 * Do not accept bytes_xfered. If reading more than one
+		 * sector, try reading one sector at a time.
+		 */
+		brq->data.bytes_xfered = 0;
+		/* FIXME: Missing single sector read for large sector size */
+		if (brq->data.blocks > 1 && !mmc_large_sector(card)) {
+			/* Redo read one sector at a time */
+			pr_warn("%s: retrying using single block read\n",
+				req->rq_disk->disk_name);
+			mmc_blk_read_single(mq, req);
+		} else {
+			mqrq->retries = MMC_NO_RETRIES;
+		}
+		break;
+	case MMC_BLK_NOMEDIUM:
+		/* Do not accept bytes_xfered. Error out the request */
+		brq->data.bytes_xfered = 0;
+		mqrq->retries = MMC_NO_RETRIES;
+		break;
+	default:
+		/* Do not accept bytes_xfered. Error out the request */
+		brq->data.bytes_xfered = 0;
+		mqrq->retries = MMC_NO_RETRIES;
+		pr_err("%s: Unhandled return value (%d)",
+		       req->rq_disk->disk_name, status);
+		break;
+	}
+}
+
+static void mmc_blk_mq_complete_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	unsigned int nr_bytes = mqrq->brq.data.bytes_xfered;
+
+	if (nr_bytes) {
+		if (blk_update_request(req, BLK_STS_OK, nr_bytes))
+			blk_mq_requeue_request(req, true);
+		else
+			__blk_mq_end_request(req, BLK_STS_OK);
+	} else if (!blk_rq_bytes(req)) {
+		__blk_mq_end_request(req, BLK_STS_IOERR);
+	} else if (mqrq->retries++ < MMC_MAX_RETRIES) {
+		blk_mq_requeue_request(req, true);
+	} else {
+		if (mmc_card_removed(mq->card))
+			req->rq_flags |= RQF_QUIET;
+		blk_mq_end_request(req, BLK_STS_IOERR);
+	}
+}
+
+static bool mmc_blk_urgent_bkops_needed(struct mmc_queue *mq,
+					struct mmc_queue_req *mqrq)
+{
+	return mmc_card_mmc(mq->card) && !mmc_host_is_spi(mq->card->host) &&
+	       (mqrq->brq.cmd.resp[0] & R1_EXCEPTION_EVENT ||
+		mqrq->brq.stop.resp[0] & R1_EXCEPTION_EVENT);
+}
+
+static void mmc_blk_urgent_bkops(struct mmc_queue *mq,
+				 struct mmc_queue_req *mqrq)
+{
+	if (mmc_blk_urgent_bkops_needed(mq, mqrq))
+		mmc_start_bkops(mq->card, true);
+}
+
+void mmc_blk_mq_complete(struct request *req)
+{
+	struct mmc_queue *mq = req->q->queuedata;
+
+	mmc_blk_mq_complete_rq(mq, req);
+}
+
+static void mmc_blk_mq_poll_completion(struct mmc_queue *mq,
+				       struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+
+	mmc_blk_mq_rw_recovery(mq, req);
+
+	mmc_blk_urgent_bkops(mq, mqrq);
+}
+
+static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req)
+{
+	struct request_queue *q = req->q;
+	unsigned long flags;
+	bool put_card;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+
+	put_card = (mmc_tot_in_flight(mq) == 0);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (put_card)
+		mmc_put_card(mq->card, &mq->ctx);
+}
+
+static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_host *host = mq->card->host;
+
+	mmc_post_req(host, mrq, 0);
+
+	blk_mq_complete_request(req);
+
+	mmc_blk_mq_dec_in_flight(mq, req);
+}
+
+static void mmc_blk_mq_complete_prev_req(struct mmc_queue *mq,
+					 struct request **prev_req)
+{
+	mutex_lock(&mq->complete_lock);
+
+	if (!mq->complete_req)
+		goto out_unlock;
+
+	mmc_blk_mq_poll_completion(mq, mq->complete_req);
+
+	if (prev_req)
+		*prev_req = mq->complete_req;
+	else
+		mmc_blk_mq_post_req(mq, mq->complete_req);
+
+	mq->complete_req = NULL;
+
+out_unlock:
+	mutex_unlock(&mq->complete_lock);
+}
+
+void mmc_blk_mq_complete_work(struct work_struct *work)
+{
+	struct mmc_queue *mq = container_of(work, struct mmc_queue,
+					    complete_work);
+
+	mmc_blk_mq_complete_prev_req(mq, NULL);
+}
+
+static void mmc_blk_mq_req_done(struct mmc_request *mrq)
+{
+	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+						  brq.mrq);
+	struct request *req = mmc_queue_req_to_req(mqrq);
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	unsigned long flags;
