[PATCH v3] OMAP: DMA: Fix omapfb/lcdc on OMAP1510 broken when PM set

With CONFIG_PM=y, the omapfb/lcdc device on Amstrad Delta, after initially
starting correctly, breaks with the following error messages:

omapfb omapfb: resetting (status 0xffffff96,reset count 1)
...
omapfb omapfb: resetting (status 0xffffff96,reset count 100)
omapfb omapfb: too many reset attempts, giving up.

Looking closer at this I have found that it had been broken almost 2 years ago
with commit 2418996e3b100114edb2ae110d5d4acb928909d2, PM fixes for OMAP1.

The definite reason for broken omapfb/lcdc behavoiur in PM mode
appeared to be ARM_IDLECT1:IDLIF_ARM (bit 6) put into idle regardless of LCD
DMA possibly running. The bit were set based on return value of the
omap_dma_running() function that did not check for dedicated LCD DMA
channel status. The patch below fixes this.

Created against linux-2.6.32-rc6

Tested on Amstrad Delta

Signed-off-by: Janusz Krzysztofik <redacted>

---
Tuesday 03 November 2009 21:10:48 Tony Lindgren wrote:

* Janusz Krzysztofik [off-list ref] [091103 12:05]:

quoted

Sorry, I've not checked for new mail before posting this one and missed
your acceptance for my idea of fixing all omap1510, not only ams_delta.
If there are no more comments, I'll submit v3 with cpu_is_omap1510()
replacing machine_is_ams_delta().

Sounds good to me.

Tony

--- linux-2.6.32-rc6/arch/arm/plat-omap/dma.c.orig	2009-11-03 20:37:49.000000000 +0100
+++ linux-2.6.32-rc6/arch/arm/plat-omap/dma.c	2009-11-05 19:30:39.000000000 +0100

@@ -1108,6 +1108,14 @@ int omap_dma_running(void)
 {
 	int lch;
 
+	/*
+	 * On OMAP1510, internal LCD controller will start the transfer
+	 * when it gets enabled, so assume DMA running if LCD enabled.
+	 */
+	if (cpu_is_omap1510())
+		if (omap_readw(0xfffec000 + 0x00) & (1 << 0))
+			return 1;
+
 	/* Check if LCD DMA is running */
 	if (cpu_is_omap16xx())
 		if (omap_readw(OMAP1610_DMA_LCD_CCR) & OMAP_DMA_CCR_EN)