[Intel-xe] [PATCH v3 2/3] drm/xe/bo: consider dma-resv fences for clear job

[Matthew Auld]

There could be active fences already in the dma-resv for the object
prior to clearing. Make sure to input them as dependencies for the clear
job.

v2 (Matt B):
  - We can use USAGE_KERNEL here, since it's only the move fences we
    care about here. Also add a comment.

Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 009d728af762..e6a31f90ebdb 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -980,8 +980,6 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		size -= clear_L0;
 
-		/* TODO: Add dependencies here */
-
 		/* Preemption is enabled again by the ring ops. */
 		if (!clear_vram) {
 			emit_pte(m, bb, clear_L0_pt, clear_vram, &src_it, clear_L0,
@@ -1010,6 +1008,18 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		}
 
 		xe_sched_job_add_migrate_flush(job, flush_flags);
+		if (!fence) {
+			/*
+			 * There can't be anything userspace related at this
+			 * point, so we just need to respect any potential move
+			 * fences, which are always tracked as
+			 * DMA_RESV_USAGE_KERNEL.
+			 */
+			err = job_add_deps(job, bo->ttm.base.resv,
+					   DMA_RESV_USAGE_KERNEL);
+			if (err)
+				goto err_job;
+		}
 
 		xe_sched_job_arm(job);
 		dma_fence_put(fence);
@@ -1024,6 +1034,8 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		xe_bb_free(bb, fence);
 		continue;
 
+err_job:
+		xe_sched_job_put(job);
 err:
 		mutex_unlock(&m->job_mutex);
 		xe_bb_free(bb, NULL);
-- 
2.41.0