Merge tag 'drm-fixes-2022-08-26-1' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly fixes, lots of amdgpu fixes mostly for IP blocks introduced in
  6.0-rc1, otherwise vc4, nouveau fixes.

  gem:
   - Fix handle release leak

  nouveau:
   - Fix fencing when moving BO

  vc4:
   - HDMI fixes

  amdgpu:
   - GFX 11.0 fixes
   - PSP XGMI handling fixes
   - GFX9 fix for compute-only IPs
   - Drop duplicated function call
   - Fix warning due to missing header
   - NBIO 7.7 fixes
   - DCN 3.1.4 fixes
   - SDMA 6.0 fixes
   - SMU 13.0 fixes
   - Arcturus GPUVM page table fix
   - MMHUB 1.0 fix

  amdkfd:
   - GC 10.3.7 fix

  radeon:
   - Delayed work flush fix"

* tag 'drm-fixes-2022-08-26-1' of git://anongit.freedesktop.org/drm/drm: (21 commits)
  drm/amdgpu: mmVM_L2_CNTL3 register not initialized correctly
  drm/amdgpu: add MGCG perfmon setting for gfx11
  drm/amdkfd: Fix isa version for the GC 10.3.7
  drm/amdgpu: Fix page table setup on Arcturus
  drm/amd/pm: update SMU 13.0.0 driver_if header
  drm/amdgpu: add sdma instance check for gfx11 CGCG
  drm/amd/display: enable PCON support for dcn314
  drm/amdgpu: enable NBIO IP v7.7.0 Clock Gating
  drm/amdgpu: add NBIO IP v7.7.0 Clock Gating support
  drm/amdgpu: add TX_POWER_CTRL_1 macro definitions for NBIO IP v7.7.0
  nouveau: explicitly wait on the fence in nouveau_bo_move_m2mf
  drm/radeon: add a force flush to delay work when radeon
  drm/amd/display: Include missing header
  drm/amdgpu: Remove the additional kfd pre reset call for sriov
  drm/amdgpu: Check num_gfx_rings for gfx v9_0 rb setup.
  drm/amdgpu: fix hive reference leak when adding xgmi device
  drm/amdgpu: Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini
  drm/amdgpu: enable GFXOFF allow control for GC IP v11.0.1
  drm/gem: Fix GEM handle release errors
  drm/vc4: hdmi: Rework power up
  ...

24 files changed, 206 insertions, 82 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e8a0b19b7398..f095a2513aff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2456,12 +2456,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!hive->reset_domain ||
 			    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 				r = -ENOENT;
+				amdgpu_put_xgmi_hive(hive);
 				goto init_failed;
 			}
 
 			/* Drop the early temporary reset domain we created for device */
 			amdgpu_reset_put_reset_domain(adev->reset_domain);
 			adev->reset_domain = hive->reset_domain;
+			amdgpu_put_xgmi_hive(hive);
 		}
 	}
 
@@ -4413,8 +4415,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 retry:
 	amdgpu_amdkfd_pre_reset(adev);
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	if (from_hypervisor)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index b067ce45d226..1036446abc30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2641,6 +2641,9 @@ static int psp_hw_fini(void *handle)
 		psp_rap_terminate(psp);
 		psp_dtm_terminate(psp);
 		psp_hdcp_terminate(psp);
+
+		if (adev->gmc.xgmi.num_physical_nodes > 1)
+			psp_xgmi_terminate(psp);
 	}
 
 	psp_asd_terminate(psp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 1b108d03e785..f2aebbf3fbe3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -742,7 +742,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		amdgpu_put_xgmi_hive(hive);
 	}
 
-	return psp_xgmi_terminate(&adev->psp);
+	return 0;
 }
 
 static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 158d87e6805d..f6b1bb40e503 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -131,6 +131,8 @@ static void gfx_v11_0_ring_invalidate_tlbs(struct amdgpu_ring *ring,
 					   bool all_hub, uint8_t dst_sel);
 static void gfx_v11_0_set_safe_mode(struct amdgpu_device *adev);
 static void gfx_v11_0_unset_safe_mode(struct amdgpu_device *adev);
+static void gfx_v11_0_update_perf_clk(struct amdgpu_device *adev,
+				      bool enable);
 
 static void gfx11_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
@@ -1139,6 +1141,7 @@ static const struct amdgpu_gfx_funcs gfx_v11_0_gfx_funcs = {
 	.read_wave_vgprs = &gfx_v11_0_read_wave_vgprs,
 	.select_me_pipe_q = &gfx_v11_0_select_me_pipe_q,
 	.init_spm_golden = &gfx_v11_0_init_spm_golden_registers,
+	.update_perfmon_mgcg = &gfx_v11_0_update_perf_clk,
 };
 
 static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev)
@@ -5182,9 +5185,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 		data = REG_SET_FIELD(data, SDMA0_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
 		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
 
