[PATCH] drm/amdgpu: protect eeprom update from GPU reset

[Dennis Li]

because i2c is unstable in GPU reset, driver need protect
eeprom update from GPU reset, to not miss any bad page record.

Signed-off-by: Dennis Li <Dennis.Li at 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 0e64c39a2372..695bcfc5c983 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -149,7 +149,11 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 
 	msg.addr = control->i2c_address;
 
+	/* i2c may be unstable in gpu reset */
+	down_read(&adev->reset_sem);
 	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	up_read(&adev->reset_sem);
+
 	if (ret < 1)
 		DRM_ERROR("Failed to write EEPROM table header, ret:%d", ret);
 
@@ -557,7 +561,11 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		control->next_addr += EEPROM_TABLE_RECORD_SIZE;
 	}
 
+	/* i2c may be unstable in gpu reset */
+	down_read(&adev->reset_sem);
 	ret = i2c_transfer(&adev->pm.smu_i2c, msgs, num);
+	up_read(&adev->reset_sem);
+
 	if (ret < 1) {
 		DRM_ERROR("Failed to process EEPROM table records, ret:%d", ret);
 
-- 
2.17.1