Merge tag 'drm-next-5.5-2019-11-22' of git://people.freedesktop.org/~agd5f/linux into drm-next

drm-next-5.5-2019-11-22:

amdgpu:
- Fix bad DMA on some PPC platforms
- MMHUB fix for powergating
- BACO fix for Navi
- Misc raven fixes
- Enable vbios fetch directly from rom on navi
- debugfs fix for DC
- SR-IOV fixes for arcturus
- Misc power fixes

radeon:
- Fix bad DMA on some PPC platforms

Signed-off-by: Dave Airlie <[e-mail]>
From: Alex Deucher <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

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

···
 	int r;
 
 	DRM_INFO("amdgpu: finishing device.\n");
-	adev->shutdown = true;
-
 	flush_delayed_work(&adev->delayed_init_work);
+	adev->shutdown = true;
 
 	/* disable all interrupts */
 	amdgpu_irq_disable_all(adev);
···
 		adev->firmware.gpu_info_fw = NULL;
 	}
 	adev->accel_working = false;
-	cancel_delayed_work_sync(&adev->delayed_init_work);
 	/* free i2c buses */
 	if (!amdgpu_device_has_dc_support(adev))
 		amdgpu_i2c_fini(adev);

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

···
 	 * Also, don't allow GTT domain if the BO doens't have USWC falg set.
 	 */
 	if (adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN &&
+	    adev->asic_type < CHIP_RAVEN &&
 	    (adev->flags & AMD_IS_APU) &&
 	    (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
 	    amdgpu_bo_support_uswc(bo_flags) &&

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

···
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
-	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},

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

···
 	}
 
 	ring = &adev->gfx.kiq.ring;
-	if (adev->asic_type >= CHIP_NAVI10 && amdgpu_async_gfx_ring)
-		kfree(adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS]);
 	kfree(adev->gfx.mec.mqd_backup[AMDGPU_MAX_COMPUTE_RINGS]);
 	amdgpu_bo_free_kernel(&ring->mqd_obj,
 			      &ring->mqd_gpu_addr,

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

···
 	uint32_t			num_me;
 	uint32_t			num_pipe_per_me;
 	uint32_t			num_queue_per_pipe;
-	void				*mqd_backup[AMDGPU_MAX_GFX_RINGS + 1];
+	void				*mqd_backup[AMDGPU_MAX_GFX_RINGS];
 
 	/* These are the resources for which amdgpu takes ownership */
 	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_GFX_QUEUES);

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

···
 struct amdgpu_vmhub {
 	uint32_t	ctx0_ptb_addr_lo32;
 	uint32_t	ctx0_ptb_addr_hi32;
+	uint32_t	vm_inv_eng0_sem;
 	uint32_t	vm_inv_eng0_req;
 	uint32_t	vm_inv_eng0_ack;
 	uint32_t	vm_context0_cntl;

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

···
 			return -ENOMEM;
 		alloc_size = info->read_mmr_reg.count * sizeof(*regs);
 
-		for (i = 0; i < info->read_mmr_reg.count; i++)
+		amdgpu_gfx_off_ctrl(adev, false);
+		for (i = 0; i < info->read_mmr_reg.count; i++) {
 			if (amdgpu_asic_read_register(adev, se_num, sh_num,
 						      info->read_mmr_reg.dword_offset + i,
 						      &regs[i])) {
 				DRM_DEBUG_KMS("unallowed offset %#x\n",
 					      info->read_mmr_reg.dword_offset + i);
 				kfree(regs);
+				amdgpu_gfx_off_ctrl(adev, true);
 				return -EFAULT;
 			}
+		}
+		amdgpu_gfx_off_ctrl(adev, true);
 		n = copy_to_user(out, regs, min(size, alloc_size));
 		kfree(regs);
 		return n ? -EFAULT : 0;

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

···
 {
 	int ret;
 
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
 	if (!psp->ras.ras_initialized)
 		return 0;
 
