1 files changed, 29 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 74ccbd566777..076ae400d099 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2473,6 +2473,11 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!amdgpu_sriov_vf(adev)) {
 				struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 
+				if (WARN_ON(!hive)) {
+					r = -ENOENT;
+					goto init_failed;
+				}
+
 				if (!hive->reset_domain ||
 				    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 					r = -ENOENT;
@@ -3011,14 +3016,15 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			continue;
 		}
 
-		/* skip suspend of gfx and psp for S0ix
+		/* skip suspend of gfx/mes and psp for S0ix
 		 * gfx is in gfxoff state, so on resume it will exit gfxoff just
 		 * like at runtime. PSP is also part of the always on hardware
 		 * so no need to suspend it.
 		 */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP ||
-		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_MES))
 			continue;
 
 		/* XXX handle errors */
@@ -4105,6 +4111,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	adev->in_suspend = true;
 
+	/* Evict the majority of BOs before grabbing the full access */
+	r = amdgpu_device_evict_resources(adev);
+	if (r)
+		return r;
+
 	if (amdgpu_sriov_vf(adev)) {
 		amdgpu_virt_fini_data_exchange(adev);
 		r = amdgpu_virt_request_full_gpu(adev, false);
@@ -4179,21 +4190,15 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 
 	r = amdgpu_device_ip_resume(adev);
 
-	/* no matter what r is, always need to properly release full GPU */
-	if (amdgpu_sriov_vf(adev)) {
-		amdgpu_virt_init_data_exchange(adev);
-		amdgpu_virt_release_full_gpu(adev, true);
-	}
-
 	if (r) {
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
-		return r;
+		goto exit;
 	}
 	amdgpu_fence_driver_hw_init(adev);
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		return r;
+		goto exit;
 
 	queue_delayed_work(system_wq, &adev->delayed_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
@@ -4201,12 +4206,19 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	if (!adev->in_s0ix) {
 		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 		if (r)
-			return r;
+			goto exit;
+	}
+
+exit:
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_init_data_exchange(adev);
+		amdgpu_virt_release_full_gpu(adev, true);
 	}
 
+	if (r)
+		return r;
+
 	/* Make sure IB tests flushed */
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_irq_gpu_reset_resume_helper(adev);
 	flush_delayed_work(&adev->delayed_init_work);
 
 	if (adev->in_s0ix) {
@@ -5043,6 +5055,8 @@ static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev)
 		pm_runtime_enable(&(p->dev));
 		pm_runtime_resume(&(p->dev));
 	}
+
+	pci_dev_put(p);
 }
 
 static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
@@ -5081,6 +5095,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 		if (expires < ktime_get_mono_fast_ns()) {
 			dev_warn(adev->dev, "failed to suspend display audio\n");
+			pci_dev_put(p);
 			/* TODO: abort the succeeding gpu reset? */
 			return -ETIMEDOUT;
 		}
@@ -5088,6 +5103,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 	pm_runtime_disable(&(p->dev));
 
+	pci_dev_put(p);
 	return 0;
 }