Merge tag 'rds-odp-for-5.5' into rdma.git for-next

From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

* tag 'rds-odp-for-5.5':
  net/rds: Use prefetch for On-Demand-Paging MR
  net/rds: Handle ODP mr registration/unregistration
  net/rds: Detect need of On-Demand-Paging memory registration
  RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
  IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
  RDMA/mlx5: Don't fake udata for kernel path
  IB/mlx5: Add ODP WQE handlers for kernel QPs
  IB/core: Add interface to advise_mr for kernel users
  IB/core: Introduce ib_reg_user_mr
  IB: Allow calls to ib_umem_get from kernel ULPs

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

26 files changed, 164 insertions, 113 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index a97fb759e2f4..3e35a8f2c5e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -613,7 +613,17 @@ static bool amdgpu_atpx_detect(void)
 	bool d3_supported = false;
 	struct pci_dev *parent_pdev;
 
-	while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) {
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
+		vga_count++;
+
+		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
+
+		parent_pdev = pci_upstream_bridge(pdev);
+		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
+		amdgpu_atpx_get_quirks(pdev);
+	}
+
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
 		vga_count++;
 
 		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0ffc9447b573..01a793a0cbf7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -142,7 +142,7 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
-int amdgpu_noretry = 1;
+int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
 
 struct amdgpu_mgpu_info mgpu_info = {
@@ -588,7 +588,7 @@ MODULE_PARM_DESC(mes,
 module_param_named(mes, amdgpu_mes, int, 0444);
 
 MODULE_PARM_DESC(noretry,
-	"Disable retry faults (0 = retry enabled, 1 = retry disabled (default))");
+	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
 /**
@@ -1359,7 +1359,8 @@ static struct drm_driver kms_driver = {
 	.driver_features =
 	    DRIVER_USE_AGP | DRIVER_ATOMIC |
 	    DRIVER_GEM |
-	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ,
+	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ |
+	    DRIVER_SYNCOBJ_TIMELINE,
 	.load = amdgpu_driver_load_kms,
 	.open = amdgpu_driver_open_kms,
 	.postclose = amdgpu_driver_postclose_kms,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 44be3a45b25e..e1b8d8daeafc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1488,7 +1488,7 @@ out:
 
 		/* Start rlc autoload after psp recieved all the gfx firmware */
 		if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ?
-		    AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) {
+		    AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_G)) {
 			ret = psp_rlc_autoload(psp);
 			if (ret) {
 				DRM_ERROR("Failed to start rlc autoload\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 410587b950f3..914acecda5cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -292,10 +292,10 @@ enum AMDGPU_UCODE_ID {
 	AMDGPU_UCODE_ID_CP_MEC2_JT,
 	AMDGPU_UCODE_ID_CP_MES,
 	AMDGPU_UCODE_ID_CP_MES_DATA,
-	AMDGPU_UCODE_ID_RLC_G,
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL,
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM,
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM,
+	AMDGPU_UCODE_ID_RLC_G,
 	AMDGPU_UCODE_ID_STORAGE,
 	AMDGPU_UCODE_ID_SMC,
 	AMDGPU_UCODE_ID_UVD,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 66328ffa395a..97105a5bb246 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1052,17 +1052,10 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		/* Disable GFXOFF on original raven.  There are combinations
-		 * of sbios and platforms that are not stable.
-		 */
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
-			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
-		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			 &&((adev->gfx.rlc_fw_version != 106 &&
-			     adev->gfx.rlc_fw_version < 531) ||
-			    (adev->gfx.rlc_fw_version == 53815) ||
-			    (adev->gfx.rlc_feature_version < 1) ||
-			    !adev->gfx.rlc.is_rlc_v2_1))
+		if (!(adev->rev_id >= 0x8 ||
+		      adev->pdev->device == 0x15d8) &&
+		    (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */
+		     !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */
 			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 
 		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
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 7aac9568d3be..803e59d97411 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3356,27 +3356,21 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
 	return color_space;
 }
 
