From: Tao Zhou <tao.zhou1@amd.com>
Date: Wed, 27 Aug 2025 11:33:02 +0000 (+0800)
Subject: drm/amdgpu: try for more times if RAS bad page number is not updated
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=334b27bf712b5ddd19908aba318175e4b9bcf839;p=thirdparty%2Fkernel%2Flinux.git

drm/amdgpu: try for more times if RAS bad page number is not updated

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

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index ec248ca6ef930..01b38a6e198e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -874,13 +874,33 @@ Out:
 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;
 }
 
 /**