mmc: Add MMC host software queue support

Now the MMC read/write stack will always wait for previous request is
completed by mmc_blk_rw_wait(), before sending a new request to hardware,
or queue a work to complete request, that will bring context switching
overhead and spend some extra time to poll the card for busy completion
for I/O writes via sending CMD13, especially for high I/O per second
rates, to affect the IO performance.

Thus this patch introduces MMC software queue interface based on the
hardware command queue engine's interfaces, which is similar with the
hardware command queue engine's idea, that can remove the context
switching. Moreover we set the default queue depth as 64 for software
queue, which allows more requests to be prepared, merged and inserted
into IO scheduler to improve performance, but we only allow 2 requests
in flight, that is enough to let the irq handler always trigger the
next request without a context switch, as well as avoiding a long latency.

Moreover the host controller should support HW busy detection for I/O
operations when enabling the host software queue. That means, the host
controller must not complete a data transfer request, until after the
card stops signals busy.

From the fio testing data in cover letter, we can see the software
queue can improve some performance with 4K block size, increasing
about 16% for random read, increasing about 90% for random write,
though no obvious improvement for sequential read and write.

Moreover we can expand the software queue interface to support MMC
packed request or packed command in future.

Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
Signed-off-by: Baolin Wang <baolin.wang7@gmail.com>
Link: https://lore.kernel.org/r/4409c1586a9b3ed20d57ad2faf6c262fc3ccb6e2.1581478568.git.baolin.wang7@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>

5 files changed, 393 insertions, 1 deletions

diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 3a5089f0332c..fcb685efe17f 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -949,6 +949,17 @@ config MMC_CQHCI
 
 	  If unsure, say N.
 
+config MMC_HSQ
+	tristate "MMC Host Software Queue support"
+	help
+	  This selects the MMC Host Software Queue support. This may increase
+	  performance, if the host controller and its driver supports it.
+
+	  If you have a controller/driver supporting this interface, say Y or M
+	  here.
+
+	  If unsure, say N.
+
 config MMC_TOSHIBA_PCI
 	tristate "Toshiba Type A SD/MMC Card Interface Driver"
 	depends on PCI
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 21d9089e5eda..b929ef941208 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_MMC_SDHCI_BRCMSTB)		+= sdhci-brcmstb.o
 obj-$(CONFIG_MMC_SDHCI_OMAP)		+= sdhci-omap.o
 obj-$(CONFIG_MMC_SDHCI_SPRD)		+= sdhci-sprd.o
 obj-$(CONFIG_MMC_CQHCI)			+= cqhci.o
+obj-$(CONFIG_MMC_HSQ)			+= mmc_hsq.o
 
 ifeq ($(CONFIG_CB710_DEBUG),y)
 	CFLAGS-cb710-mmc	+= -DDEBUG
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index 5047f7343ffc..e2ea2c4b6b94 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -321,14 +321,20 @@ static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card)
 	struct cqhci_host *cq_host = mmc->cqe_private;
 	int err;
 
+	if (!card->ext_csd.cmdq_en)
+		return -EINVAL;
+
 	if (cq_host->enabled)
 		return 0;
 
 	cq_host->rca = card->rca;
 
 	err = cqhci_host_alloc_tdl(cq_host);
-	if (err)
+	if (err) {
+		pr_err("%s: Failed to enable CQE, error %d\n",
+		       mmc_hostname(mmc), err);
 		return err;
+	}
 
