| Message ID | cover.9e7b6a702e4d90a13d08fbe3b0a319cbf4db687f.1516617243.git-series.maxime.ripard@free-electrons.com |
|---|---|
| Headers | show |
| Series | drm/sun4i: Support more planes, zpos and plane-wide alpha | expand |
On Mon, Jan 29, 2018 at 10:22:54AM +0800, Chen-Yu Tsai wrote: > On Mon, Jan 22, 2018 at 6:35 PM, Maxime Ripard > <maxime.ripard@free-electrons.com> wrote: > > Since we now have a way to enforce the zpos, check for the number of alpha > > planes, the only missing part is to assign our pipe automatically instead > > of hardcoding it. > > > > The algorithm is quite simple, but requires two iterations over the list of > > planes. > > > > In the first one (which is the same one that we've had to check for alpha, > > the frontend usage, and so on), we order the planes by their zpos. > > > > We can then do a second iteration over that array by ascending zpos > > starting with the pipe 0. When and if we encounter our alpha plane, we put > > it and all the other subsequent planes in the second pipe. > > > > And since we have runtime checks and pipe assignments now, we can just > > remove the static declaration of the planes we used to have. > > It would be slightly better if you could split this out into a separate > patch. It's not immediately obvious to others that the changes to > sun4i_layer.c are self-contained, while the change to sun4i_layer.h > is part of the new pipeline tracking thing. Plus I think the way you > structured everything means it won't break if you split it out. You're right, I'll split this patch and resend it. I've pushed the patches 9-15 to drm-misc, with your suggestions when you had some. Thanks! Maxime -- Maxime Ripard, Free Electrons Embedded Linux and Kernel engineering http://free-electrons.com
Hi, This serie aims at enhancing the support for our planes in the current drm driver on the first generation of Allwinner's display engine. This also introduces a few generic stuff, as well as some conversion for some other drivers. This series basically implements three things that look orthogonal, but due to the way the hardware works are kind of related. The main feature is that instead of implementing 2 planes per backend, we are now able to use the planes that are available in hardware. This was unsupported before because of the way the composition works in the hardware. Indeed, the planes are first grouped into 2 pipes that are doing a basic composition, in case of overlapping planes, it just takes whatever plane has the highest priority (=> zpos). Then, the alpha blending is done between the two pipes. This was simplified so far by only using two planes, one for each pipe, which was allowing us to have an illusion of proper alpha blending. This is further complicated by the bug/feature that the lowest plane must not have any alpha at all, otherwise the pixel will turn black, no matter what the value of alpha is. This basically means that we can have a plane with alpha only in the second pipe. However, as we have more and more blocks being worked on, 2 planes are getting really limited and we need to support all 4 of them. This is mostly possible by extending our atomic_check and to make sure that we enforce those constraints, and assign the pipes automatically. This is done by looking at the number of planes using an alpha component, and we then end up in various scenarios: - 0 plane with alpha => we don't care for the pipes at all. All the planes are assigned to the first pipe - 1 plane with alpha => we assign all the planes without alpha below the plane with alpha to the first pipe, and then all the remaining planes to the second pipe. The plane with alpha will be the lowest plane on that pipe, which means that whatever plane is above it will have precedence, but the alpha component will remain and will be used on pixels that are not overlapping - 2-4 planes with alpha => we can't operate that way, we just reject the configuration. In addition to the formats that embed an alpha component, we also add support for plane-wide alpha property, and in order to tweak the configuration the way we want to, we also add support for configurable zpos. Let me know what you think, Maxime Changes from v1: - Document the behaviour on concurrent usage of the alpha property and an alpha component in the format - Allowed for higher alpha values - Moved the alpha value from a helper to the struct drm_format_info - Collected tags Maxime Ripard (19): drm/fourcc: Add a alpha field to drm_format_info drm/atmel-hlcdc: Use the alpha format field in drm_format_info drm/atmel-exynos: Use the alpha format field in drm_format_info drm/rockchip: Use the alpha format field in drm_format_info drm/vc4: Use the alpha format field in drm_format_info drm/blend: Add a generic alpha property drm/atmel-hclcdc: Convert to the new generic alpha property drm/rcar-du: Convert to the new generic alpha property drm/sun4i: backend: Fix structure indentation drm/sun4i: backend: Fix define typo drm/sun4i: framebuffer: Add a custom atomic_check drm/sun4i: backend: Move the coord function in the shared part drm/sun4i: backend: Set a default zpos in our reset hook drm/sun4i: backend: Add support for zpos drm/sun4i: backend: Check for the number of alpha planes drm/sun4i: backend: Assign the pipes automatically drm/sun4i: backend: Make zpos configurable drm/sun4i: Add support for plane alpha drm/sun4i: backend: Remove ARGB spoofing Documentation/gpu/kms-properties.csv | 2 +- drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h | 13 +-- drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c | 113 ++------------- drivers/gpu/drm/drm_atomic.c | 4 +- drivers/gpu/drm/drm_atomic_helper.c | 4 +- drivers/gpu/drm/drm_blend.c | 32 ++++- drivers/gpu/drm/drm_fourcc.c | 50 +++---- drivers/gpu/drm/exynos/exynos_mixer.c | 14 +-- drivers/gpu/drm/rcar-du/rcar_du_drv.h | 1 +- drivers/gpu/drm/rcar-du/rcar_du_kms.c | 5 +- drivers/gpu/drm/rcar-du/rcar_du_plane.c | 15 +-- drivers/gpu/drm/rcar-du/rcar_du_plane.h | 2 +- drivers/gpu/drm/rcar-du/rcar_du_vsp.c | 42 +------ drivers/gpu/drm/rcar-du/rcar_du_vsp.h | 2 +- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 13 +-- drivers/gpu/drm/sun4i/sun4i_backend.c | 124 +++++++++++++++-- drivers/gpu/drm/sun4i/sun4i_backend.h | 11 +- drivers/gpu/drm/sun4i/sun4i_framebuffer.c | 18 +- drivers/gpu/drm/sun4i/sun4i_layer.c | 84 ++---------- drivers/gpu/drm/sun4i/sun4i_layer.h | 1 +- drivers/gpu/drm/vc4/vc4_plane.c | 19 +-- include/drm/drm_blend.h | 1 +- include/drm/drm_fourcc.h | 2 +- include/drm/drm_plane.h | 6 +- 24 files changed, 275 insertions(+), 303 deletions(-) base-commit: 53b519deaf2e507b121b64abcb4ba0da075bd6a7