From: Christian König <christian.koenig@amd.com>
Date: Tue, 14 Jan 2025 12:51:39 +0000 (+0100)
Subject: drm/amdgpu: grab an additional reference on the gang fence v2
X-Git-Tag: v6.6.88~280
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3ab9cd2d2e9ae89614ecf57dde11b14716f8fdaf;p=thirdparty%2Fkernel%2Fstable.git

drm/amdgpu: grab an additional reference on the gang fence v2

[ Upstream commit 0d9a95099dcb05b5f4719c830d15bf4fdcad0dc2 ]

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.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 45dd6cbad81e7..10f5a3d0f5916 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6015,6 +6015,7 @@ 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);
 		rcu_read_lock();
@@ -6024,12 +6025,19 @@ struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 		if (old == gang)
 			break;
 
-		if (!dma_fence_is_signaled(old))
+		if (!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);
 	dma_fence_put(old);
 	return NULL;
 }