drm/amdgpu: skip read eeprom for device that pending on XGMI reset

Read eeprom through SMU doesn't works stable on XGMI reset during test.
skip it for now

Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ed83a32..ea36333 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1857,6 +1857,12 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
                        goto out;
        }
 
+       /* Todo: During test the SMU might fail to read the eeprom through I2C
+        * when the GPU is pending on XGMI reset during probe time
+        * (Mostly after second bus reset), skip it now
+        */
+       if (adev->gmc.xgmi.pending_reset)
+               return 0;
        ret = amdgpu_ras_eeprom_init(&con->eeprom_control, &exc_err_limit);
        /*
         * This calling fails when exc_err_limit is true or