Merge tag 'drm-fixes-2023-03-30' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Daniel Vetter:
 "Two regression fixes in here, otherwise just the usual stuff:

   - i915 fixes for color mgmt, psr, lmem flush, hibernate oops, and
     more

   - amdgpu: dp mst and hibernate regression fix

   - etnaviv: revert fdinfo support (incl drm/sched revert), leak fix

   - misc ivpu fixes, nouveau backlight, drm buddy allocator 32bit
     fixes"

* tag 'drm-fixes-2023-03-30' of git://anongit.freedesktop.org/drm/drm: (27 commits)
  Revert "drm/scheduler: track GPU active time per entity"
  Revert "drm/etnaviv: export client GPU usage statistics via fdinfo"
  drm/etnaviv: fix reference leak when mmaping imported buffer
  drm/amdgpu: allow more APUs to do mode2 reset when go to S4
  drm/amd/display: Take FEC Overhead into Timeslot Calculation
  drm/amd/display: Add DSC Support for Synaptics Cascaded MST Hub
  drm: test: Fix 32-bit issue in drm_buddy_test
  drm: buddy_allocator: Fix buddy allocator init on 32-bit systems
  drm/nouveau/kms: Fix backlight registration
  drm/i915/perf: Drop wakeref on GuC RC error
  drm/i915/dpt: Treat the DPT BO as a framebuffer
  drm/i915/gem: Flush lmem contents after construction
  drm/i915/tc: Fix the ICL PHY ownership check in TC-cold state
  drm/i915: Disable DC states for all commits
  drm/i915: Workaround ICL CSC_MODE sticky arming
  drm/i915: Add a .color_post_update() hook
  drm/i915: Move CSC load back into .color_commit_arm() when PSR is enabled on skl/glk
  drm/i915: Split icl_color_commit_noarm() from skl_color_commit_noarm()
  drm/i915/pmu: Use functions common with sysfs to read actual freq
  accel/ivpu: Fix IPC buffer header status field value
  ...

29 files changed, 341 insertions, 193 deletions

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 231f29bb5025..6a320a73e3cc 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -8,7 +8,6 @@
 #include <linux/pci.h>
 
 #include <drm/drm_accel.h>
-#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_ioctl.h>
@@ -118,6 +117,10 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
 	struct drm_ivpu_param *args = data;
 	int ret = 0;
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
 
 	switch (args->param) {
 	case DRM_IVPU_PARAM_DEVICE_ID:
@@ -171,6 +174,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		break;
 	}
 
+	drm_dev_exit(idx);
 	return ret;
 }
 
@@ -470,8 +474,8 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 
 	vdev->hw->ops = &ivpu_hw_mtl_ops;
 	vdev->platform = IVPU_PLATFORM_INVALID;
-	vdev->context_xa_limit.min = IVPU_GLOBAL_CONTEXT_MMU_SSID + 1;
-	vdev->context_xa_limit.max = IVPU_CONTEXT_LIMIT;
+	vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
+	vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
 	atomic64_set(&vdev->unique_id_counter, 0);
 	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
@@ -565,6 +569,8 @@ err_mmu_gctx_fini:
 	ivpu_mmu_global_context_fini(vdev);
 err_power_down:
 	ivpu_hw_power_down(vdev);
+	if (IVPU_WA(d3hot_after_power_off))
+		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 err_xa_destroy:
 	xa_destroy(&vdev->submitted_jobs_xa);
 	xa_destroy(&vdev->context_xa);
@@ -575,7 +581,11 @@ static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_pm_disable(vdev);
 	ivpu_shutdown(vdev);
+	if (IVPU_WA(d3hot_after_power_off))
+		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 	ivpu_job_done_thread_fini(vdev);
+	ivpu_pm_cancel_recovery(vdev);
+
 	ivpu_ipc_fini(vdev);
 	ivpu_fw_fini(vdev);
 	ivpu_mmu_global_context_fini(vdev);
@@ -622,7 +632,7 @@ static void ivpu_remove(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
-	drm_dev_unregister(&vdev->drm);
+	drm_dev_unplug(&vdev->drm);
 	ivpu_dev_fini(vdev);
 }
 
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index f47b4965db2e..d3013fbd13b3 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -7,6 +7,7 @@
 #define __IVPU_DRV_H__
 
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_mm.h>
 #include <drm/drm_print.h>
@@ -24,7 +25,10 @@
 #define PCI_DEVICE_ID_MTL   0x7d1d
 
 #define IVPU_GLOBAL_CONTEXT_MMU_SSID 0
-#define IVPU_CONTEXT_LIMIT	     64
+/* SSID 1 is used by the VPU to represent invalid context */
+#define IVPU_USER_CONTEXT_MIN_SSID   2
+#define IVPU_USER_CONTEXT_MAX_SSID   (IVPU_USER_CONTEXT_MIN_SSID + 63)
+
 #define IVPU_NUM_ENGINES	     2
 
 #define IVPU_PLATFORM_SILICON 0
@@ -70,6 +74,7 @@
 struct ivpu_wa_table {
 	bool punit_disabled;
 	bool clear_runtime_mem;
+	bool d3hot_after_power_off;
 };
 
 struct ivpu_hw_info;
diff --git a/drivers/accel/ivpu/ivpu_hw_mtl.c b/drivers/accel/ivpu/ivpu_hw_mtl.c
index 62bfaa9081c4..382ec127be8e 100644
--- a/drivers/accel/ivpu/ivpu_hw_mtl.c
+++ b/drivers/accel/ivpu/ivpu_hw_mtl.c
@@ -12,24 +12,23 @@
 #include "ivpu_mmu.h"
 #include "ivpu_pm.h"
 
-#define TILE_FUSE_ENABLE_BOTH	     0x0
-#define TILE_FUSE_ENABLE_UPPER	     0x1
-#define TILE_FUSE_ENABLE_LOWER	     0x2
-
-#define TILE_SKU_BOTH_MTL	     0x3630
-#define TILE_SKU_LOWER_MTL	     0x3631
-#define TILE_SKU_UPPER_MTL	     0x3632
+#define TILE_FUSE_ENABLE_BOTH        0x0
+#define TILE_SKU_BOTH_MTL            0x3630
 