-		data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-		data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
-		WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
+		if (adev->sdma.num_instances > 1) {
+			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+			data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
+			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		}
 	} else {
 		/* Program RLC_CGCG_CGLS_CTRL */
 		def = data = RREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL);
@@ -5213,9 +5219,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 		data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
 		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
 
-		data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-		data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-		WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
+		if (adev->sdma.num_instances > 1) {
+			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+			data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
+			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		}
 	}
 }
 
@@ -5328,8 +5337,7 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 		break;
 	case IP_VERSION(11, 0, 1):
 		gfx_v11_cntl_pg(adev, enable);
-		/* TODO: Enable this when GFXOFF is ready */
-		// amdgpu_gfx_off_ctrl(adev, enable);
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index c6e0f9313a7f..fc9c1043244c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2587,7 +2587,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v9_0_tiling_mode_table_init(adev);
 
-	gfx_v9_0_setup_rb(adev);
+	if (adev->gfx.num_gfx_rings)
+		gfx_v9_0_setup_rb(adev);
 	gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 	adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 3f44a099c52a..3e51e773f92b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
 	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
 
+	tmp = mmVM_L2_CNTL3_DEFAULT;
 	if (adev->gmc.translate_further) {
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 6e0145b2b408..445cb06b9d26 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -295,9 +295,17 @@ static void mmhub_v9_4_disable_identity_aperture(struct amdgpu_device *adev,
 static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
+	unsigned int num_level, block_size;
 	uint32_t tmp;
 	int i;
 
+	num_level = adev->vm_manager.num_level;
+	block_size = adev->vm_manager.block_size;
+	if (adev->gmc.translate_further)
+		num_level -= 1;
+	else
+		block_size -= 9;
+
 	for (i = 0; i <= 14; i++) {
 		tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i);
@@ -305,7 +313,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    ENABLE_CONTEXT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    PAGE_TABLE_DEPTH,
-				    adev->vm_manager.num_level);
+				    num_level);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
@@ -323,7 +331,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    PAGE_TABLE_BLOCK_SIZE,
-				    adev->vm_manager.block_size - 9);
+				    block_size);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index 01e8288d09a8..1dc95ef21da6 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -247,6 +247,81 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
 
 }
 
+static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						       bool enable)
+{
+	uint32_t def, data;
+
+	if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG))
+		return;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL);
+	if (enable) {
+		data |= (BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	} else {
+		data &= ~(BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	}
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL, data);
+}
+
+static void nbio_v7_7_update_medium_grain_light_sleep(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t def, data;
+
+	if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS))
+		return;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2);
+	if (enable)
+		data |= BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK;
+	else
+		data &= ~BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK;
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2, data);
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1);
+	if (enable) {
+		data |= (BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK |
+			BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK);
+	} else {
+		data &= ~(BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK |
+			BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK);
+	}
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1, data);
+}
+
+static void nbio_v7_7_get_clockgating_state(struct amdgpu_device *adev,
+					    u64 *flags)
+{
+	uint32_t data;
+
+	/* AMD_CG_SUPPORT_BIF_MGCG */
+	data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL);
+	if (data & BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_MGCG;
+
+	/* AMD_CG_SUPPORT_BIF_LS */
+	data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2);
+	if (data & BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_LS;
+}
+
 const struct amdgpu_nbio_funcs nbio_v7_7_funcs = {
 	.get_hdp_flush_req_offset = nbio_v7_7_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v7_7_get_hdp_flush_done_offset,
@@ -262,6 +337,9 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = {
 	.enable_doorbell_aperture = nbio_v7_7_enable_doorbell_aperture,
 	.enable_doorbell_selfring_aperture = nbio_v7_7_enable_doorbell_selfring_aperture,
 	.ih_doorbell_range = nbio_v7_7_ih_doorbell_range,
+	.update_medium_grain_clock_gating = nbio_v7_7_update_medium_grain_clock_gating,
+	.update_medium_grain_light_sleep = nbio_v7_7_update_medium_grain_light_sleep,
+	.get_clockgating_state = nbio_v7_7_get_clockgating_state,
 	.ih_control = nbio_v7_7_ih_control,
 	.init_registers = nbio_v7_7_init_registers,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 1ff7fc7bb340..55284b24f113 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -494,6 +494,20 @@ static void soc21_pre_asic_init(struct amdgpu_device *adev)
 {
 }
 
