drm/amdgpu: update xgmi info and vram_base_offset on resume

For SRIOV VM env with XGMI enabled systems, XGMI physical node id may
change when hibernate and resume with different VF.

Update XGMI info and vram_base_offset on resume for gfx444 SRIOV env.
Add amdgpu_virt_xgmi_migrate_enabled() as the feature flag.

Signed-off-by: Jiang Liu <gerry@linux.alibaba.com>
Signed-off-by: Samuel Zhang <guoqing.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 31 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e1bab6a96cb6..6715d76ad03a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2773,6 +2773,12 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (!amdgpu_device_pcie_dynamic_switching_supported(adev))
 		adev->pm.pp_feature &= ~PP_PCIE_DPM_MASK;
 
+	adev->virt.is_xgmi_node_migrate_enabled = false;
+	if (amdgpu_sriov_vf(adev)) {
+		adev->virt.is_xgmi_node_migrate_enabled =
+			amdgpu_ip_version((adev), GC_HWIP, 0) == IP_VERSION(9, 4, 4);
+	}
+
 	total = true;
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		ip_block = &adev->ip_blocks[i];
@@ -5098,6 +5104,25 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	return 0;
 }
 
+static inline int amdgpu_virt_resume(struct amdgpu_device *adev)
+{
+	int r;
+	unsigned int prev_physical_node_id = adev->gmc.xgmi.physical_node_id;
+
+	r = adev->gfxhub.funcs->get_xgmi_info(adev);
+	if (r)
+		return r;
+
+	dev_info(adev->dev, "xgmi node, old id %d, new id %d\n",
+		prev_physical_node_id, adev->gmc.xgmi.physical_node_id);
+
+	adev->vm_manager.vram_base_offset = adev->gfxhub.funcs->get_mc_fb_offset(adev);
+	adev->vm_manager.vram_base_offset +=
+		adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
+
+	return 0;
+}
+
 /**
  * amdgpu_device_resume - initiate device resume
  *
@@ -5119,6 +5144,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients)
 			return r;
 	}
 
+	if (amdgpu_virt_xgmi_migrate_enabled(adev)) {
+		r = amdgpu_virt_resume(adev);
+		if (r)
+			goto exit;
+	}
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;