 	__cqhci_enable(cq_host);
 
diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c
new file mode 100644
index 000000000000..fc82593b9e27
--- /dev/null
+++ b/drivers/mmc/host/mmc_hsq.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * MMC software queue support based on command queue interfaces
+ *
+ * Copyright (C) 2019 Linaro, Inc.
+ * Author: Baolin Wang <baolin.wang@linaro.org>
+ */
+
+#include <linux/mmc/card.h>
+#include <linux/mmc/host.h>
+
+#include "mmc_hsq.h"
+
+#define HSQ_NUM_SLOTS	64
+#define HSQ_INVALID_TAG	HSQ_NUM_SLOTS
+
+static void mmc_hsq_pump_requests(struct mmc_hsq *hsq)
+{
+	struct mmc_host *mmc = hsq->mmc;
+	struct hsq_slot *slot;
+	unsigned long flags;
+
+	spin_lock_irqsave(&hsq->lock, flags);
+
+	/* Make sure we are not already running a request now */
+	if (hsq->mrq) {
+		spin_unlock_irqrestore(&hsq->lock, flags);
+		return;
+	}
+
+	/* Make sure there are remain requests need to pump */
+	if (!hsq->qcnt || !hsq->enabled) {
+		spin_unlock_irqrestore(&hsq->lock, flags);
+		return;
+	}
+
+	slot = &hsq->slot[hsq->next_tag];
+	hsq->mrq = slot->mrq;
+	hsq->qcnt--;
+
+	spin_unlock_irqrestore(&hsq->lock, flags);
+
+	mmc->ops->request(mmc, hsq->mrq);
+}
+
+static void mmc_hsq_update_next_tag(struct mmc_hsq *hsq, int remains)
+{
+	struct hsq_slot *slot;
+	int tag;
+
+	/*
+	 * If there are no remain requests in software queue, then set a invalid
+	 * tag.
+	 */
+	if (!remains) {
+		hsq->next_tag = HSQ_INVALID_TAG;
+		return;
+	}
+
+	/*
+	 * Increasing the next tag and check if the corresponding request is
+	 * available, if yes, then we found a candidate request.
+	 */
+	if (++hsq->next_tag != HSQ_INVALID_TAG) {
+		slot = &hsq->slot[hsq->next_tag];
+		if (slot->mrq)
+			return;
+	}
+
+	/* Othersie we should iterate all slots to find a available tag. */
+	for (tag = 0; tag < HSQ_NUM_SLOTS; tag++) {
+		slot = &hsq->slot[tag];
+		if (slot->mrq)
+			break;
+	}
+
+	if (tag == HSQ_NUM_SLOTS)
+		tag = HSQ_INVALID_TAG;
+
+	hsq->next_tag = tag;
+}
+
+static void mmc_hsq_post_request(struct mmc_hsq *hsq)
+{
+	unsigned long flags;
+	int remains;
+
+	spin_lock_irqsave(&hsq->lock, flags);
+
+	remains = hsq->qcnt;
+	hsq->mrq = NULL;
+
+	/* Update the next available tag to be queued. */
+	mmc_hsq_update_next_tag(hsq, remains);
+
+	if (hsq->waiting_for_idle && !remains) {
+		hsq->waiting_for_idle = false;
+		wake_up(&hsq->wait_queue);
+	}
+
+	/* Do not pump new request in recovery mode. */
+	if (hsq->recovery_halt) {
+		spin_unlock_irqrestore(&hsq->lock, flags);
+		return;
+	}
+
+	spin_unlock_irqrestore(&hsq->lock, flags);
+
+	 /*
+	  * Try to pump new request to host controller as fast as possible,
+	  * after completing previous request.
+	  */
+	if (remains > 0)
+		mmc_hsq_pump_requests(hsq);
+}
+
+/**
+ * mmc_hsq_finalize_request - finalize one request if the request is done
+ * @mmc: the host controller
+ * @mrq: the request need to be finalized
+ *
+ * Return true if we finalized the corresponding request in software queue,
+ * otherwise return false.
+ */
+bool mmc_hsq_finalize_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&hsq->lock, flags);
+
+	if (!hsq->enabled || !hsq->mrq || hsq->mrq != mrq) {
+		spin_unlock_irqrestore(&hsq->lock, flags);
+		return false;
+	}
+
+	/*
+	 * Clear current completed slot request to make a room for new request.
+	 */
+	hsq->slot[hsq->next_tag].mrq = NULL;
+
+	spin_unlock_irqrestore(&hsq->lock, flags);
+
+	mmc_cqe_request_done(mmc, hsq->mrq);
+
+	mmc_hsq_post_request(hsq);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(mmc_hsq_finalize_request);
+
+static void mmc_hsq_recovery_start(struct mmc_host *mmc)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&hsq->lock, flags);
+
+	hsq->recovery_halt = true;
+
+	spin_unlock_irqrestore(&hsq->lock, flags);
+}
+
+static void mmc_hsq_recovery_finish(struct mmc_host *mmc)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	int remains;
+
+	spin_lock_irq(&hsq->lock);
+
+	hsq->recovery_halt = false;
+	remains = hsq->qcnt;
+
+	spin_unlock_irq(&hsq->lock);
+
+	/*
+	 * Try to pump new request if there are request pending in software
+	 * queue after finishing recovery.