···
 static int psp_ras_initialize(struct psp_context *psp)
 {
 	int ret;
+
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
 
 	if (!psp->adev->psp.ta_ras_ucode_size ||
 	    !psp->adev->psp.ta_ras_start_addr) {
···
 {
 	int ret;
 
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
 	if (!psp->adev->psp.ta_hdcp_ucode_size ||
 	    !psp->adev->psp.ta_hdcp_start_addr) {
 		dev_warn(psp->adev->dev, "HDCP: hdcp ta ucode is not available\n");
···
 static int psp_hdcp_terminate(struct psp_context *psp)
 {
 	int ret;
+
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
 
 	if (!psp->hdcp_context.hdcp_initialized)
 		return 0;
···
 {
 	int ret;
 
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
 	if (!psp->adev->psp.ta_dtm_ucode_size ||
 	    !psp->adev->psp.ta_dtm_start_addr) {
 		dev_warn(psp->adev->dev, "DTM: dtm ta ucode is not available\n");
···
 static int psp_dtm_terminate(struct psp_context *psp)
 {
 	int ret;
+
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
 
 	if (!psp->dtm_context.dtm_initialized)
 		return 0;
···
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA5
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA6
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA7
-		    || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G))
+                    || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM))
 			/*skip ucode loading in SRIOV VF */
 			continue;
 

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

···
 	    TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence),
 	    TP_ARGS(sched_job, fence),
 	    TP_STRUCT__entry(
-			     __string(ring, sched_job->base.sched->name);
+			     __string(ring, sched_job->base.sched->name)
 			     __field(uint64_t, id)
 			     __field(struct dma_fence *, fence)
 			     __field(uint64_t, ctx)

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

···
 	WREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0, tmp);
 }
 
-static void gfx_v10_0_init_csb(struct amdgpu_device *adev)
+static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 {
+	int r;
+
+	if (adev->in_gpu_reset) {
+		r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+		if (r)
+			return r;
+
+		r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj,
+				   (void **)&adev->gfx.rlc.cs_ptr);
+		if (!r) {
+			adev->gfx.rlc.funcs->get_csb_buffer(adev,
+					adev->gfx.rlc.cs_ptr);
+			amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
+		}
+
+		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+		if (r)
+			return r;
+	}
+
 	/* csib */
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
 		     adev->gfx.rlc.clear_state_gpu_addr >> 32);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO,
 		     adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
+
+	return 0;
 }
 
-static void gfx_v10_0_init_pg(struct amdgpu_device *adev)
+static int gfx_v10_0_init_pg(struct amdgpu_device *adev)
 {
 	int i;
+	int r;
 
-	gfx_v10_0_init_csb(adev);
+	r = gfx_v10_0_init_csb(adev);
+	if (r)
+		return r;
 
 	for (i = 0; i < adev->num_vmhubs; i++)
 		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
 	/* TODO: init power gating */
-	return;
+	return 0;
 }
 
 void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
···
 		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
 			return r;
-		gfx_v10_0_init_pg(adev);
+
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
 
 		/* enable RLC SRM */
 		gfx_v10_0_rlc_enable_srm(adev);
···
 				return r;
 		}
 
-		gfx_v10_0_init_pg(adev);
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
+
 		adev->gfx.rlc.funcs->start(adev);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) {
···
 	return 0;
 }
 
-static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
+static int gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 {
 	int i;
 	u32 tmp = RREG32_SOC15(GC, 0, mmCP_ME_CNTL);
···
 			adev->gfx.gfx_ring[i].sched.ready = false;
 	}
 	WREG32_SOC15(GC, 0, mmCP_ME_CNTL, tmp);
-	udelay(50);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (RREG32_SOC15(GC, 0, mmCP_STAT) == 0)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		DRM_ERROR("failed to %s cp gfx\n", enable ? "unhalt" : "halt");
+
+	return 0;
 }
 
 static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
···
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v10_gfx_mqd *mqd = ring->mqd_ptr;
+	int mqd_idx = ring - &adev->gfx.gfx_ring[0];
 
 	if (!adev->in_gpu_reset && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
···
 #endif
 		nv_grbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
-		if (adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS])
-			memcpy(adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS], mqd, sizeof(*mqd));
+		if (adev->gfx.me.mqd_backup[mqd_idx])
+			memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else if (adev->in_gpu_reset) {
 		/* reset mqd with the backup copy */
-		if (adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS])
-			memcpy(mqd, adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS], sizeof(*mqd));
+		if (adev->gfx.me.mqd_backup[mqd_idx])
+			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
 		adev->wb.wb[ring->wptr_offs] = 0;

