Merge tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Merge window fixes, mostly amdgpu and xe, with a few other minor ones,
  all looks fairly normal,

  i915:
   - hdcp: Fix when the first read and write are retried

  xe:
   - Wake up waiters after wait condition set to true
   - Mark the preempt fence workqueue as reclaim
   - Update xe2 graphics name string
   - Fix a couple of guc submit races
   - Fix pat index usage in migrate
   - Ensure non-cached migrate pagetable bo mappings
   - Take a PM ref in the delayed snapshot capture worker

  amdgpu:
   - SMU 13.0.6 fixes
   - XGMI fixes
   - SMU 13.0.7 fixes
   - Misc code cleanups
   - Plane refcount fixes
   - DCN 4.0.1 fixes
   - DC power fixes
   - DTO fixes
   - NBIO 7.11 fixes
   - SMU 14.0.x fixes
   - Reset fixes
   - Enable DC on LoongArch
   - Sysfs hotplug warning fix
   - Misc small fixes
   - VCN 4.0.3 fix
   - Slab usage fix
   - Jpeg delayed work fix

  amdkfd:
   - wptr handling fixes

  radeon:
   - Use ttm_bo_move_null()
   - Constify struct pci_device_id
   - Fix spurious hotplug
   - HPD fix

  rockchip
   - fix 32-bit build"

* tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel: (48 commits)
  drm/xe: Take PM ref in delayed snapshot capture worker
  drm/xe/migrate: use XE_BO_FLAG_PAGETABLE
  drm/xe/migrate: fix pat index usage
  drm/xe/guc_submit: fix race around suspend_pending
  drm/xe/guc_submit: fix race around pending_disable
  drm/xe: Update xe2_graphics name string
  drm/rockchip: avoid 64-bit division
  Revert "drm/radeon: Delay Connector detecting when HPD singals is unstable"
  drm/amdgpu/jpeg: cancel the jpeg worker
  drm/amdgpu: fix usage slab after free
  drm/amdgpu/vcn: reset fw_shared when VCPU buffers corrupted on vcn v4.0.3
  drm/amdgpu: Fix sysfs warning when hotplugging
  drm/amdgpu: Add sysfs interface for vcn reset mask
  drm/amdgpu/gmc7: fix wait_for_idle callers
  drm/amd/pm: Remove arcturus min power limit
  drm/amd/pm: skip setting the power source on smu v14.0.2/3
  drm/amd/pm: disable pcie speed switching on Intel platform for smu v14.0.2/3
  drm/amdkfd: Use the correct wptr size
  drm/xe: Mark preempt fence workqueue as reclaim
  drm/xe/ufence: Wake up waiters after setting ufence->signalled
  ...

1 files changed, 41 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index b47422b0b5b1..74b4349e345a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -40,6 +40,11 @@
 #define smnPCS_GOPX1_PCS_ERROR_STATUS    0x12200210
 #define smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK      0x12200218
 
+#define XGMI_STATE_DISABLE                      0xD1
+#define XGMI_STATE_LS0                          0x81
+#define XGMI_LINK_ACTIVE			1
+#define XGMI_LINK_INACTIVE			0
+
 static DEFINE_MUTEX(xgmi_mutex);
 
 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4
@@ -289,6 +294,42 @@ static const struct amdgpu_pcs_ras_field xgmi3x16_pcs_ras_fields[] = {
 	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxCMDPktErr)},
 };
 
+static u32 xgmi_v6_4_get_link_status(struct amdgpu_device *adev, int global_link_num)
+{
+	const u32 smnpcs_xgmi3x16_pcs_state_hist1 = 0x11a00070;
+	const int xgmi_inst = 2;
+	u32 link_inst;
+	u64 addr;
+
+	link_inst = global_link_num % xgmi_inst;
+
+	addr = (smnpcs_xgmi3x16_pcs_state_hist1 | (link_inst << 20)) +
+		adev->asic_funcs->encode_ext_smn_addressing(global_link_num / xgmi_inst);
+
+	return RREG32_PCIE_EXT(addr);
+}
+
+int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num)
+{
+	u32 xgmi_state_reg_val;
+
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		xgmi_state_reg_val = xgmi_v6_4_get_link_status(adev, global_link_num);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if ((xgmi_state_reg_val & 0xFF) == XGMI_STATE_DISABLE)
+		return -ENOLINK;
+
+	if ((xgmi_state_reg_val & 0xFF) == XGMI_STATE_LS0)
+		return XGMI_LINK_ACTIVE;
+
+	return XGMI_LINK_INACTIVE;
+}
+
 /**
  * DOC: AMDGPU XGMI Support
  *