[PATCH 09/15] drm/xe: Convert the CPU fault handler for exhaustive eviction

[Thomas Hellström]

The CPU fault handler may populate bos and migrate, and in doing
so might interfere with other tasks validing.

Convert it for exhaustive eviction. To do this properly without
potentially introducing stalls with the mmap lock held requires
TTM work. In the meantime, let's live with those stalls that
would typically happen on memory pressure.

Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 5e40b6cb8d2a..dd1e0e9957e0 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1720,14 +1720,18 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	struct xe_device *xe = to_xe_device(ddev);
 	struct xe_bo *bo = ttm_to_xe_bo(tbo);
 	bool needs_rpm = bo->flags & XE_BO_FLAG_VRAM_MASK;
-	struct drm_exec *exec;
+	struct xe_validation_ctx ctx;
+	struct drm_exec exec;
 	vm_fault_t ret;
 	int idx;
 
 	if (needs_rpm)
 		xe_pm_runtime_get(xe);
 
-	exec = XE_VALIDATION_UNIMPLEMENTED;
+	if (xe_validation_ctx_init(&ctx, &xe->val, &exec,
+				   DRM_EXEC_INTERRUPTIBLE_WAIT, 0, false))
+		return VM_FAULT_NOPAGE;
+
 	ret = ttm_bo_vm_reserve(tbo, vmf);
 	if (ret)
 		goto out;
@@ -1735,7 +1739,7 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	if (drm_dev_enter(ddev, &idx)) {
 		trace_xe_bo_cpu_fault(bo);
 
-		xe_validation_assert_exec(xe, exec, &tbo->base);
+		xe_validation_assert_exec(xe, &exec, &tbo->base);
 		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
 					       TTM_BO_VM_NUM_PREFAULT);
 		drm_dev_exit(idx);
@@ -1761,6 +1765,7 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 
 	dma_resv_unlock(tbo->base.resv);
 out:
+	xe_validation_ctx_fini(&ctx);
 	if (needs_rpm)
 		xe_pm_runtime_put(xe);
 
-- 
2.50.1