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

···
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_4_ARCT, 0x3fffffff, 0xb90f5b1),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00),
 };
 
 static const u32 GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[] =
···
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			&&((adev->gfx.rlc_fw_version != 106 &&
+		/* Disable GFXOFF on original raven.  There are combinations
+		 * of sbios and platforms that are not stable.
+		 */
+		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+			 &&((adev->gfx.rlc_fw_version != 106 &&
 			     adev->gfx.rlc_fw_version < 531) ||
 			    (adev->gfx.rlc_fw_version == 53815) ||
 			    (adev->gfx.rlc_feature_version < 1) ||

drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c

···
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =

drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c

···
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =

drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c

···
 	const unsigned eng = 17;
 	unsigned int i;
 
+	spin_lock(&adev->gmc.invalidate_lock);
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1) {
+		for (i = 0; i < adev->usec_timeout; i++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (i >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
 	/*
···
 
 		udelay(1);
 	}
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
+	spin_unlock(&adev->gmc.invalidate_lock);
 
 	if (i < adev->usec_timeout)
 		return;
···
 	uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
···
 	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
 					    hub->vm_inv_eng0_ack + eng,
 					    req, 1 << vmid);
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
 
 	return pd_addr;
 }

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

···
 	}
 
 	spin_lock(&adev->gmc.invalidate_lock);
+
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1) {
+		for (j = 0; j < adev->usec_timeout; j++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (j >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
 	/*
···
 			break;
 		udelay(1);
 	}
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
 	spin_unlock(&adev->gmc.invalidate_lock);
+
 	if (j < adev->usec_timeout)
 		return;
 
···
 	uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
···
 	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
 					    hub->vm_inv_eng0_ack + eng,
 					    req, 1 << vmid);
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
 
 	return pd_addr;
 }

drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c

···
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =

drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c

···
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =

drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c

···
 			SOC15_REG_OFFSET(MMHUB, 0,
 			    mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) +
 			    i * MMHUB_INSTANCE_REGISTER_OFFSET;
+		hub[i]->vm_inv_eng0_sem =
+			SOC15_REG_OFFSET(MMHUB, 0,
+					 mmVML2VC0_VM_INVALIDATE_ENG0_SEM) +
+					 i * MMHUB_INSTANCE_REGISTER_OFFSET;
 		hub[i]->vm_inv_eng0_req =
 			SOC15_REG_OFFSET(MMHUB, 0,
 					 mmVML2VC0_VM_INVALIDATE_ENG0_REQ) +

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

···
 #include "gc/gc_10_1_0_sh_mask.h"
 #include "hdp/hdp_5_0_0_offset.h"
 #include "hdp/hdp_5_0_0_sh_mask.h"
+#include "smuio/smuio_11_0_0_offset.h"
 
 #include "soc15.h"
 #include "soc15_common.h"
···
 static bool nv_read_bios_from_rom(struct amdgpu_device *adev,
 				  u8 *bios, u32 length_bytes)
 {
-	/* TODO: will implement it when SMU header is available */
-	return false;
+	u32 *dw_ptr;
+	u32 i, length_dw;
+
+	if (bios == NULL)
+		return false;
+	if (length_bytes == 0)
+		return false;
+	/* APU vbios image is part of sbios image */
+	if (adev->flags & AMD_IS_APU)
+		return false;
+
+	dw_ptr = (u32 *)bios;
+	length_dw = ALIGN(length_bytes, 4) / 4;
+
+	/* set rom index to 0 */
+	WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0);
+	/* read out the rom data */
+	for (i = 0; i < length_dw; i++)
+		dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA));
+
+	return true;
 }
 