 /* Work point configuration values */
-#define WP_CONFIG_1_TILE_5_3_RATIO   0x0101
-#define WP_CONFIG_1_TILE_4_3_RATIO   0x0102
-#define WP_CONFIG_2_TILE_5_3_RATIO   0x0201
-#define WP_CONFIG_2_TILE_4_3_RATIO   0x0202
-#define WP_CONFIG_0_TILE_PLL_OFF     0x0000
+#define CONFIG_1_TILE                0x01
+#define CONFIG_2_TILE                0x02
+#define PLL_RATIO_5_3                0x01
+#define PLL_RATIO_4_3                0x02
+#define WP_CONFIG(tile, ratio)       (((tile) << 8) | (ratio))
+#define WP_CONFIG_1_TILE_5_3_RATIO   WP_CONFIG(CONFIG_1_TILE, PLL_RATIO_5_3)
+#define WP_CONFIG_1_TILE_4_3_RATIO   WP_CONFIG(CONFIG_1_TILE, PLL_RATIO_4_3)
+#define WP_CONFIG_2_TILE_5_3_RATIO   WP_CONFIG(CONFIG_2_TILE, PLL_RATIO_5_3)
+#define WP_CONFIG_2_TILE_4_3_RATIO   WP_CONFIG(CONFIG_2_TILE, PLL_RATIO_4_3)
+#define WP_CONFIG_0_TILE_PLL_OFF     WP_CONFIG(0, 0)
 
 #define PLL_REF_CLK_FREQ	     (50 * 1000000)
 #define PLL_SIMULATION_FREQ	     (10 * 1000000)
-#define PLL_RATIO_TO_FREQ(x)	     ((x) * PLL_REF_CLK_FREQ)
 #define PLL_DEFAULT_EPP_VALUE	     0x80
 
 #define TIM_SAFE_ENABLE		     0xf1d0dead
@@ -101,6 +100,7 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev)
 {
 	vdev->wa.punit_disabled = ivpu_is_fpga(vdev);
 	vdev->wa.clear_runtime_mem = false;
+	vdev->wa.d3hot_after_power_off = true;
 }
 
 static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
@@ -218,7 +218,8 @@ static int ivpu_pll_drive(struct ivpu_device *vdev, bool enable)
 		config = 0;
 	}
 
-	ivpu_dbg(vdev, PM, "PLL workpoint request: %d Hz\n", PLL_RATIO_TO_FREQ(target_ratio));
+	ivpu_dbg(vdev, PM, "PLL workpoint request: config 0x%04x pll ratio 0x%x\n",
+		 config, target_ratio);
 
 	ret = ivpu_pll_cmd_send(vdev, hw->pll.min_ratio, hw->pll.max_ratio, target_ratio, config);
 	if (ret) {
@@ -403,11 +404,6 @@ static int ivpu_boot_host_ss_axi_enable(struct ivpu_device *vdev)
 	return ivpu_boot_host_ss_axi_drive(vdev, true);
 }
 
-static int ivpu_boot_host_ss_axi_disable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_axi_drive(vdev, false);
-}
-
 static int ivpu_boot_host_ss_top_noc_drive(struct ivpu_device *vdev, bool enable)
 {
 	int ret;
@@ -441,11 +437,6 @@ static int ivpu_boot_host_ss_top_noc_enable(struct ivpu_device *vdev)
 	return ivpu_boot_host_ss_top_noc_drive(vdev, true);
 }
 
-static int ivpu_boot_host_ss_top_noc_disable(struct ivpu_device *vdev)
-{
-	return ivpu_boot_host_ss_top_noc_drive(vdev, false);
-}
-
 static void ivpu_boot_pwr_island_trickle_drive(struct ivpu_device *vdev, bool enable)
 {
 	u32 val = REGV_RD32(MTL_VPU_HOST_SS_AON_PWR_ISLAND_TRICKLE_EN0);
@@ -504,16 +495,6 @@ static void ivpu_boot_dpu_active_drive(struct ivpu_device *vdev, bool enable)
 	REGV_WR32(MTL_VPU_HOST_SS_AON_DPU_ACTIVE, val);
 }
 
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
-	ivpu_boot_dpu_active_drive(vdev, false);
-	ivpu_boot_pwr_island_isolation_drive(vdev, true);
-	ivpu_boot_pwr_island_trickle_drive(vdev, false);
-	ivpu_boot_pwr_island_drive(vdev, false);
-
-	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
 static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 {
 	int ret;
@@ -629,34 +610,10 @@ static int ivpu_boot_d0i3_drive(struct ivpu_device *vdev, bool enable)
 static int ivpu_hw_mtl_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
-	u32 tile_fuse;
-
-	tile_fuse = REGB_RD32(MTL_BUTTRESS_TILE_FUSE);
-	if (!REG_TEST_FLD(MTL_BUTTRESS_TILE_FUSE, VALID, tile_fuse))
-		ivpu_warn(vdev, "Tile Fuse: Invalid (0x%x)\n", tile_fuse);
-
-	hw->tile_fuse = REG_GET_FLD(MTL_BUTTRESS_TILE_FUSE, SKU, tile_fuse);
-	switch (hw->tile_fuse) {
-	case TILE_FUSE_ENABLE_LOWER:
-		hw->sku = TILE_SKU_LOWER_MTL;
-		hw->config = WP_CONFIG_1_TILE_5_3_RATIO;
-		ivpu_dbg(vdev, MISC, "Tile Fuse: Enable Lower\n");
-		break;
-	case TILE_FUSE_ENABLE_UPPER:
-		hw->sku = TILE_SKU_UPPER_MTL;
-		hw->config = WP_CONFIG_1_TILE_4_3_RATIO;
-		ivpu_dbg(vdev, MISC, "Tile Fuse: Enable Upper\n");
-		break;
-	case TILE_FUSE_ENABLE_BOTH:
-		hw->sku = TILE_SKU_BOTH_MTL;
-		hw->config = WP_CONFIG_2_TILE_5_3_RATIO;
-		ivpu_dbg(vdev, MISC, "Tile Fuse: Enable Both\n");
-		break;
-	default:
-		hw->config = WP_CONFIG_0_TILE_PLL_OFF;
-		ivpu_dbg(vdev, MISC, "Tile Fuse: Disable\n");
-		break;
-	}
+
+	hw->tile_fuse = TILE_FUSE_ENABLE_BOTH;
+	hw->sku = TILE_SKU_BOTH_MTL;
+	hw->config = WP_CONFIG_2_TILE_4_3_RATIO;
 
 	ivpu_pll_init_frequency_ratios(vdev);
 
