Merge tag 'v5.4-rc4' into devel

Linux 5.4-rc4

78 files changed, 615 insertions, 359 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 42e2c1f57152..00962a659009 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -54,7 +54,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
 	amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
 	amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
-	amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
+	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
 
 amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index eba42c752bca..82155ac3288a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -189,7 +189,7 @@ static int acp_hw_init(void *handle)
 	u32 val = 0;
 	u32 count = 0;
 	struct device *dev;
-	struct i2s_platform_data *i2s_pdata;
+	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
@@ -231,20 +231,21 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell),
 							GFP_KERNEL);
 
-	if (adev->acp.acp_cell == NULL)
-		return -ENOMEM;
+	if (adev->acp.acp_cell == NULL) {
+		r = -ENOMEM;
+		goto failure;
+	}
 
 	adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
 	if (adev->acp.acp_res == NULL) {
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
 	if (i2s_pdata == NULL) {
-		kfree(adev->acp.acp_res);
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	switch (adev->asic_type) {
@@ -341,14 +342,14 @@ static int acp_hw_init(void *handle)
 	r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
 								ACP_DEVS);
 	if (r)
-		return r;
+		goto failure;
 
 	for (i = 0; i < ACP_DEVS ; i++) {
 		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
 		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
 		if (r) {
 			dev_err(dev, "Failed to add dev to genpd\n");
-			return r;
+			goto failure;
 		}
 	}
 
@@ -367,7 +368,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -384,7 +386,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -393,6 +396,13 @@ static int acp_hw_init(void *handle)
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
 	return 0;
+
+failure:
+	kfree(i2s_pdata);
+	kfree(adev->acp.acp_res);
+	kfree(adev->acp.acp_cell);
+	kfree(adev->acp.acp_genpd);
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 7bcf86c61999..61e38e43ad1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -270,7 +270,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
 	if (r)
-		goto error_free;
+		return r;
 
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
@@ -283,8 +283,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
 		mutex_unlock(&fpriv->bo_list_lock);
 		if (r < 0) {
-			amdgpu_bo_list_put(list);
-			return r;
+			goto error_put_list;
 		}
 
 		handle = r;
@@ -306,9 +305,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		mutex_unlock(&fpriv->bo_list_lock);
 
 		if (IS_ERR(old)) {
-			amdgpu_bo_list_put(list);
 			r = PTR_ERR(old);
-			goto error_free;
+			goto error_put_list;
 		}
 
 		amdgpu_bo_list_put(old);
@@ -325,8 +323,10 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	return 0;
 
+error_put_list:
+	amdgpu_bo_list_put(list);
+
 error_free:
-	if (info)
-		kvfree(info);
+	kvfree(info);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 264677ab248a..2a00a36106b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -81,9 +81,10 @@
  * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS.
  * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
+ * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	34
+#define KMS_DRIVER_MINOR	35
 #define KMS_DRIVER_PATCHLEVEL	0
 
 #define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
@@ -1047,6 +1048,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+#ifdef CONFIG_DRM_AMDGPU_SI
+	if (!amdgpu_si_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	if (!amdgpu_cik_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+
 	/* Get rid of things like offb */
 	ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 554a59b3c4a6..6ee4021910e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -165,6 +165,7 @@ struct amdgpu_gfx_config {
 	uint32_t num_sc_per_sh;
 	uint32_t num_packer_per_sc;
 	uint32_t pa_sc_tile_steering_override;
+	uint64_t tcc_disabled_mask;
 };
 
 struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f6147528be64..d55f5baa83d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct amdgpu_device *adev;
 	int r, acpi_status;
 
-#ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-
 	adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
 	if (adev == NULL) {
 		return -ENOMEM;
@@ -787,6 +752,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.pa_sc_tile_steering_override =
 				adev->gfx.config.pa_sc_tile_steering_override;
 
+		dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
+
 		return copy_to_user(out, &dev_info,
 				    min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index e2fb141ff2e5..5251352f5922 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base;
 
-#if 0
 	if (vm->bulk_moveable) {
 		spin_lock(&glob->lru_lock);
 		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
 		spin_unlock(&glob->lru_lock);
 		return;
 	}
-#endif
 
 	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 638c821611ab..957811b73672 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1691,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
+{
+	/* TCCs are global (not instanced). */
+	uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
+			       RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+
+	adev->gfx.config.tcc_disabled_mask =
+		REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) |
+		(REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16);
+}
+
 static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 {
 	u32 tmp;
@@ -1702,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v10_0_setup_rb(adev);
 	gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info);
+	gfx_v10_0_get_tcc_info(adev);
 	adev->gfx.config.pa_sc_tile_steering_override =
 		gfx_v10_0_init_pa_sc_tile_steering_override(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 85393a99a848..de9b995b65b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -317,10 +317,12 @@ 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) {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = smu_baco_reset(smu);
 	} else {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = nv_asic_mode1_reset(adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index fa2f70ce2e2b..f6e81680dd7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
 	amdgpu_ring_write(ring, seq); /* reference */
-	amdgpu_ring_write(ring, 0xfffffff); /* mask */
+	amdgpu_ring_write(ring, 0xffffffff); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f70658a536a9..f8ab80c8801b 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
 			return soc15_mode2_reset(adev);
 		default:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_mode1_reset(adev);
 	}
 }
@@ -771,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
-#else
-#       warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8cab6da512a0..a52f0b13a2c8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2385,8 +2385,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 
 	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
 		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
-	if (adev->asic_type == CHIP_RENOIR)
-		dm->dc->debug.disable_stutter = true;
 
 	return 0;
 fail:
@@ -6019,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev,
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	int i;
+#ifdef CONFIG_DEBUG_FS
 	enum amdgpu_dm_pipe_crc_source source;
+#endif
 