+	 */
+	if (remains > 0)
+		mmc_hsq_pump_requests(hsq);
+}
+
+static int mmc_hsq_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	int tag = mrq->tag;
+
+	spin_lock_irq(&hsq->lock);
+
+	if (!hsq->enabled) {
+		spin_unlock_irq(&hsq->lock);
+		return -ESHUTDOWN;
+	}
+
+	/* Do not queue any new requests in recovery mode. */
+	if (hsq->recovery_halt) {
+		spin_unlock_irq(&hsq->lock);
+		return -EBUSY;
+	}
+
+	hsq->slot[tag].mrq = mrq;
+
+	/*
+	 * Set the next tag as current request tag if no available
+	 * next tag.
+	 */
+	if (hsq->next_tag == HSQ_INVALID_TAG)
+		hsq->next_tag = tag;
+
+	hsq->qcnt++;
+
+	spin_unlock_irq(&hsq->lock);
+
+	mmc_hsq_pump_requests(hsq);
+
+	return 0;
+}
+
+static void mmc_hsq_post_req(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	if (mmc->ops->post_req)
+		mmc->ops->post_req(mmc, mrq, 0);
+}
+
+static bool mmc_hsq_queue_is_idle(struct mmc_hsq *hsq, int *ret)
+{
+	bool is_idle;
+
+	spin_lock_irq(&hsq->lock);
+
+	is_idle = (!hsq->mrq && !hsq->qcnt) ||
+		hsq->recovery_halt;
+
+	*ret = hsq->recovery_halt ? -EBUSY : 0;
+	hsq->waiting_for_idle = !is_idle;
+
+	spin_unlock_irq(&hsq->lock);
+
+	return is_idle;
+}
+
+static int mmc_hsq_wait_for_idle(struct mmc_host *mmc)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	int ret;
+
+	wait_event(hsq->wait_queue,
+		   mmc_hsq_queue_is_idle(hsq, &ret));
+
+	return ret;
+}
+
+static void mmc_hsq_disable(struct mmc_host *mmc)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+	u32 timeout = 500;
+	int ret;
+
+	spin_lock_irq(&hsq->lock);
+
+	if (!hsq->enabled) {
+		spin_unlock_irq(&hsq->lock);
+		return;
+	}
+
+	spin_unlock_irq(&hsq->lock);
+
+	ret = wait_event_timeout(hsq->wait_queue,
+				 mmc_hsq_queue_is_idle(hsq, &ret),
+				 msecs_to_jiffies(timeout));
+	if (ret == 0) {
+		pr_warn("could not stop mmc software queue\n");
+		return;
+	}
+
+	spin_lock_irq(&hsq->lock);
+
+	hsq->enabled = false;
+
+	spin_unlock_irq(&hsq->lock);
+}
+
+static int mmc_hsq_enable(struct mmc_host *mmc, struct mmc_card *card)
+{
+	struct mmc_hsq *hsq = mmc->cqe_private;
+
+	spin_lock_irq(&hsq->lock);
+
+	if (hsq->enabled) {
+		spin_unlock_irq(&hsq->lock);
+		return -EBUSY;
+	}
+
+	hsq->enabled = true;
+
+	spin_unlock_irq(&hsq->lock);
+
+	return 0;
+}
+
+static const struct mmc_cqe_ops mmc_hsq_ops = {
+	.cqe_enable = mmc_hsq_enable,
+	.cqe_disable = mmc_hsq_disable,
+	.cqe_request = mmc_hsq_request,
+	.cqe_post_req = mmc_hsq_post_req,
+	.cqe_wait_for_idle = mmc_hsq_wait_for_idle,
+	.cqe_recovery_start = mmc_hsq_recovery_start,
+	.cqe_recovery_finish = mmc_hsq_recovery_finish,
+};
+
+int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc)
+{
+	hsq->num_slots = HSQ_NUM_SLOTS;
+	hsq->next_tag = HSQ_INVALID_TAG;
+
+	hsq->slot = devm_kcalloc(mmc_dev(mmc), hsq->num_slots,
+				 sizeof(struct hsq_slot), GFP_KERNEL);
+	if (!hsq->slot)
+		return -ENOMEM;
+
+	hsq->mmc = mmc;
+	hsq->mmc->cqe_private = hsq;
+	mmc->cqe_ops = &mmc_hsq_ops;
+
+	spin_lock_init(&hsq->lock);
+	init_waitqueue_head(&hsq->wait_queue);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mmc_hsq_init);
+
+void mmc_hsq_suspend(struct mmc_host *mmc)
+{
+	mmc_hsq_disable(mmc);
+}
+EXPORT_SYMBOL_GPL(mmc_hsq_suspend);
+
+int mmc_hsq_resume(struct mmc_host *mmc)
+{
+	return mmc_hsq_enable(mmc, NULL);
+}
+EXPORT_SYMBOL_GPL(mmc_hsq_resume);
diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h
new file mode 100644
index 000000000000..18b9cf55925f
--- /dev/null
+++ b/drivers/mmc/host/mmc_hsq.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_MMC_HSQ_H
+#define LINUX_MMC_HSQ_H
+
+struct hsq_slot {
+	struct mmc_request *mrq;
+};
+
+struct mmc_hsq {
+	struct mmc_host *mmc;
+	struct mmc_request *mrq;
+	wait_queue_head_t wait_queue;
+	struct hsq_slot *slot;
+	spinlock_t lock;
+
+	int next_tag;
+	int num_slots;
+	int qcnt;
+
+	bool enabled;
+	bool waiting_for_idle;
+	bool recovery_halt;
+};
+
+int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc);
+void mmc_hsq_suspend(struct mmc_host *mmc);
+int mmc_hsq_resume(struct mmc_host *mmc);
+bool mmc_hsq_finalize_request(struct mmc_host *mmc, struct mmc_request *mrq);
+
+#endif