mmc: omap_hsmmc: add DMA engine support

Add DMA engine support to the OMAP HSMMC driver.  This supplements the
private DMA API implementation contained within this driver, and the
driver can be switched at build time between using DMA engine and the
private DMA API.

Tested-by: Grazvydas Ignotas <notasas@gmail.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 389a3ee..effe328 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
+#include <linux/dmaengine.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -165,7 +166,9 @@
 	u32			bytesleft;
 	int			suspended;
 	int			irq;
-	int			use_dma, dma_ch;
+	int			use_dma, dma_ch, dma2;
+	struct dma_chan		*tx_chan;
+	struct dma_chan		*rx_chan;
 	int			dma_line_tx, dma_line_rx;
 	int			slot_id;
 	int			response_busy;
@@ -797,19 +800,26 @@
 		return DMA_FROM_DEVICE;
 }
 
+static struct dma_chan *omap_hsmmc_get_dma_chan(struct omap_hsmmc_host *host,
+	struct mmc_data *data)
+{
+	return data->flags & MMC_DATA_WRITE ? host->tx_chan : host->rx_chan;
+}
+
 static void omap_hsmmc_request_done(struct omap_hsmmc_host *host, struct mmc_request *mrq)
 {
-	int dma_ch;
+	int dma_ch, dma2;
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->irq_lock, flags);
 	host->req_in_progress = 0;
 	dma_ch = host->dma_ch;
+	dma2 = host->dma2;
 	spin_unlock_irqrestore(&host->irq_lock, flags);
 
 	omap_hsmmc_disable_irq(host);
 	/* Do not complete the request if DMA is still in progress */
-	if (mrq->data && host->use_dma && dma_ch != -1)
+	if (mrq->data && host->use_dma && (dma_ch != -1 || dma2 != -1))
 		return;
 	host->mrq = NULL;
 	mmc_request_done(host->mmc, mrq);
@@ -878,7 +888,7 @@
  */
 static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno)
 {
-	int dma_ch;
+	int dma_ch, dma2;
 	unsigned long flags;
 
 	host->data->error = errno;
@@ -886,8 +896,20 @@
 	spin_lock_irqsave(&host->irq_lock, flags);
 	dma_ch = host->dma_ch;
 	host->dma_ch = -1;
+	dma2 = host->dma2;
+	host->dma2 = -1;
 	spin_unlock_irqrestore(&host->irq_lock, flags);
 
+	if (host->use_dma && dma2 != -1) {
+		struct dma_chan *chan = omap_hsmmc_get_dma_chan(host, host->data);
+
+		dmaengine_terminate_all(chan);
+		dma_unmap_sg(chan->device->dev,
+			host->data->sg, host->data->sg_len,
+			omap_hsmmc_get_dma_dir(host, host->data));
+
+		host->data->host_cookie = 0;
+	}
 	if (host->use_dma && dma_ch != -1) {
 		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg,
 			host->data->sg_len,
@@ -1284,9 +1306,43 @@
 	}
 }
 
+static void omap_hsmmc_dma_callback(void *param)
+{
+	struct omap_hsmmc_host *host = param;
+	struct dma_chan *chan;
+	struct mmc_data *data;
+	int req_in_progress;
+
+	spin_lock_irq(&host->irq_lock);
+	if (host->dma2 < 0) {
+		spin_unlock_irq(&host->irq_lock);
+		return;
+	}
+
+	data = host->mrq->data;
+	chan = omap_hsmmc_get_dma_chan(host, data);
+	if (!data->host_cookie)
+		dma_unmap_sg(chan->device->dev,
+			     data->sg, data->sg_len,
+			     omap_hsmmc_get_dma_dir(host, data));
+
+	req_in_progress = host->req_in_progress;
+	host->dma2 = -1;
+	spin_unlock_irq(&host->irq_lock);
+
+	/* If DMA has finished after TC, complete the request */
+	if (!req_in_progress) {
+		struct mmc_request *mrq = host->mrq;
+
+		host->mrq = NULL;
+		mmc_request_done(host->mmc, mrq);
+	}
+}
+
 static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 				       struct mmc_data *data,
-				       struct omap_hsmmc_next *next)
+				       struct omap_hsmmc_next *next,
+				       struct device *dev)
 {
 	int dma_len;
 
@@ -1301,8 +1357,7 @@
 	/* Check if next job is already prepared */
 	if (next ||
 	    (!next && data->host_cookie != host->next_data.cookie)) {
-		dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
+		dma_len = dma_map_sg(dev, data->sg, data->sg_len,
 				     omap_hsmmc_get_dma_dir(host, data));
 
 	} else {
@@ -1331,6 +1386,7 @@
 {
 	int dma_ch = 0, ret = 0, i;
 	struct mmc_data *data = req->data;
+	struct dma_chan *chan;
 
 	/* Sanity check: all the SG entries must be aligned by block size. */
 	for (i = 0; i < data->sg_len; i++) {
@@ -1346,24 +1402,66 @@
 		 */
 		return -EINVAL;
 
-	BUG_ON(host->dma_ch != -1);
+	BUG_ON(host->dma_ch != -1 || host->dma2 != -1);
 