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
 				      new_crtc_state, i) {
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 1787b9bf800a..76d54885374a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 318e9c2e2ca8..89620adc81d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 83e1878161c9..21a657e79306 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 8b85e5274bba..7c52f7f9196c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 4625df9f9fd2..643ccb0ade00 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 59305e411a66..1599bb971111 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index b4e3ce22ed52..5a2763daff4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 8cd9de8b1a7a..ef673bffc241 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,7 +3,17 @@
 
 DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4
+ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
+	cc_stack_align := -mpreferred-stack-boundary=4
+else ifneq ($(call cc-option, -mstack-alignment=16),)
+	cc_stack_align := -mstack-alignment=16
+endif
+
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+
+ifdef CONFIG_CC_IS_CLANG
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
+endif
 
 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 456cd0e3289c..3b6ed60dcd35 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -39,9 +39,6 @@
  * ways. Unless there is something clearly wrong with it the code should
  * remain as-is as it provides us with a guarantee from HW that it is correct.
  */
-
-typedef unsigned int uint;
-
 typedef struct {
 	double DPPCLK;
 	double DISPCLK;
@@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0;
 				mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					uint m;
+					unsigned int m;
 
 					locals->cursor_bw[k] = 0;
 					locals->cursor_bw_pre[k] = 0;
@@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 	double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank;
 	double FullDETBufferingTimeYStutterCriticalPlane = 0;
 	double TimeToFinishSwathTransferStutterCriticalPlane = 0;
-	uint k, j;
+	unsigned int k, j;
 
 	mode_lib->vba.TotalActiveDPP = 0;
 	mode_lib->vba.TotalDCCActiveDPP = 0;
@@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep(
 		double DPPCLK[],
 		double *DCFCLKDeepSleep)
 {
-	uint k;
+	unsigned int k;
 	double DisplayPipeLineDeliveryTimeLuma;
 	double DisplayPipeLineDeliveryTimeChroma;
 	//double   DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX];
@@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes(
 		double DisplayPipeRequestDeliveryTimeChromaPrefetch[])
 {
 	double req_per_swath_ub;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (VRatio[k] <= 1) {
@@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes(
 	unsigned int dpte_groups_per_row_chroma_ub;
 	unsigned int num_group_per_lower_vm_stage;
 	unsigned int num_req_per_lower_vm_stage;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (GPUVMEnable == true) {
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 33960fb38a5d..4acf139ea014 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -843,6 +843,8 @@ static int smu_sw_init(void *handle)
 	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 
+	mutex_init(&smu->sensor_lock);
+
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index f1f072012fac..d493a3f8c07a 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	if (!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 6109815a0401..23171a4d9a31 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -344,6 +344,7 @@ struct smu_context
 	const struct smu_funcs		*funcs;
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
+	struct mutex			sensor_lock;
 	uint64_t pool_size;
 
 	struct smu_table_context	smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 12c0e469bf35..0b461404af6b 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
-	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
+	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
@@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index dc754447f0dd..23c12018dbc1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage =
-				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 7c960b07746f..ae18fbcb26fb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
-					data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+					data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 64386ee3f878..bbd8ebd58434 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index 2851cac94d86..b72840c06ab7 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder,
 	struct komeda_data_flow_cfg dflow;
 	int err;
 
-	if (!writeback_job || !writeback_job->fb) {
+	if (!writeback_job)
 		return 0;
-	}
 
 	if (!crtc_st->active) {
 		DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n");
@@ -166,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
 					   &komeda_wb_encoder_helper_funcs,
 					   formats, n_formats);
 	komeda_put_fourcc_list(formats);
-	if (err)
+	if (err) {
+		kfree(kwb_conn);
 		return err;
+	}
 
 	drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs);
 
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 22c0847986df..875a3a9eabfa 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -131,7 +131,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
 	struct drm_framebuffer *fb;
 	int i, n_planes;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -248,7 +248,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
 
 	mw_state = to_mw_state(conn_state);
 
-	if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+	if (conn_state->writeback_job) {
 		struct drm_framebuffer *fb = conn_state->writeback_job->fb;
 
 		DRM_DEV_DEBUG_DRIVER(drm->dev,
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index cebc8e620820..8a8d605021f0 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -728,6 +728,8 @@ static int tc_set_video_mode(struct tc_data *tc,
 	int lower_margin = mode->vsync_start - mode->vdisplay;
 	int vsync_len = mode->vsync_end - mode->vsync_start;
 	u32 dp0_syncval;
+	u32 bits_per_pixel = 24;
+	u32 in_bw, out_bw;
 
 	/*
 	 * Recommended maximum number of symbols transferred in a transfer unit:
@@ -735,7 +737,10 @@ static int tc_set_video_mode(struct tc_data *tc,
 	 *              (output active video bandwidth in bytes))
 	 * Must be less than tu_size.
 	 */
-	max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+
+	in_bw = mode->clock * bits_per_pixel / 8;
+	out_bw = tc->link.base.num_lanes * tc->link.base.rate;
+	max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw);
 
 	dev_dbg(tc->dev, "set mode %dx%d\n",
 		mode->hdisplay, mode->vdisplay);
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 419381abbdd1..14aeaf736321 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector,
 		return -EINVAL;
 	}
 
-	if (writeback_job->out_fence && !writeback_job->fb) {
-		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
-				 connector->base.id, connector->name);
-		return -EINVAL;
+	if (!writeback_job->fb) {
+		if (writeback_job->out_fence) {
+			DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+					 connector->base.id, connector->name);
+			return -EINVAL;
+		}
+
+		drm_writeback_cleanup_job(writeback_job);
+		state->writeback_job = NULL;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82a4ceed3fcf..6b0177112e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -159,6 +159,9 @@ static const struct edid_quirk {
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
 
+	/* Lenovo G50 */
+	{ "SDC", 18514, EDID_QUIRK_FORCE_6BPC },
+
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index ff138b6ec48b..43d9e3bb3a94 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job)
 	if (job->fb)
 		drm_framebuffer_put(job->fb);
 
+	if (job->out_fence)
+		dma_fence_put(job->out_fence);
+
 	kfree(job);
 }
 EXPORT_SYMBOL(drm_writeback_cleanup_job);
@@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
 {
 	unsigned long flags;
 	struct drm_writeback_job *job;
+	struct dma_fence *out_fence;
 
 	spin_lock_irqsave(&wb_connector->job_lock, flags);
 	job = list_first_entry_or_null(&wb_connector->job_queue,
 				       struct drm_writeback_job,
 				       list_entry);
-	if (job) {
+	if (job)
 		list_del(&job->list_entry);
-		if (job->out_fence) {
-			if (status)
-				dma_fence_set_error(job->out_fence, status);
-			dma_fence_signal(job->out_fence);
-			dma_fence_put(job->out_fence);
-		}
-	}
+
 	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
 
 	if (WARN_ON(!job))
 		return;
 
+	out_fence = job->out_fence;
+	if (out_fence) {
+		if (status)
+			dma_fence_set_error(out_fence, status);
+		dma_fence_signal(out_fence);
+		dma_fence_put(out_fence);
+		job->out_fence = NULL;
+	}
+
 	INIT_WORK(&job->cleanup_work, cleanup_work);
 	queue_work(system_long_wq, &job->cleanup_work);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..3250c1b8dcca 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
 			      "disabling port %c DVI/HDMI support\n",
 			      port_name(port), info->alternate_ddc_pin,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same ddc bin and
 		 * system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dvi = false;
 		info->supports_hdmi = false;
 		info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
 			      "disabling port %c DP support\n",
 			      port_name(port), info->alternate_aux_channel,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same aux channel
 		 * and system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dp = false;
 		info->alternate_aux_channel = 0;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b51d1ceb8739..aa54bb22796d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3280,7 +3280,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 	switch (fb->modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
-		return 4096;
+		/*
+		 * Validated limit is 4k, but has 5k should
+		 * work apart from the following features:
+		 * - Ytile (already limited to 4k)
+		 * - FP16 (already limited to 4k)
+		 * - render compression (already limited to 4k)
+		 * - KVMR sprite and cursor (don't care)
+		 * - horizontal panning (TODO verify this)
+		 * - pipe and plane scaling (TODO verify this)
+		 */
+		if (cpp == 8)
+			return 4096;
+		else
+			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 		/* FIXME AUX plane? */
@@ -7261,7 +7274,7 @@ retry:
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
-			       link_bw, &pipe_config->fdi_m_n, false);
+			       link_bw, &pipe_config->fdi_m_n, false, false);
 
 	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
@@ -7508,11 +7521,15 @@ void
 intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
 		       int pixel_clock, int link_clock,
 		       struct intel_link_m_n *m_n,
-		       bool constant_n)
+		       bool constant_n, bool fec_enable)
 {
-	m_n->tu = 64;
+	u32 data_clock = bits_per_pixel * pixel_clock;
 
-	compute_m_n(bits_per_pixel * pixel_clock,
+	if (fec_enable)
+		data_clock = intel_dp_mode_to_fec_clock(data_clock);
+
+	m_n->tu = 64;
+	compute_m_n(data_clock,
 		    link_clock * nlanes * 8,
 		    &m_n->gmch_m, &m_n->gmch_n,
 		    constant_n);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index e57e6969051d..01fa87ad3270 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -414,7 +414,7 @@ enum phy_fia {
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
-			    bool constant_n);
+			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 921ad0a2f7ba..57e9f0ba331b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -78,8 +78,8 @@
 #define DP_DSC_MAX_ENC_THROUGHPUT_0		340000
 #define DP_DSC_MAX_ENC_THROUGHPUT_1		400000
 
-/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */
-#define DP_DSC_FEC_OVERHEAD_FACTOR		976
+/* DP DSC FEC Overhead factor = 1/(0.972261) */
+#define DP_DSC_FEC_OVERHEAD_FACTOR		972261
 
 /* Compliance test status bits  */
 #define INTEL_DP_RESOLUTION_SHIFT_MASK	0
@@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 	return 0;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
+{
+	return div_u64(mul_u32_u32(mode_clock, 1000000U),
+		       DP_DSC_FEC_OVERHEAD_FACTOR);
+}
+
+static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+				       u32 mode_clock, u32 mode_hdisplay)
+{
+	u32 bits_per_pixel, max_bpp_small_joiner_ram;
+	int i;
+
+	/*
+	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
+	 * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP)
+	 * for SST -> TimeSlotsPerMTP is 1,
+	 * for MST -> TimeSlotsPerMTP has to be calculated
+	 */
+	bits_per_pixel = (link_clock * lane_count * 8) /
+			 intel_dp_mode_to_fec_clock(mode_clock);
+	DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
+
+	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
+	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+	DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
+
+	/*
+	 * Greatest allowed DSC BPP = MIN (output BPP from available Link BW
+	 * check, output bpp from small joiner RAM check)
+	 */
+	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
+
+	/* Error out if the max bpp is less than smallest allowed valid bpp */
+	if (bits_per_pixel < valid_dsc_bpp[0]) {
+		DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n",
+			      bits_per_pixel, valid_dsc_bpp[0]);
+		return 0;
+	}
+
+	/* Find the nearest match in the array of known BPPs from VESA */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
+		if (bits_per_pixel < valid_dsc_bpp[i + 1])
+			break;
+	}
+	bits_per_pixel = valid_dsc_bpp[i];
+
+	/*
+	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
+	 * fractional part is 0
+	 */
+	return bits_per_pixel << 4;
+}
+
+static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
+				       int mode_clock, int mode_hdisplay)
+{
+	u8 min_slice_count, i;
+	int max_slice_width;
+
+	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_0);
+	else
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_1);
+
+	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
+	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
+		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
+			      max_slice_width);
+		return 0;
+	}
+	/* Also take into account max slice width */
+	min_slice_count = min_t(u8, min_slice_count,
+				DIV_ROUND_UP(mode_hdisplay,
+					     max_slice_width));
+
+	/* Find the closest match to the valid slice count values */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
+		if (valid_dsc_slicecount[i] >
+		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
+						    false))
+			break;
+		if (min_slice_count  <= valid_dsc_slicecount[i])
+			return valid_dsc_slicecount[i];
+	}
+
+	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+	return 0;
+}
+
 static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
@@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n,
-			       constant_n);
+			       constant_n, pipe_config->fec_enable);
 
 	if (intel_connector->panel.downclock_mode != NULL &&
 		dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
@@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 					       intel_connector->panel.downclock_mode->clock,
 					       pipe_config->port_clock,
 					       &pipe_config->dp_m2_n2,
-					       constant_n);
+					       constant_n, pipe_config->fec_enable);
 	}
 
 	if (!HAS_DDI(dev_priv))
@@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 		DP_DPRX_ESI_LEN;
 }
 
