drm/xe: Don't compare GT ID to GT count when determining valid GTs

On current platforms with multiple GTs, all of the GT IDs are
consecutive; as a result we know that the GT IDs range from 0 to
gt_count-1 and can determine if a GT ID is valid by comparing against
the count.  The consecutive nature of GT IDs may not hold true on future
platforms if/when we have platforms that are both multi-tile and have
multiple GTs within each tile.  Once such platforms exist, it's quite
possible that we could wind up with something like a GT list composed of
IDs 0, 2, and 3 with no GT 1 (which would be a 2-tile platform with
media only on the second tile).

To future-proof the code we should stop comparing against the GT count
to determine whether a GT ID is valid or not.  Instead we should do an
actual lookup of the ID to determine whether the GT exists.  This also
means that our GT loop macro should not end at the GT count, but should
rather examine the entire space up to (# of tiles) * (max GT per tile)
to ensure it doesn't stop prematurely.

Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250701201320.2514369-15-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 4e719d398c8826a1276ce36ef605887efc0d6ded..f0eb8150f1853ee6d19731147dda47428df9fb0c 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -127,12 +127,8 @@ static inline bool xe_device_uc_enabled(struct xe_device *xe)
        for ((id__) = 1; (id__) < (xe__)->info.tile_count; (id__)++) \
                for_each_if((tile__) = &(xe__)->tiles[(id__)])
 
-/*
- * FIXME: This only works for now since multi-tile and standalone media
- * happen to be mutually exclusive.  Future platforms may change this...
- */
 #define for_each_gt(gt__, xe__, id__) \
-       for ((id__) = 0; (id__) < (xe__)->info.gt_count; (id__)++) \
+       for ((id__) = 0; (id__) < (xe__)->info.tile_count * (xe__)->info.max_gt_per_tile; (id__)++) \
                for_each_if((gt__) = xe_device_get_gt((xe__), (id__)))
 
 static inline struct xe_force_wake *gt_to_fw(struct xe_gt *gt)

diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c
index 96732613b4b7df685c5d854cb74b36858e837d77..af7916315ac664f039073604f5b2e032f863811a 100644 (file)
--- a/drivers/gpu/drm/xe/xe_eu_stall.c
+++ b/drivers/gpu/drm/xe/xe_eu_stall.c
@@ -258,11 +258,13 @@ static int set_prop_eu_stall_wait_num_reports(struct xe_device *xe, u64 value,
 static int set_prop_eu_stall_gt_id(struct xe_device *xe, u64 value,
                                   struct eu_stall_open_properties *props)
 {
-       if (value >= xe->info.gt_count) {
+       struct xe_gt *gt = xe_device_get_gt(xe, value);
+
+       if (!gt) {
                drm_dbg(&xe->drm, "Invalid GT ID %llu for EU stall sampling\n", value);
                return -EINVAL;
        }
-       props->gt = xe_device_get_gt(xe, value);
+       props->gt = gt;
        return 0;
 }
 

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index fee22358cc09be80f5a86609bc41c589f70e7946..8991b4aed440710590e0de4feee7784049c31388 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -610,7 +610,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
        if (XE_IOCTL_DBG(xe, err))
                return -EFAULT;
 
-       if (XE_IOCTL_DBG(xe, eci[0].gt_id >= xe->info.gt_count))
+       if (XE_IOCTL_DBG(xe, !xe_device_get_gt(xe, eci[0].gt_id)))
                return -EINVAL;
 
        if (args->flags & DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT)

diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 3439c8522d013178eb7ea9b992e210b3e313246f..796ba8c34a160d95df9f6d2224c48ecb29c043c2 100644 (file)
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -1059,12 +1059,13 @@ struct xe_hw_engine *
 xe_hw_engine_lookup(struct xe_device *xe,
                    struct drm_xe_engine_class_instance eci)
 {
+       struct xe_gt *gt = xe_device_get_gt(xe, eci.gt_id);
        unsigned int idx;
 
        if (eci.engine_class >= ARRAY_SIZE(user_to_xe_engine_class))
                return NULL;
 
-       if (eci.gt_id >= xe->info.gt_count)
+       if (!gt)
                return NULL;
 
        idx = array_index_nospec(eci.engine_class,