-	ret = omap_request_dma(omap_hsmmc_get_dma_sync_dev(host, data),
-			       "MMC/SD", omap_hsmmc_dma_cb, host, &dma_ch);
-	if (ret != 0) {
-		dev_err(mmc_dev(host->mmc),
-			"%s: omap_request_dma() failed with %d\n",
-			mmc_hostname(host->mmc), ret);
-		return ret;
+	chan = omap_hsmmc_get_dma_chan(host, data);
+	if (!chan) {
+		ret = omap_request_dma(omap_hsmmc_get_dma_sync_dev(host, data),
+				       "MMC/SD", omap_hsmmc_dma_cb, host, &dma_ch);
+		if (ret != 0) {
+			dev_err(mmc_dev(host->mmc),
+				"%s: omap_request_dma() failed with %d\n",
+				mmc_hostname(host->mmc), ret);
+			return ret;
+		}
+		ret = omap_hsmmc_pre_dma_transfer(host, data, NULL,
+						  mmc_dev(host->mmc));
+		if (ret)
+			return ret;
+
+		host->dma_ch = dma_ch;
+		host->dma_sg_idx = 0;
+
+		omap_hsmmc_config_dma_params(host, data, data->sg);
+	} else {
+		struct dma_slave_config cfg;
+		struct dma_async_tx_descriptor *tx;
+
+		cfg.src_addr = host->mapbase + OMAP_HSMMC_DATA;
+		cfg.dst_addr = host->mapbase + OMAP_HSMMC_DATA;
+		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		cfg.src_maxburst = data->blksz / 4;
+		cfg.dst_maxburst = data->blksz / 4;
+
+		ret = dmaengine_slave_config(chan, &cfg);
+		if (ret)
+			return ret;
+
+		ret = omap_hsmmc_pre_dma_transfer(host, data, NULL,
+						  chan->device->dev);
+		if (ret)
+			return ret;
+
+		tx = dmaengine_prep_slave_sg(chan, data->sg, data->sg_len,
+			data->flags & MMC_DATA_WRITE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!tx) {
+			dev_err(mmc_dev(host->mmc), "prep_slave_sg() failed\n");
+			/* FIXME: cleanup */
+			return -1;
+		}
+
+		tx->callback = omap_hsmmc_dma_callback;
+		tx->callback_param = host;
+
+		/* Does not fail */
+		dmaengine_submit(tx);
+
+		host->dma2 = 1;
+
+		dma_async_issue_pending(chan);
 	}
-	ret = omap_hsmmc_pre_dma_transfer(host, data, NULL);
-	if (ret)
-		return ret;
-
-	host->dma_ch = dma_ch;
-	host->dma_sg_idx = 0;
-
-	omap_hsmmc_config_dma_params(host, data, data->sg);
 
 	return 0;
 }
@@ -1446,9 +1544,12 @@
 	struct mmc_data *data = mrq->data;
 
 	if (host->use_dma) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, data);
+		struct device *dev = c ? c->device->dev : mmc_dev(mmc);
+
 		if (data->host_cookie)
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
+			dma_unmap_sg(dev,
+				     data->sg, data->sg_len,
 				     omap_hsmmc_get_dma_dir(host, data));
 		data->host_cookie = 0;
 	}
@@ -1464,10 +1565,14 @@
 		return ;
 	}
 
-	if (host->use_dma)
+	if (host->use_dma) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, mrq->data);
+		struct device *dev = c ? c->device->dev : mmc_dev(mmc);
+
 		if (omap_hsmmc_pre_dma_transfer(host, mrq->data,
-						&host->next_data))
+						&host->next_data, dev))
 			mrq->data->host_cookie = 0;
+	}
 }
 
 /*
@@ -1479,7 +1584,7 @@
 	int err;
 
 	BUG_ON(host->req_in_progress);
-	BUG_ON(host->dma_ch != -1);
+	BUG_ON(host->dma_ch != -1 || host->dma2 != -1);
 	if (host->protect_card) {
 		if (host->reqs_blocked < 3) {
 			/*
@@ -1846,6 +1951,7 @@
 	host->use_dma	= 1;
 	host->dev->dma_mask = &pdata->dma_mask;
 	host->dma_ch	= -1;
+	host->dma2	= -1;
 	host->irq	= irq;
 	host->slot_id	= 0;
 	host->mapbase	= res->start + pdata->reg_offset;
@@ -1942,6 +2048,29 @@
 	}
 	host->dma_line_rx = res->start;
 
+	{
+		dma_cap_mask_t mask;
+		unsigned sig;
+		extern bool omap_dma_filter_fn(struct dma_chan *chan, void *param);
+
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+#if 1
+		sig = host->dma_line_rx;
+		host->rx_chan = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+		if (!host->rx_chan) {
+			dev_warn(mmc_dev(host->mmc), "unable to obtain RX DMA engine channel %u\n", sig);
+		}
+#endif
+#if 1
+		sig = host->dma_line_tx;
+		host->tx_chan = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+		if (!host->tx_chan) {
+			dev_warn(mmc_dev(host->mmc), "unable to obtain TX DMA engine channel %u\n", sig);
+		}
+#endif
+	}
+
 	/* Request IRQ for MMC operations */
 	ret = request_irq(host->irq, omap_hsmmc_irq, 0,
 			mmc_hostname(mmc), host);
@@ -2019,6 +2148,10 @@
 err_irq_cd_init:
 	free_irq(host->irq, host);
 err_irq:
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
@@ -2054,6 +2187,11 @@
 	if (mmc_slot(host).card_detect_irq)
 		free_irq(mmc_slot(host).card_detect_irq, host);
 
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
+
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);