Merge tag 'amd-drm-next-5.13-2021-03-23' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.13-2021-03-23:

amdgpu:
- Debugfs cleanup
- Various cleanups and spelling fixes
- Flexible array cleanups
- Initial AMD Freesync HDMI
- Display fixes
- 10bpc dithering improvements
- Display ASSR support
- Clean up and unify powerplay and swsmu interfaces
- Vangogh fixes
- Add SMU gfx busy queues for RV/PCO
- PCIE DPM fixes
- S0ix fixes
- GPU metrics data fixes
- DCN secure display support
- Backlight type override
- Add initial support for Aldebaran
- RAS fixes
- Prime fixes for A+A systems
- Reset fixes
- Initial resource cursor support
- Drop legacy IO BAR requirements
- Various power fixes

amdkfd:
- MMU notifier fixes
- APU fixes

radeon:
- Debugfs cleanups
- Flexible array cleanups

UAPI:
- amdgpu: Add a new INFO ioctl interface to query video capabilities
  rather than hardcoding them in userspace.  This allows us to provide
  fine grained asic capabilities (e.g., if a particular part is
  bandwidth limited, we can limit the capabilities).  Proposed userspace:
  https://gitlab.freedesktop.org/leoliu/drm/-/commits/info_video_caps
  https://gitlab.freedesktop.org/leoliu/mesa/-/commits/info_video_caps
- amdkfd: bump the driver version.  There was a problem with reporting
  some RAS features on older versions of the driver. Proposed userspace:
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/7cdd63475c36bb9f49bb960f90f9a8cdb7e80a21

Danvet: A bunch of conflicts all over, but it seems to compile ... I
did put the call to dc_allow_idle_optimizations() on a single line
since it looked a bit too jarring to be left alone.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324040147.1990338-1-alexander.deucher@amd.com

1 files changed, 13 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 659b385b27b5..33f748e5bbfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -468,15 +468,22 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
 }
 
 
+/*
+ * NOTE psp_xgmi_node_info.num_hops layout is as follows:
+ * num_hops[7:6] = link type (0 = xGMI2, 1 = xGMI3, 2/3 = reserved)
+ * num_hops[5:3] = reserved
+ * num_hops[2:0] = number of hops
+ */
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 		struct amdgpu_device *peer_adev)
 {
 	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	uint8_t num_hops_mask = 0x7;
 	int i;
 
 	for (i = 0 ; i < top->num_nodes; ++i)
 		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
-			return top->nodes[i].num_hops;
+			return top->nodes[i].num_hops & num_hops_mask;
 	return	-EINVAL;
 }
 
@@ -492,7 +499,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.supported)
 		return 0;
 
-	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+	if (!adev->gmc.xgmi.pending_reset &&
+	    amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
 		ret = psp_xgmi_initialize(&adev->psp);
 		if (ret) {
 			dev_err(adev->dev,
@@ -538,7 +546,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 
 	task_barrier_add_task(&hive->tb);
 
-	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+	if (!adev->gmc.xgmi.pending_reset &&
+	    amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			/* update node list for other device in the hive */
 			if (tmp_adev != adev) {
@@ -567,7 +576,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		}
 	}
 
-	if (!ret)
+	if (!ret && !adev->gmc.xgmi.pending_reset)
 		ret = amdgpu_xgmi_sysfs_add_dev_info(adev, hive);
 
 exit_unlock: