mmc: tegra: use bounce buffer APIs

Tegra's MMC driver does DMA, and hence needs cache-aligned buffers. In
some cases (e.g. user load commands) this cannot be guaranteed by callers
of the MMC APIs. To solve this, modify the Tegra MMC driver to use the
new bounce_buffer_*() APIs.

Note: Ideally, all U-Boot code will always provide address- and size-
aligned buffers, so a bounce buffer will only ever be needed for user-
supplied buffers (e.g. load commands). Ensuring this removes the need
for performance-sucking bounce buffer cache management and memcpy()s.
The one known exception at present is the SCR buffer in sd_change_freq(),
which is only 8 bytes long. Solving this requires enhancing struct
mmc_data to know the difference between buffer size and transferred data
size, or forcing all callers of mmc_send_cmd() to have allocated buffers
using ALLOC_CACHE_ALIGN_BUFFER(), which while true in this case, is not
enforced in any way at present, and so cannot be assumed by the core MMC
code.

Signed-off-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Simon Glass <sjg@chromium.org>
Tested-by: Simon Glass <sjg@chromium.org>
Signed-off-by: Andy Fleming <afleming@freescale.com>
diff --git a/drivers/mmc/tegra_mmc.c b/drivers/mmc/tegra_mmc.c
index 8fea6a6..b141eaf 100644
--- a/drivers/mmc/tegra_mmc.c
+++ b/drivers/mmc/tegra_mmc.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <bouncebuf.h>
 #include <common.h>
 #include <asm/gpio.h>
 #include <asm/io.h>
@@ -66,14 +67,17 @@
 	host->reg = (struct tegra_mmc *)host->base;
 }
 
-static void mmc_prepare_data(struct mmc_host *host, struct mmc_data *data)
+static void mmc_prepare_data(struct mmc_host *host, struct mmc_data *data,
+				struct bounce_buffer *bbstate)
 {
 	unsigned char ctrl;
 
-	debug("data->dest: %08X, data->blocks: %u, data->blocksize: %u\n",
-	(u32)data->dest, data->blocks, data->blocksize);
 
-	writel((u32)data->dest, &host->reg->sysad);
+	debug("buf: %p (%p), data->blocks: %u, data->blocksize: %u\n",
+		bbstate->bounce_buffer, bbstate->user_buffer, data->blocks,
+		data->blocksize);
+
+	writel((u32)bbstate->bounce_buffer, &host->reg->sysad);
 	/*
 	 * DMASEL[4:3]
 	 * 00 = Selects SDMA
@@ -114,14 +118,6 @@
 	if (data->flags & MMC_DATA_READ)
 		mode |= TEGRA_MMC_TRNMOD_DATA_XFER_DIR_SEL_READ;
 
-	if (data->flags & MMC_DATA_WRITE) {
-		if ((uintptr_t)data->src & (ARCH_DMA_MINALIGN - 1))
-			printf("Warning: unaligned write to %p may fail\n",
-			       data->src);
-		flush_dcache_range((ulong)data->src, (ulong)data->src +
-			data->blocks * data->blocksize);
-	}
-
 	writew(mode, &host->reg->trnmod);
 }
 
@@ -156,8 +152,8 @@
 	return 0;
 }
 
-static int mmc_send_cmd(struct mmc *mmc, struct mmc_cmd *cmd,
-			struct mmc_data *data)
+static int mmc_send_cmd_bounced(struct mmc *mmc, struct mmc_cmd *cmd,
+			struct mmc_data *data, struct bounce_buffer *bbstate)
 {
 	struct mmc_host *host = (struct mmc_host *)mmc->priv;
 	int flags, i;
@@ -172,7 +168,7 @@
 		return result;
 
 	if (data)
-		mmc_prepare_data(host, data);
+		mmc_prepare_data(host, data, bbstate);
 
 	debug("cmd->arg: %08x\n", cmd->cmdarg);
 	writel(cmd->cmdarg, &host->reg->argument);
@@ -322,20 +318,42 @@
 			}
 		}
 		writel(mask, &host->reg->norintsts);
-		if (data->flags & MMC_DATA_READ) {
-			if ((uintptr_t)data->dest & (ARCH_DMA_MINALIGN - 1))
-				printf("Warning: unaligned read from %p "
-					"may fail\n", data->dest);
-			invalidate_dcache_range((ulong)data->dest,
-				(ulong)data->dest +
-					data->blocks * data->blocksize);
-		}
 	}
 
 	udelay(1000);
 	return 0;
 }
 
+static int mmc_send_cmd(struct mmc *mmc, struct mmc_cmd *cmd,
+			struct mmc_data *data)
+{
+	void *buf;
+	unsigned int bbflags;
+	size_t len;
+	struct bounce_buffer bbstate;
+	int ret;
+
+	if (data) {
+		if (data->flags & MMC_DATA_READ) {
+			buf = data->dest;
+			bbflags = GEN_BB_WRITE;
+		} else {
+			buf = (void *)data->src;
+			bbflags = GEN_BB_READ;
+		}
+		len = data->blocks * data->blocksize;
+
+		bounce_buffer_start(&bbstate, buf, len, bbflags);
+	}
+
+	ret = mmc_send_cmd_bounced(mmc, cmd, data, &bbstate);
+
+	if (data)
+		bounce_buffer_stop(&bbstate);
+
+	return ret;
+}
+
 static void mmc_change_clock(struct mmc_host *host, uint clock)
 {
 	int div;
diff --git a/include/configs/tegra20-common.h b/include/configs/tegra20-common.h
index 31b68be..5c0833a 100644
--- a/include/configs/tegra20-common.h
+++ b/include/configs/tegra20-common.h
@@ -202,4 +202,7 @@
 #define CONFIG_SYS_NAND_SELF_INIT
 #define CONFIG_SYS_NAND_ONFI_DETECTION
 
+/* Misc utility code */
+#define CONFIG_BOUNCE_BUFFER
+
 #endif /* __TEGRA20_COMMON_H */