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay)
-{
-	u16 bits_per_pixel, max_bpp_small_joiner_ram;
-	int i;
-
-	/*
-	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
-	 * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP)
-	 * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1,
-	 * for MST -> TimeSlotsPerMTP has to be calculated
-	 */
-	bits_per_pixel = (link_clock * lane_count * 8 *
-			  DP_DSC_FEC_OVERHEAD_FACTOR) /
-		mode_clock;
-
-	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
-	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER /
-		mode_hdisplay;
-
-	/*
-	 * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW
-	 * check, output bpp from small joiner RAM check)
-	 */
-	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
-
-	/* Error out if the max bpp is less than smallest allowed valid bpp */
-	if (bits_per_pixel < valid_dsc_bpp[0]) {
-		DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel);
-		return 0;
-	}
-
-	/* Find the nearest match in the array of known BPPs from VESA */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
-		if (bits_per_pixel < valid_dsc_bpp[i + 1])
-			break;
-	}
-	bits_per_pixel = valid_dsc_bpp[i];
-
-	/*
-	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
-	 * fractional part is 0
-	 */
-	return bits_per_pixel << 4;
-}
-
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
-				int mode_clock,
-				int mode_hdisplay)
-{
-	u8 min_slice_count, i;
-	int max_slice_width;
-
-	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_0);
-	else
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_1);
-
-	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
-	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
-		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
-			      max_slice_width);
-		return 0;
-	}
-	/* Also take into account max slice width */
-	min_slice_count = min_t(u8, min_slice_count,
-				DIV_ROUND_UP(mode_hdisplay,
-					     max_slice_width));
-
-	/* Find the closest match to the valid slice count values */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
-		if (valid_dsc_slicecount[i] >
-		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
-						    false))
-			break;
-		if (min_slice_count  <= valid_dsc_slicecount[i])
-			return valid_dsc_slicecount[i];
-	}
-
-	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
-	return 0;
-}
-
 static void
 intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 657bbb1f5ed0..00981fb9414b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
 bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay);
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock,
-				int mode_hdisplay);
 
 bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
@@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 	return ~((1 << lane_count) - 1) & 0xf;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6df240a01b8c..600873c796d0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       crtc_state->port_clock,
 			       &crtc_state->dp_m_n,
-			       constant_n);
+			       constant_n, crtc_state->fec_enable);
 	crtc_state->dp_m_n.tu = slots;
 
 	return 0;
@@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
-	intel_encoder->crtc_mask = BIT(pipe);
+	intel_encoder->crtc_mask = 0x7;
 	intel_encoder->cloneable = 0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index dea63be1964f..cae25e493128 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
+	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
 	int min_width, min_height;
@@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	if (width_bytes > 4096 || fb->pitches[0] > 4096) {
+	if (stride > 4096) {
 		DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n",
-			      fb->pitches[0], 4096);
+			      stride, 4096);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 261c9bd83f51..05289edbafe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 
 	wakeref = intel_runtime_pm_get(rpm);
 
-	srcu = intel_gt_reset_trylock(ggtt->vm.gt);
-	if (srcu < 0) {
-		ret = srcu;
+	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	if (ret)
 		goto err_rpm;
-	}
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
@@ -318,7 +316,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
-	i915_vma_set_ggtt_write(vma);
+	if (write) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		i915_vma_set_ggtt_write(vma);
+		obj->mm.dirty = true;
+	}
 
 err_fence:
 	i915_vma_unpin_fence(vma);
@@ -362,6 +364,7 @@ err:
 		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
+	case -ENODEV: /* bad object, how did you get here! */
 		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
@@ -473,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (!obj)
 		return -ENOENT;
 
+	if (i915_gem_object_never_bind_ggtt(obj)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	ret = create_mmap_offset(obj);
 	if (ret == 0)
 		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
+out:
 	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..ddf3605bea8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -153,6 +153,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 }
 
 static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
+static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
 	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index ede0eb4218a8..646859fea224 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 92e53c25424c..ad2a63dbcac2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -241,9 +241,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
-	i915_gem_restore_gtt_mappings(i915);
-	i915_gem_restore_fences(i915);
-
 	if (i915_gem_init_hw(i915))
 		goto err_wedged;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 11b231c187c5..6b3b50f0f6d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -702,6 +702,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_NO_GGTT |
 		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d3c6993f4f46..22aab8593abf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return READ_ONCE(*execlists->active);
 }
 
+static inline void
+execlists_active_lock_bh(struct intel_engine_execlists *execlists)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&execlists->tasklet);
+}
+
+static inline void
+execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
+{
+	tasklet_unlock(&execlists->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
 struct i915_request *
 execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 82630db0394b..4ce8626b140e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1197,9 +1197,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	const struct intel_engine_execlists * const execlists =
-		&engine->execlists;
-	unsigned long flags;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	u64 addr;
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
@@ -1281,7 +1279,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		spin_lock_irqsave(&engine->active.lock, flags);
+		execlists_active_lock_bh(execlists);
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[80];
 			int len;
@@ -1309,7 +1307,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				 hwsp_seqno(rq));
 			print_request(m, rq, hdr);
 		}
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+		execlists_active_unlock_bh(execlists);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1440,8 +1438,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	write_seqlock(&engine->stats.lock);
+	execlists_active_lock_bh(execlists);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1469,8 +1467,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock(&engine->stats.lock);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+	execlists_active_unlock_bh(execlists);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d42584439f51..06a506c29463 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
 
