[PATCH v3 2/6] drm/xe: Track maximum GTs per tile on a per-platform basis

Riana Tauro riana.tauro at intel.com
Wed Jul 2 04:50:32 UTC 2025


Hi Matt

On 7/1/2025 10:25 PM, Matt Roper wrote:
> On Tue, Jul 01, 2025 at 10:35:50AM +0530, Riana Tauro wrote:
>> Hi Matt
>>
>> On 6/30/2025 11:04 PM, Matt Roper wrote:
>>> Today all of our platforms fall into one of three cases:
>>>    * Single tile platforms with a single (primary) GT
>>>    * Single tile platforms with two GTs (primary + media)
>>>    * Two-tile platforms with a single GT (primary) in each
>>>
>>> Our numbering of GTs has been a bit inconsistent between platforms
>>> (e.g., GT1 is the media GT on some platforms, but the second tile's
>>> primary GT on others).  In the future we'll likely have platforms that
>>> are both multi-tile and multi-GT, which will make the situation more
>>> confusing.  We could also wind up with more than just two types of GTs
>>> at some point in the future.
>>>
>>> Going forward we should standardize the way we assign uapi GT IDs to
>>> internal GT structures.  Let's declare that for userspace GT ID n,
>>>
>>>     GT[n]'s tile             = n / (max gt per tile)
>>>     GT[n]'s slot within tile = n % (max gt per tile)
>>>
>>> We don't want the GT numbering to change for any of our current
>>> platforms since the current IDs are part of our ABI contract with
>>> userspace so this means we should track the 'max gt per tile' value on a
>>> per-platform basis rather than just using a single value across the
>>> driver.  Encode this into device descriptors in xe_pci.c and use the
>>> per-platform number for various checks in the code.  Constant
>>> XE_MAX_GT_PER_TILE will remain just as the maximum across all platforms
>>> for easy of sizing array allocations.
>>>
>>> Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>
>>> Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
>>> ---
>>>    drivers/gpu/drm/xe/xe_device.h       | 41 +++++++++++++---------------
>>>    drivers/gpu/drm/xe/xe_device_types.h |  2 ++
>>>    drivers/gpu/drm/xe/xe_pci.c          | 18 ++++++++++++
>>>    drivers/gpu/drm/xe/xe_pmu.c          |  4 ++-
>>>    drivers/gpu/drm/xe/xe_query.c        |  2 +-
>>>    5 files changed, 43 insertions(+), 24 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
>>> index e4da797a984b..4e719d398c88 100644
>>> --- a/drivers/gpu/drm/xe/xe_device.h
>>> +++ b/drivers/gpu/drm/xe/xe_device.h
>>> @@ -60,35 +60,32 @@ static inline struct xe_tile *xe_device_get_root_tile(struct xe_device *xe)
>>>    	return &xe->tiles[0];
>>>    }
>>> +/*
>>> + * Highest GT/tile count for any platform.  Used only for memory allocation
>>> + * sizing.  Any logic looping over GTs or mapping userspace GT IDs into GT
>>> + * structures should use the per-platform xe->info.max_gt_per_tile instead.
>>> + */
>>>    #define XE_MAX_GT_PER_TILE 2
>>> -static inline struct xe_gt *xe_tile_get_gt(struct xe_tile *tile, u8 gt_id)
>>> -{
>>> -	if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id >= XE_MAX_GT_PER_TILE))
>>> -		gt_id = 0;
>>> -
>>> -	return gt_id ? tile->media_gt : tile->primary_gt;
>>> -}
>>> -
>>>    static inline struct xe_gt *xe_device_get_gt(struct xe_device *xe, u8 gt_id)
>>>    {
>>> -	struct xe_tile *root_tile = xe_device_get_root_tile(xe);
>>> +	struct xe_tile *tile;
>>>    	struct xe_gt *gt;
>>> -	/*
>>> -	 * FIXME: This only works for now because multi-tile and standalone
>>> -	 * media are mutually exclusive on the platforms we have today.
>>> -	 *
>>> -	 * id => GT mapping may change once we settle on how we want to handle
>>> -	 * our UAPI.
>>> -	 */
>>> -	if (MEDIA_VER(xe) >= 13) {
>>> -		gt = xe_tile_get_gt(root_tile, gt_id);
>>> -	} else {
>>> -		if (drm_WARN_ON(&xe->drm, gt_id >= XE_MAX_TILES_PER_DEVICE))
>>> -			gt_id = 0;
>>> +	if (gt_id >= xe->info.tile_count * xe->info.max_gt_per_tile)
>>> +		return NULL;
>>> -		gt = xe->tiles[gt_id].primary_gt;
>>> +	tile = &xe->tiles[gt_id / xe->info.max_gt_per_tile];
>>> +	switch (gt_id % xe->info.max_gt_per_tile) {
>>> +	default:
>>> +		xe_assert(xe, false);
>>> +		fallthrough;
>>> +	case 0:
>>> +		gt = tile->primary_gt;
>>> +		break;
>>> +	case 1:
>>> +		gt = tile->media_gt;
>>> +		break;
>>>    	}
>>>    	if (!gt)
>>> diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
>>> index 7e4f6d846af6..78c4acafd268 100644
>>> --- a/drivers/gpu/drm/xe/xe_device_types.h
>>> +++ b/drivers/gpu/drm/xe/xe_device_types.h
>>> @@ -294,6 +294,8 @@ struct xe_device {
>>>    		u8 vram_flags;
>>>    		/** @info.tile_count: Number of tiles */
>>>    		u8 tile_count;
>>> +		/** @info.max_gt_per_tile: Number of GT IDs allocated to each tile */
>>> +		u8 max_gt_per_tile;
>>>    		/** @info.gt_count: Total number of GTs for entire device */
>>>    		u8 gt_count;
>>>    		/** @info.vm_max_level: Max VM level */
>>> diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
>>> index 824461c31288..316031854c26 100644
>>> --- a/drivers/gpu/drm/xe/xe_pci.c
>>> +++ b/drivers/gpu/drm/xe/xe_pci.c
>>> @@ -57,6 +57,7 @@ struct xe_device_desc {
>>>    	u8 dma_mask_size;
>>>    	u8 max_remote_tiles:2;
