OpenCloudOS-Kernel/Documentation/gpu/drm-kms.rst

526 lines
15 KiB
ReStructuredText
Raw Normal View History

=========================
Kernel Mode Setting (KMS)
=========================
Drivers must initialize the mode setting core by calling
:c:func:`drm_mode_config_init()` on the DRM device. The function
initializes the :c:type:`struct drm_device <drm_device>`
mode_config field and never fails. Once done, mode configuration must
be setup by initializing the following fields.
- int min_width, min_height; int max_width, max_height;
Minimum and maximum width and height of the frame buffers in pixel
units.
- struct drm_mode_config_funcs \*funcs;
Mode setting functions.
Overview
========
.. kernel-render:: DOT
:alt: KMS Display Pipeline
:caption: KMS Display Pipeline Overview
digraph "KMS" {
node [shape=box]
subgraph cluster_static {
style=dashed
label="Static Objects"
node [bgcolor=grey style=filled]
"drm_plane A" -> "drm_crtc"
"drm_plane B" -> "drm_crtc"
"drm_crtc" -> "drm_encoder A"
"drm_crtc" -> "drm_encoder B"
}
subgraph cluster_user_created {
style=dashed
label="Userspace-Created"
node [shape=oval]
"drm_framebuffer 1" -> "drm_plane A"
"drm_framebuffer 2" -> "drm_plane B"
}
subgraph cluster_connector {
style=dashed
label="Hotpluggable"
"drm_encoder A" -> "drm_connector A"
"drm_encoder B" -> "drm_connector B"
}
}
The basic object structure KMS presents to userspace is fairly simple.
Framebuffers (represented by :c:type:`struct drm_framebuffer <drm_framebuffer>`,
see `Frame Buffer Abstraction`_) feed into planes. Planes are represented by
:c:type:`struct drm_plane <drm_plane>`, see `Plane Abstraction`_ for more
details. One or more (or even no) planes feed their pixel data into a CRTC
(represented by :c:type:`struct drm_crtc <drm_crtc>`, see `CRTC Abstraction`_)
for blending. The precise blending step is explained in more detail in `Plane
Composition Properties`_ and related chapters.
For the output routing the first step is encoders (represented by
:c:type:`struct drm_encoder <drm_encoder>`, see `Encoder Abstraction`_). Those
are really just internal artifacts of the helper libraries used to implement KMS
drivers. Besides that they make it unecessarily more complicated for userspace
to figure out which connections between a CRTC and a connector are possible, and
what kind of cloning is supported, they serve no purpose in the userspace API.
Unfortunately encoders have been exposed to userspace, hence can't remove them
at this point. Futhermore the exposed restrictions are often wrongly set by
drivers, and in many cases not powerful enough to express the real restrictions.
A CRTC can be connected to multiple encoders, and for an active CRTC there must
be at least one encoder.
The final, and real, endpoint in the display chain is the connector (represented
by :c:type:`struct drm_connector <drm_connector>`, see `Connector
Abstraction`_). Connectors can have different possible encoders, but the kernel
driver selects which encoder to use for each connector. The use case is DVI,
which could switch between an analog and a digital encoder. Encoders can also
drive multiple different connectors. There is exactly one active connector for
every active encoder.
