mtd: rawnand: brcmnand: Add BCMBCA read data bus interface

The BCMBCA broadband SoC integrates the NAND controller differently than
STB, iProc and other SoCs.  It has different endianness for NAND cache
data.

Add a SoC read data bus shim for BCMBCA to meet the specific SoC need
and performance improvement using the optimized memcpy function on NAND
cache memory.
Signed-off-by: William Zhang <william.zhang@broadcom.com>
Reviewed-by: David Regan <dregan@broadcom.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20240223034758.13753-12-william.zhang@broadcom.com

drivers/mtd/nand/raw/brcmnand/bcmbca_nand.c

@@ -26,6 +26,18 @@ enum {
 	BCMBCA_CTLRDY		= BIT(4),
 };
 
+#if defined(CONFIG_ARM64)
+#define ALIGN_REQ		8
+#else
+#define ALIGN_REQ		4
+#endif
+
+static inline bool bcmbca_nand_is_buf_aligned(void *flash_cache,  void *buffer)
+{
+	return IS_ALIGNED((uintptr_t)buffer, ALIGN_REQ) &&
+				IS_ALIGNED((uintptr_t)flash_cache, ALIGN_REQ);
+}
+
 static bool bcmbca_nand_intc_ack(struct brcmnand_soc *soc)
 {
 	struct bcmbca_nand_soc *priv =
@@ -56,6 +68,20 @@ static void bcmbca_nand_intc_set(struct brcmnand_soc *soc, bool en)
 	brcmnand_writel(val, mmio);
 }
 
+static void bcmbca_read_data_bus(struct brcmnand_soc *soc,
+				 void __iomem *flash_cache,  u32 *buffer, int fc_words)
+{
+	/*
+	 * memcpy can do unaligned aligned access depending on source
+	 * and dest address, which is incompatible with nand cache. Fallback
+	 * to the memcpy_fromio in such case
+	 */
+	if (bcmbca_nand_is_buf_aligned((void *)flash_cache, buffer))
+		memcpy((void *)buffer, (void *)flash_cache, fc_words * 4);
+	else
+		memcpy_fromio((void *)buffer, flash_cache, fc_words * 4);
+}
+
 static int bcmbca_nand_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -73,6 +99,7 @@ static int bcmbca_nand_probe(struct platform_device *pdev)
 
 	soc->ctlrdy_ack = bcmbca_nand_intc_ack;
 	soc->ctlrdy_set_enabled = bcmbca_nand_intc_set;
+	soc->read_data_bus = bcmbca_read_data_bus;
 
 	return brcmnand_probe(pdev, soc);
 }

drivers/mtd/nand/raw/brcmnand/brcmnand.c

@@ -851,6 +851,20 @@ static inline u32 edu_readl(struct brcmnand_controller *ctrl,
 	return brcmnand_readl(ctrl->edu_base + offs);
 }
 
+static inline void brcmnand_read_data_bus(struct brcmnand_controller *ctrl,
+					  void __iomem *flash_cache, u32 *buffer, int fc_words)
+{
+	struct brcmnand_soc *soc = ctrl->soc;
+	int i;
+
+	if (soc->read_data_bus) {
+		soc->read_data_bus(soc, flash_cache, buffer, fc_words);
+	} else {
+		for (i = 0; i < fc_words; i++)
+			buffer[i] = brcmnand_read_fc(ctrl, i);
+	}
+}
+
 static void brcmnand_clear_ecc_addr(struct brcmnand_controller *ctrl)
 {
 
@@ -1975,7 +1989,7 @@ static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip,
 {
 	struct brcmnand_host *host = nand_get_controller_data(chip);
 	struct brcmnand_controller *ctrl = host->ctrl;
-	int i, j, ret = 0;
+	int i, ret = 0;
 
 	brcmnand_clear_ecc_addr(ctrl);
 
@@ -1988,8 +2002,8 @@ static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip,
 		if (likely(buf)) {
 			brcmnand_soc_data_bus_prepare(ctrl->soc, false);
 
-			for (j = 0; j < FC_WORDS; j++, buf++)
-				*buf = brcmnand_read_fc(ctrl, j);
+			brcmnand_read_data_bus(ctrl, ctrl->nand_fc, buf, FC_WORDS);
+			buf += FC_WORDS;
 
 			brcmnand_soc_data_bus_unprepare(ctrl->soc, false);
 		}

drivers/mtd/nand/raw/brcmnand/brcmnand.h

@@ -24,6 +24,8 @@ struct brcmnand_soc {
 	void (*ctlrdy_set_enabled)(struct brcmnand_soc *soc, bool en);
 	void (*prepare_data_bus)(struct brcmnand_soc *soc, bool prepare,
 				 bool is_param);
+	void (*read_data_bus)(struct brcmnand_soc *soc, void __iomem *flash_cache,
+			      u32 *buffer, int fc_words);
 	const struct brcmnand_io_ops *ops;
 };