+static int soc21_update_umd_stable_pstate(struct amdgpu_device *adev,
+					  bool enter)
+{
+	if (enter)
+		amdgpu_gfx_rlc_enter_safe_mode(adev);
+	else
+		amdgpu_gfx_rlc_exit_safe_mode(adev);
+
+	if (adev->gfx.funcs->update_perfmon_mgcg)
+		adev->gfx.funcs->update_perfmon_mgcg(adev, !enter);
+
+	return 0;
+}
+
 static const struct amdgpu_asic_funcs soc21_asic_funcs =
 {
 	.read_disabled_bios = &soc21_read_disabled_bios,
@@ -513,6 +527,7 @@ static const struct amdgpu_asic_funcs soc21_asic_funcs =
 	.supports_baco = &amdgpu_dpm_is_baco_supported,
 	.pre_asic_init = &soc21_pre_asic_init,
 	.query_video_codecs = &soc21_query_video_codecs,
+	.update_umd_stable_pstate = &soc21_update_umd_stable_pstate,
 };
 
 static int soc21_common_early_init(void *handle)
@@ -603,6 +618,8 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
 			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags =
@@ -702,6 +719,7 @@ static int soc21_common_set_clockgating_state(void *handle,
 	switch (adev->ip_versions[NBIO_HWIP][0]) {
 	case IP_VERSION(4, 3, 0):
 	case IP_VERSION(4, 3, 1):
+	case IP_VERSION(7, 7, 0):
 		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
@@ -709,10 +727,6 @@ static int soc21_common_set_clockgating_state(void *handle,
 		adev->hdp.funcs->update_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		break;
-	case IP_VERSION(7, 7, 0):
-		adev->hdp.funcs->update_clock_gating(adev,
-				state == AMD_CG_STATE_GATE);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 357298e69495..22c0929d410b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -382,12 +382,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 				f2g = &gfx_v10_3_kfd2kgd;
 			break;
 		case IP_VERSION(10, 3, 6):
-			gfx_target_version = 100306;
-			if (!vf)
-				f2g = &gfx_v10_3_kfd2kgd;
-			break;
 		case IP_VERSION(10, 3, 7):
-			gfx_target_version = 100307;
+			gfx_target_version = 100306;
 			if (!vf)
 				f2g = &gfx_v10_3_kfd2kgd;
 			break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index fca7cf9dbaee..987bde4dca3d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -34,6 +34,7 @@
 #include "dal_asic_id.h"
 #include "amdgpu_display.h"
 #include "amdgpu_dm_trace.h"
+#include "amdgpu_dm_plane.h"
 #include "gc/gc_11_0_0_offset.h"
 #include "gc/gc_11_0_0_sh_mask.h"
 
@@ -149,12 +150,12 @@ static void add_modifier(uint64_t **mods, uint64_t *size, uint64_t *cap, uint64_
 	*size += 1;
 }
 
-bool modifier_has_dcc(uint64_t modifier)
+static bool modifier_has_dcc(uint64_t modifier)
 {
 	return IS_AMD_FMT_MOD(modifier) && AMD_FMT_MOD_GET(DCC, modifier);
 }
 
-unsigned modifier_gfx9_swizzle_mode(uint64_t modifier)
+static unsigned modifier_gfx9_swizzle_mode(uint64_t modifier)
 {
 	if (modifier == DRM_FORMAT_MOD_LINEAR)
 		return 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
index 95168c2cfa6f..286981a2dd40 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
@@ -36,17 +36,9 @@ int fill_dc_scaling_info(struct amdgpu_device *adev,
 			 const struct drm_plane_state *state,
 			 struct dc_scaling_info *scaling_info);
 
-void get_min_max_dc_plane_scaling(struct drm_device *dev,
-				  struct drm_framebuffer *fb,
-				  int *min_downscale, int *max_upscale);
-
 int dm_plane_helper_check_state(struct drm_plane_state *state,
 				struct drm_crtc_state *new_crtc_state);
 
