[PATCH 02/23] drm/amdgpu: do RAS init in NPS mode switch

[Tao Zhou <tao.zhou1@xxxxxxx>]

NPS mode switch will call gpu reset, but this is different from normal
reset.

Signed-off-by: Tao Zhou <tao.zhou1@xxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    | 11 +++++++----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d69fcbb28b0e..635f020f8d9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3293,7 +3293,7 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	if (!amdgpu_in_reset(adev))
+	if (!amdgpu_in_reset(adev) || amdgpu_in_nps_switch(adev))
 		amdgpu_ras_set_error_query_ready(adev, true);
 
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index de1a55ae1d78..cbecf2380b51 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1253,7 +1253,8 @@ int amdgpu_ras_bind_aca(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
 	struct ras_manager *obj;
 
 	/* in resume phase, no need to create aca fs node */
-	if (adev->in_suspend || amdgpu_in_reset(adev))
+	if (adev->in_suspend ||
+	    (amdgpu_in_reset(adev) && !amdgpu_in_nps_switch(adev)))
 		return 0;
 
 	obj = get_ras_manager(adev, blk);
@@ -3780,7 +3781,8 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 
 	r = amdgpu_ras_feature_enable_on_boot(adev, ras_block, 1);
 	if (r) {
-		if (adev->in_suspend || amdgpu_in_reset(adev)) {
+		if (adev->in_suspend ||
+		    (amdgpu_in_reset(adev) && !amdgpu_in_nps_switch(adev))) {
 			/* in resume phase, if fail to enable ras,
 			 * clean up all ras fs nodes, and disable ras */
 			goto cleanup;
@@ -3792,7 +3794,8 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 	amdgpu_persistent_edc_harvesting(adev, ras_block);
 
 	/* in resume phase, no need to create ras fs node */
-	if (adev->in_suspend || amdgpu_in_reset(adev))
+	if (adev->in_suspend ||
+	    (amdgpu_in_reset(adev) && !amdgpu_in_nps_switch(adev)))
 		return 0;
 
 	ras_obj = container_of(ras_block, struct amdgpu_ras_block_object, ras_comm);
@@ -3922,7 +3925,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	amdgpu_ras_event_mgr_init(adev);
 
 	if (amdgpu_ras_aca_is_supported(adev)) {
-		if (amdgpu_in_reset(adev)) {
+		if (amdgpu_in_reset(adev) && !amdgpu_in_nps_switch(adev)) {
 			if (amdgpu_aca_is_enabled(adev))
 				r = amdgpu_aca_reset(adev);
 			else
-- 
2.34.1