[ARM] pxafb: add support for overlay1 and overlay2 as framebuffer devices

PXA27x and later processors support overlay1 and overlay2 on-top of the
base framebuffer (although under-neath the base is also possible). They
support palette and no-palette RGB formats, as well as YUV formats (only
available on overlay2). These overlays have dedicated DMA channels and
behave in a similar way as a framebuffer.

This heavily simplified and re-structured work is based on the original
pxafb_overlay.c (which is pending for mainline merge for a long time).

The major problems with this pxafb_overlay.c are (if you are interested
in the history):

  1. heavily redundant (the control logics for overlay1 and overlay2 are
     actually identical except for some small operations,  which are now
     abstracted into a 'pxafb_layer_ops' structure)

  2. a lot of useless and un-tested code (two workarounds which are now
     fixed on mature silicons)

  3. cursorfb is actually useless, hardware cursor should not be used
     this way, and the code was actually un-tested for a long time.

The code in this patch should be self-explanatory, I tried to add minimum
comments. As said, this is basically simplified, there are several things
still on the pending list:

  1. palette mode is un-supported and un-tested (although re-using the
     palette code of the base framebuffer is actually very easy now with
     previous clean-up patches)

  2. fb_pan_display for overlay(s) is un-supported

  3. the base framebuffer can actually be abstracted by 'pxafb_layer' as
     well, which will help further re-use of the code and keep a better
     and consistent structure. (This is the reason I named it 'pxafb_layer'
     instead of 'pxafb_overlay' or something alike)

See Documentation/fb/pxafb.txt for additional usage information.
Signed-off-by: Eric Miao <eric.miao@marvell.com>
Cc: Rodolfo Giometti <giometti@linux.it>
Signed-off-by: Eric Miao <ycmiao@ycmiao-hp520.(none)>

Documentation/fb/pxafb.txt

@@ -56,3 +56,87 @@ outputen:POLARITY
 pixclockpol:POLARITY
 	pixel clock polarity
 	0 => falling edge, 1 => rising edge
+
+
+Overlay Support for PXA27x and later LCD controllers
+====================================================
+
+  PXA27x and later processors support overlay1 and overlay2 on-top of the
+  base framebuffer (although under-neath the base is also possible). They
+  support palette and no-palette RGB formats, as well as YUV formats (only
+  available on overlay2). These overlays have dedicated DMA channels and
+  behave in a similar way as a framebuffer.
+
+  However, there are some differences between these overlay framebuffers
+  and normal framebuffers, as listed below:
+
+  1. overlay can start at a 32-bit word aligned position within the base
+     framebuffer, which means they have a start (x, y). This information
+     is encoded into var->nonstd (no, var->xoffset and var->yoffset are
+     not for such purpose).
+
+  2. overlay framebuffer is allocated dynamically according to specified
+     'struct fb_var_screeninfo', the amount is decided by:
+
+        var->xres_virtual * var->yres_virtual * bpp
+
+     bpp = 16 -- for RGB565 or RGBT555
+         = 24 -- for YUV444 packed
+         = 24 -- for YUV444 planar
+	 = 16 -- for YUV422 planar (1 pixel = 1 Y + 1/2 Cb + 1/2 Cr)
+	 = 12 -- for YUV420 planar (1 pixel = 1 Y + 1/4 Cb + 1/4 Cr)
+
+     NOTE:
+
+     a. overlay does not support panning in x-direction, thus
+        var->xres_virtual will always be equal to var->xres
+
+     b. line length of overlay(s) must be on a 32-bit word boundary,
+        for YUV planar modes, it is a requirement for the component
+	with minimum bits per pixel,  e.g. for YUV420, Cr component
+	for one pixel is actually 2-bits, it means the line length
+	should be a multiple of 16-pixels
+
+     c. starting horizontal position (XPOS) should start on a 32-bit
+        word boundary, otherwise the fb_check_var() will just fail.
+
+     d. the rectangle of the overlay should be within the base plane,
+        otherwise fail
+
+     Applications should follow the sequence below to operate an overlay
+     framebuffer:
+
+         a. open("/dev/fb[1-2]", ...)
+	 b. ioctl(fd, FBIOGET_VSCREENINFO, ...)
+	 c. modify 'var' with desired parameters:
+	    1) var->xres and var->yres
+	    2) larger var->yres_virtual if more memory is required,
+	       usually for double-buffering
+	    3) var->nonstd for starting (x, y) and color format
+	    4) var->{red, green, blue, transp} if RGB mode is to be used
+	 d. ioctl(fd, FBIOPUT_VSCREENINFO, ...)
+	 e. ioctl(fd, FBIOGET_FSCREENINFO, ...)
+	 f. mmap
+	 g. ...
+
+  3. for YUV planar formats, these are actually not supported within the
+     framebuffer framework, application has to take care of the offsets
+     and lengths of each component within the framebuffer.
+
+  4. var->nonstd is used to pass starting (x, y) position and color format,
+     the detailed bit fields are shown below:
+
+    31                23  20         10          0
+     +-----------------+---+----------+----------+
+     |  ... unused ... |FOR|   XPOS   |   YPOS   |
+     +-----------------+---+----------+----------+
+
+     FOR  - color format, as defined by OVERLAY_FORMAT_* in pxafb.h
+            0 - RGB
+	    1 - YUV444 PACKED
+	    2 - YUV444 PLANAR
+	    3 - YUV422 PLANAR
+	    4 - YUR420 PLANAR
+
+     XPOS - starting horizontal position
+     YPOS - starting vertical position

