[PATCH 2/2] drm/amdgpu: add debugfs node to toggle ras error cnt harvest

[Guchun Chen]

Before ras recovery is issued, user could operate this debugfs
node to enable/disable the harvest of all RAS IPs' ras error
count registers, which will help keep hardware's registers'
status instead of cleaning up them.

Signed-off-by: Guchun Chen <guchun.chen at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e6978b8e2143..31df6bf2dc1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1215,6 +1215,13 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 	 */
 	debugfs_create_bool("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
 				&con->reboot);
+
+	/*
+	 * User could set this not to clean up hardware's error count register
+	 * of RAS IPs during ras recovery.
+	 */
+	debugfs_create_bool("disable_ras_err_cnt_harvest", 0644,
+			con->dir, &con->disable_ras_err_cnt_harvest);
 }
 
 void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
-- 
2.17.1