+static void mark_eio(struct i915_request *rq)
+{
+	if (!i915_request_signaled(rq))
+		dma_fence_set_error(&rq->fence, -EIO);
+	i915_request_mark_complete(rq);
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -631,7 +638,6 @@ execlists_schedule_out(struct i915_request *rq)
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
-	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 
 	old = READ_ONCE(ce->inflight);
 	do
@@ -797,6 +803,17 @@ static bool can_merge_rq(const struct i915_request *prev,
 	GEM_BUG_ON(prev == next);
 	GEM_BUG_ON(!assert_priority_queue(prev, next));
 
+	/*
+	 * We do not submit known completed requests. Therefore if the next
+	 * request is already completed, we can pretend to merge it in
+	 * with the previous context (and we will skip updating the ELSP
+	 * and tracking). Thus hopefully keeping the ELSP full with active
+	 * contexts, despite the best efforts of preempt-to-busy to confuse
+	 * us.
+	 */
+	if (i915_request_completed(next))
+		return true;
+
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
 		return false;
 
@@ -893,7 +910,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 static struct i915_request *
 last_active(const struct intel_engine_execlists *execlists)
 {
-	struct i915_request * const *last = execlists->active;
+	struct i915_request * const *last = READ_ONCE(execlists->active);
 
 	while (*last && i915_request_completed(*last))
 		last++;
@@ -1172,21 +1189,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				continue;
 			}
 
-			if (i915_request_completed(rq)) {
-				ve->request = NULL;
-				ve->base.execlists.queue_priority_hint = INT_MIN;
-				rb_erase_cached(rb, &execlists->virtual);
-				RB_CLEAR_NODE(rb);
-
-				rq->engine = engine;
-				__i915_request_submit(rq);
-
-				spin_unlock(&ve->base.active.lock);
-
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
-
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
 				return; /* leave this for another */
@@ -1237,11 +1239,24 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				GEM_BUG_ON(ve->siblings[0] != engine);
 			}
 
-			__i915_request_submit(rq);
-			if (!i915_request_completed(rq)) {
+			if (__i915_request_submit(rq)) {
 				submit = true;
 				last = rq;
 			}
+			i915_request_put(rq);
+
+			/*
+			 * Hmm, we have a bunch of virtual engine requests,
+			 * but the first one was already completed (thanks
+			 * preempt-to-busy!). Keep looking at the veng queue
+			 * until we have no more relevant requests (i.e.
+			 * the normal submit queue has higher priority).
+			 */
+			if (!submit) {
+				spin_unlock(&ve->base.active.lock);
+				rb = rb_first_cached(&execlists->virtual);
+				continue;
+			}
 		}
 
 		spin_unlock(&ve->base.active.lock);
@@ -1254,8 +1269,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (i915_request_completed(rq))
-				goto skip;
+			bool merge = true;
 
 			/*
 			 * Can we combine this request with the current port?
@@ -1296,14 +1310,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				    ctx_single_port_submission(rq->hw_context))
 					goto done;
 
-				*port = execlists_schedule_in(last, port - execlists->pending);
-				port++;
+				merge = false;
 			}
 
-			last = rq;
-			submit = true;
-skip:
-			__i915_request_submit(rq);
+			if (__i915_request_submit(rq)) {
+				if (!merge) {
+					*port = execlists_schedule_in(last, port - execlists->pending);
+					port++;
+					last = NULL;
+				}
+
+				GEM_BUG_ON(last &&
+					   !can_merge_ctx(last->hw_context,
+							  rq->hw_context));
+
+				submit = true;
+				last = rq;
+			}
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -1593,8 +1616,11 @@ static void process_csb(struct intel_engine_cs *engine)
 static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->active.lock);
-	if (!engine->execlists.pending[0])
+	if (!engine->execlists.pending[0]) {
+		rcu_read_lock(); /* protect peeking at execlists->active */
 		execlists_dequeue(engine);
+		rcu_read_unlock();
+	}
 }
 
 /*
@@ -2399,10 +2425,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 
 static struct i915_request *active_request(struct i915_request *rq)
 {
-	const struct list_head * const list = &rq->timeline->requests;
 	const struct intel_context * const ce = rq->hw_context;
 	struct i915_request *active = NULL;
+	struct list_head *list;
 
+	if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+		return rq;
+
+	list = &rq->timeline->requests;
 	list_for_each_entry_from_reverse(rq, list, link) {
 		if (i915_request_completed(rq))
 			break;
@@ -2552,12 +2582,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	__execlists_reset(engine, true);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		if (!i915_request_signaled(rq))
-			dma_fence_set_error(&rq->fence, -EIO);
-
-		i915_request_mark_complete(rq);
-	}
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2565,10 +2591,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			list_del_init(&rq->sched.link);
+			mark_eio(rq);
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2584,13 +2608,15 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		if (ve->request) {
-			ve->request->engine = engine;
-			__i915_request_submit(ve->request);
-			dma_fence_set_error(&ve->request->fence, -EIO);
-			i915_request_mark_complete(ve->request);
+		rq = fetch_and_zero(&ve->request);
+		if (rq) {
+			mark_eio(rq);
+
+			rq->engine = engine;
+			__i915_request_submit(rq);
+			i915_request_put(rq);
+
 			ve->base.execlists.queue_priority_hint = INT_MIN;
-			ve->request = NULL;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
@@ -3594,6 +3620,8 @@ submit_engine:
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	struct i915_request *old;
+	unsigned long flags;
 
