drm/amd/ras: add append func for pmfw eeprom

add append func for pmfw eeprom

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

diff --git a/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.c b/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.c
index 34a4161251b3d5614c0d7dc00f41cb141fd4242c..580dd7b09d00d9648ffdcbbcb45ed347bbb0fa87 100644 (file)
--- a/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.c
+++ b/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.c
@@ -220,3 +220,42 @@ bool ras_fw_eeprom_check_safety_watermark(struct ras_core_context *ras_core)
 
        return ret;
 }
+
+int ras_fw_eeprom_append(struct ras_core_context *ras_core,
+                          struct eeprom_umc_record *record, const u32 num)
+{
+       struct ras_fw_eeprom_control *control = &ras_core->ras_fw_eeprom;
+       int threshold_config = control->record_threshold_config;
+       int i, bad_page_count;
+
+       mutex_lock(&control->ras_tbl_mutex);
+
+       for (i = 0; i < num; i++) {
+               /* update bad channel bitmap */
+               if ((record[i].mem_channel < BITS_PER_TYPE(control->bad_channel_bitmap)) &&
+                       !(control->bad_channel_bitmap & (1 << record[i].mem_channel))) {
+                       control->bad_channel_bitmap |= 1 << record[i].mem_channel;
+                       control->update_channel_flag = true;
+               }
+       }
+       control->ras_num_recs += num;
+
+       bad_page_count = ras_umc_get_badpage_count(ras_core);
+
+       if (threshold_config != 0 &&
+               bad_page_count > control->record_threshold_count) {
+               RAS_DEV_WARN(ras_core->dev,
+                       "Saved bad pages %d reaches threshold value %d\n",
+                       bad_page_count, control->record_threshold_count);
+
+               if ((threshold_config != WARN_NONSTOP_OVER_THRESHOLD) &&
+                       (threshold_config != NONSTOP_OVER_THRESHOLD))
+                       ras_core->is_rma = true;
+
+               /* ignore the -ENOTSUPP return value */
+               ras_core_event_notify(ras_core, RAS_EVENT_ID__DEVICE_RMA, NULL);
+       }
+
+       mutex_unlock(&control->ras_tbl_mutex);
+       return 0;
+}

diff --git a/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.h b/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.h
index b0d3eade43770839e87a852d6ff31470094a947b..b94d3c9703e34e17268d186ab8e1cfb48848e3a0 100644 (file)
--- a/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.h
+++ b/drivers/gpu/drm/amd/ras/rascore/ras_eeprom_fw.h
@@ -68,5 +68,7 @@ int ras_fw_erase_ras_table(struct ras_core_context *ras_core,
                                   uint32_t *result);
 int ras_fw_eeprom_reset_table(struct ras_core_context *ras_core);
 bool ras_fw_eeprom_check_safety_watermark(struct ras_core_context *ras_core);
+int ras_fw_eeprom_append(struct ras_core_context *ras_core,
+                          struct eeprom_umc_record *record, const u32 num);
 
 #endif

diff --git a/drivers/gpu/drm/amd/ras/rascore/ras_umc.c b/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
index 2abe8553e479e318883747db951b2c62fb2ceba2..f7c2cb0a8a0c26041c9eb2a1f9708329b40c58ad 100644 (file)
--- a/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
+++ b/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
@@ -491,9 +491,13 @@ static int ras_umc_save_bad_pages(struct ras_core_context *ras_core)
        save_count = data->count - eeprom_record_num;
        /* only new entries are saved */
        if (save_count > 0) {
-               if (ras_eeprom_append(ras_core,
-                                          &data->bps[eeprom_record_num],
-                                          save_count)) {
+               if (ras_fw_eeprom_supported(ras_core))
+                       ret = ras_fw_eeprom_append(ras_core, &data->bps[eeprom_record_num],
+                                       save_count);
+               else
+                       ret = ras_eeprom_append(ras_core, &data->bps[eeprom_record_num],
+                                       save_count);
+               if (ret) {
                        RAS_DEV_ERR(ras_core->dev, "Failed to save EEPROM table data!");
                        ret = -EIO;
                        goto exit;