drm/amdgpu: optimize timeout implemention in ras_eeprom_update_record_num

The busy status returned by ras_eeprom_update_record_num may not be
an error, increase timeout to exclude false busy status. Also add more
comments to make the code readable.

v2: define a macro for the timeout value.

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 99aa1908833d3778f26419de1ee567e3724f9781..64dd7a81bff5faa0cbe4515dd707a1d7a6a54ef2 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -124,6 +124,8 @@
                                        RAS_TABLE_V2_1_INFO_SIZE) \
                                        / RAS_TABLE_RECORD_SIZE)
 
+#define RAS_SMU_MESSAGE_TIMEOUT_MS 1000 /* 1s */
+
 /* Given a zero-based index of an EEPROM RAS record, yields the EEPROM
  * offset off of RAS_TABLE_START.  That is, this is something you can
  * add to control->i2c_address, and then tell I2C layer to read
@@ -874,7 +876,7 @@ 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;
+       int ret, retry = 20;
 
        if (!amdgpu_ras_smu_eeprom_supported(adev))
                return 0;
@@ -882,17 +884,23 @@ int amdgpu_ras_eeprom_update_record_num(struct amdgpu_ras_eeprom_control *contro
        control->ras_num_recs_old = control->ras_num_recs;
 
        do {
+               /* 1000ms timeout is long enough, smu_get_badpage_count won't
+                * return -EBUSY before timeout.
+                */
                ret = amdgpu_ras_smu_get_badpage_count(adev,
-                       &(control->ras_num_recs), 12);
+                       &(control->ras_num_recs), RAS_SMU_MESSAGE_TIMEOUT_MS);
                if (!ret &&
                    (control->ras_num_recs_old == control->ras_num_recs)) {
-                       /* record number update in PMFW needs some time */
+                       /* record number update in PMFW needs some time,
+                        * smu_get_badpage_count may return immediately without
+                        * count update, sleep for a while and retry again.
+                        */
                        msleep(50);
-                       timeout -= 50;
+                       retry--;
                } else {
                        break;
                }
-       } while (timeout);
+       } while (retry);
 
        /* no update of record number is not a real failure,
         * don't print warning here