 	GEM_TRACE("%s: rq=%llx:%lld\n",
 		  ve->base.name,
@@ -3602,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	GEM_BUG_ON(ve->request);
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	spin_lock_irqsave(&ve->base.active.lock, flags);
+
+	old = ve->request;
+	if (old) { /* background completion event from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(old));
+		__i915_request_submit(old);
+		i915_request_put(old);
+	}
+
+	if (i915_request_completed(rq)) {
+		__i915_request_submit(rq);
+
+		ve->base.execlists.queue_priority_hint = INT_MIN;
+		ve->request = NULL;
+	} else {
+		ve->base.execlists.queue_priority_hint = rq_prio(rq);
+		ve->request = i915_request_get(rq);
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
-	WRITE_ONCE(ve->request, rq);
+		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+		list_move_tail(&rq->sched.link, virtual_queue(ve));
 
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
+		tasklet_schedule(&ve->base.execlists.tasklet);
+	}
 
-	tasklet_schedule(&ve->base.execlists.tasklet);
+	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
 static struct ve_bond *
@@ -3631,18 +3675,22 @@ static void
 virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	intel_engine_mask_t allowed, exec;
 	struct ve_bond *bond;
 
+	allowed = ~to_request(signal)->engine->mask;
+
 	bond = virtual_find_bond(ve, to_request(signal)->engine);
-	if (bond) {
-		intel_engine_mask_t old, new, cmp;
+	if (bond)
+		allowed &= bond->sibling_mask;
 
-		cmp = READ_ONCE(rq->execution_mask);
-		do {
-			old = cmp;
-			new = cmp & bond->sibling_mask;
-		} while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old);
-	}
+	/* Restrict the bonded request to run on only the available engines */
+	exec = READ_ONCE(rq->execution_mask);
+	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
+		;
+
+	/* Prevent the master from being re-run on the bonded engines */
+	to_request(signal)->execution_mask &= ~allowed;
 }
 
 struct intel_context *
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b9d84d52e986..8cea42379dd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq)
 	struct intel_engine_cs *engine = rq->engine;
 	struct i915_gem_context *hung_ctx = rq->gem_context;
 
-	lockdep_assert_held(&engine->active.lock);
-
 	if (!i915_request_is_active(rq))
 		return;
 
+	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->gem_context == hung_ctx)
 			i915_request_skip(rq, -EIO);
@@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		  rq->fence.seqno,
 		  yesno(guilty));
 
-	lockdep_assert_held(&rq->engine->active.lock);
 	GEM_BUG_ON(i915_request_completed(rq));
 
 	if (guilty) {
@@ -1214,10 +1212,8 @@ out:
 	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 }
 
-int intel_gt_reset_trylock(struct intel_gt *gt)
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
 {
-	int srcu;
-
 	might_lock(&gt->reset.backoff_srcu);
 	might_sleep();
 
@@ -1232,10 +1228,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt)
 
 		rcu_read_lock();
 	}
-	srcu = srcu_read_lock(&gt->reset.backoff_srcu);
+	*srcu = srcu_read_lock(&gt->reset.backoff_srcu);
 	rcu_read_unlock();
 
-	return srcu;
+	return 0;
 }
 
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 37a987b17108..52c00199e069 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine,
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
-int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
 void intel_gt_set_wedged(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 601c16239fdf..bacaa7bb8c9a 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1573,7 +1573,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	struct intel_engine_cs *engine = rq->engine;
 	enum intel_engine_id id;
 	const int num_engines =
-		IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
+		IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
 	bool force_restore = false;
 	int len;
 	u32 *cs;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 45481eb1fa3c..5f6ec2fd29a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1063,6 +1063,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w)
 
 	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
 	whitelist_reg(w, GEN8_HDC_CHICKEN1);
+
+	/* WaSendPushConstantsFromMMIO:skl,bxt */
+	whitelist_reg(w, COMMON_SLICE_CHICKEN2);
 }
 
 static void skl_whitelist_build(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 020696726f9e..bb6f86c7067a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1924,6 +1924,11 @@ static int i915_drm_resume(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_restore_gtt_mappings(dev_priv);
+	i915_gem_restore_fences(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
 	intel_csr_ucode_resume(dev_priv);
 
 	i915_restore_state(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..d0f94f239919 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -969,6 +969,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
+	if (i915_gem_object_never_bind_ggtt(obj))
+		return ERR_PTR(-ENODEV);
+
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
 		/* If the required space is larger than the available
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 167a7b56ed5b..6795f1daa3d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -77,6 +77,12 @@ struct drm_i915_private;
 
 #define I915_GEM_IDLE_TIMEOUT (HZ / 5)
 
+static inline void tasklet_lock(struct tasklet_struct *t)
+{
+	while (!tasklet_trylock(t))
+		cpu_relax();
+}
+
 static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 {
 	if (!atomic_fetch_inc(&t->count))
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a53777dd371c..1c5506822dc7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -194,6 +194,27 @@ static void free_capture_list(struct i915_request *request)
 	}
 }
 
+static void remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		spin_lock(&engine->active.lock);
+		locked = engine;
+	}
+	list_del(&rq->sched.link);
+	spin_unlock(&locked->active.lock);
+}
+
 static bool i915_request_retire(struct i915_request *rq)
 {
 	struct i915_active_request *active, *next;
@@ -259,9 +280,7 @@ static bool i915_request_retire(struct i915_request *rq)
 	 * request that we have removed from the HW and put back on a run
 	 * queue.
 	 */
-	spin_lock(&rq->engine->active.lock);
-	list_del(&rq->sched.link);
-	spin_unlock(&rq->engine->active.lock);
+	remove_from_engine(rq);
 
 	spin_lock(&rq->lock);
 	i915_request_mark_complete(rq);
@@ -358,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq,
 	return 0;
 }
 
-void __i915_request_submit(struct i915_request *request)
+bool __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
+	bool result = false;
 
 	GEM_TRACE("%s fence %llx:%lld, current %d\n",
 		  engine->name,
@@ -370,6 +390,25 @@ void __i915_request_submit(struct i915_request *request)
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
 