Internally the output pipeline is a bit more complex and matches today's
hardware more closely:
.. kernel-render:: DOT
:alt: KMS Output Pipeline
:caption: KMS Output Pipeline
digraph "Output Pipeline" {
node [shape=box]
subgraph {
"drm_crtc" [bgcolor=grey style=filled]
}
subgraph cluster_internal {
style=dashed
label="Internal Pipeline"
{
node [bgcolor=grey style=filled]
"drm_encoder A";
"drm_encoder B";
"drm_encoder C";
}
{
node [bgcolor=grey style=filled]
"drm_encoder B" -> "drm_bridge B"
"drm_encoder C" -> "drm_bridge C1"
"drm_bridge C1" -> "drm_bridge C2";
}
}
"drm_crtc" -> "drm_encoder A"
"drm_crtc" -> "drm_encoder B"
"drm_crtc" -> "drm_encoder C"
subgraph cluster_output {
style=dashed
label="Outputs"
"drm_encoder A" -> "drm_connector A";
"drm_bridge B" -> "drm_connector B";
"drm_bridge C2" -> "drm_connector C";
"drm_panel"
}
}
Internally two additional helper objects come into play. First, to be able to
share code for encoders (sometimes on the same SoC, sometimes off-chip) one or
more :ref:`drm_bridges` (represented by :c:type:`struct drm_bridge
<drm_bridge>`) can be linked to an encoder. This link is static and cannot be
changed, which means the cross-bar (if there is any) needs to be mapped between
the CRTC and any encoders. Often for drivers with bridges there's no code left
at the encoder level. Atomic drivers can leave out all the encoder callbacks to
essentially only leave a dummy routing object behind, which is needed for
backwards compatibility since encoders are exposed to userspace.
The second object is for panels, represented by :c:type:`struct drm_panel
<drm_panel>`, see :ref:`drm_panel_helper`. Panels do not have a fixed binding
point, but are generally linked to the driver private structure that embeds
:c:type:`struct drm_connector <drm_connector>`.
Note that currently the bridge chaining and interactions with connectors and
panels are still in-flux and not really fully sorted out yet.
KMS Core Structures and Functions
=================================
.. kernel-doc:: include/drm/drm_mode_config.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_mode_config.c
:export:
Modeset Base Object Abstraction
===============================
.. kernel-render:: DOT
:alt: Mode Objects and Properties
:caption: Mode Objects and Properties
digraph {
node [shape=box]
"drm_property A" -> "drm_mode_object A"
"drm_property A" -> "drm_mode_object B"
"drm_property B" -> "drm_mode_object A"
}
The base structure for all KMS objects is :c:type:`struct drm_mode_object
<drm_mode_object>`. One of the base services it provides is tracking properties,
which are especially important for the atomic IOCTL (see `Atomic Mode
Setting`_). The somewhat surprising part here is that properties are not
directly instantiated on each object, but free-standing mode objects themselves,
represented by :c:type:`struct drm_property <drm_property>`, which only specify
the type and value range of a property. Any given property can be attached
multiple times to different objects using :c:func:`drm_object_attach_property()
<drm_object_attach_property>`.
.. kernel-doc:: include/drm/drm_mode_object.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_mode_object.c
:export:
Atomic Mode Setting
===================
.. kernel-render:: DOT
:alt: Mode Objects and Properties
:caption: Mode Objects and Properties
digraph {
node [shape=box]
subgraph cluster_state {
style=dashed
label="Free-standing state"
"drm_atomic_state" -> "duplicated drm_plane_state A"
"drm_atomic_state" -> "duplicated drm_plane_state B"
"drm_atomic_state" -> "duplicated drm_crtc_state"
"drm_atomic_state" -> "duplicated drm_connector_state"
"drm_atomic_state" -> "duplicated driver private state"
}
subgraph cluster_current {
style=dashed
label="Current state"
"drm_device" -> "drm_plane A"
"drm_device" -> "drm_plane B"
"drm_device" -> "drm_crtc"
"drm_device" -> "drm_connector"
"drm_device" -> "driver private object"
"drm_plane A" -> "drm_plane_state A"
"drm_plane B" -> "drm_plane_state B"
"drm_crtc" -> "drm_crtc_state"
"drm_connector" -> "drm_connector_state"
"driver private object" -> "driver private state"
}
"drm_atomic_state" -> "drm_device" [label="atomic_commit"]
"duplicated drm_plane_state A" -> "drm_device"[style=invis]
}
Atomic provides transactional modeset (including planes) updates, but a
bit differently from the usual transactional approach of try-commit and
rollback:
- Firstly, no hardware changes are allowed when the commit would fail. This
allows us to implement the DRM_MODE_ATOMIC_TEST_ONLY mode, which allows
userspace to explore whether certain configurations would work or not.
