[PATCH] drm/amdgpu: fix ib test hang with gfxoff enabled

[Huang Rui]

After defer the execution of gfx/compute ib tests. However, at that time, the
gfx already go into "mid state" of gfxoff.

PWR_MISC_CNTL_STATUS: PWR_GFXOFF_STATUS field (2:1 bits)
0 = GFXOFF.
1 = Transition out of GFXOFF state.
2 = Not in GFXOFF.
3 = Transition into GFXOFF.

If hit the mid state (1 or 3), the doorbell writing interrupt cannot wake up the
gfx back successfully. And the field value is 1 when we issue the ib test at
that, so we got the hang. This is the root cause that we encountered the issue.

Meanwhile, we cannot set clockgating of GFX after gfx is already in "off" state.
So here we should move the gfx powergating and gfxoff enabling behavior at the
end of initialization behind ib test and clockgating.

Signed-off-by: Huang Rui <ray.huang at amd.com>
Cc: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c        | 10 ++++++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c             |  5 -----
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c     |  2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c |  4 ++--
 4 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f509d32..e1c8806 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1723,6 +1723,16 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 			}
 		}
 	}
+
+	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_GFX,
+						       AMD_CG_STATE_GATE);
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_SMC,
+						       AMD_CG_STATE_GATE);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 2c5e2a4..31ecc86 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3358,11 +3358,6 @@ static int gfx_v9_0_late_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_GFX,
-						   AMD_PG_STATE_GATE);
-	if (r)
-		return r;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index b493369..d0e6e2d 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -245,7 +245,7 @@ static int pp_set_powergating_state(void *handle,
 	}
 
 	if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
-		pr_info("%s was not implemented.\n", __func__);
+		pr_debug("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 7712eb6..b72d089 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -284,7 +284,7 @@ static int smu10_disable_gfx_off(struct pp_hwmgr *hwmgr)
 
 static int smu10_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
-	return smu10_disable_gfx_off(hwmgr);
+	return 0;
 }
 
 static int smu10_enable_gfx_off(struct pp_hwmgr *hwmgr)
@@ -299,7 +299,7 @@ static int smu10_enable_gfx_off(struct pp_hwmgr *hwmgr)
 
 static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
-	return smu10_enable_gfx_off(hwmgr);
+	return 0;
 }
 
 static int smu10_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
-- 
2.7.4