+	/*
+	 * With the advent of preempt-to-busy, we frequently encounter
+	 * requests that we have unsubmitted from HW, but left running
+	 * until the next ack and so have completed in the meantime. On
+	 * resubmission of that completed request, we can skip
+	 * updating the payload, and execlists can even skip submitting
+	 * the request.
+	 *
+	 * We must remove the request from the caller's priority queue,
+	 * and the caller must only call us when the request is in their
+	 * priority queue, under the active.lock. This ensures that the
+	 * request has *not* yet been retired and we can safely move
+	 * the request into the engine->active.list where it will be
+	 * dropped upon retiring. (Otherwise if resubmit a *retired*
+	 * request, this would be a horrible use-after-free.)
+	 */
+	if (i915_request_completed(request))
+		goto xfer;
+
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
@@ -393,13 +432,18 @@ void __i915_request_submit(struct i915_request *request)
 	    i915_sw_fence_signaled(&request->semaphore))
 		engine->saturated |= request->sched.semaphores;
 
-	/* We may be recursing from the signal callback of another i915 fence */
-	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+	engine->emit_fini_breadcrumb(request,
+				     request->ring->vaddr + request->postfix);
 
-	list_move_tail(&request->sched.link, &engine->active.requests);
+	trace_i915_request_execute(request);
+	engine->serial++;
+	result = true;
+
+xfer:	/* We may be recursing from the signal callback of another i915 fence */
+	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+		list_move_tail(&request->sched.link, &engine->active.requests);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -410,12 +454,7 @@ void __i915_request_submit(struct i915_request *request)
 
 	spin_unlock(&request->lock);
 
-	engine->emit_fini_breadcrumb(request,
-				     request->ring->vaddr + request->postfix);
-
-	engine->serial++;
-
-	trace_i915_request_execute(request);
+	return result;
 }
 
 void i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 8ac6e1226a56..e4dd013761e8 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq);
 
-void __i915_request_submit(struct i915_request *request);
+bool __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
 void i915_request_skip(struct i915_request *request, int error);
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index fa864d8f2b73..15f8bff141f9 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e6a2d65f19c6..c29c81ec7971 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -41,6 +41,7 @@ enum intel_pch {
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_MCC2_DEVICE_ID_TYPE		0x3880
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bb6dd54a6ff3..37593831b539 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		intel_gt_sanitize(&i915->gt, false);
 		i915_gem_sanitize(i915);
+
+		mutex_lock(&i915->drm.struct_mutex);
+		i915_gem_restore_gtt_mappings(i915);
+		i915_gem_restore_fences(i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+
 		i915_gem_resume(i915);
 	}
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 663ff9f4fac9..1e7b1be25bb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -26,6 +26,8 @@
 #include "dsi_cfg.h"
 #include "msm_kms.h"
 
+#define DSI_RESET_TOGGLE_DELAY_MS 20
+
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
 	u32 ver;
@@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host)
 	wmb(); /* clocks need to be enabled before reset */
 
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb(); /* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 }
 
@@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
 
 	/* dsi controller can only be reset while clocks are running */
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb();	/* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 	wmb();	/* controller out of reset */
 	dsi_write(msm_host, REG_DSI_CTRL, data0);
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index e226324adb69..4bdd63b57100 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1083,7 +1083,7 @@ static const struct dss_features omap34xx_dss_feats = {
 
 static const struct dss_features omap3630_dss_feats = {
 	.model			=	DSS_MODEL_OMAP3,
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.fck_freq_max		=	173000000,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index fc82a525b071..ee4379729a5b 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -220,9 +220,17 @@ static const struct of_device_id lb035q02_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, lb035q02_of_match);
 
+static const struct spi_device_id lb035q02_ids[] = {
+	{ "lb035q02", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, lb035q02_ids);
+
 static struct spi_driver lb035q02_driver = {
 	.probe		= lb035q02_probe,
 	.remove		= lb035q02_remove,
+	.id_table	= lb035q02_ids,
 	.driver		= {
 		.name	= "panel-lg-lb035q02",
 		.of_match_table = lb035q02_of_match,
@@ -231,7 +239,6 @@ static struct spi_driver lb035q02_driver = {
 
 module_spi_driver(lb035q02_driver);
 
-MODULE_ALIAS("spi:lgphilips,lb035q02");
 MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("LG.Philips LB035Q02 LCD Panel driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index 299b217c83e1..20f17e46e65d 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -230,9 +230,17 @@ static const struct of_device_id nl8048_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, nl8048_of_match);
 
+static const struct spi_device_id nl8048_ids[] = {
+	{ "nl8048hl11", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, nl8048_ids);
+
 static struct spi_driver nl8048_driver = {
 	.probe		= nl8048_probe,
 	.remove		= nl8048_remove,
+	.id_table	= nl8048_ids,
 	.driver		= {
 		.name	= "panel-nec-nl8048hl11",
 		.pm	= &nl8048_pm_ops,
@@ -242,7 +250,6 @@ static struct spi_driver nl8048_driver = {
 
 module_spi_driver(nl8048_driver);
 
-MODULE_ALIAS("spi:nec,nl8048hl11");
 MODULE_AUTHOR("Erik Gilling <konkers@android.com>");
 MODULE_DESCRIPTION("NEC-NL8048HL11 Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index 305259b58767..3d5b9c4f68d9 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -684,9 +684,17 @@ static const struct of_device_id acx565akm_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, acx565akm_of_match);
 
+static const struct spi_device_id acx565akm_ids[] = {
+	{ "acx565akm", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, acx565akm_ids);
+
 static struct spi_driver acx565akm_driver = {
 	.probe		= acx565akm_probe,
 	.remove		= acx565akm_remove,
+	.id_table	= acx565akm_ids,
 	.driver		= {
 		.name	= "panel-sony-acx565akm",
 		.of_match_table = acx565akm_of_match,
@@ -695,7 +703,6 @@ static struct spi_driver acx565akm_driver = {
 
 module_spi_driver(acx565akm_driver);
 
-MODULE_ALIAS("spi:sony,acx565akm");
 MODULE_AUTHOR("Nokia Corporation");
 MODULE_DESCRIPTION("Sony ACX565AKM LCD Panel Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index d7b2e34626ef..f2baff827f50 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -375,8 +375,7 @@ static const struct of_device_id td028ttec1_of_match[] = {
 MODULE_DEVICE_TABLE(of, td028ttec1_of_match);
 
 static const struct spi_device_id td028ttec1_ids[] = {
-	{ "tpo,td028ttec1", 0},
-	{ "toppoly,td028ttec1", 0 },
+	{ "td028ttec1", 0 },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 84370562910f..ba163c779084 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -491,9 +491,17 @@ static const struct of_device_id td043mtea1_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, td043mtea1_of_match);
 
+static const struct spi_device_id td043mtea1_ids[] = {
+	{ "td043mtea1", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, td043mtea1_ids);
+
 static struct spi_driver td043mtea1_driver = {
 	.probe		= td043mtea1_probe,
 	.remove		= td043mtea1_remove,
+	.id_table	= td043mtea1_ids,
 	.driver		= {
 		.name	= "panel-tpo-td043mtea1",
 		.pm	= &td043mtea1_pm_ops,
@@ -503,7 +511,6 @@ static struct spi_driver td043mtea1_driver = {
 
 module_spi_driver(td043mtea1_driver);
 
-MODULE_ALIAS("spi:tpo,td043mtea1");
 MODULE_AUTHOR("Gražvydas Ignotas <notasas@gmail.com>");
 MODULE_DESCRIPTION("TPO TD043MTEA1 Panel Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f67ed925c0ef..8822ec13a0d6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
 	pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES);
 	pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES);
 	pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES);
+	pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
+	pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
+	pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
 	pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
 	for (i = 0; i < 4; i++)
 		pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..21f34d44aac2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	mutex_lock(&pfdev->reset_lock);
+	if (!mutex_trylock(&pfdev->reset_lock))
+		return;
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+		drm_sched_stop(sched, sched_job);
+		if (js != i)
+			/* Ensure any timeouts on other slots have finished */
+			cancel_delayed_work_sync(&sched->work_tdr);
+	}
 
-	if (sched_job)
-		drm_sched_increase_karma(sched_job);
+	drm_sched_increase_karma(sched_job);
 
 	spin_lock_irqsave(&pfdev->js->job_lock, flags);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d0bc91ed7c90..9e55076578c6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -379,19 +379,11 @@ radeon_pci_remove(struct pci_dev *pdev)
 static void
 radeon_pci_shutdown(struct pci_dev *pdev)
 {
-	struct drm_device *ddev = pci_get_drvdata(pdev);
-
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown
 	 */
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
-
-	/* Some adapters need to be suspended before a
-	* shutdown occurs in order to prevent an error
-	* during kexec.
-	*/
-	radeon_suspend_kms(ddev, true, true, false);
 }
 
 static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
index ae07290bba6a..04efa78d70b6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
@@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
 	unsigned int i;
 
 	state = rcrtc->writeback.base.state;
-	if (!state || !state->writeback_job || !state->writeback_job->fb)
+	if (!state || !state->writeback_job)
 		return;
 
 	fb = state->writeback_job->fb;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 525dc1c0f1c1..530edb3b51cc 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -7,6 +7,7 @@
 #include <linux/gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 
 #include <drm/drm_atomic_helper.h>
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 504763423d46..a46ac284dd5e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -63,7 +63,6 @@ config TINYDRM_REPAPER
 	depends on DRM && SPI
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
-	depends on THERMAL || !THERMAL
 	help
 	  DRM driver for the following Pervasive Displays panels:
 	  1.44" TFT EPD Panel (E1144CS021)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20ff56f27aa4..98819462f025 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 	kref_get(&bo->list_kref);
 
-	if (bo->ttm && !(bo->ttm->page_flags &
-			 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
+	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
+				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
 		kref_get(&bo->list_kref);
 	}
@@ -878,11 +879,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	if (!bo) {
 		if (busy_bo)
-			ttm_bo_get(busy_bo);
+			kref_get(&busy_bo->list_kref);
 		spin_unlock(&glob->lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
-			ttm_bo_put(busy_bo);
+			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 76eedb963693..46dc3de7e81b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		else
 			ret = vmf_insert_pfn(&cvma, address, pfn);
 
-		/*
-		 * Somebody beat us to this PTE or prefaulting to
-		 * an already populated PTE, or prefaulting error.
-		 */
-
-		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
-			break;
-		else if (unlikely(ret & VM_FAULT_ERROR))
-			goto out_io_unlock;
+		/* Never error on prefaulted PTEs */
+		if (unlikely((ret & VM_FAULT_ERROR))) {
+			if (i == 0)
+				goto out_io_unlock;
+			else
+				break;
+		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 1ce4d7142b6e..bf720206727f 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -231,7 +231,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 	int i;
 
 	conn_state = drm_atomic_get_new_connector_state(state, conn);
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
@@ -271,8 +271,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 	u32 ctrl;
 	int i;
 
-	if (WARN_ON(!conn_state->writeback_job ||
-		    !conn_state->writeback_job->fb))
+	if (WARN_ON(!conn_state->writeback_job))
 		return;
 
 	mode = &conn_state->crtc->state->adjusted_mode;
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index ba1828acd8c9..4be49c1aef51 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -718,17 +718,9 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
 	struct device *dev = &xb_dev->dev;
 	int ret;
 
-	/*
-	 * The device is not spawn from a device tree, so arch_setup_dma_ops
-	 * is not called, thus leaving the device with dummy DMA ops.
-	 * This makes the device return error on PRIME buffer import, which
-	 * is not correct: to fix this call of_dma_configure() with a NULL
-	 * node to set default DMA ops.
-	 */
-	dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	ret = of_dma_configure(dev, NULL, true);
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret < 0) {
-		DRM_ERROR("Cannot setup DMA ops, ret %d", ret);
+		DRM_ERROR("Cannot setup DMA mask, ret %d", ret);
 		return ret;
 	}