Add timing data for Hitachi SP10Q010 display and allow configuration
of the 4bpp palette. For 4bpp framebuffer enable reversed order of
pixels in a byte. This requires defining FB_CFB_REV_PIXELS_IN_BYTE
and additionally setting var.nonstd to the value FB_NONSTD_REV_PIX_IN_B.
Note that it is not enough to set da8xx_fb_var.nonstd to this value
statically, since FBIOPUT_VSCREENINFO ioctl might pass var struct with
.nonstd field set to zero or another value. Therefore this setting must
be adjusted in fb_check_var() according to the requested bpp value.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
Cc: Manjunathappa, Prakash <prakash.pm@ti.com>
Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>

Timing info is not properly reported by the driver, e.g.:

$ fbset -i
mode "480x272-35"
    # D: 7.895 MHz, H: 12.165 kHz, V: 35.158 Hz
    geometry 480 272 480 544 16
    timings 126666 64 64 32 32 41 10

According to the timing values defined for LK043T1DG01 display
it should be reported as:

mode "480x272-53"
    # D: 7.895 MHz, H: 15.038 kHz, V: 52.579 Hz
    geometry 480 272 480 544 16
    timings 126666 2 2 2 2 41 10

Initialize additional fb_var_screeninfo fields so fix this problem.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
Cc: Manjunathappa, Prakash <prakash.pm@ti.com>
Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>

Convert calls to free_irq so that the second argument is the same as the
last argument of the corresponding call to request_irq.  Without this
property, free_irq does nothing.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>

Currently the shadow-dirty flags for manual update displays is cleared
in the apply_irq_handler when an update has finished. This is not
correct, as the shadow registers are taken into use (i.e. after that
they are not dirty) when the update is started.

Move the mgr_clear_shadow_dirty() call from apply_irq_handler to
dss_mgr_start_update() to fix this.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>

Supporting runtime PM is very nice, but that's not a reason not to
implement system suspend/resume properly.
Reported-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The meram_register(), meram_unregister() and meram_update() operations
check that the pointers they get from the caller are not NULL. Those
checks can be remove, as the caller already ensures that the pointers
are valid.

The platform sanity checks can also be removed, as the operations can't
be accessed without valid platform data anyway.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Remove the RGB or Y/C base address update from the meram_register()
operation, as this belongs to the meram_update() operation.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The structures, passed to the sh_mobile_lcdcfb driver through platform
data, are read only by the driver. Make them const.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Instead of copying the whole platform data structure to struct
sh_mobile_lcdc_chan, store a const pointer to the channel platform data.

MERAM configuration information needs to be changed at runtime, so copy
it to struct sh_mobile_lcdc_chan.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The marker_icb and cache_icb fields are not used anymore, remove them.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The marker and cache ICBs are now allocated automatically, there's no
need to specify them manually anymore.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Instead of manually specifying the ICBs to use in platform data,
allocate them automatically at runtime. The range of reserved ICBs (for
instance to be used through UIO), if any, is passed in the platform data
reserved_icbs field as a bitmask.

The MERAM registration function now returns a pointer to an opaque MERAM
object, which is passed to the update and unregistration functions.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Instead of requiring the users to hardcode MERAM allocation in platform
data, allocate blocks at runtime using genalloc.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

And rename a couple of constants to make prefixes more uniform.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Let the compiler decide which complex functions to inline, and constify
constant static arrays.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The new structure stores ICB parameters for ICBs.

Instead of modifying the struct sh_mobile_meram_cfg instances passed by
callers, store the ICB parameters internally and make the public API
take const pointers to sh_mobile_meram_cfg.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Make sure current_reg == 0/1 always mean register set A/B through all
the code.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Many variables, such as loop counters, sizes and offsets, should be
unsigned integers. Make them so.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The structure describe ICB configuration, no ICB objects themselves.
Rename it to sh_mobile_meram_icb_cfg in preparation for the addition of
an ICB structure.

All the structure fields are unsigned integers, make them so.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Make sure the registers and MERAM spaces are reserved before using them.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The MERAM resource currently combines both the registers space and the
MERAM space. Only the register space needs to be ioremapped, split the
resource to make that possible.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The sh_mobile_wait_for_vsync() function isn't related to the fbdev API,
make it generic by passing a channel pointer instead of an fb_info
pointer.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Store the frame buffer configuration (colorspace, visible/virtual
horizontal and vertical resolutions and line pitch) in the
sh_mobile_lcdc_chan structure, and use it instead of accessing fb_info.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The dma_map_sg() and dma_unmap_sg() functions need a pointer to the
physical device.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Store the active format in the channel structure, and use it instead of
parsing info->var all over the place when the format is needed.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The function returns a pointer to a structure describing a format based
on its fourcc. Use the function where applicable instead of hardcoded
switch-case statements.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Group fields by purpose, and make the separation between core fields and
FB-related fields clear.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The struct sh_mobile_lcdc_chan_cfg platform data contains a list of
video modes. Name the lcd_cfg and num_cfg fields to reflect that they
describe video modes.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Embed struct fb_videomode instead of struct fb_var_screeninfo in struct
sh_mobile_lcdc_chan to store the display mode.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The LCDC fb_info structure is only used to retrieve the default video
mode in case none of the modes advertised by EDID information is
acceptable. Pass a pointer to the default mode through the
sh_mobile_lcdc_entity structure instead.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The struct sh_hdmi mode field is only used after being assigned by the
EDID read code. There is thus no need to initialize it from the LCDC
display var in the display on handler.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Pass pointers to struct fb_videomode and struct fb_monspecs instead of
struct fb_var_screeninfo to the notify callback.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Instead of accessing the LCDC channel and fb_info structures directly,
use the LCDC notification callback to inform the LCDC driver about
display-related events.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The callback implements 3 notification events:

- SH_MOBILE_LCDC_EVENT_DISPLAY_CONNECT notifies the LCDC that the
  display has been connected
- SH_MOBILE_LCDC_EVENT_DISPLAY_DISCONNECT notifies the LCDC that the
  display has been disconnected
- SH_MOBILE_LCDC_EVENT_DISPLAY_MODE notifies that LCDC that a display
  mode has been detected
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

Return true if the display is connected and false otherwise. Set the fb
info state to FBINFO_STATE_SUSPENDED in the sh_mobile_lcdc driver when
the display is not connected.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

The parameter is unused, remove it.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>