[MTD] [NAND] atmel_nand speedup via {read,write}s{b,w}()

This uses __raw_{read,write}s{b,w}() primitives to access data on NAND
chips for more efficient I/O.

On an arm926 with memory clocked at 100 MHz, this reduced the elapsed time
for a 64 MiB read by 16%.  ("dd" /dev/mtd0 to /dev/null, with an 8-bit
NAND using hardware ECC and 128KiB blocksize.)

Also some minor section tweaks:

  - Use platform_driver_probe() so no pointer to probe() lingers
    after that code has been removed at run-time.

  - Use __exit and __exit_p so the remove() code will normally be
    removed by the linker.

Since these buffer read/write calls are new, this increases the runtime
code footprint (by 88 bytes on my build, after the section tweaks).

[haavard.skinnemoen@atmel.com: rebase onto atmel_nand rename]
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Håvard Skinnemoen <haavard.skinnemoen@atmel.com>
Acked-by: Andrew Victor <linux@maxim.org.za>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

drivers/mtd/nand/atmel_nand.c

@@ -141,6 +141,37 @@ static int atmel_nand_device_ready(struct mtd_info *mtd)
 	return gpio_get_value(host->board->rdy_pin);
 }
 
+/*
+ * Minimal-overhead PIO for data access.
+ */
+static void atmel_read_buf(struct mtd_info *mtd, u8 *buf, int len)
+{
+	struct nand_chip	*nand_chip = mtd->priv;
+
+	__raw_readsb(nand_chip->IO_ADDR_R, buf, len);
+}
+
+static void atmel_read_buf16(struct mtd_info *mtd, u8 *buf, int len)
+{
+	struct nand_chip	*nand_chip = mtd->priv;
+
+	__raw_readsw(nand_chip->IO_ADDR_R, buf, len / 2);
+}
+
+static void atmel_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
+{
+	struct nand_chip	*nand_chip = mtd->priv;
+
+	__raw_writesb(nand_chip->IO_ADDR_W, buf, len);
+}
+
+static void atmel_write_buf16(struct mtd_info *mtd, const u8 *buf, int len)
+{
+	struct nand_chip	*nand_chip = mtd->priv;
+
+	__raw_writesw(nand_chip->IO_ADDR_W, buf, len / 2);
+}
+
 /*
  * write oob for small pages
  */
@@ -436,8 +467,14 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 
 	nand_chip->chip_delay = 20;		/* 20us command delay time */
 
-	if (host->board->bus_width_16)		/* 16-bit bus width */
+	if (host->board->bus_width_16) {	/* 16-bit bus width */
 		nand_chip->options |= NAND_BUSWIDTH_16;
+		nand_chip->read_buf = atmel_read_buf16;
+		nand_chip->write_buf = atmel_write_buf16;
+	} else {
+		nand_chip->read_buf = atmel_read_buf;
+		nand_chip->write_buf = atmel_write_buf;
+	}
 
 	platform_set_drvdata(pdev, host);
 	atmel_nand_enable(host);
@@ -546,7 +583,7 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 /*
  * Remove a NAND device.
  */
-static int __devexit atmel_nand_remove(struct platform_device *pdev)
+static int __exit atmel_nand_remove(struct platform_device *pdev)
 {
 	struct atmel_nand_host *host = platform_get_drvdata(pdev);
 	struct mtd_info *mtd = &host->mtd;
@@ -564,8 +601,7 @@ static int __devexit atmel_nand_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver atmel_nand_driver = {
-	.probe		= atmel_nand_probe,
-	.remove		= atmel_nand_remove,
+	.remove		= __exit_p(atmel_nand_remove),
 	.driver		= {
 		.name	= "atmel_nand",
 		.owner	= THIS_MODULE,
@@ -574,7 +610,7 @@ static struct platform_driver atmel_nand_driver = {
 
 static int __init atmel_nand_init(void)
 {
-	return platform_driver_register(&atmel_nand_driver);
+	return platform_driver_probe(&atmel_nand_driver, atmel_nand_probe);
 }