-static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
-{
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
-
-	timing_out->display_color_depth--;
-}
-
-static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
-						const struct drm_display_info *info)
+static bool adjust_colour_depth_from_display_info(
+	struct dc_crtc_timing *timing_out,
+	const struct drm_display_info *info)
 {
+	enum dc_color_depth depth = timing_out->display_color_depth;
 	int normalized_clk;
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
 	do {
 		normalized_clk = timing_out->pix_clk_100hz / 10;
 		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
 		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
 			normalized_clk /= 2;
 		/* Adjusting pix clock following on HDMI spec based on colour depth */
-		switch (timing_out->display_color_depth) {
+		switch (depth) {
+		case COLOR_DEPTH_888:
+			break;
 		case COLOR_DEPTH_101010:
 			normalized_clk = (normalized_clk * 30) / 24;
 			break;
@@ -3387,14 +3381,15 @@ static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_
 			normalized_clk = (normalized_clk * 48) / 24;
 			break;
 		default:
-			return;
+			/* The above depths are the only ones valid for HDMI. */
+			return false;
 		}
-		if (normalized_clk <= info->max_tmds_clock)
-			return;
-		reduce_mode_colour_depth(timing_out);
-
-	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
-
+		if (normalized_clk <= info->max_tmds_clock) {
+			timing_out->display_color_depth = depth;
+			return true;
+		}
+	} while (--depth > COLOR_DEPTH_666);
+	return false;
 }
 
 static void fill_stream_properties_from_drm_display_mode(
@@ -3474,8 +3469,14 @@ static void fill_stream_properties_from_drm_display_mode(
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
-	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-		adjust_colour_depth_from_display_info(timing_out, info);
+	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		if (!adjust_colour_depth_from_display_info(timing_out, info) &&
+		    drm_mode_is_420_also(info, mode_in) &&
+		    timing_out->pixel_encoding != PIXEL_ENCODING_YCBCR420) {
+			timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+			adjust_colour_depth_from_display_info(timing_out, info);
+		}
+	}
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 5ff7ccedfbed..a23729d3174b 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -866,6 +866,7 @@ static int smu_sw_init(void *handle)
 	smu->smu_baco.platform_support = false;
 
 	mutex_init(&smu->sensor_lock);
+	mutex_init(&smu->metrics_lock);
 
 	smu->watermarks_bitmap = 0;
 	smu->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 cc71a1078a7a..472e9fed411a 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -862,18 +862,21 @@ static int arcturus_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	if (!smu_table->metrics_time ||
 	     time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_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 ac9758305ab3..41fce75b263f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -349,6 +349,7 @@ struct smu_context
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
 	struct mutex			sensor_lock;
+	struct mutex			metrics_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 4a14fd1f9fd5..ca62e92e5a4f 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -562,17 +562,20 @@ static int navi10_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	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) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 60b9ff097142..0d3a3b0a934e 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -1678,17 +1678,20 @@ static int vega20_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 875a3a9eabfa..7d0e7b031e44 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -56,7 +56,7 @@ malidp_mw_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
 	.get_modes = malidp_mw_connector_get_modes,
 	.mode_valid = malidp_mw_connector_mode_valid,
 };
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 273dd80fabf3..644c72f9c594 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -393,7 +393,7 @@ drm_dp_encode_sideband_req(const struct drm_dp_sideband_msg_req_body *req,
 			memcpy(&buf[idx], req->u.i2c_read.transactions[i].bytes, req->u.i2c_read.transactions[i].num_bytes);
 			idx += req->u.i2c_read.transactions[i].num_bytes;
 
-			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 5;
+			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 4;
 			buf[idx] |= (req->u.i2c_read.transactions[i].i2c_transaction_delay & 0xf);
 			idx++;
 		}
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 8ebeccdeed23..d8e8f3960f4d 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1283,7 +1283,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	 * Changes struct fb_var_screeninfo are currently not pushed back
 	 * to KMS, hence fail if different settings are requested.
 	 */
-	if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
+	if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
 	    var->xres > fb->width || var->yres > fb->height ||
 	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
 		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
@@ -1309,6 +1309,11 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	}
 
 	/*
+	 * Likewise, bits_per_pixel should be rounded up to a supported value.
+	 */
+	var->bits_per_pixel = fb->format->cpp[0] * 8;
+
+	/*
 	 * drm fbdev emulation doesn't support changing the pixel format at all,
 	 * so reject all pixel format changing requests.
 	 */
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 85e6b2bbb34f..3a5ac13d5801 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -856,7 +856,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 		}
 
 		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
-		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		if (IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, true);
 
 		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -875,7 +875,7 @@ static void i915_audio_component_put_power(struct device *kdev,
 
 	/* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
 	if (--dev_priv->audio_power_refcount == 0)
-		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		if (IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, false);
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index effc4250b230..301897791627 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4515,8 +4515,6 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
 {
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	i915_reg_t reg;
-	u32 trans_ddi_func_ctl2_val;
 
 	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
 		return;
@@ -4524,10 +4522,7 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
 	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
 		      transcoder_name(old_crtc_state->cpu_transcoder));
 
