[RFC v1 1/2] drm/amdgpu: update cached vram base addresses on resume

[Jiang Liu]

When resume on a different SR-IOV vGPU device, the VRAM base addresses
may have changed. So we need to update those cached addresses.

Signed-off-by: Jiang Liu <gerry at linux.alibaba.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 15 +++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h    |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c     |  7 +++++++
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c      |  6 ++++++
 4 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 36053b3d48b3..c9df54127417 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4970,6 +4970,21 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	/* Get xgmi info again for sriov to detect device changes */
+	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;
+		if (adev->gmc.xgmi.physical_node_id != adev->gmc.xgmi.prev_physical_node_id)
+			adev->gmc.xgmi.physical_node_id_changed = true;
+		else
+			adev->gmc.xgmi.physical_node_id_changed = false;
+	}
+
 	if (adev->in_s0ix)
 		amdgpu_dpm_gfx_state_change(adev, sGpuChangeState_D0Entry);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 459a30fe239f..a32ab7b61cfd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -184,10 +184,12 @@ struct amdgpu_xgmi {
 	u64 hive_id;
 	/* fixed per family */
 	u64 node_segment_size;
-	/* physical node (0-3) */
-	unsigned physical_node_id;
 	/* number of nodes (0-4) */
 	unsigned num_physical_nodes;
+	/* physical node (0-3) */
+	unsigned physical_node_id;
+	unsigned prev_physical_node_id;
+	bool physical_node_id_changed;
 	/* gpu list in the same hive */
 	struct list_head head;
 	bool supported;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 9bedca9a79c6..94d86e9a08e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1065,8 +1065,15 @@ static int gmc_v10_0_suspend(struct amdgpu_ip_block *ip_block)
 
 static int gmc_v10_0_resume(struct amdgpu_ip_block *ip_block)
 {
+	struct amdgpu_device *adev = ip_block->adev;
 	int r;
 
+	if (adev->gmc.xgmi.physical_node_id_changed) {
+		r = gmc_v10_0_mc_init(adev);
+		if (r)
+			return r;
+	}
+
 	r = gmc_v10_0_hw_init(ip_block);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 291549765c38..db118e07efde 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2532,6 +2532,12 @@ static int gmc_v9_0_resume(struct amdgpu_ip_block *ip_block)
 		adev->gmc.reset_flags &= ~AMDGPU_GMC_INIT_RESET_NPS;
 	}
 
+	if (adev->gmc.xgmi.physical_node_id_changed) {
+		r = gmc_v9_0_mc_init(adev);
+		if (r)
+			return r;
+	}
+
 	r = gmc_v9_0_hw_init(ip_block);
 	if (r)
 		return r;
-- 
2.43.5