arch/arm/mach-pxa/include/mach/regs-lcd.h

@@ -12,7 +12,8 @@
 #define LCCR3		(0x00C)	/* LCD Controller Control Register 3 */
 #define LCCR4		(0x010)	/* LCD Controller Control Register 4 */
 #define LCCR5		(0x014)	/* LCD Controller Control Register 5 */
-#define LCSR		(0x038)	/* LCD Controller Status Register */
+#define LCSR		(0x038)	/* LCD Controller Status Register 0 */
+#define LCSR1		(0x034)	/* LCD Controller Status Register 1 */
 #define LIIDR		(0x03C)	/* LCD Controller Interrupt ID Register */
 #define TMEDRGBR	(0x040)	/* TMED RGB Seed Register */
 #define TMEDCR		(0x044)	/* TMED Control Register */
@@ -25,6 +26,11 @@
 #define FBR5		(0x110) /* DMA Channel 2 Frame Branch Register */
 #define FBR6		(0x114) /* DMA Channel 2 Frame Branch Register */
 
+#define OVL1C1		(0x050)	/* Overlay 1 Control Register 1 */
+#define OVL1C2		(0x060)	/* Overlay 1 Control Register 2 */
+#define OVL2C1		(0x070)	/* Overlay 2 Control Register 1 */
+#define OVL2C2		(0x080)	/* Overlay 2 Control Register 2 */
+
 #define CMDCR		(0x100)	/* Command Control Register */
 #define PRSR		(0x104)	/* Panel Read Status Register */
 
@@ -42,16 +48,12 @@
 #define LCCR4_PAL_FOR_MASK	(3 << 15)
 
 #define FDADR0		(0x200)	/* DMA Channel 0 Frame Descriptor Address Register */
-#define FSADR0		(0x204)	/* DMA Channel 0 Frame Source Address Register */
-#define FIDR0		(0x208)	/* DMA Channel 0 Frame ID Register */
-#define LDCMD0		(0x20C)	/* DMA Channel 0 Command Register */
 #define FDADR1		(0x210)	/* DMA Channel 1 Frame Descriptor Address Register */
-#define FSADR1		(0x214)	/* DMA Channel 1 Frame Source Address Register */
-#define FIDR1		(0x218)	/* DMA Channel 1 Frame ID Register */
-#define LDCMD1		(0x21C)	/* DMA Channel 1 Command Register */
+#define FDADR2		(0x220)	/* DMA Channel 2 Frame Descriptor Address Register */
+#define FDADR3		(0x230)	/* DMA Channel 3 Frame Descriptor Address Register */
+#define FDADR4		(0x240)	/* DMA Channel 4 Frame Descriptor Address Register */
+#define FDADR5		(0x250)	/* DMA Channel 5 Frame Descriptor Address Register */
 #define FDADR6		(0x260) /* DMA Channel 6 Frame Descriptor Address Register */
-#define FSADR6		(0x264) /* DMA Channel 6 Frame Source Address Register */
-#define FIDR6		(0x268) /* DMA Channel 6 Frame ID Register */
 