-bool modifier_has_dcc(uint64_t modifier);
-
-unsigned int modifier_gfx9_swizzle_mode(uint64_t modifier);
-
 int fill_plane_buffer_attributes(struct amdgpu_device *adev,
 				 const struct amdgpu_framebuffer *afb,
 				 const enum surface_pixel_format format,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 85f32206a766..3a9e3870b3a9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -1750,6 +1750,7 @@ static bool dcn314_resource_construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.dp_hpo = true;
+	dc->caps.dp_hdmi21_pcon_support = true;
 	dc->caps.edp_dsc_support = true;
 	dc->caps.extended_aux_timeout_support = true;
 	dc->caps.dmcub_support = true;
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
index 2ed95790a600..cf8d60c4df1b 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
@@ -15243,6 +15243,8 @@
 #define regBIF0_PCIE_TX_TRACKING_ADDR_HI_BASE_IDX                                                       5
 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS                                                            0x420186
 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS_BASE_IDX                                                   5
+#define regBIF0_PCIE_TX_POWER_CTRL_1                                                                    0x420187
+#define regBIF0_PCIE_TX_POWER_CTRL_1_BASE_IDX                                                           5
 #define regBIF0_PCIE_TX_CTRL_4                                                                          0x42018b
 #define regBIF0_PCIE_TX_CTRL_4_BASE_IDX                                                                 5
 #define regBIF0_PCIE_TX_STATUS                                                                          0x420194
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
index eb62a18fcc48..3d60c9e92548 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
@@ -85627,6 +85627,19 @@
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_PORT_MASK                                              0x0000000EL
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_UNIT_ID_MASK                                           0x00007F00L
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_STATUS_VALID_MASK                                      0x00008000L
+//BIF0_PCIE_TX_POWER_CTRL_1
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN__SHIFT                                                       0x0
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN__SHIFT                                                       0x1
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN__SHIFT                                                       0x2
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN__SHIFT                                                    0x3
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN__SHIFT                                                    0x4
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN__SHIFT                                                    0x5
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK                                                         0x00000001L
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN_MASK                                                         0x00000002L
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN_MASK                                                         0x00000004L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK                                                      0x00000008L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN_MASK                                                      0x00000010L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN_MASK                                                      0x00000020L
 //BIF0_PCIE_TX_CTRL_4
 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW__SHIFT                                                 0x0
 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW_MASK                                                   0x0000000FL
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
index 78620b0bd279..f745cd8f1ab7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
@@ -24,12 +24,8 @@
 #ifndef SMU13_DRIVER_IF_V13_0_0_H
 #define SMU13_DRIVER_IF_V13_0_0_H
 
-// *** IMPORTANT ***
-// PMFW TEAM: Always increment the interface version on any change to this file
-#define SMU13_DRIVER_IF_VERSION  0x23
-
 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x1D
+#define PPTABLE_VERSION 0x22
 
 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -1193,8 +1189,17 @@ typedef struct {
   // SECTION: Advanced Options
   uint32_t          DebugOverrides;
 
+  // Section: Total Board Power idle vs active coefficients
+  uint8_t     TotalBoardPowerSupport;
+  uint8_t     TotalBoardPowerPadding[3];
+
+  int16_t     TotalIdleBoardPowerM;
+  int16_t     TotalIdleBoardPowerB;
+  int16_t     TotalBoardPowerM;
+  int16_t     TotalBoardPowerB;
+
   // SECTION: Sku Reserved
-  uint32_t         Spare[64];
+  uint32_t         Spare[61];
 
   // Padding for MMHUB - do not modify this
   uint32_t     MmHubPadding[8];
@@ -1259,7 +1264,8 @@ typedef struct {
   // SECTION: Clock Spread Spectrum
 
   // UCLK Spread Spectrum
-  uint16_t     UclkSpreadPadding;
+  uint8_t      UclkTrainingModeSpreadPercent;
+  uint8_t      UclkSpreadPadding;
   uint16_t     UclkSpreadFreq;      // kHz
 
   // UCLK Spread Spectrum
@@ -1272,11 +1278,7 @@ typedef struct {
 
   // Section: Memory Config
   uint8_t      DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e
-  uint8_t      PaddingMem1[3];
-
-  // Section: Total Board Power
-  uint16_t     TotalBoardPower;     //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power
-  uint16_t     BoardPowerPadding;
+  uint8_t      PaddingMem1[7];
 
   // SECTION: UMC feature flags
   uint8_t      HsrEnabled;
@@ -1375,8 +1377,11 @@ typedef struct {
   uint16_t Vcn1ActivityPercentage  ;
 
   uint32_t EnergyAccumulator;
-  uint16_t AverageSocketPower    ;
+  uint16_t AverageSocketPower;
+  uint16_t AverageTotalBoardPower;
+
   uint16_t AvgTemperature[TEMP_COUNT];
+  uint16_t TempPadding;
 
   uint8_t  PcieRate               ;
   uint8_t  PcieWidth              ;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 6fe2fe92ebd7..ac308e72241a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -30,7 +30,7 @@
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2C
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2E
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
 