+	bool waiting;
+
+	/*
+	 * We cannot complete the request in this context, so record that there
+	 * is a request to complete, and that a following request does not need
+	 * to wait (although it does need to complete complete_req first).
+	 */
+	spin_lock_irqsave(q->queue_lock, flags);
+	mq->complete_req = req;
+	mq->rw_wait = false;
+	waiting = mq->waiting;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	/*
+	 * If 'waiting' then the waiting task will complete this request,
+	 * otherwise queue a work to do it. Note that complete_work may still
+	 * race with the dispatch of a following request.
+	 */
+	if (waiting)
+		wake_up(&mq->wait);
+	else
+		kblockd_schedule_work(&mq->complete_work);
+}
+
+static bool mmc_blk_rw_wait_cond(struct mmc_queue *mq, int *err)
+{
+	struct request_queue *q = mq->queue;
+	unsigned long flags;
+	bool done;
+
+	/*
+	 * Wait while there is another request in progress. Also indicate that
+	 * there is a request waiting to start.
+	 */
+	spin_lock_irqsave(q->queue_lock, flags);
+	done = !mq->rw_wait;
+	mq->waiting = !done;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return done;
+}
+
+static int mmc_blk_rw_wait(struct mmc_queue *mq, struct request **prev_req)
+{
+	int err = 0;
+
+	wait_event(mq->wait, mmc_blk_rw_wait_cond(mq, &err));
+
+	/* Always complete the previous request if there is one */
+	mmc_blk_mq_complete_prev_req(mq, prev_req);
+
+	return err;
+}
+
+static int mmc_blk_mq_issue_rw_rq(struct mmc_queue *mq,
+				  struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_host *host = mq->card->host;
+	struct request *prev_req = NULL;
+	int err = 0;
+
+	mmc_blk_rw_rq_prep(mqrq, mq->card, 0, mq);
+
+	mqrq->brq.mrq.done = mmc_blk_mq_req_done;
+
+	mmc_pre_req(host, &mqrq->brq.mrq);
+
+	err = mmc_blk_rw_wait(mq, &prev_req);
+	if (err)
+		goto out_post_req;
+
+	mq->rw_wait = true;
+
+	err = mmc_start_request(host, &mqrq->brq.mrq);
+
+	if (prev_req)
+		mmc_blk_mq_post_req(mq, prev_req);
+
+	if (err) {
+		mq->rw_wait = false;
+		mmc_retune_release(host);
+	}
+
+out_post_req:
+	if (err)
+		mmc_post_req(host, &mqrq->brq.mrq, err);
+
+	return err;
+}
+
+static int mmc_blk_wait_for_idle(struct mmc_queue *mq, struct mmc_host *host)
+{
+	return mmc_blk_rw_wait(mq, NULL);
+}
+
+enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_blk_data *md = mq->blkdata;
+	struct mmc_card *card = md->queue.card;
+	struct mmc_host *host = card->host;
+	int ret;
+
+	ret = mmc_blk_part_switch(card, md->part_type);
+	if (ret)
+		return MMC_REQ_FAILED_TO_START;
+
+	switch (mmc_issue_type(mq, req)) {
+	case MMC_ISSUE_SYNC:
+		ret = mmc_blk_wait_for_idle(mq, host);
+		if (ret)
+			return MMC_REQ_BUSY;
+		switch (req_op(req)) {
+		case REQ_OP_DRV_IN:
+		case REQ_OP_DRV_OUT:
+			mmc_blk_issue_drv_op(mq, req);
+			break;
+		case REQ_OP_DISCARD:
+			mmc_blk_issue_discard_rq(mq, req);
+			break;
+		case REQ_OP_SECURE_ERASE:
+			mmc_blk_issue_secdiscard_rq(mq, req);
+			break;
+		case REQ_OP_FLUSH:
+			mmc_blk_issue_flush(mq, req);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return MMC_REQ_FAILED_TO_START;
+		}
+		return MMC_REQ_FINISHED;
+	case MMC_ISSUE_ASYNC:
+		switch (req_op(req)) {
+		case REQ_OP_READ:
+		case REQ_OP_WRITE:
+			ret = mmc_blk_mq_issue_rw_rq(mq, req);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			ret = -EINVAL;
+		}
+		if (!ret)
+			return MMC_REQ_STARTED;
+		return ret == -EBUSY ? MMC_REQ_BUSY : MMC_REQ_FAILED_TO_START;
+	default:
+		WARN_ON_ONCE(1);
+		return MMC_REQ_FAILED_TO_START;
+	}
+}
+
 static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
 			       struct mmc_blk_request *brq, struct request *req,
 			       bool old_req_pending)

