drm/amdgpu: rework resume handling for display (v2)

commit 73dae652dcac776296890da215ee7dec357a1032 upstream.

Split resume into a 3rd step to handle displays when DCC is
enabled on DCN 4.0.1.  Move display after the buffer funcs
have been re-enabled so that the GPU will do the move and
properly set the DCC metadata for DCN.

v2: fix fence irq resume ordering

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.11.x
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 43 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 07f93f77de7d..51904906545e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3666,7 +3666,7 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev)
  *
  * @adev: amdgpu_device pointer
  *
- * First resume function for hardware IPs.  The list of all the hardware
+ * Second resume function for hardware IPs.  The list of all the hardware
  * IPs that make up the asic is walked and the resume callbacks are run for
  * all blocks except COMMON, GMC, and IH.  resume puts the hardware into a
  * functional state after a suspend and updates the software state as
@@ -3684,6 +3684,7 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH ||
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->resume(adev);
@@ -3699,6 +3700,36 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 }
 
 /**
+ * amdgpu_device_ip_resume_phase3 - run resume for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Third resume function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked and the resume callbacks are run for
+ * all DCE.  resume puts the hardware into a functional state after a suspend
+ * and updates the software state as necessary.  This function is also used
+ * for restoring the GPU after a GPU reset.
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_resume_phase3(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.valid || adev->ip_blocks[i].status.hw)
+			continue;
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) {
+			r = adev->ip_blocks[i].version->funcs->resume(adev);
+			if (r)
+				return r;
+		}
+	}
+
+	return 0;
+}
+
+/**
  * amdgpu_device_ip_resume - run resume for hardware IPs
  *
  * @adev: amdgpu_device pointer
@@ -3727,6 +3758,13 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 	if (adev->mman.buffer_funcs_ring->sched.ready)
 		amdgpu_ttm_set_buffer_funcs_status(adev, true);
 
+	if (r)
+		return r;
+
+	amdgpu_fence_driver_hw_init(adev);
+
+	r = amdgpu_device_ip_resume_phase3(adev);
+
 	return r;
 }
 
@@ -4809,7 +4847,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
 		goto exit;
 	}
-	amdgpu_fence_driver_hw_init(adev);
 
 	if (!adev->in_s0ix) {
 		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
@@ -5431,6 +5468,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				if (tmp_adev->mman.buffer_funcs_ring->sched.ready)
 					amdgpu_ttm_set_buffer_funcs_status(tmp_adev, true);
 
+				r = amdgpu_device_ip_resume_phase3(tmp_adev);
+				if (r)
+					goto out;
+
 				if (vram_lost)
 					amdgpu_device_fill_reset_magic(tmp_adev);