drm/xe/vm: Use for_each_tlb_inval() to calculate invalidation fences

ops_execute() calculates the size of a fence array based on
XE_MAX_GT_PER_TILE, while the code that actually fills in the fence
array uses a for_each_tlb_inval() iterator.  This works out okay today
since both approaches come up with the same number of invalidation
fences (2: primary GT invalidation + media GT invalidation), but could
be problematic in the future if there isn't a 1:1 relationship between
TLBs needing invalidation and potential GTs on the tile.

Adjust the allocation code to use the same for_each_tlb_inval()
counting logic as the code that fills the array to future-proof the
code.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251118202604.3715782-2-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 7cac646bdf1c03689bca9511f5e1f40270811622..f9989a7a710c188aad99439889bdb6aef2211def 100644 (file)
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3104,19 +3104,19 @@ static struct dma_fence *ops_execute(struct xe_vm *vm,
        struct dma_fence *fence = NULL;
        struct dma_fence **fences = NULL;
        struct dma_fence_array *cf = NULL;
-       int number_tiles = 0, current_fence = 0, n_fence = 0, err;
+       int number_tiles = 0, current_fence = 0, n_fence = 0, err, i;
        u8 id;
 
        number_tiles = vm_ops_setup_tile_args(vm, vops);
        if (number_tiles == 0)
                return ERR_PTR(-ENODATA);
 
-       if (vops->flags & XE_VMA_OPS_FLAG_SKIP_TLB_WAIT) {
-               for_each_tile(tile, vm->xe, id)
-                       ++n_fence;
-       } else {
-               for_each_tile(tile, vm->xe, id)
-                       n_fence += (1 + XE_MAX_GT_PER_TILE);
+       for_each_tile(tile, vm->xe, id) {
+               ++n_fence;
+
+               if (!(vops->flags & XE_VMA_OPS_FLAG_SKIP_TLB_WAIT))
+                       for_each_tlb_inval(i)
+                               ++n_fence;
        }
 
        fences = kmalloc_array(n_fence, sizeof(*fences), GFP_KERNEL);
@@ -3146,7 +3146,6 @@ static struct dma_fence *ops_execute(struct xe_vm *vm,
 
        for_each_tile(tile, vm->xe, id) {
                struct xe_exec_queue *q = vops->pt_update_ops[tile->id].q;
-               int i;
 
                fence = NULL;
                if (!vops->pt_update_ops[id].num_ops)