Commit 2bc9c04e authored by Matthew Auld's avatar Matthew Auld

drm/doc/rfc: i915 DG1 uAPI

Add an entry for the new uAPI needed for DG1. Also add the overall
upstream plan, including some notes for the TTM conversion.

v2(Daniel):
  - include the overall upstreaming plan
  - add a note for mmap, there are differences here for TTM vs i915
  - bunch of other suggestions from Daniel
v3:
 (Daniel)
  - add a note for set/get caching stuff
  - add some more docs for existing query and extensions stuff
  - add an actual code example for regions query
  - bunch of other stuff
 (Jason)
  - uAPI change(!):
	- try a simpler design with the placements extension
	- rather than have a generic setparam which can cover multiple
	  use cases, have each extension be responsible for one thing
	  only
v4:
 (Daniel)
  - add some more notes for ttm conversion
  - bunch of other stuff
 (Jason)
  - uAPI change(!):
	- drop all the extra rsvd members for the region_query and
	  region_info, just keep the bare minimum needed for padding
v5:
(Jason)
  - for the upstream plan, add a requirement that we send the uAPI bits
    again for final sign off before turning it on for real
  - document how we intend to extend the rsvd bits for the region query
(Kenneth)
  - improve the comment for the smem+lmem mmap mode and caching
Signed-off-by: default avatarMatthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@linux.intel.com>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Jordan Justen <jordan.l.justen@intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Dave Airlie <airlied@gmail.com>
Cc: dri-devel@lists.freedesktop.org
Cc: mesa-dev@lists.freedesktop.org
Acked-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: default avatarDave Airlie <airlied@redhat.com>
Acked-by: default avatarKenneth Graunke <kenneth@whitecape.org>
Acked-by: default avatarJon Bloomfield <jon.bloomfield@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-1-matthew.auld@intel.com
parent 0333ec88
/**
* enum drm_i915_gem_memory_class - Supported memory classes
*/
enum drm_i915_gem_memory_class {
/** @I915_MEMORY_CLASS_SYSTEM: System memory */
I915_MEMORY_CLASS_SYSTEM = 0,
/** @I915_MEMORY_CLASS_DEVICE: Device local-memory */
I915_MEMORY_CLASS_DEVICE,
};
/**
* struct drm_i915_gem_memory_class_instance - Identify particular memory region
*/
struct drm_i915_gem_memory_class_instance {
/** @memory_class: See enum drm_i915_gem_memory_class */
__u16 memory_class;
/** @memory_instance: Which instance */
__u16 memory_instance;
};
/**
* struct drm_i915_memory_region_info - Describes one region as known to the
* driver.
*
* Note that we reserve some stuff here for potential future work. As an example
* we might want expose the capabilities for a given region, which could include
* things like if the region is CPU mappable/accessible, what are the supported
* mapping types etc.
*
* Note that to extend struct drm_i915_memory_region_info and struct
* drm_i915_query_memory_regions in the future the plan is to do the following:
*
* .. code-block:: C
*
* struct drm_i915_memory_region_info {
* struct drm_i915_gem_memory_class_instance region;
* union {
* __u32 rsvd0;
* __u32 new_thing1;
* };
* ...
* union {
* __u64 rsvd1[8];
* struct {
* __u64 new_thing2;
* __u64 new_thing3;
* ...
* };
* };
* };
*
* With this things should remain source compatible between versions for
* userspace, even as we add new fields.
*
* Note this is using both struct drm_i915_query_item and struct drm_i915_query.
* For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
* at &drm_i915_query_item.query_id.
*/
struct drm_i915_memory_region_info {
/** @region: The class:instance pair encoding */
struct drm_i915_gem_memory_class_instance region;
/** @rsvd0: MBZ */
__u32 rsvd0;
/** @probed_size: Memory probed by the driver (-1 = unknown) */
__u64 probed_size;
/** @unallocated_size: Estimate of memory remaining (-1 = unknown) */
__u64 unallocated_size;
/** @rsvd1: MBZ */
__u64 rsvd1[8];
};
/**
* struct drm_i915_query_memory_regions
*
* The region info query enumerates all regions known to the driver by filling
* in an array of struct drm_i915_memory_region_info structures.
*
* Example for getting the list of supported regions:
*
* .. code-block:: C
*
* struct drm_i915_query_memory_regions *info;
* struct drm_i915_query_item item = {
* .query_id = DRM_I915_QUERY_MEMORY_REGIONS;
* };
* 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 regions. The kernel will fill out the
* // item.length for us, which is the number of bytes we need.