-	reg = TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder);
-	trans_ddi_func_ctl2_val = ~(PORT_SYNC_MODE_ENABLE |
-				    PORT_SYNC_MODE_MASTER_SELECT_MASK);
-	I915_WRITE(reg, trans_ddi_func_ctl2_val);
+	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
 }
 
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 75dd0e0367b7..68179fb56427 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4416,9 +4416,11 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 	ve->base.gt = siblings[0]->gt;
 	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
+
 	ve->base.class = OTHER_CLASS;
 	ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
 	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
 
 	/*
 	 * The decision on whether to submit a request using semaphores
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a47d5a7c32c9..93026217c121 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -1413,14 +1413,6 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	int len;
 	u32 *cs;
 
-	flags |= MI_MM_SPACE_GTT;
-	if (IS_HASWELL(i915))
-		/* These flags are for resource streamer on HSW+ */
-		flags |= HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN;
-	else
-		/* We need to save the extended state for powersaving modes */
-		flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN;
-
 	len = 4;
 	if (IS_GEN(i915, 7))
 		len += 2 + (num_engines ? 4 * num_engines + 6 : 0);
@@ -1589,22 +1581,21 @@ static int switch_context(struct i915_request *rq)
 	}
 
 	if (ce->state) {
-		u32 hw_flags;
+		u32 flags;
 
 		GEM_BUG_ON(rq->engine->id != RCS0);
 
-		/*
-		 * The kernel context(s) is treated as pure scratch and is not
-		 * expected to retain any state (as we sacrifice it during
-		 * suspend and on resume it may be corrupted). This is ok,
-		 * as nothing actually executes using the kernel context; it
-		 * is purely used for flushing user contexts.
-		 */
-		hw_flags = 0;
-		if (i915_gem_context_is_kernel(rq->gem_context))
-			hw_flags = MI_RESTORE_INHIBIT;
+		/* For resource streamer on HSW+ and power context elsewhere */
+		BUILD_BUG_ON(HSW_MI_RS_SAVE_STATE_EN != MI_SAVE_EXT_STATE_EN);
+		BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
+
+		flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
+		if (!i915_gem_context_is_kernel(rq->gem_context))
+			flags |= MI_RESTORE_EXT_STATE_EN;
+		else
+			flags |= MI_RESTORE_INHIBIT;
 
-		ret = mi_set_context(rq, hw_flags);
+		ret = mi_set_context(rq, flags);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e29bc137e7ba..21aa08f55811 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1660,8 +1660,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 	(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
 
 /* WaRsDisableCoarsePowerGating:skl,cnl */
-#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
+#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv)			\
+	(IS_CANNONLAKE(dev_priv) ||					\
+	 IS_SKL_GT3(dev_priv) ||					\
+	 IS_SKL_GT4(dev_priv))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4fd3d76db346..094011b8f64d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4177,7 +4177,13 @@ enum {
 #define  CPSSUNIT_CLKGATE_DIS		REG_BIT(9)
 
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
-#define  VFUNIT_CLKGATE_DIS		(1 << 20)
+#define   VFUNIT_CLKGATE_DIS		REG_BIT(20)
+#define   HSUNIT_CLKGATE_DIS		REG_BIT(8)
+#define   VSUNIT_CLKGATE_DIS		REG_BIT(3)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x94e4)
+#define   VSUNIT_CLKGATE_DIS_TGL	REG_BIT(19)
+#define   PSDUNIT_CLKGATE_DIS		REG_BIT(5)
 
 #define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
 #define   CGPSF_CLKGATE_DIS		(1 << 3)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ae6f495161..86379eddc908 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6565,6 +6565,17 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaEnable32PlaneMode:icl */
 	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
 		   _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
+
+	/*
+	 * Wa_1408615072:icl,ehl  (vsunit)
+	 * Wa_1407596294:icl,ehl  (hsunit)
+	 */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE,
+			 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
+	/* Wa_1407352427:icl,ehl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, PSDUNIT_CLKGATE_DIS);
 }
 
 static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index f80a8ba75977..3305a94fc930 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -215,11 +215,12 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_ddp_comp *comp;
 	int i, count = 0;
+	unsigned int local_index = plane - mtk_crtc->planes;
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		comp = mtk_crtc->ddp_comp[i];
-		if (plane->index < (count + mtk_ddp_comp_layer_nr(comp))) {
-			*local_layer = plane->index - count;
+		if (local_index < (count + mtk_ddp_comp_layer_nr(comp))) {
+			*local_layer = local_index - count;
 			return comp;
 		}
 		count += mtk_ddp_comp_layer_nr(comp);
@@ -310,7 +311,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 
 		plane_state = to_mtk_plane_state(plane->state);
 		comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
-		mtk_ddp_comp_layer_config(comp, local_layer, plane_state);
+		if (comp)
+			mtk_ddp_comp_layer_config(comp, local_layer,
+						  plane_state);
 	}
 
 	return 0;
@@ -386,8 +389,9 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
 							  &local_layer);
 
-			mtk_ddp_comp_layer_config(comp, local_layer,
-						  plane_state);
+			if (comp)
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state);
 			plane_state->pending.config = false;
 		}
 		mtk_crtc->pending_planes = false;
@@ -401,7 +405,9 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 	struct mtk_ddp_comp *comp;
 
 	comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
-	return mtk_ddp_comp_layer_check(comp, local_layer, state);
+	if (comp)
+		return mtk_ddp_comp_layer_check(comp, local_layer, state);
+	return 0;
 }
 
 static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index e9931bbbe846..d77c9f484ce3 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -230,28 +230,25 @@ static void mtk_dsi_mask(struct mtk_dsi *dsi, u32 offset, u32 mask, u32 data)
 static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi)
 {
 	u32 timcon0, timcon1, timcon2, timcon3;
-	u32 ui, cycle_time;
+	u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, 1000000);
 	struct mtk_phy_timing *timing = &dsi->phy_timing;
 
-	ui = DIV_ROUND_UP(1000000000, dsi->data_rate);
-	cycle_time = div_u64(8000000000ULL, dsi->data_rate);
+	timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1;
+	timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000;
+	timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 -
+			     timing->da_hs_prepare;
+	timing->da_hs_trail = timing->da_hs_prepare + 1;
 
-	timing->lpx = NS_TO_CYCLE(60, cycle_time);
-	timing->da_hs_prepare = NS_TO_CYCLE(50 + 5 * ui, cycle_time);
-	timing->da_hs_zero = NS_TO_CYCLE(110 + 6 * ui, cycle_time);
-	timing->da_hs_trail = NS_TO_CYCLE(77 + 4 * ui, cycle_time);
+	timing->ta_go = 4 * timing->lpx - 2;
+	timing->ta_sure = timing->lpx + 2;
+	timing->ta_get = 4 * timing->lpx;
+	timing->da_hs_exit = 2 * timing->lpx + 1;
 
-	timing->ta_go = 4 * timing->lpx;
-	timing->ta_sure = 3 * timing->lpx / 2;
-	timing->ta_get = 5 * timing->lpx;
-	timing->da_hs_exit = 2 * timing->lpx;
-
-	timing->clk_hs_zero = NS_TO_CYCLE(336, cycle_time);
-	timing->clk_hs_trail = NS_TO_CYCLE(100, cycle_time) + 10;
-
-	timing->clk_hs_prepare = NS_TO_CYCLE(64, cycle_time);
-	timing->clk_hs_post = NS_TO_CYCLE(80 + 52 * ui, cycle_time);
-	timing->clk_hs_exit = 2 * timing->lpx;
+	timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000);
+	timing->clk_hs_post = timing->clk_hs_prepare + 8;
+	timing->clk_hs_trail = timing->clk_hs_prepare;
+	timing->clk_hs_zero = timing->clk_hs_trail * 4;
+	timing->clk_hs_exit = 2 * timing->clk_hs_trail;
 
 	timcon0 = timing->lpx | timing->da_hs_prepare << 8 |
 		  timing->da_hs_zero << 16 | timing->da_hs_trail << 24;
@@ -482,27 +479,39 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 			dsi_tmp_buf_bpp - 10);
 
 	data_phy_cycles = timing->lpx + timing->da_hs_prepare +
-				  timing->da_hs_zero + timing->da_hs_exit + 2;
+			  timing->da_hs_zero + timing->da_hs_exit + 3;
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
-		if (vm->hfront_porch * dsi_tmp_buf_bpp >
+		if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
 		    data_phy_cycles * dsi->lanes + 18) {
-			horizontal_frontporch_byte = vm->hfront_porch *
-						     dsi_tmp_buf_bpp -
-						     data_phy_cycles *
-						     dsi->lanes - 18;
+			horizontal_frontporch_byte =
+				vm->hfront_porch * dsi_tmp_buf_bpp -
+				(data_phy_cycles * dsi->lanes + 18) *
+				vm->hfront_porch /
+				(vm->hfront_porch + vm->hback_porch);
+
+			horizontal_backporch_byte =
+				horizontal_backporch_byte -
+				(data_phy_cycles * dsi->lanes + 18) *
+				vm->hback_porch /
+				(vm->hfront_porch + vm->hback_porch);
 		} else {
 			DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
 			horizontal_frontporch_byte = vm->hfront_porch *
 						     dsi_tmp_buf_bpp;
 		}
 	} else {
-		if (vm->hfront_porch * dsi_tmp_buf_bpp >
+		if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
 		    data_phy_cycles * dsi->lanes + 12) {
-			horizontal_frontporch_byte = vm->hfront_porch *
-						     dsi_tmp_buf_bpp -
-						     data_phy_cycles *
-						     dsi->lanes - 12;
+			horizontal_frontporch_byte =
+				vm->hfront_porch * dsi_tmp_buf_bpp -
+				(data_phy_cycles * dsi->lanes + 12) *
+				vm->hfront_porch /
+				(vm->hfront_porch + vm->hback_porch);
+			horizontal_backporch_byte = horizontal_backporch_byte -
+				(data_phy_cycles * dsi->lanes + 12) *
+				vm->hback_porch /
+				(vm->hfront_porch + vm->hback_porch);
 		} else {
 			DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
 			horizontal_frontporch_byte = vm->hfront_porch *
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index a7c4654445c7..68d4644ac2dc 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -685,8 +685,6 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master,
 	struct sun4i_hdmi *hdmi = dev_get_drvdata(dev);
 
 	cec_unregister_adapter(hdmi->cec_adap);
-	drm_connector_cleanup(&hdmi->connector);
-	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
 	i2c_put_adapter(hdmi->ddc_i2c);
 	clk_disable_unprepare(hdmi->mod_clk);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 42651d737c55..c81cdce6ed55 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -489,7 +489,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 
 	WARN_ON(!tcon->quirks->has_channel_0);
 
-	tcon->dclk_min_div = 1;
+	tcon->dclk_min_div = tcon->quirks->dclk_min_div;
 	tcon->dclk_max_div = 127;
 	sun4i_tcon0_mode_set_common(tcon, mode);
 
@@ -1426,12 +1426,14 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon,
 static const struct sun4i_tcon_quirks sun4i_a10_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	.set_mux		= sun4i_a10_tcon_set_mux,
 };
 
 static const struct sun4i_tcon_quirks sun5i_a13_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	.set_mux		= sun5i_a13_tcon_set_mux,
 };
 
@@ -1440,6 +1442,7 @@ static const struct sun4i_tcon_quirks sun6i_a31_quirks = {
 	.has_channel_1		= true,
 	.has_lvds_alt		= true,
 	.needs_de_be_mux	= true,
+	.dclk_min_div		= 1,
 	.set_mux		= sun6i_tcon_set_mux,
 };
 
@@ -1447,11 +1450,13 @@ static const struct sun4i_tcon_quirks sun6i_a31s_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
 	.needs_de_be_mux	= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun7i_a20_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	/* Same display pipeline structure as A10 */
 	.set_mux		= sun4i_a10_tcon_set_mux,
 };
@@ -1459,11 +1464,13 @@ static const struct sun4i_tcon_quirks sun7i_a20_quirks = {
 static const struct sun4i_tcon_quirks sun8i_a33_quirks = {
 	.has_channel_0		= true,
 	.has_lvds_alt		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = {
 	.supports_lvds		= true,
 	.has_channel_0		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun8i_a83t_tv_quirks = {
@@ -1477,11 +1484,13 @@ static const struct sun4i_tcon_quirks sun8i_r40_tv_quirks = {
 
 static const struct sun4i_tcon_quirks sun8i_v3s_quirks = {
 	.has_channel_0		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun9i_a80_tcon_lcd_quirks = {
-	.has_channel_0	= true,
-	.needs_edp_reset = true,
+	.has_channel_0		= true,
+	.needs_edp_reset	= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun9i_a80_tcon_tv_quirks = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h
index f9f1fe80b206..a62ec826ae71 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.h
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h
@@ -224,6 +224,7 @@ struct sun4i_tcon_quirks {
 	bool	needs_de_be_mux; /* sun6i needs mux to select backend */
 	bool    needs_edp_reset; /* a80 edp reset needed for tcon0 access */
 	bool	supports_lvds;   /* Does the TCON support an LVDS output? */
+	u8	dclk_min_div;	/* minimum divider for TCON0 DCLK */
 
 	/* callback to handle tcon muxing options */
 	int	(*set_mux)(struct sun4i_tcon *, const struct drm_encoder *);