[PATCH AUTOSEL 5.14 32/40] drm/amdgpu: fix gart.bo pin_count leak
Sasha Levin
sashal at kernel.org
Tue Oct 5 13:50:11 UTC 2021
From: Leslie Shi <Yuliang.Shi at amd.com>
[ Upstream commit 66805763a97f8f7bdf742fc0851d85c02ed9411f ]
gmc_v{9,10}_0_gart_disable() isn't called matched with
correspoding gart_enbale function in SRIOV case. This will
lead to gart.bo pin_count leak on driver unload.
Cc: Hawking Zhang <Hawking.Zhang at amd.com>
Signed-off-by: Leslie Shi <Yuliang.Shi at amd.com>
Signed-off-by: Guchun Chen <guchun.chen at amd.com>
Reviewed-by: Christian König <christian.koenig at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 4523df2785d6..5b6317bf9751 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1094,6 +1094,8 @@ static int gmc_v10_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ gmc_v10_0_gart_disable(adev);
+
if (amdgpu_sriov_vf(adev)) {
/* full access mode, so don't touch any GMC register */
DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1102,7 +1104,6 @@ static int gmc_v10_0_hw_fini(void *handle)
amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
- gmc_v10_0_gart_disable(adev);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 7eb70d69f760..f3cd2b3fb4cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1764,6 +1764,8 @@ static int gmc_v9_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ gmc_v9_0_gart_disable(adev);
+
if (amdgpu_sriov_vf(adev)) {
/* full access mode, so don't touch any GMC register */
DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1772,7 +1774,6 @@ static int gmc_v9_0_hw_fini(void *handle)
amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
- gmc_v9_0_gart_disable(adev);
return 0;
}
--
2.33.0
More information about the amd-gfx
mailing list