>>> +	u8 max_gt_per_tile:2;
>>>    	u8 require_force_probe:1;
>>>    	u8 is_dgfx:1;
>>> @@ -208,6 +209,7 @@ static const struct xe_device_desc tgl_desc = {
>>>    	.dma_mask_size = 39,
>>>    	.has_display = true,
>>>    	.has_llc = true,
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    };
>>> @@ -218,6 +220,7 @@ static const struct xe_device_desc rkl_desc = {
>>>    	.dma_mask_size = 39,
>>>    	.has_display = true,
>>>    	.has_llc = true,
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    };
>>> @@ -231,6 +234,7 @@ static const struct xe_device_desc adl_s_desc = {
>>>    	.has_display = true,
>>>    	.has_llc = true,
>>>    	.has_sriov = IS_ENABLED(CONFIG_DRM_XE_DEBUG),
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    	.subplatforms = (const struct xe_subplatform_desc[]) {
>>>    		{ XE_SUBPLATFORM_ALDERLAKE_S_RPLS, "RPLS", adls_rpls_ids },
>>> @@ -248,6 +252,7 @@ static const struct xe_device_desc adl_p_desc = {
>>>    	.has_display = true,
>>>    	.has_llc = true,
>>>    	.has_sriov = IS_ENABLED(CONFIG_DRM_XE_DEBUG),
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    	.subplatforms = (const struct xe_subplatform_desc[]) {
>>>    		{ XE_SUBPLATFORM_ALDERLAKE_P_RPLU, "RPLU", adlp_rplu_ids },
>>> @@ -263,6 +268,7 @@ static const struct xe_device_desc adl_n_desc = {
>>>    	.has_display = true,
>>>    	.has_llc = true,
>>>    	.has_sriov = IS_ENABLED(CONFIG_DRM_XE_DEBUG),
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    };
>>> @@ -278,6 +284,7 @@ static const struct xe_device_desc dg1_desc = {
>>>    	.has_display = true,
>>>    	.has_gsc_nvm = 1,
>>>    	.has_heci_gscfi = 1,
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    };
>>> @@ -301,6 +308,7 @@ static const struct xe_device_desc ats_m_desc = {
>>>    	.pre_gmdid_graphics_ip = &graphics_ip_xehpg,
>>>    	.pre_gmdid_media_ip = &media_ip_xehpm,
>>>    	.dma_mask_size = 46,
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    	DG2_FEATURES,
>>> @@ -312,6 +320,7 @@ static const struct xe_device_desc dg2_desc = {
>>>    	.pre_gmdid_graphics_ip = &graphics_ip_xehpg,
>>>    	.pre_gmdid_media_ip = &media_ip_xehpm,
>>>    	.dma_mask_size = 46,
>>> +	.max_gt_per_tile = 1,
>>>    	.require_force_probe = true,
>>>    	DG2_FEATURES,
>>> @@ -328,6 +337,7 @@ static const __maybe_unused struct xe_device_desc pvc_desc = {
>>>    	.has_display = false,
>>>    	.has_gsc_nvm = 1,
>>>    	.has_heci_gscfi = 1,
>>> +	.max_gt_per_tile = 1,
>>>    	.max_remote_tiles = 1,
>>>    	.require_force_probe = true,
>>>    	.has_mbx_power_limits = false,
>>> @@ -340,6 +350,7 @@ static const struct xe_device_desc mtl_desc = {
>>>    	.dma_mask_size = 46,
>>>    	.has_display = true,
>>>    	.has_pxp = true,
>>> +	.max_gt_per_tile = 2,
>>>    };
>>>    static const struct xe_device_desc lnl_desc = {
>>> @@ -347,6 +358,7 @@ static const struct xe_device_desc lnl_desc = {
>>>    	.dma_mask_size = 46,
>>>    	.has_display = true,
>>>    	.has_pxp = true,
>>> +	.max_gt_per_tile = 2,
>>>    	.needs_scratch = true,
>>>    };
>>> @@ -359,6 +371,7 @@ static const struct xe_device_desc bmg_desc = {
>>>    	.has_mbx_power_limits = true,
>>>    	.has_gsc_nvm = 1,
>>>    	.has_heci_cscfi = 1,
>>> +	.max_gt_per_tile = 2,
>>>    	.needs_scratch = true,
>>>    };
>>> @@ -367,6 +380,7 @@ static const struct xe_device_desc ptl_desc = {
>>>    	.dma_mask_size = 46,
>>>    	.has_display = true,
>>>    	.has_sriov = true,
>>> +	.max_gt_per_tile = 2,
>>>    	.require_force_probe = true,
>>>    	.needs_scratch = true,
>>>    };
>>> @@ -616,6 +630,10 @@ static int xe_info_init_early(struct xe_device *xe,
>>>    	xe->info.probe_display = IS_ENABLED(CONFIG_DRM_XE_DISPLAY) &&
>>>    				 xe_modparam.probe_display &&
>>>    				 desc->has_display;
>>> +
>>> +	xe_assert(xe, desc->max_gt_per_tile > 0);
>>> +	xe_assert(xe, desc->max_gt_per_tile <= XE_MAX_GT_PER_TILE);
>>> +	xe->info.max_gt_per_tile = desc->max_gt_per_tile;
>>>    	xe->info.tile_count = 1 + desc->max_remote_tiles;
>>>    	err = xe_tile_init_early(xe_device_get_root_tile(xe), xe, 0);
>>> diff --git a/drivers/gpu/drm/xe/xe_pmu.c b/drivers/gpu/drm/xe/xe_pmu.c
>>> index 69df0e3520a5..94a8e1db71e4 100644
>>> --- a/drivers/gpu/drm/xe/xe_pmu.c
>>> +++ b/drivers/gpu/drm/xe/xe_pmu.c
>>> @@ -160,7 +160,9 @@ static bool event_gt_forcewake(struct perf_event *event)
>>>    static bool event_supported(struct xe_pmu *pmu, unsigned int gt,
>>>    			    unsigned int id)
>>>    {
>>> -	if (gt >= XE_MAX_GT_PER_TILE)
>>> +	struct xe_device *xe = container_of(pmu, typeof(*xe), pmu);
>>> +
>>> +	if (gt >= xe->info.max_gt_per_tile)
>>>    		return false;
>>
>> This will not work.  For pmu events, gt will be across multiple tiles.
>>
>> Here for example, if a tile has 2 gts and there are 2 tiles. Then a valid gt
>> id is 3. But max_gt_per_tile is 2. So it will return a false
> 
> So it sounds like the change here is an accurate conversion of the
> existing code (changing the global constant XE_MAX_GT_PER_TILE into a
> platform-specific xe->info.max_gt_per_tile value), but the original
> logic is already problematic? 