 #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500  //500ms
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 86d670c71286..ad068865ba20 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -168,21 +168,6 @@ void drm_gem_private_object_init(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_gem_private_object_init);
 
-static void
-drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
-{
-	/*
-	 * Note: obj->dma_buf can't disappear as long as we still hold a
-	 * handle reference in obj->handle_count.
-	 */
-	mutex_lock(&filp->prime.lock);
-	if (obj->dma_buf) {
-		drm_prime_remove_buf_handle_locked(&filp->prime,
-						   obj->dma_buf);
-	}
-	mutex_unlock(&filp->prime.lock);
-}
-
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
  * @obj: GEM object to clean up.
@@ -253,7 +238,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	if (obj->funcs->close)
 		obj->funcs->close(obj, file_priv);
 
-	drm_gem_remove_prime_handles(obj, file_priv);
+	drm_prime_remove_buf_handle(&file_priv->prime, id);
 	drm_vma_node_revoke(&obj->vma_node, file_priv);
 
 	drm_gem_object_handle_put_unlocked(obj);
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 1fbbc19f1ac0..7bb98e6a446d 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
 void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf);
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle);
 
 /* drm_drv.c */
 struct drm_minor *drm_minor_acquire(unsigned int minor_id);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index a3f180653b8b..eb09e86044c6 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 	return -ENOENT;
 }
 
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf)
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle)
 {
 	struct rb_node *rb;
 
-	rb = prime_fpriv->dmabufs.rb_node;
+	mutex_lock(&prime_fpriv->lock);
+
+	rb = prime_fpriv->handles.rb_node;
 	while (rb) {
 		struct drm_prime_member *member;
 
-		member = rb_entry(rb, struct drm_prime_member, dmabuf_rb);
-		if (member->dma_buf == dma_buf) {
+		member = rb_entry(rb, struct drm_prime_member, handle_rb);
+		if (member->handle == handle) {
 			rb_erase(&member->handle_rb, &prime_fpriv->handles);
 			rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs);
 
-			dma_buf_put(dma_buf);
+			dma_buf_put(member->dma_buf);
 			kfree(member);
-			return;
-		} else if (member->dma_buf < dma_buf) {
+			break;
+		} else if (member->handle < handle) {
 			rb = rb->rb_right;
 		} else {
 			rb = rb->rb_left;
 		}
 	}
+
+	mutex_unlock(&prime_fpriv->lock);
 }
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 05076e530e7d..e29175e4b44c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -820,6 +820,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
+				/* TODO: figure out a better solution here
+				 *
+				 * wait on the fence here explicitly as going through
+				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+				 *
+				 * Without this the operation can timeout and we'll fallback to a
+				 * software copy, which might take several minutes to finish.
+				 */
+				nouveau_fence_wait(fence, false, false);
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
 								evict, false,
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 2b12389f841a..ee0165687239 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1605,6 +1605,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 		if (r) {
 			/* delay GPU reset to resume */
 			radeon_fence_driver_force_completion(rdev, i);
+		} else {
+			/* finish executing delayed work */
+			flush_delayed_work(&rdev->fence_drv[i].lockup_work);
 		}
 	}
 
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 061be9a6619d..b0f3117102ca 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -8,6 +8,7 @@ config DRM_VC4
 	depends on DRM
 	depends on SND && SND_SOC
 	depends on COMMON_CLK
+	depends on PM
 	select DRM_DISPLAY_HDMI_HELPER
 	select DRM_DISPLAY_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 592c3b5d03e6..1e5f68704d7d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -2855,7 +2855,7 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-static int __maybe_unused vc4_hdmi_runtime_suspend(struct device *dev)
+static int vc4_hdmi_runtime_suspend(struct device *dev)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
@@ -2972,17 +2972,15 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 			vc4_hdmi->disable_4kp60 = true;
 	}
 
+	pm_runtime_enable(dev);
+
 	/*
-	 * We need to have the device powered up at this point to call
-	 * our reset hook and for the CEC init.
+	 *  We need to have the device powered up at this point to call
+	 *  our reset hook and for the CEC init.
 	 */
-	ret = vc4_hdmi_runtime_resume(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
-		goto err_put_ddc;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+		goto err_disable_runtime_pm;
 
 	if ((of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi0") ||
 	     of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi1")) &&
@@ -3028,6 +3026,7 @@ err_destroy_conn:
 err_destroy_encoder:
 	drm_encoder_cleanup(encoder);
 	pm_runtime_put_sync(dev);
+err_disable_runtime_pm:
 	pm_runtime_disable(dev);
 err_put_ddc:
 	put_device(&vc4_hdmi->ddc->dev);