 #define LCCR0_ENB	(1 << 0)	/* LCD Controller enable */
 #define LCCR0_CMS	(1 << 1)	/* Color/Monochrome Display Select */
@@ -151,8 +153,22 @@
 #define LCSR_RD_ST	(1 << 11)	/* read status */
 #define LCSR_CMD_INT	(1 << 12)	/* command interrupt */
 
+#define LCSR1_IU(x)	(1 << ((x) + 23)) /* Input FIFO underrun */
+#define LCSR1_BS(x)	(1 << ((x) + 15)) /* Branch Status */
+#define LCSR1_EOF(x)	(1 << ((x) + 7))  /* End of Frame Status */
+#define LCSR1_SOF(x)	(1 << ((x) - 1))  /* Start of Frame Status */
+
 #define LDCMD_PAL	(1 << 26)	/* instructs DMA to load palette buffer */
 
+/* overlay control registers */
+#define OVLxC1_PPL(x)	((((x) - 1) & 0x3ff) << 0)	/* Pixels Per Line */
+#define OVLxC1_LPO(x)	((((x) - 1) & 0x3ff) << 10)	/* Number of Lines */
+#define OVLxC1_BPP(x)	(((x) & 0xf) << 20)	/* Bits Per Pixel */
+#define OVLxC1_OEN	(1 << 31)		/* Enable bit for Overlay */
+#define OVLxC2_XPOS(x)	(((x) & 0x3ff) << 0)	/* Horizontal Position */
+#define OVLxC2_YPOS(x)	(((x) & 0x3ff) << 10)	/* Vertical Position */
+#define OVL2C2_PFOR(x)	(((x) & 0x7) << 20)	/* Pixel Format */
+
 /* smartpanel related */
 #define PRSR_DATA(x)	((x) & 0xff)	/* Panel Data */
 #define PRSR_A0		(1 << 8)	/* Read Data Source */

drivers/video/Kconfig

@@ -1817,6 +1817,11 @@ config FB_PXA
 
 	  If unsure, say N.
 
+config FB_PXA_OVERLAY
+	bool "Support PXA27x/PXA3xx Overlay(s) as framebuffer"
+	default n
+	depends on FB_PXA && (PXA27x || PXA3xx)
+
 config FB_PXA_SMARTPANEL
 	bool "PXA Smartpanel LCD support"
 	default n

drivers/video/pxafb.h

@@ -64,6 +64,47 @@ struct pxafb_dma_buff {
 	struct pxafb_dma_descriptor dma_desc[DMA_MAX * 2];
 };
 
+enum {
+	OVERLAY1,
+	OVERLAY2,
+};
+
+enum {
+	OVERLAY_FORMAT_RGB = 0,
+	OVERLAY_FORMAT_YUV444_PACKED,
+	OVERLAY_FORMAT_YUV444_PLANAR,
+	OVERLAY_FORMAT_YUV422_PLANAR,
+	OVERLAY_FORMAT_YUV420_PLANAR,
+};
+
+#define NONSTD_TO_XPOS(x)	(((x) >> 0)  & 0x3ff)
+#define NONSTD_TO_YPOS(x)	(((x) >> 10) & 0x3ff)
+#define NONSTD_TO_PFOR(x)	(((x) >> 20) & 0x7)
+
+struct pxafb_layer;
+
+struct pxafb_layer_ops {
+	void (*enable)(struct pxafb_layer *);
+	void (*disable)(struct pxafb_layer *);
+	void (*setup)(struct pxafb_layer *);
+};
+
+struct pxafb_layer {
+	struct fb_info		fb;
+	int			id;
+	atomic_t		usage;
+	uint32_t		control[2];
+
+	struct pxafb_layer_ops	*ops;
+
+	void __iomem		*video_mem;
+	unsigned long		video_mem_phys;
+	size_t			video_mem_size;
+	struct completion	branch_done;
+
+	struct pxafb_info	*fbi;
+};
+
 struct pxafb_info {
 	struct fb_info		fb;
 	struct device		*dev;
@@ -114,6 +155,10 @@ struct pxafb_info {
 	struct task_struct	*smart_thread;
 #endif
 
+#ifdef CONFIG_FB_PXA_OVERLAY
+	struct pxafb_layer	overlay[2];
+#endif
+
 #ifdef CONFIG_CPU_FREQ
 	struct notifier_block	freq_transition;
 	struct notifier_block	freq_policy;