* 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 the all the region info.
* item.data_ptr = (uintptr_t)&info,
*
* err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
* if (err) ...
*
* // We can now access each region in the array
* for (i = 0; i < info->num_regions; i++) {
* struct drm_i915_memory_region_info mr = info->regions[i];
* u16 class = mr.region.class;
* u16 instance = mr.region.instance;
*
* ....
* }
*
* free(info);
*/
struct drm_i915_query_memory_regions {
/** @num_regions: Number of supported regions */
__u32 num_regions;
/** @rsvd: MBZ */
__u32 rsvd[3];
/** @regions: Info about each supported region */
struct drm_i915_memory_region_info regions[];
};
#define DRM_I915_GEM_CREATE_EXT 0xdeadbeaf
#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
/**
* struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
* extension support using struct i915_user_extension.
*
* Note that in the future we want to have our buffer flags here, at least for
* the stuff that is immutable. Previously we would have two ioctls, one to
* create the object with gem_create, and another to apply various parameters,
* however this creates some ambiguity for the params which are considered
* immutable. Also in general we're phasing out the various SET/GET ioctls.
*/
struct drm_i915_gem_create_ext {
/**
* @size: Requested size for the object.
*
* The (page-aligned) allocated size for the object will be returned.
*
* Note that for some devices we have might have further minimum
* page-size restrictions(larger than 4K), like for device local-memory.
* However in general the final size here should always reflect any
* rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS
* extension to place the object in device local-memory.
*/
__u64 size;
/**
* @handle: Returned handle for the object.
*
* Object handles are nonzero.
*/
__u32 handle;
/** @flags: MBZ */
__u32 flags;
/**
* @extensions: The chain of extensions to apply to this object.
*
* This will be useful in the future when we need to support several
* different extensions, and we need to apply more than one when
* creating the object. See struct i915_user_extension.
*
* If we don't supply any extensions then we get the same old gem_create
* behaviour.
*
* For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
* struct drm_i915_gem_create_ext_memory_regions.
*/
#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
__u64 extensions;
};
/**
* struct drm_i915_gem_create_ext_memory_regions - The
* I915_GEM_CREATE_EXT_MEMORY_REGIONS extension.
*
* Set the object with the desired set of placements/regions in priority
* order. Each entry must be unique and supported by the device.
*
* This is provided as an array of struct drm_i915_gem_memory_class_instance, or
* an equivalent layout of class:instance pair encodings. See struct
* drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to
* query the supported regions for a device.
*
* As an example, on discrete devices, if we wish to set the placement as
* device local-memory we can do something like:
*
* .. code-block:: C
*
* struct drm_i915_gem_memory_class_instance region_lmem = {
* .memory_class = I915_MEMORY_CLASS_DEVICE,
* .memory_instance = 0,
* };
* struct drm_i915_gem_create_ext_memory_regions regions = {
* .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS },
* .regions = (uintptr_t)&region_lmem,
* .num_regions = 1,
* };
* struct drm_i915_gem_create_ext create_ext = {
* .size = 16 * PAGE_SIZE,
* .extensions = (uintptr_t)&regions,
* };
*
* int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
* if (err) ...
*
* At which point we get the object handle in &drm_i915_gem_create_ext.handle,
* along with the final object size in &drm_i915_gem_create_ext.size, which
* should account for any rounding up, if required.
*/
struct drm_i915_gem_create_ext_memory_regions {
/** @base: Extension link. See struct i915_user_extension. */
struct i915_user_extension base;
/** @pad: MBZ */
__u32 pad;
/** @num_regions: Number of elements in the @regions array. */
__u32 num_regions;
/**
* @regions: The regions/placements array.
*
* An array of struct drm_i915_gem_memory_class_instance.
*/
__u64 regions;
};
=========================
I915 DG1/LMEM RFC Section
=========================
Upstream plan
=============
For upstream the overall plan for landing all the DG1 stuff and turning it for
real, with all the uAPI bits is:
* Merge basic HW enabling of DG1(still without pciid)
* Merge the uAPI bits behind special CONFIG_BROKEN(or so) flag
* At this point we can still make changes, but importantly this lets us
start running IGTs which can utilize local-memory in CI
* Convert over to TTM, make sure it all keeps working. Some of the work items:
* TTM shrinker for discrete
* dma_resv_lockitem for full dma_resv_lock, i.e not just trylock
* Use TTM CPU pagefault handler
* Route shmem backend over to TTM SYSTEM for discrete
* TTM purgeable object support
* Move i915 buddy allocator over to TTM
* MMAP ioctl mode(see `I915 MMAP`_)
* SET/GET ioctl caching(see `I915 SET/GET CACHING`_)
* Send RFC(with mesa-dev on cc) for final sign off on the uAPI
* Add pciid for DG1 and turn on uAPI for real
New object placement and region query uAPI
==========================================
Starting from DG1 we need to give userspace the ability to allocate buffers from
device local-memory. Currently the driver supports gem_create, which can place
buffers in system memory via shmem, and the usual assortment of other
interfaces, like dumb buffers and userptr.