Yes the original logic is problematic. Have sent a separate patch
too.

> In that case we should probably fix this
> as a follow-up patch to avoid mixing two different kinds of changes into
> the same patch.>
>>
>> Can we have
>>
>> if (gt_id >= xe->info.tile_count * xe->info.max_gt_per_tile) or a
>> xe_device_get_gt check similar to
>> https://patchwork.freedesktop.org/series/150943/
> 
> If we're trying to make sure the GT itself is valid, then it would
> probably be easier (and more accurate) to just do
> 
>          if (!xe_device_get_gt(xe, gt_id))
>                  return -EINVAL;
> 
> since that would also accurately raise an error on unused GT IDs that
> fall in the middle of the valid range.  E.g., if a platform only has GT
> IDs 0, 2, and 3 (media fused off on the first tile), then it would warn
> if an ID of 1 is passed too.

Yeah this should be the case. If the gt id passed in pmu config does not
exist then it should return event not supported

Thanks
Riana

> 
> 
> Matt
> 
>>
>> Thanks
>> Riana>
>>>    	return id < sizeof(pmu->supported_events) * BITS_PER_BYTE &&
>>> diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
>>> index e8e1743dcb1e..e615b0916217 100644
>>> --- a/drivers/gpu/drm/xe/xe_query.c
>>> +++ b/drivers/gpu/drm/xe/xe_query.c
>>> @@ -141,7 +141,7 @@ query_engine_cycles(struct xe_device *xe,
>>>    		return -EINVAL;
>>>    	eci = &resp.eci;
>>> -	if (eci->gt_id >= XE_MAX_GT_PER_TILE)
>>> +	if (eci->gt_id >= xe->info.max_gt_per_tile)
>>>    		return -EINVAL;
>>>    	gt = xe_device_get_gt(xe, eci->gt_id);
>>
>>
> 




More information about the Intel-xe mailing list