mmc: sdhci: use pipeline mmc requests to improve performance

This patch is based on the patches by Per Forlin, Tony Lin and Ryan QIAN.

This patch complete the API 'post_req' and 'pre_req' in sdhci host side,

Test Env:
1. i.MX6Q-SABREAUTO board, CPU @ 996MHz, use ADMA in uSDHC controller.
2. Test command:
		$ echo 1 > /proc/sys/vm/drop_caches
	write to sd card:
		$ dd if=/dev/zero of=/dev/mmcblk0 bs=1M count=2000 conv=fsync
	read the sd card:
		$ dd if=/dev/mmcblk0 of=/dev/null bs=1M count=2000

3. TOSHIBA 16GB SD3.0 card, running at 4 bit, SDR104 @ 198MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~76.7 MB/s |  ~23.3 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~60.5 MB/s |  ~22.5 MB/s |
	  -------------------------------------------------

4. SanDisk 8GB SD3.0 card, running at 4 bit, DDR50 @ 50MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~40.5 MB/s |  ~15.6 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~36.1 MB/s |  ~14.1 MB/s |
	  -------------------------------------------------

5. Kingston 8GB SD2.0 card, running at 4 bit, High-speed @ 50MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~22.7 MB/s |  ~8.2 MB/s  |
	  |------------------------------------------------
	  |without this patch  | ~21.3 MB/s |  ~8.0 MB/s  |
	  -------------------------------------------------

6. About eMMC, Sandisk 8GB eMMC on i.MX6DL-sabresd board, CPU @ 792MHZ,
   eMMC running at 8 bit, DDR52 @ 52MHZ.
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~37.3 MB/s |  ~10.5 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~33.4 MB/s |  ~10.5 MB/s |
	  -------------------------------------------------

Signed-off-by: Haibo Chen <haibo.chen@freescale.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>

drivers/mmc/host/sdhci.c

@@ -53,6 +53,9 @@ static void sdhci_finish_command(struct sdhci_host *);
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
 static void sdhci_tuning_timer(unsigned long data);
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
+static int sdhci_pre_dma_transfer(struct sdhci_host *host,
+					struct mmc_data *data,
+					struct sdhci_host_next *next);
 
 #ifdef CONFIG_PM
 static int sdhci_runtime_pm_get(struct sdhci_host *host);
@@ -505,9 +508,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		goto fail;
 	BUG_ON(host->align_addr & host->align_mask);
 
-	host->sg_count = dma_map_sg(mmc_dev(host->mmc),
+	host->sg_count = sdhci_pre_dma_transfer(host, data, NULL);
-		data->sg, data->sg_len, direction);
+	if (host->sg_count < 0)
-	if (host->sg_count == 0)
 		goto unmap_align;
 
 	desc = host->adma_table;
@@ -645,6 +647,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		}
 	}
 
+	if (!data->host_cookie)
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg,
 			data->sg_len, direction);
 }
@@ -842,11 +845,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 		} else {
 			int sg_cnt;
 
-			sg_cnt = dma_map_sg(mmc_dev(host->mmc),
+			sg_cnt = sdhci_pre_dma_transfer(host, data, NULL);
-					data->sg, data->sg_len,
-					(data->flags & MMC_DATA_READ) ?
-						DMA_FROM_DEVICE :
-						DMA_TO_DEVICE);
 			if (sg_cnt == 0) {
 				/*
 				 * This only happens when someone fed
@@ -959,8 +958,10 @@ static void sdhci_finish_data(struct sdhci_host *host)
 		if (host->flags & SDHCI_USE_ADMA)
 			sdhci_adma_table_post(host, data);
 		else {
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
+			if (!data->host_cookie)
-				data->sg_len, (data->flags & MMC_DATA_READ) ?
+				dma_unmap_sg(mmc_dev(host->mmc),
+					data->sg, data->sg_len,
+					(data->flags & MMC_DATA_READ) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE);
 		}
 	}
@@ -2125,6 +2126,77 @@ static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 	}
 }
 
+static void sdhci_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+				int err)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (host->flags & SDHCI_REQ_USE_DMA) {
+		if (data->host_cookie)
+			dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+					 data->flags & MMC_DATA_WRITE ?
+					 DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		mrq->data->host_cookie = 0;
+	}
+}
+
+static int sdhci_pre_dma_transfer(struct sdhci_host *host,
+				       struct mmc_data *data,
+				       struct sdhci_host_next *next)
+{
+	int sg_count;
+
+	if (!next && data->host_cookie &&
+	    data->host_cookie != host->next_data.cookie) {
+		pr_debug(DRIVER_NAME "[%s] invalid cookie: %d, next-cookie %d\n",
+			__func__, data->host_cookie, host->next_data.cookie);
+		data->host_cookie = 0;
+	}
+
+	/* Check if next job is already prepared */
+	if (next ||
+	    (!next && data->host_cookie != host->next_data.cookie)) {
+		sg_count = dma_map_sg(mmc_dev(host->mmc), data->sg,
+				     data->sg_len,
+				     data->flags & MMC_DATA_WRITE ?
+				     DMA_TO_DEVICE : DMA_FROM_DEVICE);
+
+	} else {
+		sg_count = host->next_data.sg_count;
+		host->next_data.sg_count = 0;
+	}
+
+
+	if (sg_count == 0)
+		return -EINVAL;
+
+	if (next) {
+		next->sg_count = sg_count;
+		data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie;
+	} else
+		host->sg_count = sg_count;
+
+	return sg_count;
+}
+
+static void sdhci_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
+			       bool is_first_req)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	if (mrq->data->host_cookie) {
+		mrq->data->host_cookie = 0;
+		return;
+	}
+
+	if (host->flags & SDHCI_REQ_USE_DMA)
+		if (sdhci_pre_dma_transfer(host,
+					mrq->data,
+					&host->next_data) < 0)
+			mrq->data->host_cookie = 0;
+}
+
 static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
@@ -2158,6 +2230,8 @@ static void sdhci_card_event(struct mmc_host *mmc)
 
 static const struct mmc_host_ops sdhci_ops = {
 	.request	= sdhci_request,
+	.post_req	= sdhci_post_req,
+	.pre_req	= sdhci_pre_req,
 	.set_ios	= sdhci_set_ios,
 	.get_cd		= sdhci_get_cd,
 	.get_ro		= sdhci_get_ro,
@@ -3015,6 +3089,7 @@ int sdhci_add_host(struct sdhci_host *host)
 		host->max_clk = host->ops->get_max_clock(host);
 	}
 
+	host->next_data.cookie = 1;
 	/*
 	 * In case of Host Controller v3.00, find out whether clock
 	 * multiplier is supported.

include/linux/mmc/sdhci.h

@@ -17,6 +17,11 @@
 #include <linux/io.h>
 #include <linux/mmc/host.h>
 
+struct sdhci_host_next {
+	unsigned int	sg_count;
+	s32		cookie;
+};
+
 struct sdhci_host {
 	/* Data set by hardware interface driver */
 	const char *hw_name;	/* Hardware bus name */
@@ -203,6 +208,7 @@ struct sdhci_host {
 #define SDHCI_TUNING_MODE_1	0
 	struct timer_list	tuning_timer;	/* Timer for tuning */
 
+	struct sdhci_host_next	next_data;
 	unsigned long private[0] ____cacheline_aligned;
 };
 #endif /* LINUX_MMC_SDHCI_H */