Commit 57772953 authored by Tvrtko Ursulin's avatar Tvrtko Ursulin

drm/i915: Document the Virtual Engine uAPI

A little bit of documentation covering the topics of engine discovery,
context engine maps and virtual engines. It is not very detailed but
supposed to be a starting point of giving a brief high level overview of
general principles and intended use cases.

v2:
 * Have the text in uapi header and link from there.

v4:
 * Link from driver-uapi.rst.
Signed-off-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Acked-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210618150036.2507653-1-tvrtko.ursulin@linux.intel.com
parent bfde26df
...@@ -5,4 +5,25 @@ DRM Driver uAPI ...@@ -5,4 +5,25 @@ DRM Driver uAPI
drm/i915 uAPI drm/i915 uAPI
============= =============
Engine Discovery uAPI
---------------------
.. kernel-doc:: include/uapi/drm/i915_drm.h
:doc: Engine Discovery uAPI
Context Engine Map uAPI
-----------------------
.. kernel-doc:: include/uapi/drm/i915_drm.h
:doc: Context Engine Map uAPI
Virtual Engine uAPI
-------------------
.. kernel-doc:: include/uapi/drm/i915_drm.h
:doc: Virtual Engine uAPI
i915_drm.h
----------
.. kernel-doc:: include/uapi/drm/i915_drm.h .. kernel-doc:: include/uapi/drm/i915_drm.h
:internal:
...@@ -1806,6 +1806,69 @@ struct drm_i915_gem_context_param_sseu { ...@@ -1806,6 +1806,69 @@ struct drm_i915_gem_context_param_sseu {
__u32 rsvd; __u32 rsvd;
}; };
/**
* DOC: Virtual Engine uAPI
*
* Virtual engine is a concept where userspace is able to configure a set of
* physical engines, submit a batch buffer, and let the driver execute it on any
* engine from the set as it sees fit.
*
* This is primarily useful on parts which have multiple instances of a same
* class engine, like for example GT3+ Skylake parts with their two VCS engines.
*
* For instance userspace can enumerate all engines of a certain class using the
* previously described `Engine Discovery uAPI`_. After that userspace can
* create a GEM context with a placeholder slot for the virtual engine (using
* `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
* and instance respectively) and finally using the
* `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
* the same reserved slot.
*
* Example of creating a virtual engine and submitting a batch buffer to it:
*
* .. code-block:: C
*
* I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
* .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
* .engine_index = 0, // Place this virtual engine into engine map slot 0
* .num_siblings = 2,
* .engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
* { I915_ENGINE_CLASS_VIDEO, 1 }, },
* };
* I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
* .engines = { { I915_ENGINE_CLASS_INVALID,
* I915_ENGINE_CLASS_INVALID_NONE } },
* .extensions = to_user_pointer(&virtual), // Chains after load_balance extension
* };
* struct drm_i915_gem_context_create_ext_setparam p_engines = {
* .base = {
* .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
* },
* .param = {
* .param = I915_CONTEXT_PARAM_ENGINES,
* .value = to_user_pointer(&engines),
* .size = sizeof(engines),
* },
* };
* struct drm_i915_gem_context_create_ext create = {
* .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
* .extensions = to_user_pointer(&p_engines);
* };
*
* ctx_id = gem_context_create_ext(drm_fd, &create);
*
* // Now we have created a GEM context with its engine map containing a
* // single virtual engine. Submissions to this slot can go either to
* // vcs0 or vcs1, depending on the load balancing algorithm used inside
* // the driver. The load balancing is dynamic from one batch buffer to
* // another and transparent to userspace.
*
* ...
* execbuf.rsvd1 = ctx_id;
* execbuf.flags = 0; // Submits to index 0 which is the virtual engine
* gem_execbuf(drm_fd, &execbuf);
*/
/* /*
* i915_context_engines_load_balance: * i915_context_engines_load_balance:
* *
...@@ -1882,6 +1945,61 @@ struct i915_context_engines_bond { ...@@ -1882,6 +1945,61 @@ struct i915_context_engines_bond {
struct i915_engine_class_instance engines[N__]; \ struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__ } __attribute__((packed)) name__
/**
* DOC: Context Engine Map uAPI
*
* Context engine map is a new way of addressing engines when submitting batch-
* buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
* inside the flags field of `struct drm_i915_gem_execbuffer2`.
*
* To use it created GEM contexts need to be configured with a list of engines