To support this new capability, while also providing a uAPI which will work
beyond just DG1, we propose to offer three new bits of uAPI:
DRM_I915_QUERY_MEMORY_REGIONS
-----------------------------
New query ID which allows userspace to discover the list of supported memory
regions(like system-memory and local-memory) for a given device. We identify
each region with a class and instance pair, which should be unique. The class
here would be DEVICE or SYSTEM, and the instance would be zero, on platforms
like DG1.
Side note: The class/instance design is borrowed from our existing engine uAPI,
where we describe every physical engine in terms of its class, and the
particular instance, since we can have more than one per class.
In the future we also want to expose more information which can further
describe the capabilities of a region.
.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h
:functions: drm_i915_gem_memory_class drm_i915_gem_memory_class_instance drm_i915_memory_region_info drm_i915_query_memory_regions
GEM_CREATE_EXT
--------------
New ioctl which is basically just gem_create but now allows userspace to provide
a chain of possible extensions. Note that if we don't provide any extensions and
set flags=0 then we get the exact same behaviour as gem_create.
Side note: We also need to support PXP[1] in the near future, which is also
applicable to integrated platforms, and adds its own gem_create_ext extension,
which basically lets userspace mark a buffer as "protected".
.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h
:functions: drm_i915_gem_create_ext
I915_GEM_CREATE_EXT_MEMORY_REGIONS
----------------------------------
Implemented as an extension for gem_create_ext, we would now allow userspace to
optionally provide an immutable list of preferred placements at creation time,
in priority order, for a given buffer object. For the placements we expect
them each to use the class/instance encoding, as per the output of the regions
query. Having the list in priority order will be useful in the future when
placing an object, say during eviction.
.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h
:functions: drm_i915_gem_create_ext_memory_regions
One fair criticism here is that this seems a little over-engineered[2]. If we
just consider DG1 then yes, a simple gem_create.flags or something is totally
all that's needed to tell the kernel to allocate the buffer in local-memory or
whatever. However looking to the future we need uAPI which can also support
upcoming Xe HP multi-tile architecture in a sane way, where there can be
multiple local-memory instances for a given device, and so using both class and
instance in our uAPI to describe regions is desirable, although specifically
for DG1 it's uninteresting, since we only have a single local-memory instance.
Existing uAPI issues
====================
Some potential issues we still need to resolve.
I915 MMAP
---------
In i915 there are multiple ways to MMAP GEM object, including mapping the same
object using different mapping types(WC vs WB), i.e multiple active mmaps per
object. TTM expects one MMAP at most for the lifetime of the object. If it
turns out that we have to backpedal here, there might be some potential
userspace fallout.
I915 SET/GET CACHING
--------------------
In i915 we have set/get_caching ioctl. TTM doesn't let us to change this, but
DG1 doesn't support non-snooped pcie transactions, so we can just always
allocate as WB for smem-only buffers. If/when our hw gains support for
non-snooped pcie transactions then we must fix this mode at allocation time as
a new GEM extension.
This is related to the mmap problem, because in general (meaning, when we're
not running on intel cpus) the cpu mmap must not, ever, be inconsistent with
allocation mode.
Possible idea is to let the kernel picks the mmap mode for userspace from the
following table:
smem-only: WB. Userspace does not need to call clflush.
smem+lmem: We only ever allow a single mode, so simply allocate this as uncached
memory, and always give userspace a WC mapping. GPU still does snooped access
here(assuming we can't turn it off like on DG1), which is a bit inefficient.
lmem only: always WC
This means on discrete you only get a single mmap mode, all others must be
rejected. That's probably going to be a new default mode or something like
that.
Links
=====
[1] https://patchwork.freedesktop.org/series/86798/
[2] https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5599#note_553791
...@@ -15,3 +15,7 @@ host such documentation: ...@@ -15,3 +15,7 @@ host such documentation:
* Once the code has landed move all the documentation to the right places in * Once the code has landed move all the documentation to the right places in
the main core, helper or driver sections. the main core, helper or driver sections.
.. toctree::
i915_gem_lmem.rst
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