[PATCH AUTOSEL 5.0 27/99] drm/amdgpu: shadow in shadow_list without tbo.mem.start cause page fault in sriov TDR

Sasha Levin sashal at kernel.org
Tue May 7 05:31:21 UTC 2019


From: wentalou <Wentao.Lou at amd.com>

[ Upstream commit b575f10dbd6f84c2c8744ff1f486bfae1e4f6f38 ]

shadow was added into shadow_list by amdgpu_bo_create_shadow.
meanwhile, shadow->tbo.mem was not fully configured.
tbo.mem would be fully configured by amdgpu_vm_sdma_map_table until calling amdgpu_vm_clear_bo.
If sriov TDR occurred between amdgpu_bo_create_shadow and amdgpu_vm_sdma_map_table,
amdgpu_device_recover_vram would deal with shadow without tbo.mem.start.

Signed-off-by: Wentao Lou <Wentao.Lou 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/amdgpu_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7ff3a28fc903..5336b2c9b615 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3150,6 +3150,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 
 		/* No need to recover an evicted BO */
 		if (shadow->tbo.mem.mem_type != TTM_PL_TT ||
+		    shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET ||
 		    shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM)
 			continue;
 
-- 
2.20.1



More information about the dri-devel mailing list