On 3/7/2025 7:18 PM, Christian König wrote:
We keep the gang submission fence around in adev, make sure that it
stays alive.
v2: fix memory leak on retry
Signed-off-by: Christian König <christian.koe...@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 198d29faa754..337543ec615c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6889,18 +6889,26 @@ struct dma_fence *amdgpu_device_switch_gang(struct
amdgpu_device *adev,
{
struct dma_fence *old = NULL;
+ dma_fence_get(gang);
do {
dma_fence_put(old);
old = amdgpu_device_get_gang(adev);
if (old == gang)
break;
- if (!dma_fence_is_signaled(old))
+ if (!dma_fence_is_signaled(old)) {
Here, should we need to check ?
// Check if old fence isn't signaled
if (old && !dma_fence_is_signaled(old)) {
+ dma_fence_put(gang);
return old;
+ }
} while (cmpxchg((struct dma_fence __force **)&adev->gang_submit,
old, gang) != old);
+ /*
+ * Drop it once for the exchanged reference in adev and once for the
+ * thread local reference acquired in amdgpu_device_get_gang().
+ */
+ dma_fence_put(old);
if (old)
dma_fence_put(old); // Ensure to release old reference only if it
is valid?
dma_fence_put(old);
return NULL;
}
