Merge drm/drm-next into drm-misc-next

Backmerging drm/drm-next to get the latest changes in the xlnx driver.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

257 files changed, 10196 insertions, 5097 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index ae9371b172e3..8639a4f9c6e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -274,9 +274,6 @@ extern int amdgpu_vcnfw_log;
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
-#define AMDGPU_RESET_LEVEL_SOFT_RECOVERY (1 << 0)
-#define AMDGPU_RESET_LEVEL_MODE2 (1 << 1)
-
 /* max cursor sizes (in pixels) */
 #define CIK_CURSOR_WIDTH 128
 #define CIK_CURSOR_HEIGHT 128
@@ -1065,7 +1062,6 @@ struct amdgpu_device {
 
 	struct work_struct		reset_work;
 
-	uint32_t						amdgpu_reset_level_mask;
 	bool                            job_hang;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index cf58c1125e60..046d466b4ee4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -134,7 +134,6 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 	reset_context.method = AMD_RESET_METHOD_NONE;
 	reset_context.reset_req_dev = adev;
 	clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-	clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
index 0b0a72ca5695..7e80caa05060 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
@@ -111,7 +111,7 @@ static int init_interrupts_v11(struct amdgpu_device *adev, uint32_t pipe_id)
 
 	lock_srbm(adev, mec, pipe, 0, 0);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, regCPC_INT_CNTL),
+	WREG32_SOC15(GC, 0, regCPC_INT_CNTL,
 		CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
 		CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 6066aebf491c..de61a85c4b02 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1954,8 +1954,6 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 		return PTR_ERR(ent);
 	}
 
-	debugfs_create_u32("amdgpu_reset_level", 0600, root, &adev->amdgpu_reset_level_mask);
-
 	/* Register debugfs entries for amdgpu_ttm */
 	amdgpu_ttm_debugfs_init(adev);
 	amdgpu_debugfs_pm_init(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ab8f970b2849..e0445e8cc342 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2928,6 +2928,14 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
+	/*
+	 * Per PMFW team's suggestion, driver needs to handle gfxoff
+	 * and df cstate features disablement for gpu reset(e.g. Mode1Reset)
+	 * scenario. Add the missing df cstate disablement here.
+	 */
+	if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_DISALLOW))
+		dev_warn(adev->dev, "Failed to disallow df cstate");
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -5210,7 +5218,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	reset_context->job = job;
 	reset_context->hive = hive;
-
 	/*
 	 * Build list of devices to reset.
 	 * In case we are in XGMI hive mode, resort the device list
@@ -5337,11 +5344,8 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 			amdgpu_ras_resume(adev);
 	} else {
 		r = amdgpu_do_asic_reset(device_list_handle, reset_context);
-		if (r && r == -EAGAIN) {
-			set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags);
-			adev->asic_reset_res = 0;
+		if (r && r == -EAGAIN)
 			goto retry;
-		}
 
 		if (!r && gpu_reset_for_dev_remove)
 			goto recover_end;
@@ -5777,7 +5781,6 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
-	set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 	adev->no_hw_access = true;
 	r = amdgpu_device_pre_asic_reset(adev, &reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 172572cfed36..032651a655f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -72,7 +72,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
 		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-		clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 		r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 2dad7aa9a03b..a4b47e1bd111 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1950,7 +1950,6 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
 		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-		clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 		amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
 	}
@@ -2268,6 +2267,25 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
 
 static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev)
 {
+	if (amdgpu_sriov_vf(adev)) {
+		switch (adev->ip_versions[MP0_HWIP][0]) {
+		case IP_VERSION(13, 0, 2):
+			return true;
+		default:
+			return false;
+		}
+	}
+
+	if (adev->asic_type == CHIP_IP_DISCOVERY) {
+		switch (adev->ip_versions[MP0_HWIP][0]) {
+		case IP_VERSION(13, 0, 0):
+		case IP_VERSION(13, 0, 10):
+			return true;
+		default:
+			return false;
+		}
+	}
+
 	return adev->asic_type == CHIP_VEGA10 ||
 		adev->asic_type == CHIP_VEGA20 ||
 		adev->asic_type == CHIP_ARCTURUS ||
@@ -2311,11 +2329,6 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 	    !amdgpu_ras_asic_supported(adev))
 		return;
 
-	/* If driver run on sriov guest side, only enable ras for aldebaran */
-	if (amdgpu_sriov_vf(adev) &&
-		adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 2))
-		return;
-
 	if (!adev->gmc.xgmi.connected_to_cpu) {
 		if (amdgpu_atomfirmware_mem_ecc_supported(adev)) {
 			dev_info(adev->dev, "MEM ECC is active.\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index 9da5ead50c90..f778466bb9db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -37,8 +37,6 @@ int amdgpu_reset_init(struct amdgpu_device *adev)
 {
 	int ret = 0;
 
-	adev->amdgpu_reset_level_mask = 0x1;
-
 	switch (adev->ip_versions[MP1_HWIP][0]) {
 	case IP_VERSION(13, 0, 2):
 		ret = aldebaran_reset_init(adev);
@@ -76,12 +74,6 @@ int amdgpu_reset_prepare_hwcontext(struct amdgpu_device *adev,
 {
 	struct amdgpu_reset_handler *reset_handler = NULL;
 
-	if (!(adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_MODE2))
-		return -ENOSYS;
-
-	if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
-		return -ENOSYS;
-
 	if (adev->reset_cntl && adev->reset_cntl->get_reset_handler)
 		reset_handler = adev->reset_cntl->get_reset_handler(
 			adev->reset_cntl, reset_context);
@@ -98,12 +90,6 @@ int amdgpu_reset_perform_reset(struct amdgpu_device *adev,
 	int ret;
 	struct amdgpu_reset_handler *reset_handler = NULL;
 
-	if (!(adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_MODE2))
-		return -ENOSYS;
-
-	if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
-		return -ENOSYS;
-
 	if (adev->reset_cntl)
 		reset_handler = adev->reset_cntl->get_reset_handler(
 			adev->reset_cntl, reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index f5318fedf2f0..f4a501ff87d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -30,8 +30,7 @@ enum AMDGPU_RESET_FLAGS {
 
 	AMDGPU_NEED_FULL_RESET = 0,
 	AMDGPU_SKIP_HW_RESET = 1,
-	AMDGPU_SKIP_MODE2_RESET = 2,
-	AMDGPU_RESET_FOR_DEVICE_REMOVE = 3,
+	AMDGPU_RESET_FOR_DEVICE_REMOVE = 2,
 };
 
 struct amdgpu_reset_context {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 3e316b013fd9..d3558c34d406 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -405,9 +405,6 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
 {
 	ktime_t deadline = ktime_add_us(ktime_get(), 10000);
 
-	if (!(ring->adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_SOFT_RECOVERY))
-		return false;
-
 	if (amdgpu_sriov_vf(ring->adev) || !ring->funcs->soft_recovery || !fence)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9f5c1d86d2ab..aea8d26b1724 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -430,6 +430,9 @@ static bool amdgpu_mem_visible(struct amdgpu_device *adev,
 	while (cursor.remaining) {
 		amdgpu_res_next(&cursor, cursor.size);
 
+		if (!cursor.remaining)
+			break;
+
 		/* ttm_resource_ioremap only supports contiguous memory */
 		if (end != cursor.start)
 			return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index e4af40b9a8aa..9c765b04aae3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -726,6 +726,12 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev)
 			adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE;
 	}
 
+	if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)
+		/* VF MMIO access (except mailbox range) from CPU
+		 * will be blocked during sriov runtime
+		 */
+		adev->virt.caps |= AMDGPU_VF_MMIO_ACCESS_PROTECT;
+
 	/* we have the ability to check now */
 	if (amdgpu_sriov_vf(adev)) {
 		switch (adev->asic_type) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index d94c31e68a14..49c4347d154c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -31,6 +31,7 @@
 #define AMDGPU_SRIOV_CAPS_IS_VF        (1 << 2) /* this GPU is a virtual function */
 #define AMDGPU_PASSTHROUGH_MODE        (1 << 3) /* thw whole GPU is pass through for VM */
 #define AMDGPU_SRIOV_CAPS_RUNTIME      (1 << 4) /* is out of full access mode */
+#define AMDGPU_VF_MMIO_ACCESS_PROTECT  (1 << 5) /* MMIO write access is not allowed in sriov runtime */
 
 /* flags for indirect register access path supported by rlcg for sriov */
 #define AMDGPU_RLCG_GC_WRITE_LEGACY    (0x8 << 28)
@@ -297,6 +298,9 @@ struct amdgpu_video_codec_info;
 #define amdgpu_passthrough(adev) \
 ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE)
 
+#define amdgpu_sriov_vf_mmio_access_protection(adev) \
+((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT)
+
 static inline bool is_virtual_machine(void)
 {
 #if defined(CONFIG_X86)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 83b0c5d86e48..2291aa14d888 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2338,7 +2338,11 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	 */
 #ifdef CONFIG_X86_64
 	if (amdgpu_vm_update_mode == -1) {
-		if (amdgpu_gmc_vram_full_visible(&adev->gmc))
+		/* For asic with VF MMIO access protection
+		 * avoid using CPU for VM table updates
+		 */
+		if (amdgpu_gmc_vram_full_visible(&adev->gmc) &&
+		    !amdgpu_sriov_vf_mmio_access_protection(adev))
 			adev->vm_manager.vm_update_mode =
 				AMDGPU_VM_USE_CPU_FOR_COMPUTE;
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index df6fd6d6a82c..59cf64216fbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -139,8 +139,15 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 				   DMA_RESV_USAGE_BOOKKEEP);
 	}
 
-	if (fence && !p->immediate)
+	if (fence && !p->immediate) {
+		/*
+		 * Most hw generations now have a separate queue for page table
+		 * updates, but when the queue is shared with userspace we need
+		 * the extra CPU round trip to correctly flush the TLB.
+		 */
+		set_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &f->flags);
 		swap(*fence, f);
+	}
 	dma_fence_put(f);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 251109723ab6..671ca5a0f208 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1571,7 +1571,7 @@ static void gfx_v11_0_init_compute_vmid(struct amdgpu_device *adev)
 		WREG32_SOC15(GC, 0, regSH_MEM_BASES, sh_mem_bases);
 
 		/* Enable trap for each kfd vmid. */
-		data = RREG32(SOC15_REG_OFFSET(GC, 0, regSPI_GDBG_PER_VMID_CNTL));
+		data = RREG32_SOC15(GC, 0, regSPI_GDBG_PER_VMID_CNTL);
 		data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1);
 	}
 	soc21_grbm_select(adev, 0, 0, 0, 0);
@@ -5076,6 +5076,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle,
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);
 	        break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 846ccb6cf07d..66dfb574cc7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -186,6 +186,10 @@ static void gmc_v11_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	/* Use register 17 for GART */
 	const unsigned eng = 17;
 	unsigned int i;
+	unsigned char hub_ip = 0;
+
+	hub_ip = (vmhub == AMDGPU_GFXHUB_0) ?
+		   GC_HWIP : MMHUB_HWIP;
 
 	spin_lock(&adev->gmc.invalidate_lock);
 	/*
@@ -199,8 +203,8 @@ static void gmc_v11_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	if (use_semaphore) {
 		for (i = 0; i < adev->usec_timeout; i++) {
 			/* a read return value of 1 means semaphore acuqire */
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-					    hub->eng_distance * eng);
+			tmp = RREG32_RLC_NO_KIQ(hub->vm_inv_eng0_sem +
+					    hub->eng_distance * eng, hub_ip);
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -210,12 +214,12 @@ static void gmc_v11_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
 	}
 
-	WREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
+	WREG32_RLC_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req, hub_ip);
 
 	/* Wait for ACK with a delay.*/
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack +
-				    hub->eng_distance * eng);
+		tmp = RREG32_RLC_NO_KIQ(hub->vm_inv_eng0_ack +
+				    hub->eng_distance * eng, hub_ip);
 		tmp &= 1 << vmid;
 		if (tmp)
 			break;
@@ -229,8 +233,8 @@ static void gmc_v11_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 		 * add semaphore release after invalidation,
 		 * write with 0 means semaphore release
 		 */
-		WREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-			      hub->eng_distance * eng, 0);
+		WREG32_RLC_NO_KIQ(hub->vm_inv_eng0_sem +
+			      hub->eng_distance * eng, 0, hub_ip);
 
 	/* Issue additional private vm invalidation to MMHUB */
 	if ((vmhub != AMDGPU_GFXHUB_0) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 5cec6b259b7f..fef7d020bc5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1156,6 +1156,42 @@ static int mes_v11_0_sw_fini(void *handle)
 	return 0;
 }
 
+static void mes_v11_0_kiq_dequeue_sched(struct amdgpu_device *adev)
+{
+	uint32_t data;
+	int i;
+
+	mutex_lock(&adev->srbm_mutex);
+	soc21_grbm_select(adev, 3, AMDGPU_MES_SCHED_PIPE, 0, 0);
+
+	/* disable the queue if it's active */
+	if (RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1) {
+		WREG32_SOC15(GC, 0, regCP_HQD_DEQUEUE_REQUEST, 1);
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+	}
+	data = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_EN, 0);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_HIT, 1);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, data);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, 0);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_LO, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_HI, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR, 0);
+
+	soc21_grbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+
+	adev->mes.ring.sched.ready = false;
+}
+
 static void mes_v11_0_kiq_setting(struct amdgpu_ring *ring)
 {
 	uint32_t tmp;
@@ -1207,6 +1243,9 @@ failure:
 
 static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev)
 {
+	if (adev->mes.ring.sched.ready)
+		mes_v11_0_kiq_dequeue_sched(adev);
+
 	mes_v11_0_enable(adev, false);
 	return 0;
 }
@@ -1262,9 +1301,6 @@ failure:
 
 static int mes_v11_0_hw_fini(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	adev->mes.ring.sched.ready = false;
 	return 0;
 }
 
@@ -1296,7 +1332,8 @@ static int mes_v11_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_in_reset(adev))
+	if (!amdgpu_in_reset(adev) &&
+	    (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3)))
 		amdgpu_mes_self_test(adev);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index a2f04b249132..12906ba74462 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -290,7 +290,6 @@ flr_done:
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
 		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-		clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 		amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index a977f0027928..e07757eea7ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -317,7 +317,6 @@ flr_done:
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
 		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-		clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 		amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index fd14fa9b9cd7..288c414babdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -529,7 +529,6 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
 		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-		clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 		amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 298fa11702e7..1122bd4eae98 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1417,11 +1417,6 @@ static int sdma_v4_0_start(struct amdgpu_device *adev)
 		WREG32_SDMA(i, mmSDMA0_CNTL, temp);
 
 		if (!amdgpu_sriov_vf(adev)) {
-			ring = &adev->sdma.instance[i].ring;
-			adev->nbio.funcs->sdma_doorbell_range(adev, i,
-				ring->use_doorbell, ring->doorbell_index,
-				adev->doorbell_index.sdma_doorbell_range);
-
 			/* unhalt engine */
 			temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL);
 			temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
index 7aa570c1ce4a..81a6d5b94987 100644
--- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
+++ b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
@@ -31,12 +31,23 @@
 #include "amdgpu_psp.h"
 #include "amdgpu_xgmi.h"
 
+static bool sienna_cichlid_is_mode2_default(struct amdgpu_reset_control *reset_ctl)
+{
+#if 0
+	struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle;
+
+	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7) &&
+	    adev->pm.fw_version >= 0x3a5500 && !amdgpu_sriov_vf(adev))
+		return true;
+#endif
+	return false;
+}
+
 static struct amdgpu_reset_handler *
 sienna_cichlid_get_reset_handler(struct amdgpu_reset_control *reset_ctl,
 			    struct amdgpu_reset_context *reset_context)
 {
 	struct amdgpu_reset_handler *handler;
-	struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle;
 
 	if (reset_context->method != AMD_RESET_METHOD_NONE) {
 		list_for_each_entry(handler, &reset_ctl->reset_handlers,
@@ -44,15 +55,13 @@ sienna_cichlid_get_reset_handler(struct amdgpu_reset_control *reset_ctl,
 			if (handler->reset_method == reset_context->method)
 				return handler;
 		}
-	} else {
-		list_for_each_entry(handler, &reset_ctl->reset_handlers,
+	}
+
+	if (sienna_cichlid_is_mode2_default(reset_ctl)) {
+		list_for_each_entry (handler, &reset_ctl->reset_handlers,
 				     handler_list) {
-			if (handler->reset_method == AMD_RESET_METHOD_MODE2 &&
-			    adev->pm.fw_version >= 0x3a5500 &&
-			    !amdgpu_sriov_vf(adev)) {
-				reset_context->method = AMD_RESET_METHOD_MODE2;
+			if (handler->reset_method == AMD_RESET_METHOD_MODE2)
 				return handler;
-			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 183024d7c184..e3b2b6b4f1a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1211,6 +1211,20 @@ static int soc15_common_sw_fini(void *handle)
 	return 0;
 }
 
+static void soc15_sdma_doorbell_range_init(struct amdgpu_device *adev)
+{
+	int i;
+
+	/* sdma doorbell range is programed by hypervisor */
+	if (!amdgpu_sriov_vf(adev)) {
+		for (i = 0; i < adev->sdma.num_instances; i++) {
+			adev->nbio.funcs->sdma_doorbell_range(adev, i,
+				true, adev->doorbell_index.sdma_engine[i] << 1,
+				adev->doorbell_index.sdma_doorbell_range);
+		}
+	}
+}
+
 static int soc15_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1230,6 +1244,13 @@ static int soc15_common_hw_init(void *handle)
 
 	/* enable the doorbell aperture */
 	soc15_enable_doorbell_aperture(adev, true);
+	/* HW doorbell routing policy: doorbell writing not
+	 * in SDMA/IH/MM/ACV range will be routed to CP. So
+	 * we need to init SDMA doorbell range prior
+	 * to CP ip block init and ring test.  IH already
+	 * happens before CP.
+	 */
+	soc15_sdma_doorbell_range_init(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 795706b3b092..e08044008186 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -423,6 +423,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 0):
 		return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC);
 	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
 		return false;
 	default:
 		return true;
@@ -636,7 +637,11 @@ static int soc21_common_early_init(void *handle)
 		break;
 	case IP_VERSION(11, 0, 3):
 		adev->cg_flags = AMD_CG_SUPPORT_VCN_MGCG |
-			AMD_CG_SUPPORT_JPEG_MGCG;
+			AMD_CG_SUPPORT_JPEG_MGCG |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_MGCG;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index d70838edba80..ca7d24000621 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -77,7 +77,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_32.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_rq_dlg_calc_32.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_util_32.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_util_32.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn321/dcn321_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/dcn31_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index e85364dff4e0..5cb3e8634739 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -262,8 +262,9 @@ struct kfd2kgd_calls {
 				uint32_t queue_id);
 
 	int (*hqd_destroy)(struct amdgpu_device *adev, void *mqd,
-				uint32_t reset_type, unsigned int timeout,
-				uint32_t pipe_id, uint32_t queue_id);
+				enum kfd_preempt_type reset_type,
+				unsigned int timeout, uint32_t pipe_id,
+				uint32_t queue_id);
 
 	bool (*hqd_sdma_is_occupied)(struct amdgpu_device *adev, void *mqd);
 
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 948cc75376f8..236657eece47 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3362,11 +3362,11 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 	if (adev->pm.sysfs_initialized)
 		return 0;
 
+	INIT_LIST_HEAD(&adev->pm.pm_attr_list);
+
 	if (adev->pm.dpm_enabled == 0)
 		return 0;
 
-	INIT_LIST_HEAD(&adev->pm.pm_attr_list);
-
 	adev->pm.int_hwmon_dev = hwmon_device_register_with_groups(adev->dev,
 								   DRIVER_NAME, adev,
 								   hwmon_groups);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
index 190af79f3236..dad3e3741a4e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
@@ -67,21 +67,22 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed)
 {
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t duty100, duty;
-	uint64_t tmp64;
+	uint32_t current_rpm;
+	uint32_t percent = 0;
 
-	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
-				CG_FDO_CTRL1, FMAX_DUTY100);
-	duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS),
-				CG_THERMAL_STATUS, FDO_PWM_DUTY);
+	if (hwmgr->thermal_controller.fanInfo.bNoFan)
+		return 0;
 
-	if (!duty100)
-		return -EINVAL;
+	if (vega10_get_current_rpm(hwmgr, &current_rpm))
+		return -1;
+
+	if (hwmgr->thermal_controller.
+			advanceFanControlParameters.usMaxFanRPM != 0)
+		percent = current_rpm * 255 /
+			hwmgr->thermal_controller.
+			advanceFanControlParameters.usMaxFanRPM;
 
-	tmp64 = (uint64_t)duty * 255;
-	do_div(tmp64, duty100);
-	*speed = MIN((uint32_t)tmp64, 255);
+	*speed = MIN(percent, 255);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 13c5c7f1ecb9..4fe75dd2b329 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1314,8 +1314,8 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 
 	ret = smu_enable_thermal_alert(smu);
 	if (ret) {
-		dev_err(adev->dev, "Failed to enable thermal alert!\n");
-		return ret;
+	  dev_err(adev->dev, "Failed to enable thermal alert!\n");
+	  return ret;
 	}
 
 	ret = smu_notify_display_change(smu);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
index ae2d337158f3..f77401709d83 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 5
+#define PMFW_DRIVER_IF_VERSION 7
 
 typedef struct {
   int32_t value;
@@ -163,8 +163,8 @@ typedef struct {
   uint16_t DclkFrequency;               //[MHz]
   uint16_t MemclkFrequency;             //[MHz]
   uint16_t spare;                       //[centi]
-  uint16_t UvdActivity;                 //[centi]
   uint16_t GfxActivity;                 //[centi]
+  uint16_t UvdActivity;                 //[centi]
 
   uint16_t Voltage[2];                  //[mV] indices: VDDCR_VDD, VDDCR_SOC
   uint16_t Current[2];                  //[mA] indices: VDDCR_VDD, VDDCR_SOC
@@ -199,6 +199,19 @@ typedef struct {
   uint16_t DeviceState;
   uint16_t CurTemp;                     //[centi-Celsius]
   uint16_t spare2;
+
+  uint16_t AverageGfxclkFrequency;
+  uint16_t AverageFclkFrequency;
+  uint16_t AverageGfxActivity;
+  uint16_t AverageSocclkFrequency;
+  uint16_t AverageVclkFrequency;
+  uint16_t AverageVcnActivity;
+  uint16_t AverageDRAMReads;          //Filtered DF Bandwidth::DRAM Reads
+  uint16_t AverageDRAMWrites;         //Filtered DF Bandwidth::DRAM Writes
+  uint16_t AverageSocketPower;        //Filtered value of CurrentSocketPower
+  uint16_t AverageCorePower;          //Filtered of [sum of CorePower[8]])
+  uint16_t AverageCoreC0Residency[8]; //Filtered of [average C0 residency %  per core]
+  uint32_t MetricsCounter;            //Counts the # of metrics table parameter reads per update to the metrics table, i.e. if the metrics table update happens every 1 second, this value could be up to 1000 if the smu collected metrics data every cycle, or as low as 0 if the smu was asleep the whole time. Reset to 0 after writing.
 } SmuMetrics_t;
 
 typedef struct {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 9d62ea2af132..8f72202aea8e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -28,7 +28,7 @@
 #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 445005571f76..9cd005131f56 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -2242,9 +2242,17 @@ static void arcturus_get_unique_id(struct smu_context *smu)
 static int arcturus_set_df_cstate(struct smu_context *smu,
 				  enum pp_df_cstate state)
 {
+	struct amdgpu_device *adev = smu->adev;
 	uint32_t smu_version;
 	int ret;
 
+	/*
+	 * Arcturus does not need the cstate disablement
+	 * prerequisite for gpu reset.
+	 */
+	if (amdgpu_in_reset(adev) || adev->in_suspend)
+		return 0;
+
 	ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
 	if (ret) {
 		dev_err(smu->adev->dev, "Failed to get smu version!\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 619aee51b123..d30ec3005ea1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1640,6 +1640,15 @@ static bool aldebaran_is_baco_supported(struct smu_context *smu)
 static int aldebaran_set_df_cstate(struct smu_context *smu,
 				   enum pp_df_cstate state)
 {
+	struct amdgpu_device *adev = smu->adev;
+
+	/*
+	 * Aldebaran does not need the cstate disablement
+	 * prerequisite for gpu reset.
+	 */
+	if (amdgpu_in_reset(adev) || adev->in_suspend)
+		return 0;
+
 	return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_DFCstateControl, state, NULL);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 93fffdbab4f0..c4552ade8d44 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -211,7 +211,8 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 		return 0;
 
 	if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) ||
-	    (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)))
+	    (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) ||
+	    (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10)))
 		return 0;
 
 	/* override pptable_id from driver parameter */
@@ -454,9 +455,6 @@ int smu_v13_0_setup_pptable(struct smu_context *smu)
 		dev_info(adev->dev, "override pptable id %d\n", pptable_id);
 	} else {
 		pptable_id = smu->smu_table.boot_values.pp_table_id;
-
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10))
-			pptable_id = 6666;
 	}
 
 	/* force using vbios pptable in sriov mode */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 1d454485e0d9..29529328152d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -119,6 +119,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(NotifyPowerSource,		PPSMC_MSG_NotifyPowerSource,           0),
 	MSG_MAP(Mode1Reset,			PPSMC_MSG_Mode1Reset,                  0),
 	MSG_MAP(PrepareMp1ForUnload,		PPSMC_MSG_PrepareMp1ForUnload,         0),
+	MSG_MAP(DFCstateControl,		PPSMC_MSG_SetExternalClientDfCstateAllow, 0),
 };
 
 static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = {
@@ -1753,6 +1754,15 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_v13_0_0_set_df_cstate(struct smu_context *smu,
+				     enum pp_df_cstate state)
+{
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_DFCstateControl,
+					       state,
+					       NULL);
+}
+
 static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_0_set_default_dpm_table,
@@ -1822,6 +1832,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.mode1_reset_is_support = smu_v13_0_0_is_mode1_reset_supported,
 	.mode1_reset = smu_v13_0_mode1_reset,
 	.set_mp1_state = smu_v13_0_0_set_mp1_state,
+	.set_df_cstate = smu_v13_0_0_set_df_cstate,
 };
 
 void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index c422bf8a09b1..c4102cfb734c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -121,6 +121,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(Mode1Reset,             PPSMC_MSG_Mode1Reset,                  0),
 	MSG_MAP(PrepareMp1ForUnload,		PPSMC_MSG_PrepareMp1ForUnload,         0),
 	MSG_MAP(SetMGpuFanBoostLimitRpm,	PPSMC_MSG_SetMGpuFanBoostLimitRpm,     0),
+	MSG_MAP(DFCstateControl,		PPSMC_MSG_SetExternalClientDfCstateAllow, 0),
 };
 
 static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = {
@@ -1587,6 +1588,16 @@ static bool smu_v13_0_7_is_mode1_reset_supported(struct smu_context *smu)
 
 	return true;
 }
+
+static int smu_v13_0_7_set_df_cstate(struct smu_context *smu,
+				     enum pp_df_cstate state)
+{
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_DFCstateControl,
+					       state,
+					       NULL);
+}
+
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -1649,6 +1660,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.mode1_reset_is_support = smu_v13_0_7_is_mode1_reset_supported,
 	.mode1_reset = smu_v13_0_mode1_reset,
 	.set_mp1_state = smu_v13_0_7_set_mp1_state,
+	.set_df_cstate = smu_v13_0_7_set_df_cstate,
 };
 
 void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 223ff2666c3c..547356e00341 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -436,7 +436,7 @@ int drmm_connector_init(struct drm_device *dev,
 	if (drm_WARN_ON(dev, funcs && funcs->destroy))
 		return -EINVAL;
 
-	ret = __drm_connector_init(dev, connector, funcs, connector_type, NULL);
+	ret = __drm_connector_init(dev, connector, funcs, connector_type, ddc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index 39328567c200..7cc38d25ee5c 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -57,10 +57,28 @@ config DRM_I915_PREEMPT_TIMEOUT
 	default 640 # milliseconds
 	help
 	  How long to wait (in milliseconds) for a preemption event to occur
-	  when submitting a new context via execlists. If the current context
-	  does not hit an arbitration point and yield to HW before the timer
-	  expires, the HW will be reset to allow the more important context
-	  to execute.
+	  when submitting a new context. If the current context does not hit
+	  an arbitration point and yield to HW before the timer expires, the
+	  HW will be reset to allow the more important context to execute.
+
+	  This is adjustable via
+	  /sys/class/drm/card?/engine/*/preempt_timeout_ms
+
+	  May be 0 to disable the timeout.
+
+	  The compiled in default may get overridden at driver probe time on
+	  certain platforms and certain engines which will be reflected in the
+	  sysfs control.
+
+config DRM_I915_PREEMPT_TIMEOUT_COMPUTE
+	int "Preempt timeout for compute engines (ms, jiffy granularity)"
+	default 7500 # milliseconds
+	help
+	  How long to wait (in milliseconds) for a preemption event to occur
+	  when submitting a new context to a compute capable engine. If the
+	  current context does not hit an arbitration point and yield to HW
+	  before the timer expires, the HW will be reset to allow the more
+	  important context to execute.
 
 	  This is adjustable via
 	  /sys/class/drm/card?/engine/*/preempt_timeout_ms
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index a26edcdadc21..51704b54317c 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -209,6 +209,9 @@ i915-y += gt/uc/intel_uc.o \
 # graphics system controller (GSC) support
 i915-y += gt/intel_gsc.o
 
+# graphics hardware monitoring (HWMON) support
+i915-$(CONFIG_HWMON) += i915_hwmon.o
+
 # modesetting core code
 i915-y += \
 	display/hsw_ips.o \
@@ -282,6 +285,7 @@ i915-y += \
 	display/intel_ddi.o \
 	display/intel_ddi_buf_trans.o \
 	display/intel_display_trace.o \
+	display/intel_dkl_phy.o \
 	display/intel_dp.o \
 	display/intel_dp_aux.o \
 	display/intel_dp_aux_backlight.o \
@@ -309,15 +313,18 @@ i915-y += \
 
 i915-y += i915_perf.o
 
-# Protected execution platform (PXP) support
-i915-$(CONFIG_DRM_I915_PXP) += \
+# Protected execution platform (PXP) support. Base support is required for HuC
+i915-y += \
 	pxp/intel_pxp.o \
+	pxp/intel_pxp_tee.o \
+	pxp/intel_pxp_huc.o
+
+i915-$(CONFIG_DRM_I915_PXP) += \
 	pxp/intel_pxp_cmd.o \
 	pxp/intel_pxp_debugfs.o \
 	pxp/intel_pxp_irq.o \
 	pxp/intel_pxp_pm.o \
-	pxp/intel_pxp_session.o \
-	pxp/intel_pxp_tee.o
+	pxp/intel_pxp_session.o
 
