drm/amd: Disable S/G for APUs when 64GB or more host memory

Users report a white flickering screen on multiple systems that
is tied to having 64GB or more memory.  When S/G is enabled pages
will get pinned to both VRAM carve out and system RAM leading to
this.

Until it can be fixed properly, disable S/G when 64GB of memory or
more is detected.  This will force pages to be pinned into VRAM.
This should fix white screen flickers but if VRAM pressure is
encountered may lead to black screens.  It's a trade-off for now.

Fixes: 81d0bcf9 ("drm/amdgpu: make display pinning more flexible (v2)")
Cc: Hamza Mahfooz <Hamza.Mahfooz@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: <stable@vger.kernel.org> # 6.1.y: bf0207e1 ("drm/amdgpu: add S/G display parameter")
Cc: <stable@vger.kernel.org> # 6.4.y
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2735
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1294,6 +1294,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev);
 bool amdgpu_device_pcie_dynamic_switching_supported(void);
 bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
 bool amdgpu_device_aspm_support_quirk(void);

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -1296,6 +1296,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 	return true;
 }
 
+/*
+ * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
+ * Disable S/G on such systems until we have a proper fix.
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
+ */
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
+{
+	switch (amdgpu_sg_display) {
+	case -1:
+		break;
+	case 0:
+		return false;
+	case 1:
+		return true;
+	default:
+		return false;
+	}
+	if ((totalram_pages() << (PAGE_SHIFT - 10)) +
+	    (adev->gmc.real_vram_size / 1024) >= 64000000) {
+		DRM_WARN("Disabling S/G due to >=64GB RAM\n");
+		return false;
+	}
+	return true;
+}
+
 /*
  * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
  * speed switching. Until we have confirmation from Intel that a specific host

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1639,9 +1639,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		}
 		break;
 	}
-	if (init_data.flags.gpu_vm_support &&
-	    (amdgpu_sg_display == 0))
-		init_data.flags.gpu_vm_support = false;
+	if (init_data.flags.gpu_vm_support)
+		init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev);
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;