drm/ttm: use the parent resv for ghost objects v3

Submitted by Huang, Ray on Oct. 25, 2019, 7:04 a.m.

Details

Message ID MN2PR12MB3309282BBF66E364EFEA8984EC650@MN2PR12MB3309.namprd12.prod.outlook.com
State New
Headers show
Series "drm/ttm: use the parent resv for ghost objects v3" ( rev: 2 ) in DRI devel

Not browsing as part of any series.

Commit Message

Huang, Ray Oct. 25, 2019, 7:04 a.m.
Reviewed-by: Huang Rui <ray.huang@amd.com>


-----Original Message-----
From: amd-gfx <amd-gfx-bounces@lists.freedesktop.org> On Behalf Of Christian König

Sent: Thursday, October 24, 2019 7:17 PM
To: dri-devel@lists.freedesktop.org; amd-gfx@lists.freedesktop.org; Zhou, David(ChunMing) <David1.Zhou@amd.com>
Subject: [PATCH] drm/ttm: use the parent resv for ghost objects v3

This way the TTM is destroyed with the correct dma_resv object locked and we can even pipeline imported BO evictions.

v2: Limit this to only cases when the parent object uses a separate
    reservation object as well. This fixes another OOM problem.
v3: fix init and try_lock on the wrong object

Signed-off-by: Christian König <christian.koenig@amd.com>

---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
 	}
 
@@ -771,7 +773,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		dma_resv_add_excl_fence(ghost_obj->base.resv, fence);
+		dma_resv_add_excl_fence(&ghost_obj->base._resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object @@ -784,7 +786,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) { @@ -840,7 +842,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	if (ret)
 		return ret;
 
-	ret = dma_resv_copy_fences(ghost->base.resv, bo->base.resv);
+	ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
 	/* Last resort, wait for the BO to be idle when we are OOM */
 	if (ret)
 		ttm_bo_wait(bo, false, false);
@@ -849,7 +851,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->mem.mem_type = TTM_PL_SYSTEM;
 	bo->ttm = NULL;
 
-	ttm_bo_unreserve(ghost);
+	dma_resv_unlock(&ghost->base._resv);
 	ttm_bo_put(ghost);
 
 	return 0;
--
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 73a1b0186029..f7b57ca1a95b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -516,9 +516,11 @@  static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	kref_init(&fbo->base.kref);
 	fbo->base.destroy = &ttm_transfered_destroy;
 	fbo->base.acc_size = 0;
-	fbo->base.base.resv = &fbo->base.base._resv;
-	dma_resv_init(fbo->base.base.resv);
-	ret = dma_resv_trylock(fbo->base.base.resv);
+	if (bo->base.resv == &bo->base._resv)
+		fbo->base.base.resv = &fbo->base.base._resv;
+
+	dma_resv_init(&fbo->base.base._resv);
+	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
 	*new_obj = &fbo->base;
@@ -715,7 +717,7 @@  int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		dma_resv_add_excl_fence(ghost_obj->base.resv, fence);
+		dma_resv_add_excl_fence(&ghost_obj->base._resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object @@ -728,7 +730,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,