- This would still allow setting and rollback of just the software state,
simplifying conversion of existing drivers. But auditing drivers for
correctness of the atomic_check code becomes really hard with that: Rolling
back changes in data structures all over the place is hard to get right.
- Lastly, for backwards compatibility and to support all use-cases, atomic
updates need to be incremental and be able to execute in parallel. Hardware
doesn't always allow it, but where possible plane updates on different CRTCs
should not interfere, and not get stalled due to output routing changing on
different CRTCs.
Taken all together there's two consequences for the atomic design:
- The overall state is split up into per-object state structures:
:c:type:`struct drm_plane_state <drm_plane_state>` for planes, :c:type:`struct
drm_crtc_state <drm_crtc_state>` for CRTCs and :c:type:`struct
drm_connector_state <drm_connector_state>` for connectors. These are the only
objects with userspace-visible and settable state. For internal state drivers
can subclass these structures through embeddeding, or add entirely new state
structures for their globally shared hardware functions.
- An atomic update is assembled and validated as an entirely free-standing pile
of structures within the :c:type:`drm_atomic_state <drm_atomic_state>`
container. Driver private state structures are also tracked in the same
structure; see the next chapter. Only when a state is committed is it applied
to the driver and modeset objects. This way rolling back an update boils down
to releasing memory and unreferencing objects like framebuffers.
Read on in this chapter, and also in :ref:`drm_atomic_helper` for more detailed
coverage of specific topics.
Handling Driver Private State
-----------------------------
.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
:doc: handling driver private state
Atomic Mode Setting Function Reference
--------------------------------------
.. kernel-doc:: include/drm/drm_atomic.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
:export:
Atomic Mode Setting IOCTL and UAPI Functions
--------------------------------------------
.. kernel-doc:: drivers/gpu/drm/drm_atomic_uapi.c
:doc: overview
.. kernel-doc:: drivers/gpu/drm/drm_atomic_uapi.c
:export:
CRTC Abstraction
================
.. kernel-doc:: drivers/gpu/drm/drm_crtc.c
:doc: overview
CRTC Functions Reference
--------------------------------
.. kernel-doc:: include/drm/drm_crtc.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_crtc.c
:export:
Frame Buffer Abstraction
========================
.. kernel-doc:: drivers/gpu/drm/drm_framebuffer.c
:doc: overview
Frame Buffer Functions Reference
--------------------------------
.. kernel-doc:: include/drm/drm_framebuffer.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_framebuffer.c
:export:
DRM Format Handling
===================
.. kernel-doc:: include/uapi/drm/drm_fourcc.h
:doc: overview
Format Functions Reference
--------------------------
.. kernel-doc:: include/drm/drm_fourcc.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_fourcc.c
:export:
Dumb Buffer Objects
===================
.. kernel-doc:: drivers/gpu/drm/drm_dumb_buffers.c
:doc: overview
Plane Abstraction
=================
.. kernel-doc:: drivers/gpu/drm/drm_plane.c
:doc: overview
Plane Functions Reference
-------------------------
.. kernel-doc:: include/drm/drm_plane.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_plane.c
:export:
Display Modes Function Reference
================================
.. kernel-doc:: include/drm/drm_modes.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_modes.c
:export:
Connector Abstraction
=====================
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:doc: overview
Connector Functions Reference
-----------------------------
.. kernel-doc:: include/drm/drm_connector.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:export:
drm: Add writeback connector type Writeback connectors represent writeback engines which can write the CRTC output to a memory framebuffer. Add a writeback connector type and related support functions. Drivers should initialize a writeback connector with drm_writeback_connector_init() which takes care of setting up all the writeback-specific details on top of the normal functionality of drm_connector_init(). Writeback connectors have a WRITEBACK_FB_ID property, used to set the output framebuffer, and a WRITEBACK_PIXEL_FORMATS blob used to expose the supported writeback formats to userspace. When a framebuffer is attached to a writeback connector with the WRITEBACK_FB_ID property, it is used only once (for the commit in which it was included), and userspace can never read back the value of WRITEBACK_FB_ID. WRITEBACK_FB_ID can only be set if the connector is attached to a CRTC. Changes since v1: - Added drm_writeback.c + documentation - Added helper to initialize writeback connector in one go - Added core checks - Squashed into a single commit - Dropped the client cap - Writeback framebuffers are no longer persistent Changes since v2: Daniel Vetter: - Subclass drm_connector to drm_writeback_connector - Relax check to allow CRTC to be set without an FB - Add some writeback_ prefixes - Drop PIXEL_FORMATS_SIZE property, as it was unnecessary Gustavo Padovan: - Add drm_writeback_job to handle writeback signalling centrally Changes since v3: - Rebased - Rename PIXEL_FORMATS -> WRITEBACK_PIXEL_FORMATS Chances since v4: - Embed a drm_encoder inside the drm_writeback_connector to reduce the amount of boilerplate code required from the drivers that are using it. Changes since v5: - Added Rob Clark's atomic_commit() vfunc to connector helper funcs, so that writeback jobs are committed from atomic helpers - Updated create_writeback_properties() signature to return an error code rather than a boolean false for failure. - Free writeback job with the connector state rather than when doing the cleanup_work() Changes since v7: - fix extraneous use of out_fence that is only introduced in a subsequent patch. Changes since v8: - whitespace changes pull from subsequent patch Changes since v9: - Revert the v6 changes that free the writeback job in the connector state cleanup and return to doing it in the cleanup_work() function Signed-off-by: Brian Starkey <brian.starkey@arm.com> [rebased and fixed conflicts] Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com> [rebased and added atomic_commit() vfunc for writeback jobs] Signed-off-by: Rob Clark <robdclark@gmail.com> Signed-off-by: Liviu Dudau <liviu.dudau@arm.com> Reviewed-by: Eric Anholt <eric@anholt.net> Link: https://patchwork.freedesktop.org/patch/229037/
2017-03-30 00:42:32 +08:00
Writeback Connectors
--------------------
.. kernel-doc:: drivers/gpu/drm/drm_writeback.c
:doc: overview
.. kernel-doc:: drivers/gpu/drm/drm_writeback.c
:export:
Encoder Abstraction
===================
.. kernel-doc:: drivers/gpu/drm/drm_encoder.c
:doc: overview
Encoder Functions Reference
---------------------------
.. kernel-doc:: include/drm/drm_encoder.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_encoder.c
:export:
KMS Locking
===========
.. kernel-doc:: drivers/gpu/drm/drm_modeset_lock.c
:doc: kms locking
.. kernel-doc:: include/drm/drm_modeset_lock.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_modeset_lock.c
:export:
KMS Properties
==============
Property Types and Blob Property Support
----------------------------------------
.. kernel-doc:: drivers/gpu/drm/drm_property.c
:doc: overview
.. kernel-doc:: include/drm/drm_property.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_property.c
:export:
Standard Connector Properties
-----------------------------
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:doc: standard connector properties
drm: content-type property for HDMI connector Added content_type property to drm_connector_state in order to properly handle external HDMI TV content-type setting. v2: * Moved helper function which attaches content type property to the drm core, as was suggested. Removed redundant connector state initialization. v3: * Removed caps in drm_content_type_enum_list. After some discussion it turned out that HDMI Spec 1.4 was wrongly assuming that IT Content(itc) bit doesn't affect Content type states, however itc bit needs to be manupulated as well. In order to not expose additional property for itc, for sake of simplicity it was decided to bind those together in same "content type" property. v4: * Added it_content checking in intel_digital_connector_atomic_check. Fixed documentation for new content type enum. v5: * Moved patch revision's description to commit messages. v6: * Minor naming fix for the content type enumeration string. v7: * Fix parameter name for documentation and parameter alignment in order not to get warning. Added Content Type description to new HDMI connector properties section. v8: * Thrown away unneeded numbers from HDMI content-type property description. Switch to strings desription instead of plain definitions. v9: * Moved away hdmi specific content-type enum from drm_connector_state. Content type property should probably not be bound to any specific connector interface in drm_connector_state. Same probably should be done to hdmi_picture_aspect_ration enum which is also contained in drm_connector_state. Added special helper function to get derive hdmi specific relevant infoframe fields. v10: * Added usage description to HDMI properties kernel doc. v11: * Created centralized function for filling HDMI AVI infoframe, based on correspondent DRM property value. Acked-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180515135928.31092-2-stanislav.lisovskiy@intel.com [vsyrjala: clean up checkpatch multiple blank lines warnings] Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