 static struct soc15_allowed_register_entry nv_allowed_read_registers[] = {

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

···
 	u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
 
 	si_ih_disable_interrupts(adev);
-	WREG32(INTERRUPT_CNTL2, adev->irq.ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, adev->dummy_page_addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	interrupt_cntl &= ~IH_DUMMY_RD_OVERRIDE;
 	interrupt_cntl &= ~IH_REQ_NONSNOOP_EN;

drivers/gpu/drm/amd/amdgpu/soc15.h

···
 #include "nbio_v7_0.h"
 #include "nbio_v7_4.h"
 
-#define SOC15_FLUSH_GPU_TLB_NUM_WREG		4
-#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	1
+#define SOC15_FLUSH_GPU_TLB_NUM_WREG		6
+#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	3
 
 extern const struct amd_ip_funcs soc15_common_ip_funcs;
 

drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring;
-	int i;
+	int i, j;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
···
 
 		ring->sched.ready = false;
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-			ring = &adev->vcn.inst[i].ring_enc[i];
+		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->sched.ready = false;
 		}
 

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

···
 	 */
 	if (adev->flags & AMD_IS_APU &&
 	    adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN)
+	    adev->asic_type < CHIP_RAVEN)
 		init_data.flags.gpu_vm_support = true;
 
 	if (amdgpu_dc_feature_mask & DC_FBC_MASK)

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

···
 #include "dc_link_ddc.h"
 
 #include "i2caux_interface.h"
-
+#if defined(CONFIG_DEBUG_FS)
+#include "amdgpu_dm_debugfs.h"
+#endif
 /* #define TRACE_DPCD */
 
 #ifdef TRACE_DPCD
···
 	struct amdgpu_dm_connector *amdgpu_dm_connector =
 		to_amdgpu_dm_connector(connector);
 	struct drm_dp_mst_port *port = amdgpu_dm_connector->port;
+
+#if defined(CONFIG_DEBUG_FS)
+	connector_debugfs_init(amdgpu_dm_connector);
+	amdgpu_dm_connector->debugfs_dpcd_address = 0;
+	amdgpu_dm_connector->debugfs_dpcd_size = 0;
+#endif
 
 	return drm_dp_mst_connector_late_register(connector, port);
 }

drivers/gpu/drm/amd/powerplay/amdgpu_smu.c

···
 	smu_table->power_play_table = smu_table->hardcode_pptable;
 	smu_table->power_play_table_size = size;
 
+	/*
+	 * Special hw_fini action(for Navi1x, the DPMs disablement will be
+	 * skipped) may be needed for custom pptable uploading.
+	 */
+	smu->uploading_custom_pp_table = true;
+
 	ret = smu_reset(smu);
 	if (ret)
 		pr_info("smu reset failed, ret = %d\n", ret);
+
+	smu->uploading_custom_pp_table = false;
 
 failed:
 	mutex_unlock(&smu->mutex);
···
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		vega20_set_ppt_funcs(smu);
 		break;
 	case CHIP_NAVI10:
···
 		navi10_set_ppt_funcs(smu);
 		break;
 	case CHIP_ARCTURUS:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		arcturus_set_ppt_funcs(smu);
 		/* OD is not supported on Arcturus */
 		smu->od_enabled =false;
···
 		return ret;
 	}
 
-	ret = smu_stop_dpms(smu);
-	if (ret) {
-		pr_warn("Fail to stop Dpms!\n");
-		return ret;
+	/*
+	 * For custom pptable uploading, skip the DPM features
+	 * disable process on Navi1x ASICs.
+	 *   - As the gfx related features are under control of
+	 *     RLC on those ASICs. RLC reinitialization will be
+	 *     needed to reenable them. That will cost much more
+	 *     efforts.
+	 *
+	 *   - SMU firmware can handle the DPM reenablement
+	 *     properly.
+	 */
+	if (!smu->uploading_custom_pp_table ||
+	    !((adev->asic_type >= CHIP_NAVI10) &&
+	      (adev->asic_type <= CHIP_NAVI12))) {
+		ret = smu_stop_dpms(smu);
+		if (ret) {
+			pr_warn("Fail to stop Dpms!\n");
+			return ret;
+		}
 	}
 
 	kfree(table_context->driver_pptable);

drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c

···
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev;
+
 	if (!hwmgr)
 		return -EINVAL;
 
