mmc: hsq: Improve random I/O write performance for 4k buffers

By dynamically adjusting the host->hsq_depth, based upon the buffer size
being 4k and that we get at least two I/O write requests in flight, we can
improve the throughput a bit. This is typical for a random I/O write
pattern.

More precisely, by dynamically changing the number of requests in flight
from 2 to 5, we can on some platforms observe ~4-5% increase in throughput.

Signed-off-by: Wenchao Chen <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
[Ulf: Re-wrote the commitmsg, minor adjustment to the code - all to clarify.]
Signed-off-by: Ulf Hansson <[e-mail]>

drivers/mmc/host/mmc_hsq.c

···
 	mmc->ops->request(mmc, hsq->mrq);
 }
 
+static void mmc_hsq_modify_threshold(struct mmc_hsq *hsq)
+{
+	struct mmc_host *mmc = hsq->mmc;
+	struct mmc_request *mrq;
+	unsigned int tag, need_change = 0;
+
+	mmc->hsq_depth = HSQ_NORMAL_DEPTH;
+	for (tag = 0; tag < HSQ_NUM_SLOTS; tag++) {
+		mrq = hsq->slot[tag].mrq;
+		if (mrq && mrq->data &&
+		   (mrq->data->blksz * mrq->data->blocks == 4096) &&
+		   (mrq->data->flags & MMC_DATA_WRITE) &&
+		   (++need_change == 2)) {
+			mmc->hsq_depth = HSQ_PERFORMANCE_DEPTH;
+			break;
+		}
+	}
+}
+
 static void mmc_hsq_pump_requests(struct mmc_hsq *hsq)
 {
 	struct mmc_host *mmc = hsq->mmc;
···
 		spin_unlock_irqrestore(&hsq->lock, flags);
 		return;
 	}
+
+	mmc_hsq_modify_threshold(hsq);
 
 	slot = &hsq->slot[hsq->next_tag];
 	hsq->mrq = slot->mrq;

drivers/mmc/host/mmc_hsq.h

···
  * flight to avoid a long latency.
  */
 #define HSQ_NORMAL_DEPTH	2
+/*
+ * For 4k random writes, we allow hsq_depth to increase to 5
+ * for better performance.
+ */
+#define HSQ_PERFORMANCE_DEPTH	5
 
 struct hsq_slot {
 	struct mmc_request *mrq;