2018-05-15 21:59:27 +08:00
HDMI Specific Connector Properties
----------------------------------
drm: content-type property for HDMI connector Added content_type property to drm_connector_state in order to properly handle external HDMI TV content-type setting. v2: * Moved helper function which attaches content type property to the drm core, as was suggested. Removed redundant connector state initialization. v3: * Removed caps in drm_content_type_enum_list. After some discussion it turned out that HDMI Spec 1.4 was wrongly assuming that IT Content(itc) bit doesn't affect Content type states, however itc bit needs to be manupulated as well. In order to not expose additional property for itc, for sake of simplicity it was decided to bind those together in same "content type" property. v4: * Added it_content checking in intel_digital_connector_atomic_check. Fixed documentation for new content type enum. v5: * Moved patch revision's description to commit messages. v6: * Minor naming fix for the content type enumeration string. v7: * Fix parameter name for documentation and parameter alignment in order not to get warning. Added Content Type description to new HDMI connector properties section. v8: * Thrown away unneeded numbers from HDMI content-type property description. Switch to strings desription instead of plain definitions. v9: * Moved away hdmi specific content-type enum from drm_connector_state. Content type property should probably not be bound to any specific connector interface in drm_connector_state. Same probably should be done to hdmi_picture_aspect_ration enum which is also contained in drm_connector_state. Added special helper function to get derive hdmi specific relevant infoframe fields. v10: * Added usage description to HDMI properties kernel doc. v11: * Created centralized function for filling HDMI AVI infoframe, based on correspondent DRM property value. Acked-by: Hans Verkuil <hans.verkuil@cisco.com> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180515135928.31092-2-stanislav.lisovskiy@intel.com [vsyrjala: clean up checkpatch multiple blank lines warnings] Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
2018-05-15 21:59:27 +08:00
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:doc: HDMI connector properties
Plane Composition Properties
----------------------------
.. kernel-doc:: drivers/gpu/drm/drm_blend.c
:doc: overview
.. kernel-doc:: drivers/gpu/drm/drm_blend.c
:export:
FB_DAMAGE_CLIPS
~~~~~~~~~~~~~~~
.. kernel-doc:: drivers/gpu/drm/drm_damage_helper.c
:doc: overview
.. kernel-doc:: drivers/gpu/drm/drm_damage_helper.c
:export:
.. kernel-doc:: include/drm/drm_damage_helper.h
:internal:
Color Management Properties
---------------------------
.. kernel-doc:: drivers/gpu/drm/drm_color_mgmt.c
:doc: overview
.. kernel-doc:: drivers/gpu/drm/drm_color_mgmt.c
:export:
Tile Group Property
-------------------
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:doc: Tile group
Explicit Fencing Properties
---------------------------
.. kernel-doc:: drivers/gpu/drm/drm_atomic_uapi.c
:doc: explicit fencing properties
Variable Refresh Properties
---------------------------
.. kernel-doc:: drivers/gpu/drm/drm_connector.c
:doc: Variable refresh properties
Existing KMS Properties
-----------------------
The following table gives description of drm properties exposed by various
modules/drivers. Because this table is very unwieldy, do not add any new
properties here. Instead document them in a section above.
.. csv-table::
:header-rows: 1
:file: kms-properties.csv
Vertical Blanking
=================
.. kernel-doc:: drivers/gpu/drm/drm_vblank.c
:doc: vblank handling
Vertical Blanking and Interrupt Handling Functions Reference
------------------------------------------------------------
.. kernel-doc:: include/drm/drm_vblank.h
:internal:
.. kernel-doc:: drivers/gpu/drm/drm_vblank.c
:export: