Merge tag 'drm-fixes-for-v4.9-rc2' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes from Dave Airlie:
 "Just had a couple of amdgpu fixes and one core fix I wanted to get out
  early to fix some regressions.

  I'm sure I'll have more stuff this week for -rc2"

* tag 'drm-fixes-for-v4.9-rc2' of git://people.freedesktop.org/~airlied/linux: (22 commits)
  drm: Print device information again in debugfs
  drm/amd/powerplay: fix bug stop dpm can't work on Vi.
  drm/amd/powerplay: notify smu no display by default.
  drm/amdgpu/dpm: implement thermal sensor for CZ/ST
  drm/amdgpu/powerplay: implement thermal sensor for CZ/ST
  drm/amdgpu: disable smu hw first on tear down
  drm/amdgpu: fix amdgpu_need_full_reset (v2)
  drm/amdgpu/si_dpm: Limit clocks on HD86xx part
  drm/amd/powerplay: fix static checker warnings in smu7_hwmgr.c
  drm/amdgpu: potential NULL dereference in debugfs code
  drm/amd/powerplay: fix static checker warnings in smu7_hwmgr.c
  drm/amd/powerplay: fix static checker warnings in iceland_smc.c
  drm/radeon: change vblank_time's calculation method to reduce computational error.
  drm/amdgpu: change vblank_time's calculation method to reduce computational error.
  drm/amdgpu: clarify UVD/VCE special handling for CG
  drm/amd/amdgpu: enable clockgating only after late init
  drm/radeon: allow TA_CS_BC_BASE_ADDR on SI
  drm/amdgpu: initialize the context reset_counter in amdgpu_ctx_init
  drm/amdgpu/gfx8: fix CGCG_CGLS handling
  drm/radeon: fix modeset tear down code
  ...

1 files changed, 52 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7dbe85d67d26..b4f4a9239069 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1408,16 +1408,6 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_block_status[i].valid)
 			continue;
-		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_UVD ||
-			adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_VCE)
-			continue;
-		/* enable clockgating to save power */
-		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
-								    AMD_CG_STATE_GATE);
-		if (r) {
-			DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
-			return r;
-		}
 		if (adev->ip_blocks[i].funcs->late_init) {
 			r = adev->ip_blocks[i].funcs->late_init((void *)adev);
 			if (r) {
@@ -1426,6 +1416,18 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 			}
 			adev->ip_block_status[i].late_initialized = true;
 		}
+		/* skip CG for VCE/UVD, it's handled specially */
+		if (adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_UVD &&
+		    adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_VCE) {
+			/* enable clockgating to save power */
+			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+									    AMD_CG_STATE_GATE);
+			if (r) {
+				DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+				return r;
+			}
+		}
 	}
 
 	return 0;
@@ -1435,6 +1437,30 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	/* need to disable SMC first */
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].hw)
+			continue;
+		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) {
+			/* ungate blocks before hw fini so that we can shutdown the blocks safely */
+			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+									    AMD_CG_STATE_UNGATE);
+			if (r) {
+				DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+				return r;
+			}
+			r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_DEBUG("hw_fini of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+			}
+			adev->ip_block_status[i].hw = false;
+			break;
+		}
+	}
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_block_status[i].hw)
 			continue;
@@ -2073,7 +2099,8 @@ static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
 		if (!adev->ip_block_status[i].valid)
 			continue;
 		if (adev->ip_blocks[i].funcs->check_soft_reset)
-			adev->ip_blocks[i].funcs->check_soft_reset(adev);
+			adev->ip_block_status[i].hang =
+				adev->ip_blocks[i].funcs->check_soft_reset(adev);
 		if (adev->ip_block_status[i].hang) {
 			DRM_INFO("IP block:%d is hang!\n", i);
 			asic_hang = true;
@@ -2102,12 +2129,20 @@ static int amdgpu_pre_soft_reset(struct amdgpu_device *adev)
 
 static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
 {
-	if (adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_SMC].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_ACP].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang) {
-		DRM_INFO("Some block need full reset!\n");
-		return true;
+	int i;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
+		if ((adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_ACP) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_DCE)) {
+			if (adev->ip_block_status[i].hang) {
+				DRM_INFO("Some block need full reset!\n");
+				return true;
+			}
+		}
 	}
 	return false;
 }