drivers/mmc/core/block.h

@@ -7,4 +7,13 @@ struct request;
 
 void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
 
+enum mmc_issued;
+
+enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req);
+void mmc_blk_mq_complete(struct request *req);
+
+struct work_struct;
+
+void mmc_blk_mq_complete_work(struct work_struct *work);
+
 #endif

drivers/mmc/core/queue.c

@@ -22,6 +22,7 @@
 #include "block.h"
 #include "core.h"
 #include "card.h"
+#include "host.h"
 
 /*
  * Prepare a MMC request. This just filters out odd stuff.
@@ -34,10 +35,25 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 		return BLKPREP_KILL;
 
 	req->rq_flags |= RQF_DONTPREP;
+	req_to_mmc_queue_req(req)->retries = 0;
 
 	return BLKPREP_OK;
 }
 
+enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req)
+{
+	if (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_WRITE)
+		return MMC_ISSUE_ASYNC;
+
+	return MMC_ISSUE_SYNC;
+}
+
+static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
+						 bool reserved)
+{
+	return BLK_EH_RESET_TIMER;
+}
+
 static int mmc_queue_thread(void *d)
 {
 	struct mmc_queue *mq = d;
@@ -154,11 +170,10 @@ static void mmc_queue_setup_discard(struct request_queue *q,
  * @req: the request
  * @gfp: memory allocation policy
  */
-static int mmc_init_request(struct request_queue *q, struct request *req,
-			    gfp_t gfp)
+static int __mmc_init_request(struct mmc_queue *mq, struct request *req,
+			      gfp_t gfp)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
-	struct mmc_queue *mq = q->queuedata;
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
@@ -169,6 +184,12 @@ static int mmc_init_request(struct request_queue *q, struct request *req,
 	return 0;
 }
 
+static int mmc_init_request(struct request_queue *q, struct request *req,
+			    gfp_t gfp)
+{
+	return __mmc_init_request(q->queuedata, req, gfp);
+}
+
 static void mmc_exit_request(struct request_queue *q, struct request *req)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
@@ -177,6 +198,112 @@ static void mmc_exit_request(struct request_queue *q, struct request *req)
 	mq_rq->sg = NULL;
 }
 
