mmc: block: Add CQE support

Add CQE support to the block driver, including:
    - optionally using DCMD for flush requests
    - "manually" issuing discard requests
    - issuing read / write requests to the CQE
    - supporting block-layer timeouts
    - handling recovery
    - supporting re-tuning

CQE offers 25% - 50% better random multi-threaded I/O.  There is a slight
(e.g. 2%) drop in sequential read speed but no observable change to sequential
write.

CQE automatically sends the commands to complete requests.  However it only
supports reads / writes and so-called "direct commands" (DCMD).  Furthermore
DCMD is limited to one command at a time, but discards require 3 commands.
That makes issuing discards through CQE very awkward, but some CQE's don't
support DCMD anyway.  So for discards, the existing non-CQE approach is
taken, where the mmc core code issues the 3 commands one at a time i.e.
mmc_erase(). Where DCMD is used, is for issuing flushes.

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>

1 files changed, 148 insertions, 2 deletions

diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 7874c3bbf6b5..7275ac5d6799 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -112,6 +112,7 @@ struct mmc_blk_data {
 #define MMC_BLK_WRITE		BIT(1)
 #define MMC_BLK_DISCARD		BIT(2)
 #define MMC_BLK_SECDISCARD	BIT(3)
+#define MMC_BLK_CQE_RECOVERY	BIT(4)
 
 	/*
 	 * Only set in main mmc_blk_data associated
@@ -1730,6 +1731,138 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 		*do_data_tag_p = do_data_tag;
 }
 
+#define MMC_CQE_RETRIES 2
+
+static void mmc_blk_cqe_complete_rq(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 request_queue *q = req->q;
+	struct mmc_host *host = mq->card->host;
+	unsigned long flags;
+	bool put_card;
+	int err;
+
+	mmc_cqe_post_req(host, mrq);
+
+	if (mrq->cmd && mrq->cmd->error)
+		err = mrq->cmd->error;
+	else if (mrq->data && mrq->data->error)
+		err = mrq->data->error;
+	else
+		err = 0;
+
+	if (err) {
+		if (mqrq->retries++ < MMC_CQE_RETRIES)
+			blk_mq_requeue_request(req, true);
+		else
+			blk_mq_end_request(req, BLK_STS_IOERR);
+	} else if (mrq->data) {
+		if (blk_update_request(req, BLK_STS_OK, mrq->data->bytes_xfered))
+			blk_mq_requeue_request(req, true);
+		else
+			__blk_mq_end_request(req, BLK_STS_OK);
+	} else {
+		blk_mq_end_request(req, BLK_STS_OK);
+	}
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+
+	put_card = (mmc_tot_in_flight(mq) == 0);
+
+	mmc_cqe_check_busy(mq);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (!mq->cqe_busy)
+		blk_mq_run_hw_queues(q, true);
+
+	if (put_card)
+		mmc_put_card(mq->card, &mq->ctx);
+}
+
+void mmc_blk_cqe_recovery(struct mmc_queue *mq)
+{
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	int err;
+
+	pr_debug("%s: CQE recovery start\n", mmc_hostname(host));
+
+	err = mmc_cqe_recovery(host);
+	if (err)
+		mmc_blk_reset(mq->blkdata, host, MMC_BLK_CQE_RECOVERY);
+	else
+		mmc_blk_reset_success(mq->blkdata, MMC_BLK_CQE_RECOVERY);
+
+	pr_debug("%s: CQE recovery done\n", mmc_hostname(host));
+}
+
+static void mmc_blk_cqe_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;
+
+	/*
+	 * Block layer timeouts race with completions which means the normal
+	 * completion path cannot be used during recovery.
+	 */
+	if (mq->in_recovery)
+		mmc_blk_cqe_complete_rq(mq, req);
+	else
+		blk_mq_complete_request(req);
+}
+
+static int mmc_blk_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	mrq->done		= mmc_blk_cqe_req_done;
+	mrq->recovery_notifier	= mmc_cqe_recovery_notifier;
+
+	return mmc_cqe_start_req(host, mrq);
+}
+
+static struct mmc_request *mmc_blk_cqe_prep_dcmd(struct mmc_queue_req *mqrq,
+						 struct request *req)
+{
+	struct mmc_blk_request *brq = &mqrq->brq;
+
+	memset(brq, 0, sizeof(*brq));
+
+	brq->mrq.cmd = &brq->cmd;
+	brq->mrq.tag = req->tag;
+
+	return &brq->mrq;
+}
+
+static int mmc_blk_cqe_issue_flush(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = mmc_blk_cqe_prep_dcmd(mqrq, req);
+
+	mrq->cmd->opcode = MMC_SWITCH;
+	mrq->cmd->arg = (MMC_SWITCH_MODE_WRITE_BYTE << 24) |
+			(EXT_CSD_FLUSH_CACHE << 16) |
+			(1 << 8) |
+			EXT_CSD_CMD_SET_NORMAL;
+	mrq->cmd->flags = MMC_CMD_AC | MMC_RSP_R1B;
+
+	return mmc_blk_cqe_start_req(mq->card->host, mrq);
+}
+
+static int mmc_blk_cqe_issue_rw_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+
+	mmc_blk_data_prep(mq, mqrq, 0, NULL, NULL);
+
+	return mmc_blk_cqe_start_req(mq->card->host, &mqrq->brq.mrq);
+}
+
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 			       struct mmc_card *card,
 			       int disable_multi,
@@ -2038,7 +2171,10 @@ void mmc_blk_mq_complete(struct request *req)
 {
 	struct mmc_queue *mq = req->q->queuedata;
 
-	mmc_blk_mq_complete_rq(mq, req);
+	if (mq->use_cqe)
+		mmc_blk_cqe_complete_rq(mq, req);
+	else
+		mmc_blk_mq_complete_rq(mq, req);
 }
 
 static void mmc_blk_mq_poll_completion(struct mmc_queue *mq,
@@ -2212,6 +2348,9 @@ out_post_req:
 
 static int mmc_blk_wait_for_idle(struct mmc_queue *mq, struct mmc_host *host)
 {
+	if (mq->use_cqe)
+		return host->cqe_ops->cqe_wait_for_idle(host);
+
 	return mmc_blk_rw_wait(mq, NULL);
 }
 
@@ -2250,11 +2389,18 @@ enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req)
 			return MMC_REQ_FAILED_TO_START;
 		}
 		return MMC_REQ_FINISHED;
+	case MMC_ISSUE_DCMD:
 	case MMC_ISSUE_ASYNC:
 		switch (req_op(req)) {
+		case REQ_OP_FLUSH:
+			ret = mmc_blk_cqe_issue_flush(mq, req);
+			break;
 		case REQ_OP_READ:
 		case REQ_OP_WRITE:
-			ret = mmc_blk_mq_issue_rw_rq(mq, req);
+			if (mq->use_cqe)
+				ret = mmc_blk_cqe_issue_rw_rq(mq, req);
+			else
+				ret = mmc_blk_mq_issue_rw_rq(mq, req);
 			break;
 		default:
 			WARN_ON_ONCE(1);