15 files changed, 95 insertions, 57 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 50dff69a0f6e..b1172d93c99c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -192,30 +192,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev)
 
 static bool amdgpu_read_platform_bios(struct amdgpu_device *adev)
 {
-	uint8_t __iomem *bios;
-	size_t size;
+	phys_addr_t rom = adev->pdev->rom;
+	size_t romlen = adev->pdev->romlen;
+	void __iomem *bios;
 
 	adev->bios = NULL;
 
-	bios = pci_platform_rom(adev->pdev, &size);
-	if (!bios) {
+	if (!rom || romlen == 0)
 		return false;
-	}
 
-	adev->bios = kzalloc(size, GFP_KERNEL);
-	if (adev->bios == NULL)
+	adev->bios = kzalloc(romlen, GFP_KERNEL);
+	if (!adev->bios)
 		return false;
 
-	memcpy_fromio(adev->bios, bios, size);
+	bios = ioremap(rom, romlen);
+	if (!bios)
+		goto free_bios;
 
-	if (!check_atom_bios(adev->bios, size)) {
-		kfree(adev->bios);
-		return false;
-	}
+	memcpy_fromio(adev->bios, bios, romlen);
+	iounmap(bios);
 
-	adev->bios_size = size;
+	if (!check_atom_bios(adev->bios, romlen))
+		goto free_bios;
+
+	adev->bios_size = romlen;
 
 	return true;
+free_bios:
+	kfree(adev->bios);
+	return false;
 }
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index faa3e7102156..f84f9e35a73b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2008,8 +2008,24 @@ static void amdgpu_device_fill_reset_magic(struct amdgpu_device *adev)
  */
 static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
 {
-	return !!memcmp(adev->gart.ptr, adev->reset_magic,
-			AMDGPU_RESET_MAGIC_NUM);
+	if (memcmp(adev->gart.ptr, adev->reset_magic,
+			AMDGPU_RESET_MAGIC_NUM))
+		return true;
+
+	if (!adev->in_gpu_reset)
+		return false;
+
+	/*
+	 * For all ASICs with baco/mode1 reset, the VRAM is
+	 * always assumed to be lost.
+	 */
+	switch (amdgpu_asic_reset_method(adev)) {
+	case AMD_RESET_METHOD_BACO:
+	case AMD_RESET_METHOD_MODE1:
+		return true;
+	default:
+		return false;
+	}
 }
 
 /**
@@ -3356,6 +3372,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		}
 	}
 
+	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
+	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
+
 	amdgpu_amdkfd_suspend(adev, !fbcon);
 
 	amdgpu_ras_suspend(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f197f1be0969..abe94a55ecad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -89,7 +89,8 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 			adev->pm.ac_power = true;
 		else
 			adev->pm.ac_power = false;
-		if (adev->powerplay.pp_funcs->enable_bapm)
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->enable_bapm)
 			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
 		mutex_unlock(&adev->pm.mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index be50867ea644..deaa26808841 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -818,7 +818,7 @@ static int psp_ras_initialize(struct psp_context *psp)
 
 	if (!psp->adev->psp.ta_ras_ucode_size ||
 	    !psp->adev->psp.ta_ras_start_addr) {
-		dev_warn(psp->adev->dev, "RAS: ras ta ucode is not available\n");
+		dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n");
 		return 0;
 	}
 
@@ -902,7 +902,7 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 
 	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");
+		dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n");
 		return 0;
 	}
 
@@ -1048,7 +1048,7 @@ static int psp_dtm_initialize(struct psp_context *psp)
 
 	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");
+		dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n");
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 3c32a94d2424..ab379b44679c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1424,12 +1424,22 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 {
 	struct amdgpu_ras *ras =
 		container_of(work, struct amdgpu_ras, recovery_work);
+	struct amdgpu_device *remote_adev = NULL;
+	struct amdgpu_device *adev = ras->adev;
+	struct list_head device_list, *device_list_handle =  NULL;
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false);
+
+	/* Build list of devices to query RAS related errors */
+	if  (hive && adev->gmc.xgmi.num_physical_nodes > 1) {
+		device_list_handle = &hive->device_list;
+	} else {
+		list_add_tail(&adev->gmc.xgmi.head, &device_list);
+		device_list_handle = &device_list;
+	}
 
-	/*
-	 * Query and print non zero error counter per IP block for
-	 * awareness before recovering GPU.
-	 */
-	amdgpu_ras_log_on_err_counter(ras->adev);
+	list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) {
+		amdgpu_ras_log_on_err_counter(remote_adev);
+	}
 
 	if (amdgpu_device_should_recover_gpu(ras->adev))
 		amdgpu_device_gpu_recover(ras->adev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9f44ba7d9d97..6309ff72bd78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -770,7 +770,6 @@ struct amdgpu_ttm_tt {
 static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = {
 	(1 << 0), /* HMM_PFN_VALID */
 	(1 << 1), /* HMM_PFN_WRITE */
-	0 /* HMM_PFN_DEVICE_PRIVATE */
 };
 
 static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = {
@@ -851,7 +850,7 @@ retry:
 	range->notifier_seq = mmu_interval_read_begin(&bo->notifier);
 
 	down_read(&mm->mmap_sem);
-	r = hmm_range_fault(range, 0);
+	r = hmm_range_fault(range);
 	up_read(&mm->mmap_sem);
 	if (unlikely(r <= 0)) {
 		/*
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 006f21ef7ddf..62635e58e45e 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1358,8 +1358,6 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = cik_asic_pci_config_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index c8f2aa1db13b..f92c158d89a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1113,7 +1113,7 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size);
+	memset(hpd, 0, mec_hpd_size);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
@@ -4104,6 +4104,12 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 
 	/* It is disabled by HW by default */
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		/* 0 - Disable some blocks' MGCG */
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xe0000000);
+		WREG32_SOC15(GC, 0, mmCGTT_WD_CLK_CTRL, 0xff000000);
+		WREG32_SOC15(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xff000000);
+		WREG32_SOC15(GC, 0, mmCGTT_IA_CLK_CTRL, 0xff000000);
+
 		/* 1 - RLC_CGTT_MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
@@ -4143,19 +4149,20 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-		/* 2 - disable MGLS in RLC */
+		/* 2 - disable MGLS in CP */
+		data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL);
+		if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) {
+			data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
+			WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
+		}
+
+		/* 3 - disable MGLS in RLC */
 		data = RREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL);
 		if (data & RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK) {
 			data &= ~RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK;
 			WREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL, data);
 		}
 
-		/* 3 - disable MGLS in CP */
-		data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL);
-		if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) {
-			data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
-			WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
-		}
 	}
 }
 
@@ -4266,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		/* ===  CGCG /CGLS for GFX 3D Only === */
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  MGCG + MGLS === */
-		gfx_v10_0_update_medium_grain_clock_gating(adev, enable);
+		/* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */
 	}
 
 	if (adev->cg_flags &
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 37c8231f1407..0c390485bc10 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1217,6 +1217,8 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 			adev->gfx.mec_fw_write_wait = true;
 		break;
 	default:
+		adev->gfx.me_fw_write_wait = true;
+		adev->gfx.mec_fw_write_wait = true;
 		break;
 	}
 }
@@ -1232,6 +1234,8 @@ struct amdgpu_gfxoff_quirk {
 static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = {
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=204689 */
 	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 },
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */
+	{ 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 },
 	{ 0, 0, 0, 0, 0 },
 };
 
@@ -1946,7 +1950,7 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size);
+	memset(hpd, 0, mec_hpd_size);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
index cceb46faf212..dce945ef21a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
@@ -710,14 +710,16 @@ static int gfx_v9_4_query_utc_edc_status(struct amdgpu_device *adev,
 
 		sec_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, SEC_COUNT);
 		if (sec_count) {
-			DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i,
+			dev_info(adev->dev,
+				 "Instance[%d]: SubBlock %s, SEC %d\n", i,
 				 vml2_mems[i], sec_count);
 			err_data->ce_count += sec_count;
 		}
 
 		ded_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, DED_COUNT);
 		if (ded_count) {
-			DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i,
+			dev_info(adev->dev,
+				 "Instance[%d]: SubBlock %s, DED %d\n", i,
 				 vml2_mems[i], ded_count);
 			err_data->ue_count += ded_count;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 0d413fabd015..c0e3efcb09bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -1539,8 +1539,11 @@ static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = {
 	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_EDC_CNT3), 0, 0, 0 },
 };
 
-static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg,
-	uint32_t value, uint32_t *sec_count, uint32_t *ded_count)
+static int mmhub_v9_4_get_ras_error_count(struct amdgpu_device *adev,
+					  const struct soc15_reg_entry *reg,
+					  uint32_t value,
+					  uint32_t *sec_count,
+					  uint32_t *ded_count)
 {
 	uint32_t i;
 	uint32_t sec_cnt, ded_cnt;
@@ -1553,7 +1556,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg,
 				mmhub_v9_4_ras_fields[i].sec_count_mask) >>
 				mmhub_v9_4_ras_fields[i].sec_count_shift;
 		if (sec_cnt) {
-			DRM_INFO("MMHUB SubBlock %s, SEC %d\n",
+			dev_info(adev->dev, "MMHUB SubBlock %s, SEC %d\n",
 				mmhub_v9_4_ras_fields[i].name,
 				sec_cnt);
 			*sec_count += sec_cnt;
@@ -1563,7 +1566,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg,
 				mmhub_v9_4_ras_fields[i].ded_count_mask) >>
 				mmhub_v9_4_ras_fields[i].ded_count_shift;
 		if (ded_cnt) {
-			DRM_INFO("MMHUB SubBlock %s, DED %d\n",
+			dev_info(adev->dev, "MMHUB SubBlock %s, DED %d\n",
 				mmhub_v9_4_ras_fields[i].name,
 				ded_cnt);
 			*ded_count += ded_cnt;
@@ -1588,7 +1591,7 @@ static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev,
 		reg_value =
 			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i]));
 		if (reg_value)
-			mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i],
+			mmhub_v9_4_get_ras_error_count(adev, &mmhub_v9_4_edc_cnt_regs[i],
 				reg_value, &sec_count, &ded_count);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 033cbbca2072..52318b03c424 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -351,8 +351,6 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		ret = smu_baco_enter(smu);
 		if (ret)
 			return ret;
@@ -360,8 +358,6 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 		if (ret)
 			return ret;
 	} else {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		ret = nv_asic_mode1_reset(adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 9159bd46482b..5f3a5ee2a3f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -677,7 +677,7 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 }
 
 /**
- * sdma_v4_0_ring_set_wptr - commit the write pointer
+ * sdma_v4_0_page_ring_set_wptr - commit the write pointer
  *
  * @ring: amdgpu ring pointer
  *
@@ -977,7 +977,7 @@ static void sdma_v4_0_page_stop(struct amdgpu_device *adev)
 }
 
 /**
- * sdma_v_0_ctx_switch_enable - stop the async dma engines context switch
+ * sdma_v4_0_ctx_switch_enable - stop the async dma engines context switch
  *
  * @adev: amdgpu_device pointer
  * @enable: enable/disable the DMA MEs context switch.
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index a40499d51c93..d42a8d8a0dea 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -569,14 +569,10 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
-			if (!adev->in_suspend)
-				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
 			return amdgpu_dpm_mode2_reset(adev);
 		default:
-			if (!adev->in_suspend)
-				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_mode1_reset(adev);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 78b35901643b..3ce10e05d0d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -765,8 +765,6 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = vi_asic_pci_config_reset(adev);