drm/amdgpu: timely save bad pages to eeprom after gpu ras reset is completed

The problem case is as follows:
1. GPU A triggers a gpu ras reset, and GPU A drives
   GPU B to also perform a gpu ras reset.
2. After gpu B ras reset started, gpu B queried a DE
   data. Since the DE data was queried in the ras reset
   thread instead of the page retirement thread, bad
   page retirement work would not be triggered. Then
   even if all gpu resets are completed, the bad pages
   will be cached in RAM until GPU B's bad page retirement
   work is triggered again and then saved to eeprom.

This patch can save the bad pages to eeprom in time after gpu
ras reset is completed.

v2:
  1. Add the above description to code comments.
  2. Reuse existing function.

Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: YiPeng Chai

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -2934,8 +2934,12 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 	struct ras_err_data err_data;
 	unsigned long err_cnt;
 
-	if (amdgpu_in_reset(adev) || amdgpu_ras_in_recovery(adev))
+	/* If gpu reset is ongoing, delay retiring the bad pages */
+	if (amdgpu_in_reset(adev) || amdgpu_ras_in_recovery(adev)) {
+		amdgpu_ras_schedule_retirement_dwork(con,
+				AMDGPU_RAS_RETIRE_PAGE_INTERVAL * 3);
 		return;
+	}
 
 	amdgpu_ras_error_data_init(&err_data);
 

drivers/gpu/drm/amd/amdgpu/umc_v12_0.c

@@ -29,6 +29,7 @@
 #include "mp/mp_13_0_6_sh_mask.h"
 
 #define MAX_ECC_NUM_PER_RETIREMENT  32
+#define DELAYED_TIME_FOR_GPU_RESET  1000  //ms
 
 static inline uint64_t get_umc_v12_0_reg_offset(struct amdgpu_device *adev,
 					    uint32_t node_inst,
@@ -568,6 +569,23 @@ static int umc_v12_0_update_ecc_status(struct amdgpu_device *adev,
 
 	con->umc_ecc_log.de_queried_count++;
 
+	/* The problem case is as follows:
+	 * 1. GPU A triggers a gpu ras reset, and GPU A drives
+	 *    GPU B to also perform a gpu ras reset.
+	 * 2. After gpu B ras reset started, gpu B queried a DE
+	 *    data. Since the DE data was queried in the ras reset
+	 *    thread instead of the page retirement thread, bad
+	 *    page retirement work would not be triggered. Then
+	 *    even if all gpu resets are completed, the bad pages
+	 *    will be cached in RAM until GPU B's bad page retirement
+	 *    work is triggered again and then saved to eeprom.
+	 * Trigger delayed work to save the bad pages to eeprom in time
+	 * after gpu ras reset is completed.
+	 */
+	if (amdgpu_ras_in_recovery(adev))
+		schedule_delayed_work(&con->page_retirement_dwork,
+			msecs_to_jiffies(DELAYED_TIME_FOR_GPU_RESET));
+
 	return 0;
 }