···
 	hwmgr_init_workload_prority(hwmgr);
 	hwmgr->gfxoff_state_changed_by_workload = false;
 
+	adev = hwmgr->adev;
+
 	switch (hwmgr->chip_family) {
 	case AMDGPU_FAMILY_CI:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->smumgr_funcs = &ci_smu_funcs;
 		ci_set_asic_special_caps(hwmgr);
 		hwmgr->feature_mask &= ~(PP_VBI_TIME_SUPPORT_MASK |
···
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_CZ:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->od_enabled = false;
 		hwmgr->smumgr_funcs = &smu8_smu_funcs;
 		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		smu8_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_VI:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_TOPAZ:
···
 	case AMDGPU_FAMILY_AI:
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
···
 			vega12_hwmgr_init(hwmgr);
 			break;
 		case CHIP_VEGA20:
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega20_smu_funcs;
 			vega20_hwmgr_init(hwmgr);

drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c

···
 
 static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int i;
 	u32 tmp = 0;
 
 	if (!query)
 		return -EINVAL;
 
-	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
-	tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
-	*query = tmp;
+	/*
+	 * PPSMC_MSG_GetCurrPkgPwr is not supported on:
+	 *  - Hawaii
+	 *  - Bonaire
+	 *  - Fiji
+	 *  - Tonga
+	 */
+	if ((adev->asic_type != CHIP_HAWAII) &&
+	    (adev->asic_type != CHIP_BONAIRE) &&
+	    (adev->asic_type != CHIP_FIJI) &&
+	    (adev->asic_type != CHIP_TONGA)) {
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
+		tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
+		*query = tmp;
 
-	if (tmp != 0)
-		return 0;
+		if (tmp != 0)
+			return 0;
+	}
 
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart);
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,

drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h

···
 
 	uint32_t smc_if_version;
 
+	bool uploading_custom_pp_table;
 };
 
 struct i2c_adapter;

drivers/gpu/drm/amd/powerplay/navi10_ppt.c

···
 	case SMU_UCLK:
 	case SMU_DCEFCLK:
 	case SMU_FCLK:
+		/* There is only 2 levels for fine grained DPM */
+		if (navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+			soft_max_level = (soft_max_level >= 1 ? 1 : 0);
+			soft_min_level = (soft_min_level >= 1 ? 1 : 0);
+		}
+
 		ret = smu_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
 			return size;
···
 	return ret;
 }
 
+static int navi10_run_btc(struct smu_context *smu)
+{
+	int ret = 0;
+
+	ret = smu_send_smc_msg(smu, SMU_MSG_RunBtc);
+	if (ret)
+		pr_err("RunBtc failed!\n");
+
+	return ret;
+}
+
 static const struct pptable_funcs navi10_ppt_funcs = {
 	.tables_init = navi10_tables_init,
 	.alloc_dpm_context = navi10_allocate_dpm_context,
···
 	.set_default_od_settings = navi10_set_default_od_settings,
 	.od_edit_dpm_table = navi10_od_edit_dpm_table,
 	.get_pptable_power_limit = navi10_get_pptable_power_limit,
+	.run_btc = navi10_run_btc,
 };
 
 void navi10_set_ppt_funcs(struct smu_context *smu)

drivers/gpu/drm/radeon/cik.c

···
 	}
 
 	/* setup interrupt control */
-	/* XXX this should actually be a bus address, not an MC address. same on older asics */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN

drivers/gpu/drm/radeon/r600.c

···
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN

drivers/gpu/drm/radeon/si.c

···
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN