diff mbox series

[v6,08/40] drm/msm: Don't close VMAs on purge

Message ID 20250605183111.163594-9-robin.clark@oss.qualcomm.com
State New
Headers show
Series drm/msm: sparse / "VM_BIND" support | expand

Commit Message

Rob Clark June 5, 2025, 6:28 p.m. UTC 
From: Rob Clark <robdclark@chromium.org>

Previously we'd also tear down the VMA, making the address space
available again.  But with drm_gpuvm conversion, this would require
holding the locks of all VMs the GEM object is mapped in.  Which is
problematic for the shrinker.

Instead just let the VMA hang around until the GEM object is freed.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 4c10eca404e0..50b866dcf439 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -763,7 +763,7 @@  void msm_gem_purge(struct drm_gem_object *obj)
 	GEM_WARN_ON(!is_purgeable(msm_obj));
 
 	/* Get rid of any iommu mapping(s): */
-	put_iova_spaces(obj, true);
+	put_iova_spaces(obj, false);
 
 	msm_gem_vunmap(obj);