* the user is intending to submit to. This is accomplished using the
* `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
* i915_context_param_engines`.
*
* For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
* configured map.
*
* Example of creating such context and submitting against it:
*
* .. code-block:: C
*
* I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
* .engines = { { I915_ENGINE_CLASS_RENDER, 0 },
* { I915_ENGINE_CLASS_COPY, 0 } }
* };
* struct drm_i915_gem_context_create_ext_setparam p_engines = {
* .base = {
* .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
* },
* .param = {
* .param = I915_CONTEXT_PARAM_ENGINES,
* .value = to_user_pointer(&engines),
* .size = sizeof(engines),
* },
* };
* struct drm_i915_gem_context_create_ext create = {
* .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
* .extensions = to_user_pointer(&p_engines);
* };
*
* ctx_id = gem_context_create_ext(drm_fd, &create);
*
* // We have now created a GEM context with two engines in the map:
* // Index 0 points to rcs0 while index 1 points to bcs0. Other engines
* // will not be accessible from this context.
*
* ...
* execbuf.rsvd1 = ctx_id;
* execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
* gem_execbuf(drm_fd, &execbuf);
*
* ...
* execbuf.rsvd1 = ctx_id;
* execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
* gem_execbuf(drm_fd, &execbuf);
*/
struct i915_context_param_engines { struct i915_context_param_engines {
__u64 extensions; /* linked chain of extension blocks, 0 terminates */ __u64 extensions; /* linked chain of extension blocks, 0 terminates */
#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
...@@ -2375,6 +2493,76 @@ struct drm_i915_query_topology_info { ...@@ -2375,6 +2493,76 @@ struct drm_i915_query_topology_info {
__u8 data[]; __u8 data[];
}; };
/**
* DOC: Engine Discovery uAPI
*
* Engine discovery uAPI is a way of enumerating physical engines present in a
* GPU associated with an open i915 DRM file descriptor. This supersedes the old
* way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
* `I915_PARAM_HAS_BLT`.
*
* The need for this interface came starting with Icelake and newer GPUs, which
* started to establish a pattern of having multiple engines of a same class,
* where not all instances were always completely functionally equivalent.
*
* Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
* `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
*
* Example for getting the list of engines:
*
* .. code-block:: C
*
* struct drm_i915_query_engine_info *info;
* struct drm_i915_query_item item = {
* .query_id = DRM_I915_QUERY_ENGINE_INFO;
* };
* struct drm_i915_query query = {
* .num_items = 1,
* .items_ptr = (uintptr_t)&item,
* };
* int err, i;
*
* // First query the size of the blob we need, this needs to be large
* // enough to hold our array of engines. The kernel will fill out the
* // item.length for us, which is the number of bytes we need.
* //
* // Alternatively a large buffer can be allocated straight away enabling
* // querying in one pass, in which case item.length should contain the
* // length of the provided buffer.
* err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
* if (err) ...
*
* info = calloc(1, item.length);
* // Now that we allocated the required number of bytes, we call the ioctl
* // again, this time with the data_ptr pointing to our newly allocated
* // blob, which the kernel can then populate with info on all engines.
* item.data_ptr = (uintptr_t)&info,
*
* err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
* if (err) ...
*
* // We can now access each engine in the array
* for (i = 0; i < info->num_engines; i++) {
* struct drm_i915_engine_info einfo = info->engines[i];
* u16 class = einfo.engine.class;
* u16 instance = einfo.engine.instance;
* ....
* }
*
* free(info);
*
* Each of the enumerated engines, apart from being defined by its class and
* instance (see `struct i915_engine_class_instance`), also can have flags and
* capabilities defined as documented in i915_drm.h.
*
* For instance video engines which support HEVC encoding will have the
* `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
*
* Engine discovery only fully comes to its own when combined with the new way
* of addressing engines when submitting batch buffers using contexts with
* engine maps configured.
*/
/** /**
* struct drm_i915_engine_info * struct drm_i915_engine_info
* *
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment