Am 14.04.25 um 12:46 schrieb Samuel Zhang:
> For virtual machine with vGPUs in SRIOV single device mode and XGMI
> is enabled, XGMI physical node ids may change when waking up from
> hiberation with different vGPU devices. So update XGMI physical node
> ids on resume.
>
> Update GPU memory controller configuration on resume if XGMI physical
> node ids are changed.
>
> Signed-off-by: Jiang Liu <ge...@linux.alibaba.com>
> Signed-off-by: Samuel Zhang <guoqing.zh...@amd.com>
> Change-Id: I0bcac2d46fdeed66c9cf7e6a378134769c95df61
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 25 ++++++++++++++++++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 2 ++
> drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h | 2 ++
> drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 8 +++++++
> 4 files changed, 37 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index f212ce3f5d34..12f115602ab2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5098,6 +5098,28 @@ int amdgpu_device_suspend(struct drm_device *dev, bool
> notify_clients)
> return 0;
> }
>
> +static int amdgpu_device_update_xgmi_nodes(struct amdgpu_device *adev)
> +{
> + int r = 0;
> + /* Get xgmi info again for sriov to detect device changes */
General coding style: Don't initialize return values if not necessary and add
an empty line between declaration and code.
> + if (amdgpu_sriov_vf(adev) &&
> + !(adev->flags & AMD_IS_APU) &&
> + adev->gmc.xgmi.supported &&
> + !adev->gmc.xgmi.connected_to_cpu) {
> + adev->gmc.xgmi.prev_physical_node_id =
> adev->gmc.xgmi.physical_node_id;
> + r = adev->gfxhub.funcs->get_xgmi_info(adev);
> + if (r)
> + return r;
> +
> + adev->gmc.xgmi.physical_node_id_changed =
> + adev->gmc.xgmi.physical_node_id !=
> adev->gmc.xgmi.prev_physical_node_id;
> + dev_info(adev->dev, "xgmi node, old id %d, new id %d\n",
> + adev->gmc.xgmi.prev_physical_node_id,
> adev->gmc.xgmi.physical_node_id);
> + }
> + return 0;
> +}
> +
> +
> /**
> * amdgpu_device_resume - initiate device resume
> *
> @@ -5117,6 +5139,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool
> notify_clients)
> r = amdgpu_virt_request_full_gpu(adev, true);
> if (r)
> return r;
> + r = amdgpu_device_update_xgmi_nodes(adev);
> + if (r)
> + return r;
> }
>
> if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index ecb74ccf1d90..5b60d714e089 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -1288,6 +1288,8 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device
> *adev,
>
> refresh = (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) &&
> (adev->gmc.reset_flags & AMDGPU_GMC_INIT_RESET_NPS);
> + if (adev->gmc.xgmi.physical_node_id_changed)
> + refresh = true;
> ret = amdgpu_discovery_get_nps_info(adev, &nps_type, &ranges,
> &range_cnt, refresh);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
> index 32dabba4062f..3d5f01a1b657 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
> @@ -89,6 +89,8 @@ struct amdgpu_xgmi {
> u64 node_segment_size;
> /* physical node (0-3) */
> unsigned physical_node_id;
> + unsigned prev_physical_node_id;
> + bool physical_node_id_changed;
Please drop that.
> /* number of nodes (0-4) */
> unsigned num_physical_nodes;
> /* gpu list in the same hive */
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 8d3560314e5b..7c7a9fe6be6d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -2515,6 +2515,14 @@ static int gmc_v9_0_resume(struct amdgpu_ip_block
> *ip_block)
> struct amdgpu_device *adev = ip_block->adev;
> int r;
>
> + /* Update MC configuration if XGMI physical node id has changed for
> dGPU. */
> + if (adev->gmc.xgmi.physical_node_id_changed) {
> + r = gmc_v9_0_mc_init(adev);
> + if (r)
> + return r;
> + gmc_v9_0_init_sw_mem_ranges(adev, adev->gmc.mem_partitions);
> + }
> +
Just always update that on resume.
Regards,
Christian.
> /* If a reset is done for NPS mode switch, read the memory range
> * information again.
> */