@@ -797,21 +754,8 @@ static int ivpu_hw_mtl_power_down(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	/* FPGA requires manual clearing of IP_Reset bit by enabling quiescent state */
-	if (ivpu_is_fpga(vdev)) {
-		if (ivpu_boot_host_ss_top_noc_disable(vdev)) {
-			ivpu_err(vdev, "Failed to disable TOP NOC\n");
-			ret = -EIO;
-		}
-
-		if (ivpu_boot_host_ss_axi_disable(vdev)) {
-			ivpu_err(vdev, "Failed to disable AXI\n");
-			ret = -EIO;
-		}
-	}
-
-	if (ivpu_boot_pwr_domain_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable power domain\n");
+	if (ivpu_hw_mtl_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset the VPU\n");
 		ret = -EIO;
 	}
 
@@ -844,6 +788,19 @@ static void ivpu_hw_mtl_wdt_disable(struct ivpu_device *vdev)
 	REGV_WR32(MTL_VPU_CPU_SS_TIM_GEN_CONFIG, val);
 }
 
+static u32 ivpu_hw_mtl_pll_to_freq(u32 ratio, u32 config)
+{
+	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
+	u32 cpu_clock;
+
+	if ((config & 0xff) == PLL_RATIO_4_3)
+		cpu_clock = pll_clock * 2 / 4;
+	else
+		cpu_clock = pll_clock * 2 / 5;
+
+	return cpu_clock;
+}
+
 /* Register indirect accesses */
 static u32 ivpu_hw_mtl_reg_pll_freq_get(struct ivpu_device *vdev)
 {
@@ -855,7 +812,7 @@ static u32 ivpu_hw_mtl_reg_pll_freq_get(struct ivpu_device *vdev)
 	if (!ivpu_is_silicon(vdev))
 		return PLL_SIMULATION_FREQ;
 
-	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
+	return ivpu_hw_mtl_pll_to_freq(pll_curr_ratio, vdev->hw->config);
 }
 
 static u32 ivpu_hw_mtl_reg_telemetry_offset_get(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 9838202ecfad..68f5b6668e00 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -21,7 +21,7 @@ struct ivpu_bo;
 #define IVPU_IPC_ALIGNMENT	   64
 
 #define IVPU_IPC_HDR_FREE	   0
-#define IVPU_IPC_HDR_ALLOCATED	   0
+#define IVPU_IPC_HDR_ALLOCATED	   1
 
 /**
  * struct ivpu_ipc_hdr - The IPC message header structure, exchanged
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 94068aedf97c..910301fae435 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -489,12 +489,12 @@ unlock_reservations:
 
 int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	int ret = 0;
 	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct drm_ivpu_submit *params = data;
 	struct ivpu_job *job;
 	u32 *buf_handles;
+	int idx, ret;
 
 	if (params->engine > DRM_IVPU_ENGINE_COPY)
 		return -EINVAL;
@@ -523,6 +523,11 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto free_handles;
 	}
 
+	if (!drm_dev_enter(&vdev->drm, &idx)) {
+		ret = -ENODEV;
+		goto free_handles;
+	}
+
 	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n",
 		 file_priv->ctx.id, params->buffer_count);
 
@@ -530,7 +535,7 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (!job) {
 		ivpu_err(vdev, "Failed to create job\n");
 		ret = -ENOMEM;
-		goto free_handles;
+		goto dev_exit;
 	}
 
 	ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, params->buffer_count,
@@ -548,6 +553,8 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 job_put:
 	job_put(job);
+dev_exit:
+	drm_dev_exit(idx);
 free_handles:
 	kfree(buf_handles);
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 553bcbd787b3..7df72fa8100f 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -98,12 +98,18 @@ retry:
 static void ivpu_pm_recovery_work(struct work_struct *work)
 {
 	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
-	struct ivpu_device *vdev =  pm->vdev;
+	struct ivpu_device *vdev = pm->vdev;
 	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
 	int ret;
 
-	ret = pci_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret)
+retry:
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
+		cond_resched();
+		goto retry;
+	}
+
+	if (ret && ret != -EAGAIN)
 		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
@@ -306,6 +312,11 @@ int ivpu_pm_init(struct ivpu_device *vdev)
 	return 0;
 }
 
+void ivpu_pm_cancel_recovery(struct ivpu_device *vdev)
+{
+	cancel_work_sync(&vdev->pm->recovery_work);
+}
+
 void ivpu_pm_enable(struct ivpu_device *vdev)
 {
 	struct device *dev = vdev->drm.dev;
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index dc1b3758e13f..baca98187255 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -21,6 +21,7 @@ struct ivpu_pm_info {
 int ivpu_pm_init(struct ivpu_device *vdev);
 void ivpu_pm_enable(struct ivpu_device *vdev);
 void ivpu_pm_disable(struct ivpu_device *vdev);
+void ivpu_pm_cancel_recovery(struct ivpu_device *vdev);
 
 int ivpu_pm_suspend_cb(struct device *dev);
 int ivpu_pm_resume_cb(struct device *dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 60b1857f469e..aeeec211861c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -981,7 +981,12 @@ static bool amdgpu_atcs_pci_probe_handle(struct pci_dev *pdev)
  */
 bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
 {
-	if (adev->flags & AMD_IS_APU)
+	if ((adev->flags & AMD_IS_APU) &&
+	    adev->gfx.imu.funcs) /* Not need to do mode2 reset for IMU enabled APUs */
+		return false;
+
+	if ((adev->flags & AMD_IS_APU) &&
+	    amdgpu_acpi_is_s3_active(adev))
 		return false;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index e25e1b2bf194..8dc442f90eaf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -212,6 +212,21 @@ bool needs_dsc_aux_workaround(struct dc_link *link)
 	return false;
 }
 
+bool is_synaptics_cascaded_panamera(struct dc_link *link, struct drm_dp_mst_port *port)
+{
+	u8 branch_vendor_data[4] = { 0 }; // Vendor data 0x50C ~ 0x50F
+
+	if (drm_dp_dpcd_read(port->mgr->aux, DP_BRANCH_VENDOR_SPECIFIC_START, &branch_vendor_data, 4) == 4) {
+		if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 &&
+				IS_SYNAPTICS_CASCADED_PANAMERA(link->dpcd_caps.branch_dev_name, branch_vendor_data)) {
+			DRM_INFO("Synaptics Cascaded MST hub\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector)
 {
 	struct dc_sink *dc_sink = aconnector->dc_sink;
@@ -235,6 +250,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	    needs_dsc_aux_workaround(aconnector->dc_link))
 		aconnector->dsc_aux = &aconnector->mst_root->dm_dp_aux.aux;
 
+	/* synaptics cascaded MST hub case */
+	if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port))
+		aconnector->dsc_aux = port->mgr->aux;
+
 	if (!aconnector->dsc_aux)
 		return false;
 
@@ -662,12 +681,25 @@ struct dsc_mst_fairness_params {
 	struct amdgpu_dm_connector *aconnector;
 };
 
-static int kbps_to_peak_pbn(int kbps)
+static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link)
+{
+	u8 link_coding_cap;
+	uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B;
+
+	link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link);
+	if (link_coding_cap == DP_128b_132b_ENCODING)
+		fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B;
+
+	return fec_overhead_multiplier_x1000;
+}
+
+static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000)
 {
 	u64 peak_kbps = kbps;
 
 	peak_kbps *= 1006;
-	peak_kbps = div_u64(peak_kbps, 1000);
+	peak_kbps *= fec_overhead_multiplier_x1000;
+	peak_kbps = div_u64(peak_kbps, 1000 * 1000);
 	return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000));
 }
 
@@ -761,11 +793,12 @@ static int increase_dsc_bpp(struct drm_atomic_state *state,
 	int link_timeslots_used;
 	int fair_pbn_alloc;
 	int ret = 0;
+	uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
 
 	for (i = 0; i < count; i++) {
 		if (vars[i + k].dsc_enabled) {
 			initial_slack[i] =
-			kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn;
+			kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn;
 			bpp_increased[i] = false;
 			remaining_to_increase += 1;
 		} else {
@@ -861,6 +894,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
 	int next_index;
 	int remaining_to_try = 0;
 	int ret;
+	uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
 
 	for (i = 0; i < count; i++) {
 		if (vars[i + k].dsc_enabled
@@ -890,7 +924,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
 		if (next_index == -1)
 			break;
 
-		vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps);
+		vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
 		ret = drm_dp_atomic_find_time_slots(state,
 						    params[next_index].port->mgr,
 						    params[next_index].port,
@@ -903,7 +937,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
 			vars[next_index].dsc_enabled = false;
 			vars[next_index].bpp_x16 = 0;
 		} else {
-			vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps);
+			vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps, fec_overhead_multiplier_x1000);
 			ret = drm_dp_atomic_find_time_slots(state,
 							    params[next_index].port->mgr,
 							    params[next_index].port,
@@ -932,6 +966,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	int count = 0;
 	int i, k, ret;
 	bool debugfs_overwrite = false;
+	uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
 
 	memset(params, 0, sizeof(params));
 
@@ -993,7 +1028,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	/* Try no compression */
 	for (i = 0; i < count; i++) {
 		vars[i + k].aconnector = params[i].aconnector;
-		vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+		vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
 		vars[i + k].dsc_enabled = false;
 		vars[i + k].bpp_x16 = 0;
 		ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port,
@@ -1012,7 +1047,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	/* Try max compression */
 	for (i = 0; i < count; i++) {
 		if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) {
-			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000);
 			vars[i + k].dsc_enabled = true;
 			vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
 			ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr,
@@ -1020,7 +1055,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 			if (ret < 0)
 				return ret;
 		} else {
-			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
 			vars[i + k].dsc_enabled = false;
 			vars[i + k].bpp_x16 = 0;
 			ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 97fd70df531b..1e4ede1e57ab 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -34,6 +34,21 @@
 #define SYNAPTICS_RC_OFFSET        0x4BC
 #define SYNAPTICS_RC_DATA          0x4C0
 
+#define DP_BRANCH_VENDOR_SPECIFIC_START 0x50C
+
+/**
+ * Panamera MST Hub detection
+ * Offset DPCD 050Eh == 0x5A indicates cascaded MST hub case
+ * Check from beginning of branch device vendor specific field (050Ch)
+ */
+#define IS_SYNAPTICS_PANAMERA(branchDevName) (((int)branchDevName[4] & 0xF0) == 0x50 ? 1 : 0)
+#define BRANCH_HW_REVISION_PANAMERA_A2 0x10
+#define SYNAPTICS_CASCADED_HUB_ID  0x5A
+#define IS_SYNAPTICS_CASCADED_PANAMERA(devName, data) ((IS_SYNAPTICS_PANAMERA(devName) && ((int)data[2] == SYNAPTICS_CASCADED_HUB_ID)) ? 1 : 0)
+
+#define PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B	1031
+#define PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B	1000
+
 struct amdgpu_display_manager;
 struct amdgpu_dm_connector;
 
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 3d1f50f481cf..7098f125b54a 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -146,8 +146,8 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
 		unsigned int order;
 		u64 root_size;
 
-		root_size = rounddown_pow_of_two(size);
-		order = ilog2(root_size) - ilog2(chunk_size);
+		order = ilog2(size) - ilog2(chunk_size);
+		root_size = chunk_size << order;
 
 		root = drm_block_alloc(mm, NULL, order, offset);
 		if (!root)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 44ca803237a5..31a7f59ccb49 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -22,7 +22,6 @@
 #include "etnaviv_gem.h"
 #include "etnaviv_mmu.h"
 #include "etnaviv_perfmon.h"
-#include "common.xml.h"
 
 /*
  * DRM operations:
@@ -476,47 +475,7 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = {
 	ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW),
 };
 
-static void etnaviv_fop_show_fdinfo(struct seq_file *m, struct file *f)
-{
-	struct drm_file *file = f->private_data;
-	struct drm_device *dev = file->minor->dev;
-	struct etnaviv_drm_private *priv = dev->dev_private;
-	struct etnaviv_file_private *ctx = file->driver_priv;
-
-	/*
-	 * For a description of the text output format used here, see
-	 * Documentation/gpu/drm-usage-stats.rst.
-	 */
-	seq_printf(m, "drm-driver:\t%s\n", dev->driver->name);
-	seq_printf(m, "drm-client-id:\t%u\n", ctx->id);
-
-	for (int i = 0; i < ETNA_MAX_PIPES; i++) {
-		struct etnaviv_gpu *gpu = priv->gpu[i];
-		char engine[10] = "UNK";
-		int cur = 0;
-
-		if (!gpu)
-			continue;
-
-		if (gpu->identity.features & chipFeatures_PIPE_2D)
-			cur = snprintf(engine, sizeof(engine), "2D");
-		if (gpu->identity.features & chipFeatures_PIPE_3D)
-			cur = snprintf(engine + cur, sizeof(engine) - cur,
-				       "%s3D", cur ? "/" : "");
-		if (gpu->identity.nn_core_count > 0)
-			cur = snprintf(engine + cur, sizeof(engine) - cur,
-				       "%sNN", cur ? "/" : "");
-
-		seq_printf(m, "drm-engine-%s:\t%llu ns\n", engine,
-			   ctx->sched_entity[i].elapsed_ns);
-	}
-}
-
-static const struct file_operations fops = {
-	.owner = THIS_MODULE,
-	DRM_GEM_FOPS,
-	.show_fdinfo = etnaviv_fop_show_fdinfo,
-};
+DEFINE_DRM_GEM_FOPS(fops);
 
 static const struct drm_driver etnaviv_drm_driver = {
 	.driver_features    = DRIVER_GEM | DRIVER_RENDER,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 7031db145a77..3524b5811682 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -91,7 +91,15 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj)
 static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 		struct vm_area_struct *vma)
 {
-	return dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0);
+	int ret;
+
+	ret = dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0);
+	if (!ret) {
+		/* Drop the reference acquired by drm_gem_mmap_obj(). */
+		drm_gem_object_put(&etnaviv_obj->base);
+	}
+
+	return ret;
 }
 
 static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = {
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 8d97c299e657..bd598a7f5047 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -47,6 +47,11 @@ struct intel_color_funcs {
 	 */
 	void (*color_commit_arm)(const struct intel_crtc_state *crtc_state);
 	/*
+	 * Perform any extra tasks needed after all the
+	 * double buffered registers have been latched.
+	 */
+	void (*color_post_update)(const struct intel_crtc_state *crtc_state);
+	/*
 	 * Load LUTs (and other single buffered color management
 	 * registers). Will (hopefully) be called during the vblank
 	 * following the latching of any double buffered registers
@@ -614,9 +619,33 @@ static void ilk_lut_12p4_pack(struct drm_color_lut *entry, u32 ldw, u32 udw)
 
 static void icl_color_commit_noarm(const struct intel_crtc_state *crtc_state)
 {
+	/*
+	 * Despite Wa_1406463849, ICL no longer suffers from the SKL
+	 * DC5/PSR CSC black screen issue (see skl_color_commit_noarm()).
+	 * Possibly due to the extra sticky CSC arming
+	 * (see icl_color_post_update()).
+	 *
+	 * On TGL+ all CSC arming issues have been properly fixed.
+	 */
 	icl_load_csc_matrix(crtc_state);
 }
 
+static void skl_color_commit_noarm(const struct intel_crtc_state *crtc_state)
+{
+	/*
+	 * Possibly related to display WA #1184, SKL CSC loses the latched
+	 * CSC coeff/offset register values if the CSC registers are disarmed
+	 * between DC5 exit and PSR exit. This will cause the plane(s) to
+	 * output all black (until CSC_MODE is rearmed and properly latched).
+	 * Once PSR exit (and proper register latching) has occurred the
+	 * danger is over. Thus when PSR is enabled the CSC coeff/offset
+	 * register programming will be peformed from skl_color_commit_arm()
+	 * which is called after PSR exit.
+	 */
+	if (!crtc_state->has_psr)
+		ilk_load_csc_matrix(crtc_state);
+}
+
 static void ilk_color_commit_noarm(const struct intel_crtc_state *crtc_state)
 {
 	ilk_load_csc_matrix(crtc_state);
@@ -659,6 +688,9 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state)
 	enum pipe pipe = crtc->pipe;
 	u32 val = 0;
 
+	if (crtc_state->has_psr)
+		ilk_load_csc_matrix(crtc_state);
+
 	/*
 	 * We don't (yet) allow userspace to control the pipe background color,
 	 * so force it to black, but apply pipe gamma and CSC appropriately
@@ -677,6 +709,47 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state)
 			  crtc_state->csc_mode);
 }
 
+static void icl_color_commit_arm(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+
+	/*
+	 * We don't (yet) allow userspace to control the pipe background color,
+	 * so force it to black.
+	 */
+	intel_de_write(i915, SKL_BOTTOM_COLOR(pipe), 0);
+
+	intel_de_write(i915, GAMMA_MODE(crtc->pipe),
+		       crtc_state->gamma_mode);
+
+	intel_de_write_fw(i915, PIPE_CSC_MODE(crtc->pipe),
+			  crtc_state->csc_mode);
+}
+
+static void icl_color_post_update(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	/*
+	 * Despite Wa_1406463849, ICL CSC is no longer disarmed by
+	 * coeff/offset register *writes*. Instead, once CSC_MODE
+	 * is armed it stays armed, even after it has been latched.
+	 * Afterwards the coeff/offset registers become effectively
+	 * self-arming. That self-arming must be disabled before the
+	 * next icl_color_commit_noarm() tries to write the next set
+	 * of coeff/offset registers. Fortunately register *reads*
+	 * do still disarm the CSC. Naturally this must not be done
+	 * until the previously written CSC registers have actually
+	 * been latched.
+	 *
+	 * TGL+ no longer need this workaround.
+	 */
+	intel_de_read_fw(i915, PIPE_CSC_PREOFF_HI(crtc->pipe));
+}
+
 static struct drm_property_blob *
 create_linear_lut(struct drm_i915_private *i915, int lut_size)
 {
@@ -1373,6 +1446,14 @@ void intel_color_commit_arm(const struct intel_crtc_state *crtc_state)
 	i915->display.funcs.color->color_commit_arm(crtc_state);
 }
 
+void intel_color_post_update(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
+
+	if (i915->display.funcs.color->color_post_update)
+		i915->display.funcs.color->color_post_update(crtc_state);
+}
+
 void intel_color_prepare_commit(struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
@@ -3064,10 +3145,20 @@ static const struct intel_color_funcs i9xx_color_funcs = {
 	.lut_equal = i9xx_lut_equal,
 };
 
+static const struct intel_color_funcs tgl_color_funcs = {
+	.color_check = icl_color_check,
+	.color_commit_noarm = icl_color_commit_noarm,
+	.color_commit_arm = icl_color_commit_arm,
+	.load_luts = icl_load_luts,
+	.read_luts = icl_read_luts,
+	.lut_equal = icl_lut_equal,
+};
+
 static const struct intel_color_funcs icl_color_funcs = {
 	.color_check = icl_color_check,
 	.color_commit_noarm = icl_color_commit_noarm,
-	.color_commit_arm = skl_color_commit_arm,
+	.color_commit_arm = icl_color_commit_arm,
+	.color_post_update = icl_color_post_update,
 	.load_luts = icl_load_luts,
 	.read_luts = icl_read_luts,
 	.lut_equal = icl_lut_equal,
@@ -3075,7 +3166,7 @@ static const struct intel_color_funcs icl_color_funcs = {
 
 static const struct intel_color_funcs glk_color_funcs = {
 	.color_check = glk_color_check,
-	.color_commit_noarm = ilk_color_commit_noarm,
+	.color_commit_noarm = skl_color_commit_noarm,
 	.color_commit_arm = skl_color_commit_arm,
 	.load_luts = glk_load_luts,
 	.read_luts = glk_read_luts,
@@ -3084,7 +3175,7 @@ static const struct intel_color_funcs glk_color_funcs = {
 
 static const struct intel_color_funcs skl_color_funcs = {
 	.color_check = ivb_color_check,
-	.color_commit_noarm = ilk_color_commit_noarm,
+	.color_commit_noarm = skl_color_commit_noarm,
 	.color_commit_arm = skl_color_commit_arm,
 	.load_luts = bdw_load_luts,
 	.read_luts = bdw_read_luts,
@@ -3180,7 +3271,9 @@ void intel_color_init_hooks(struct drm_i915_private *i915)
 		else
 			i915->display.funcs.color = &i9xx_color_funcs;
 	} else {
-		if (DISPLAY_VER(i915) >= 11)
+		if (DISPLAY_VER(i915) >= 12)
+			i915->display.funcs.color = &tgl_color_funcs;
+		else if (DISPLAY_VER(i915) == 11)
 			i915->display.funcs.color = &icl_color_funcs;
 		else if (DISPLAY_VER(i915) == 10)
 			i915->display.funcs.color = &glk_color_funcs;
diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h
index d620b5b1e2a6..8002492be709 100644
--- a/drivers/gpu/drm/i915/display/intel_color.h
+++ b/drivers/gpu/drm/i915/display/intel_color.h
@@ -21,6 +21,7 @@ void intel_color_prepare_commit(struct intel_crtc_state *crtc_state);
 void intel_color_cleanup_commit(struct intel_crtc_state *crtc_state);
 void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state);
 void intel_color_commit_arm(const struct intel_crtc_state *crtc_state);
+void intel_color_post_update(const struct intel_crtc_state *crtc_state);
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state);
 void intel_color_get_config(struct intel_crtc_state *crtc_state);
 bool intel_color_lut_equal(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 208b1b5b15dd..63b4b73f47c6 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -1209,6 +1209,9 @@ static void intel_post_plane_update(struct intel_atomic_state *state,
 	if (needs_cursorclk_wa(old_crtc_state) &&
 	    !needs_cursorclk_wa(new_crtc_state))
 		icl_wa_cursorclkgating(dev_priv, pipe, false);
+
+	if (intel_crtc_needs_color_update(new_crtc_state))
+		intel_color_post_update(new_crtc_state);
 }
 
 static void intel_crtc_enable_flip_done(struct intel_atomic_state *state,
@@ -7091,6 +7094,8 @@ static void intel_update_crtc(struct intel_atomic_state *state,
 
 	intel_fbc_update(state, crtc);
 
+	drm_WARN_ON(&i915->drm, !intel_display_power_is_enabled(i915, POWER_DOMAIN_DC_OFF));
+
 	if (!modeset &&
 	    intel_crtc_needs_color_update(new_crtc_state))
 		intel_color_commit_noarm(new_crtc_state);
@@ -7458,8 +7463,28 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	drm_atomic_helper_wait_for_dependencies(&state->base);
 	drm_dp_mst_atomic_wait_for_dependencies(&state->base);
 
-	if (state->modeset)
-		wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
+	/*
+	 * During full modesets we write a lot of registers, wait
+	 * for PLLs, etc. Doing that while DC states are enabled
+	 * is not a good idea.
+	 *
+	 * During fastsets and other updates we also need to
+	 * disable DC states due to the following scenario:
+	 * 1. DC5 exit and PSR exit happen
+	 * 2. Some or all _noarm() registers are written
+	 * 3. Due to some long delay PSR is re-entered
+	 * 4. DC5 entry -> DMC saves the already written new
+	 *    _noarm() registers and the old not yet written
+	 *    _arm() registers
+	 * 5. DC5 exit -> DMC restores a mixture of old and
+	 *    new register values and arms the update
+	 * 6. PSR exit -> hardware latches a mixture of old and
+	 *    new register values -> corrupted frame, or worse
+	 * 7. New _arm() registers are finally written
+	 * 8. Hardware finally latches a complete set of new
+	 *    register values, and subsequent frames will be OK again
+	 */
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_DC_OFF);
 
 	intel_atomic_prepare_plane_clear_colors(state);
 
@@ -7608,8 +7633,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		 * the culprit.
 		 */
 		intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore);
-		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET, wakeref);
 	}
+	intel_display_power_put(dev_priv, POWER_DOMAIN_DC_OFF, wakeref);
 	intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref);
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index ad1a37b515fb..2a9f40a2b3ed 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -301,6 +301,7 @@ intel_dpt_create(struct intel_framebuffer *fb)
 	vm->pte_encode = gen8_ggtt_pte_encode;
 
 	dpt->obj = dpt_obj;
+	dpt->obj->is_dpt = true;
 
 	return &dpt->vm;
 }
@@ -309,5 +310,6 @@ void intel_dpt_destroy(struct i915_address_space *vm)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 
+	dpt->obj->is_dpt = false;
 	i915_vm_put(&dpt->vm);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index f45328712bff..be510b9c0d07 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -418,9 +418,9 @@ static bool icl_tc_phy_is_owned(struct intel_digital_port *dig_port)
 	val = intel_de_read(i915, PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia));
 	if (val == 0xffffffff) {
 		drm_dbg_kms(&i915->drm,
-			    "Port %s: PHY in TCCOLD, assume safe mode\n",
+			    "Port %s: PHY in TCCOLD, assume not owned\n",
 			    dig_port->tc_port_name);
-		return true;
+		return false;
 	}
 
 	return val & DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 8949fb0a944f..3198b64ad7db 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -127,7 +127,8 @@ i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
 
 	memcpy(map, data, size);
 
-	i915_gem_object_unpin_map(obj);
+	i915_gem_object_flush_map(obj);
+	__i915_gem_object_release_map(obj);
 
 	return obj;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index f9a8acbba715..885ccde9dc3c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -303,7 +303,7 @@ i915_gem_object_never_mmap(const struct drm_i915_gem_object *obj)
 static inline bool
 i915_gem_object_is_framebuffer(const struct drm_i915_gem_object *obj)
 {
-	return READ_ONCE(obj->frontbuffer);
+	return READ_ONCE(obj->frontbuffer) || obj->is_dpt;
 }
 
 static inline unsigned int
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 19c9bdd8f905..5dcbbef31d44 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -491,6 +491,9 @@ struct drm_i915_gem_object {
 	 */
 	unsigned int cache_dirty:1;
 
+	/* @is_dpt: Object houses a display page table (DPT) */
+	unsigned int is_dpt:1;
+
 	/**
 	 * @read_domains: Read memory domains.
 	 *
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index f5d7b5126433..2c92fa9d1942 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -2075,16 +2075,6 @@ void intel_rps_sanitize(struct intel_rps *rps)
 		rps_disable_interrupts(rps);
 }
 
-u32 intel_rps_read_rpstat_fw(struct intel_rps *rps)
-{
-	struct drm_i915_private *i915 = rps_to_i915(rps);
-	i915_reg_t rpstat;
-
-	rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1;
-
-	return intel_uncore_read_fw(rps_to_gt(rps)->uncore, rpstat);
-}
-
 u32 intel_rps_read_rpstat(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
@@ -2095,7 +2085,7 @@ u32 intel_rps_read_rpstat(struct intel_rps *rps)
 	return intel_uncore_read(rps_to_gt(rps)->uncore, rpstat);
 }
 
-u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
+static u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	u32 cagf;
@@ -2118,10 +2108,11 @@ u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
 	return cagf;
 }
 
-static u32 read_cagf(struct intel_rps *rps)
+static u32 __read_cagf(struct intel_rps *rps, bool take_fw)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	struct intel_uncore *uncore = rps_to_uncore(rps);
+	i915_reg_t r = INVALID_MMIO_REG;
 	u32 freq;
 
 	/*
@@ -2129,22 +2120,30 @@ static u32 read_cagf(struct intel_rps *rps)
 	 * registers will return 0 freq when GT is in RC6
 	 */
 	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) {
-		freq = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1);
+		r = MTL_MIRROR_TARGET_WP1;
 	} else if (GRAPHICS_VER(i915) >= 12) {
-		freq = intel_uncore_read(uncore, GEN12_RPSTAT1);
+		r = GEN12_RPSTAT1;
 	} else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
 		vlv_punit_get(i915);
 		freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
 		vlv_punit_put(i915);
 	} else if (GRAPHICS_VER(i915) >= 6) {
-		freq = intel_uncore_read(uncore, GEN6_RPSTAT1);
+		r = GEN6_RPSTAT1;
 	} else {
-		freq = intel_uncore_read(uncore, MEMSTAT_ILK);
+		r = MEMSTAT_ILK;
 	}
 
+	if (i915_mmio_reg_valid(r))
+		freq = take_fw ? intel_uncore_read(uncore, r) : intel_uncore_read_fw(uncore, r);
+
 	return intel_rps_get_cagf(rps, freq);
 }
 
+static u32 read_cagf(struct intel_rps *rps)
+{
+	return __read_cagf(rps, true);
+}
+
 u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 {
 	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
@@ -2157,7 +2156,12 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 	return freq;
 }
 
-u32 intel_rps_read_punit_req(struct intel_rps *rps)
+u32 intel_rps_read_actual_frequency_fw(struct intel_rps *rps)
+{
+	return intel_gpu_freq(rps, __read_cagf(rps, false));
+}
+
+static u32 intel_rps_read_punit_req(struct intel_rps *rps)
 {
 	struct intel_uncore *uncore = rps_to_uncore(rps);
 	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index c622962c6bef..a3fa987aa91f 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -37,8 +37,8 @@ void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive);
 
 int intel_gpu_freq(struct intel_rps *rps, int val);
 int intel_freq_opcode(struct intel_rps *rps, int val);
-u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1);
 u32 intel_rps_read_actual_frequency(struct intel_rps *rps);
+u32 intel_rps_read_actual_frequency_fw(struct intel_rps *rps);
 u32 intel_rps_get_requested_frequency(struct intel_rps *rps);
 u32 intel_rps_get_min_frequency(struct intel_rps *rps);
 u32 intel_rps_get_min_raw_freq(struct intel_rps *rps);
@@ -49,10 +49,8 @@ int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val);
 u32 intel_rps_get_rp0_frequency(struct intel_rps *rps);
 u32 intel_rps_get_rp1_frequency(struct intel_rps *rps);
 u32 intel_rps_get_rpn_frequency(struct intel_rps *rps);
-u32 intel_rps_read_punit_req(struct intel_rps *rps);
 u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps);
 u32 intel_rps_read_rpstat(struct intel_rps *rps);
-u32 intel_rps_read_rpstat_fw(struct intel_rps *rps);
 void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps);
 void intel_rps_raise_unslice(struct intel_rps *rps);
 void intel_rps_lower_unslice(struct intel_rps *rps);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 824a34ec0b83..283a4a3c6862 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1592,9 +1592,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	/*
 	 * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6.
 	 */
-	if (intel_uc_uses_guc_rc(&gt->uc) &&
-	    (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
-	     IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)))
+	if (stream->override_gucrc)
 		drm_WARN_ON(&gt->i915->drm,
 			    intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc));
 
@@ -3305,8 +3303,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		if (ret) {
 			drm_dbg(&stream->perf->i915->drm,
 				"Unable to override gucrc mode\n");
-			goto err_config;
+			goto err_gucrc;
 		}
+
+		stream->override_gucrc = true;
 	}
 
 	ret = alloc_oa_buffer(stream);
@@ -3345,11 +3345,15 @@ err_enable:
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-	free_oa_configs(stream);
+	if (stream->override_gucrc)
+		intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc);
 
+err_gucrc:
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
 
+	free_oa_configs(stream);
+
 err_config:
 	free_noa_wait(stream);
 
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index ca150b7af3f2..4d5d8c365d9e 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -316,6 +316,12 @@ struct i915_perf_stream {
 	 * buffer should be checked for available data.
 	 */
 	u64 poll_oa_period;
+
+	/**
+	 * @override_gucrc: GuC RC has been overridden for the perf stream,
+	 * and we need to restore the default configuration on release.
+	 */
+	bool override_gucrc;
 };
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 52531ab28c5f..6d422b056f8a 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -393,14 +393,12 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 		 * case we assume the system is running at the intended
 		 * frequency. Fortunately, the read should rarely fail!
 		 */
-		val = intel_rps_read_rpstat_fw(rps);
-		if (val)
-			val = intel_rps_get_cagf(rps, val);
-		else
-			val = rps->cur_freq;
+		val = intel_rps_read_actual_frequency_fw(rps);
+		if (!val)
+			val = intel_gpu_freq(rps, rps->cur_freq);
 
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
-				intel_gpu_freq(rps, val), period_ns / 1000);
+				val, period_ns / 1000);
 	}
 
 	if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 40409a29f5b6..91b5ecc57538 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -33,6 +33,7 @@
 #include <linux/apple-gmux.h>
 #include <linux/backlight.h>
 #include <linux/idr.h>
+#include <drm/drm_probe_helper.h>
 
 #include "nouveau_drv.h"
 #include "nouveau_reg.h"
@@ -299,8 +300,12 @@ nv50_backlight_init(struct nouveau_backlight *bl,
 	struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
 	struct nvif_object *device = &drm->client.device.object;
 
+	/*
+	 * Note when this runs the connectors have not been probed yet,
+	 * so nv_conn->base.status is not set yet.
+	 */
 	if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1)) ||
-	    nv_conn->base.status != connector_status_connected)
+	    drm_helper_probe_detect(&nv_conn->base, NULL, false) != connector_status_connected)
 		return -ENODEV;
 
 	if (nv_conn->type == DCB_CONNECTOR_eDP) {
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 4e6ad6e122bc..0e4378420271 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -906,12 +906,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
 	spin_unlock(&sched->job_list_lock);
 
-	if (job) {
-		job->entity->elapsed_ns += ktime_to_ns(
-			ktime_sub(job->s_fence->finished.timestamp,
-				  job->s_fence->scheduled.timestamp));
-	}
-
 	return job;
 }
 
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index f8ee714df396..09ee6f6af896 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -89,7 +89,8 @@ static int check_block(struct kunit *test, struct drm_buddy *mm,
 		err = -EINVAL;
 	}
 
-	if (!is_power_of_2(block_size)) {
+	/* We can't use is_power_of_2() for a u64 on 32-bit systems. */
+	if (block_size & (block_size - 1)) {
 		kunit_err(test, "block size not power of two\n");
 		err = -EINVAL;
 	}