The basic idea is taken from the linux-kernel, but further optimized.
First align the buffer to 8 bytes, then use ldrd/strd to read and store
in 8 byte quantities, then do the final bytes.
Signed-off-by: Nico Erfurth <n...@erfurth.eu>
Cc: Prafulla Wadaskar <prafu...@marvell.com>
---
drivers/mtd/nand/kirkwood_nand.c | 29 +++++++++++++++++++++++++++++
1 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/drivers/mtd/nand/kirkwood_nand.c b/drivers/mtd/nand/kirkwood_nand.c
index bdab5aa..e04a59f 100644
--- a/drivers/mtd/nand/kirkwood_nand.c
+++ b/drivers/mtd/nand/kirkwood_nand.c
@@ -38,6 +38,34 @@ struct kwnandf_registers {
static struct kwnandf_registers *nf_reg =
(struct kwnandf_registers *)KW_NANDF_BASE;
+
+/* The basic idea is stolen from the linux kernel, but the inner loop is
optimized a bit more */
+static void kw_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
+{
+ struct nand_chip *chip = mtd->priv;
+
+ while (len && (unsigned long)buf & 7)
+ {
+ *buf++ = readb(chip->IO_ADDR_R);
+ len--;
+ };
+
+ asm volatile (
+ ".LFlashLoop:\n"
+ " subs\t%0, #8\n"
+ " ldrpld\tr2, [%2]\n" // Read 2 words
+ " strpld\tr2, [%1], #8\n" // Read 2 words
+ " bpl\t.LFlashLoop\n" // This results in one additional loop
if len%8 <> 0
+ " addne\t%0, #8\n"
+ : "+&r" (len), "+&r" (buf)
+ : "r" (chip->IO_ADDR_R)
+ : "r2", "r3", "memory", "cc"
+ );
+
+ while (len--)
+ *buf++ = readb(chip->IO_ADDR_R);
+}
+
/*
* hardware specific access to control-lines/bits
*/
@@ -76,6 +104,7 @@ int board_nand_init(struct nand_chip *nand)
nand->options = NAND_COPYBACK | NAND_CACHEPRG | NAND_NO_PADDING;
nand->ecc.mode = NAND_ECC_SOFT;
nand->cmd_ctrl = kw_nand_hwcontrol;
+ nand->read_buf = kw_nand_read_buf;
nand->chip_delay = 40;
nand->select_chip = kw_nand_select_chip;
return 0;
--
1.7.3.4
_______________________________________________
U-Boot mailing list
U-Boot@lists.denx.de
http://lists.denx.de/mailman/listinfo/u-boot
