spi: cadence_qspi_apb: Make flash writes 32 bit aligned

Make flash writes 32 bit aligned by using bounce buffers to deal with
non 32 bit aligned buffers.
This is required because as per TI K2G TRM[1], the external master is
only permitted to issue 32-bit data interface writes until the last word
of an indirect transfer. Otherwise indirect writes is known to fail
sometimes.

[1] http://www.ti.com/lit/ug/spruhy8g/spruhy8g.pdf

Signed-off-by: Vignesh R <vigneshr@ti.com>
Acked-by: Marek Vasut <marex@denx.de>
Acked-by: Simon Goldschmidt <sgoldschmidt@de.pepperl-fuchs.com>
Reviewed-by: Jason Rush <jarush@gmail.com>
Acked-by: Jason Rush <jarush@gmail.com>
Reviewed-by: Jagan Teki <jagan@openedev.com>

drivers/spi/cadence_qspi_apb.c

@@ -30,6 +30,7 @@
 #include <linux/errno.h>
 #include <wait_bit.h>
 #include <spi.h>
+#include <malloc.h>
 #include "cadence_qspi.h"
 
 #define CQSPI_REG_POLL_US			1 /* 1us */
@@ -719,9 +720,23 @@ int cadence_qspi_apb_indirect_write_execute(struct cadence_spi_platdata *plat,
 {
 	unsigned int page_size = plat->page_size;
 	unsigned int remaining = n_tx;
+	const u8 *bb_txbuf = txbuf;
+	void *bounce_buf = NULL;
 	unsigned int write_bytes;
 	int ret;
 
+	/*
+	 * Use bounce buffer for non 32 bit aligned txbuf to avoid data
+	 * aborts
+	 */
+	if ((uintptr_t)txbuf % 4) {
+		bounce_buf = malloc(n_tx);
+		if (!bounce_buf)
+			return -ENOMEM;
+		memcpy(bounce_buf, txbuf, n_tx);
+		bb_txbuf = bounce_buf;
+	}
+
 	/* Configure the indirect read transfer bytes */
 	writel(n_tx, plat->regbase + CQSPI_REG_INDIRECTWRBYTES);
 
@@ -731,11 +746,11 @@ int cadence_qspi_apb_indirect_write_execute(struct cadence_spi_platdata *plat,
 
 	while (remaining > 0) {
 		write_bytes = remaining > page_size ? page_size : remaining;
-		/* Handle non-4-byte aligned access to avoid data abort. */
-		if (((uintptr_t)txbuf % 4) || (write_bytes % 4))
-			writesb(plat->ahbbase, txbuf, write_bytes);
-		else
-			writesl(plat->ahbbase, txbuf, write_bytes >> 2);
+		writesl(plat->ahbbase, bb_txbuf, write_bytes >> 2);
+		if (write_bytes % 4)
+			writesb(plat->ahbbase,
+				bb_txbuf + rounddown(write_bytes, 4),
+				write_bytes % 4);
 
 		ret = wait_for_bit_le32(plat->regbase + CQSPI_REG_SDRAMLEVEL,
 					CQSPI_REG_SDRAMLEVEL_WR_MASK <<
@@ -745,7 +760,7 @@ int cadence_qspi_apb_indirect_write_execute(struct cadence_spi_platdata *plat,
 			goto failwr;
 		}
 
-		txbuf += write_bytes;
+		bb_txbuf += write_bytes;
 		remaining -= write_bytes;
 	}
 
@@ -760,12 +775,16 @@ int cadence_qspi_apb_indirect_write_execute(struct cadence_spi_platdata *plat,
 	/* Clear indirect completion status */
 	writel(CQSPI_REG_INDIRECTWR_DONE,
 	       plat->regbase + CQSPI_REG_INDIRECTWR);
+	if (bounce_buf)
+		free(bounce_buf);
 	return 0;
 
 failwr:
 	/* Cancel the indirect write */
 	writel(CQSPI_REG_INDIRECTWR_CANCEL,
 	       plat->regbase + CQSPI_REG_INDIRECTWR);
+	if (bounce_buf)
+		free(bounce_buf);
 	return ret;
 }