+static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
+			       unsigned int hctx_idx, unsigned int numa_node)
+{
+	return __mmc_init_request(set->driver_data, req, GFP_KERNEL);
+}
+
+static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
+				unsigned int hctx_idx)
+{
+	struct mmc_queue *mq = set->driver_data;
+
+	mmc_exit_request(mq->queue, req);
+}
+
+/*
+ * We use BLK_MQ_F_BLOCKING and have only 1 hardware queue, which means requests
+ * will not be dispatched in parallel.
+ */
+static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+				    const struct blk_mq_queue_data *bd)
+{
+	struct request *req = bd->rq;
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	struct mmc_card *card = mq->card;
+	enum mmc_issue_type issue_type;
+	enum mmc_issued issued;
+	bool get_card;
+	int ret;
+
+	if (mmc_card_removed(mq->card)) {
+		req->rq_flags |= RQF_QUIET;
+		return BLK_STS_IOERR;
+	}
+
+	issue_type = mmc_issue_type(mq, req);
+
+	spin_lock_irq(q->queue_lock);
+
+	switch (issue_type) {
+	case MMC_ISSUE_ASYNC:
+		break;
+	default:
+		/*
+		 * Timeouts are handled by mmc core, and we don't have a host
+		 * API to abort requests, so we can't handle the timeout anyway.
+		 * However, when the timeout happens, blk_mq_complete_request()
+		 * no longer works (to stop the request disappearing under us).
+		 * To avoid racing with that, set a large timeout.
+		 */
+		req->timeout = 600 * HZ;
+		break;
+	}
+
+	mq->in_flight[issue_type] += 1;
+	get_card = (mmc_tot_in_flight(mq) == 1);
+
+	spin_unlock_irq(q->queue_lock);
+
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		req_to_mmc_queue_req(req)->retries = 0;
+		req->rq_flags |= RQF_DONTPREP;
+	}
+
+	if (get_card)
+		mmc_get_card(card, &mq->ctx);
+
+	blk_mq_start_request(req);
+
+	issued = mmc_blk_mq_issue_rq(mq, req);
+
+	switch (issued) {
+	case MMC_REQ_BUSY:
+		ret = BLK_STS_RESOURCE;
+		break;
+	case MMC_REQ_FAILED_TO_START:
+		ret = BLK_STS_IOERR;
+		break;
+	default:
+		ret = BLK_STS_OK;
+		break;
+	}
+
+	if (issued != MMC_REQ_STARTED) {
+		bool put_card = false;
+
+		spin_lock_irq(q->queue_lock);
+		mq->in_flight[issue_type] -= 1;
+		if (mmc_tot_in_flight(mq) == 0)
+			put_card = true;
+		spin_unlock_irq(q->queue_lock);
+		if (put_card)
+			mmc_put_card(card, &mq->ctx);
+	}
+
+	return ret;
+}
+
+static const struct blk_mq_ops mmc_mq_ops = {
+	.queue_rq	= mmc_mq_queue_rq,
+	.init_request	= mmc_mq_init_request,
+	.exit_request	= mmc_mq_exit_request,
+	.complete	= mmc_blk_mq_complete,
+	.timeout	= mmc_mq_timed_out,
+};
+
 static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -198,6 +325,70 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 
 	/* Initialize thread_sem even if it is not used */
 	sema_init(&mq->thread_sem, 1);
+
+	INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);
+
+	mutex_init(&mq->complete_lock);
+
+	init_waitqueue_head(&mq->wait);
+}
+
+static int mmc_mq_init_queue(struct mmc_queue *mq, int q_depth,
+			     const struct blk_mq_ops *mq_ops, spinlock_t *lock)
+{
+	int ret;
+
+	memset(&mq->tag_set, 0, sizeof(mq->tag_set));
+	mq->tag_set.ops = mq_ops;
+	mq->tag_set.queue_depth = q_depth;
+	mq->tag_set.numa_node = NUMA_NO_NODE;
+	mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE |
+			    BLK_MQ_F_BLOCKING;
+	mq->tag_set.nr_hw_queues = 1;
+	mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
+	mq->tag_set.driver_data = mq;
+
+	ret = blk_mq_alloc_tag_set(&mq->tag_set);
+	if (ret)
+		return ret;
+
+	mq->queue = blk_mq_init_queue(&mq->tag_set);
+	if (IS_ERR(mq->queue)) {
+		ret = PTR_ERR(mq->queue);
+		goto free_tag_set;
+	}
+
+	mq->queue->queue_lock = lock;
+	mq->queue->queuedata = mq;
+
+	return 0;
+
+free_tag_set:
+	blk_mq_free_tag_set(&mq->tag_set);
+
+	return ret;
+}
+
+/* Set queue depth to get a reasonable value for q->nr_requests */
+#define MMC_QUEUE_DEPTH 64
+
+static int mmc_mq_init(struct mmc_queue *mq, struct mmc_card *card,
+			 spinlock_t *lock)
+{
+	int q_depth;
+	int ret;
+
+	q_depth = MMC_QUEUE_DEPTH;
+
+	ret = mmc_mq_init_queue(mq, q_depth, &mmc_mq_ops, lock);
+	if (ret)
+		return ret;
+
+	blk_queue_rq_timeout(mq->queue, 60 * HZ);
+
+	mmc_setup_queue(mq, card);
+
+	return 0;
 }
 
 /**
@@ -216,6 +407,10 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	int ret = -ENOMEM;
 
 	mq->card = card;
+
+	if (mmc_host_use_blk_mq(host))
+		return mmc_mq_init(mq, card, lock);
+
 	mq->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!mq->queue)
 		return -ENOMEM;
@@ -251,11 +446,70 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	return ret;
 }
 
+static void mmc_mq_queue_suspend(struct mmc_queue *mq)
+{
+	blk_mq_quiesce_queue(mq->queue);
+
+	/*
+	 * The host remains claimed while there are outstanding requests, so
+	 * simply claiming and releasing here ensures there are none.
+	 */
+	mmc_claim_host(mq->card->host);
+	mmc_release_host(mq->card->host);
+}
+
+static void mmc_mq_queue_resume(struct mmc_queue *mq)
+{
+	blk_mq_unquiesce_queue(mq->queue);
+}
+
+static void __mmc_queue_suspend(struct mmc_queue *mq)
+{
+	struct request_queue *q = mq->queue;
+	unsigned long flags;
+
+	if (!mq->suspended) {
+		mq->suspended |= true;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_stop_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+
+		down(&mq->thread_sem);
+	}
+}
+
+static void __mmc_queue_resume(struct mmc_queue *mq)
+{
+	struct request_queue *q = mq->queue;
+	unsigned long flags;
+
+	if (mq->suspended) {
+		mq->suspended = false;
+
+		up(&mq->thread_sem);
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_start_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+}
+
 void mmc_cleanup_queue(struct mmc_queue *mq)
 {
 	struct request_queue *q = mq->queue;
 	unsigned long flags;
 
