[PATCH 7/8] drm/amdgpu: try for more times if RAS bad page number is not updated

[Tao Zhou]

RAS info update in PMFW is time cost, wait for it.

Signed-off-by: Tao Zhou <tao.zh...@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c    | 22 ++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 511c5882b37e..de7b268a9862 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -867,13 +867,33 @@ amdgpu_ras_eeprom_update_header(struct 
amdgpu_ras_eeprom_control *control)
 int amdgpu_ras_eeprom_update_record_num(struct amdgpu_ras_eeprom_control 
*control)
 {
        struct amdgpu_device *adev = to_amdgpu_device(control);
+       int ret, timeout = 1000;
 
        if (!amdgpu_ras_smu_eeprom_supported(adev))
                return 0;
 
        control->ras_num_recs_old = control->ras_num_recs;
-       return amdgpu_ras_smu_get_badpage_count(adev,
+
+       do {
+               ret = amdgpu_ras_smu_get_badpage_count(adev,
                        &(control->ras_num_recs), 12);
+               if (!ret &&
+                   (control->ras_num_recs_old == control->ras_num_recs)) {
+                       /* record number update in PMFW needs some time */
+                       msleep(50);
+                       timeout -= 50;
+               } else {
+                       break;
+               }
+       } while (timeout);
+
+       /* no update of record number is not a real failure,
+        * don't print warning here
+        */
+       if (!ret && (control->ras_num_recs_old == control->ras_num_recs))
+               ret = -EINVAL;
+
+       return ret;
 }
 
 /**
-- 
2.34.1