+	if (q->mq_ops) {
+		/*
+		 * The legacy code handled the possibility of being suspended,
+		 * so do that here too.
+		 */
+		if (blk_queue_quiesced(q))
+			blk_mq_unquiesce_queue(q);
+		goto out_cleanup;
+	}
+
 	/* Make sure the queue isn't suspended, as that will deadlock */
 	mmc_queue_resume(mq);
 
@@ -268,8 +522,16 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 	blk_start_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
+out_cleanup:
 	blk_cleanup_queue(q);
 
+	/*
+	 * A request can be completed before the next request, potentially
+	 * leaving a complete_work with nothing to do. Such a work item might
+	 * still be queued at this point. Flush it.
+	 */
+	flush_work(&mq->complete_work);
+
 	mq->card = NULL;
 }
 
@@ -284,17 +546,11 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 void mmc_queue_suspend(struct mmc_queue *mq)
 {
 	struct request_queue *q = mq->queue;
-	unsigned long flags;
-
-	if (!mq->suspended) {
-		mq->suspended |= true;
-
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_stop_queue(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
 
-		down(&mq->thread_sem);
-	}
+	if (q->mq_ops)
+		mmc_mq_queue_suspend(mq);
+	else
+		__mmc_queue_suspend(mq);
 }
 
 /**
@@ -304,17 +560,11 @@ void mmc_queue_suspend(struct mmc_queue *mq)
 void mmc_queue_resume(struct mmc_queue *mq)
 {
 	struct request_queue *q = mq->queue;
-	unsigned long flags;
 
-	if (mq->suspended) {
-		mq->suspended = false;
-
-		up(&mq->thread_sem);
-
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_start_queue(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-	}
+	if (q->mq_ops)
+		mmc_mq_queue_resume(mq);
+	else
+		__mmc_queue_resume(mq);
 }
 
 /*

drivers/mmc/core/queue.h

@@ -8,6 +8,19 @@
 #include <linux/mmc/core.h>
 #include <linux/mmc/host.h>
 
+enum mmc_issued {
+	MMC_REQ_STARTED,
+	MMC_REQ_BUSY,
+	MMC_REQ_FAILED_TO_START,
+	MMC_REQ_FINISHED,
+};
+
+enum mmc_issue_type {
+	MMC_ISSUE_SYNC,
+	MMC_ISSUE_ASYNC,
+	MMC_ISSUE_MAX,
+};
+
 static inline struct mmc_queue_req *req_to_mmc_queue_req(struct request *rq)
 {
 	return blk_mq_rq_to_pdu(rq);
@@ -57,12 +70,15 @@ struct mmc_queue_req {
 	int			drv_op_result;
 	void			*drv_op_data;
 	unsigned int		ioc_count;
+	int			retries;
 };
 
 struct mmc_queue {
 	struct mmc_card		*card;
 	struct task_struct	*thread;
 	struct semaphore	thread_sem;
+	struct mmc_ctx		ctx;
+	struct blk_mq_tag_set	tag_set;
 	bool			suspended;
 	bool			asleep;
 	struct mmc_blk_data	*blkdata;
@@ -74,6 +90,14 @@ struct mmc_queue {
 	 * associated mmc_queue_req data.
 	 */
 	int			qcnt;
+
+	int			in_flight[MMC_ISSUE_MAX];
+	bool			rw_wait;
+	bool			waiting;
+	wait_queue_head_t	wait;
+	struct request		*complete_req;
+	struct mutex		complete_lock;
+	struct work_struct	complete_work;
 };
 
 extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
@@ -84,4 +108,12 @@ extern void mmc_queue_resume(struct mmc_queue *);
 extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
 				     struct mmc_queue_req *);
 
+enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req);
+
+static inline int mmc_tot_in_flight(struct mmc_queue *mq)
+{
+	return mq->in_flight[MMC_ISSUE_SYNC] +
+	       mq->in_flight[MMC_ISSUE_ASYNC];
+}
+
 #endif