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c
index 2b73f5ff0d02..8aadf96fa5e9 100644
--- a/drivers/gpu/drm/i915/display/g4x_hdmi.c
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c
@@ -585,7 +585,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 	} else {
 		intel_encoder->pipe_mask = ~0;
 	}
-	intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG;
+	intel_encoder->cloneable = BIT(INTEL_OUTPUT_ANALOG);
 	intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port);
 	/*
 	 * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems
@@ -593,7 +593,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 	 * only one port anyway, nothing is lost by allowing it.
 	 */
 	if (IS_G4X(dev_priv))
-		intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI;
+		intel_encoder->cloneable |= BIT(INTEL_OUTPUT_HDMI);
 
 	dig_port->hdmi.hdmi_reg = hdmi_reg;
 	dig_port->dp.output_reg = INVALID_MMIO_REG;
diff --git a/drivers/gpu/drm/i915/display/hsw_ips.c b/drivers/gpu/drm/i915/display/hsw_ips.c
index a5be4af792cb..83aa3800245f 100644
--- a/drivers/gpu/drm/i915/display/hsw_ips.c
+++ b/drivers/gpu/drm/i915/display/hsw_ips.c
@@ -104,8 +104,7 @@ static bool hsw_ips_need_disable(struct intel_atomic_state *state,
 	 * Disable IPS before we program the LUT.
 	 */
 	if (IS_HASWELL(i915) &&
-	    (new_crtc_state->uapi.color_mgmt_changed ||
-	     new_crtc_state->update_pipe) &&
+	    intel_crtc_needs_color_update(new_crtc_state) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
 
@@ -146,8 +145,7 @@ static bool hsw_ips_need_enable(struct intel_atomic_state *state,
 	 * Re-enable IPS after the LUT has been programmed.
 	 */
 	if (IS_HASWELL(i915) &&
-	    (new_crtc_state->uapi.color_mgmt_changed ||
-	     new_crtc_state->update_pipe) &&
+	    intel_crtc_needs_color_update(new_crtc_state) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
 
@@ -155,7 +153,7 @@ static bool hsw_ips_need_enable(struct intel_atomic_state *state,
 	 * We can't read out IPS on broadwell, assume the worst and
 	 * forcibly enable IPS on the first fastset.
 	 */
-	if (new_crtc_state->update_pipe && old_crtc_state->inherited)
+	if (intel_crtc_needs_fastset(new_crtc_state) && old_crtc_state->inherited)
 		return true;
 
 	return !old_crtc_state->ips_enabled;
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index ed4d93942dbd..e05e7cd6c412 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1974,16 +1974,8 @@ static void icl_dsi_add_properties(struct intel_connector *connector)
 {
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_preferred_fixed_mode(connector);
-	u32 allowed_scalers;
 
-	allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) |
-			   BIT(DRM_MODE_SCALE_FULLSCREEN) |
-			   BIT(DRM_MODE_SCALE_CENTER);
-
-	drm_connector_attach_scaling_mode_property(&connector->base,
-						   allowed_scalers);
-
-	connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT;
+	intel_attach_scaling_mode_property(&connector->base);
 
 	drm_connector_set_panel_orientation_with_quirk(&connector->base,
 						       intel_dsi_get_panel_orientation(connector),
@@ -1993,7 +1985,6 @@ static void icl_dsi_add_properties(struct intel_connector *connector)
 
 void icl_dsi_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_dsi *intel_dsi;
 	struct intel_encoder *encoder;
 	struct intel_connector *intel_connector;
@@ -2018,7 +2009,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	connector = &intel_connector->base;
 
 	/* register DSI encoder with DRM subsystem */
-	drm_encoder_init(dev, &encoder->base, &gen11_dsi_encoder_funcs,
+	drm_encoder_init(&dev_priv->drm, &encoder->base, &gen11_dsi_encoder_funcs,
 			 DRM_MODE_ENCODER_DSI, "DSI %c", port_name(port));
 
 	encoder->pre_pll_enable = gen11_dsi_pre_pll_enable;
@@ -2042,12 +2033,10 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	encoder->is_clock_enabled = gen11_dsi_is_clock_enabled;
 
 	/* register DSI connector with DRM subsystem */
-	drm_connector_init(dev, connector, &gen11_dsi_connector_funcs,
+	drm_connector_init(&dev_priv->drm, connector, &gen11_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 	drm_connector_helper_add(connector, &gen11_dsi_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
 
 	/* attach connector to encoder */
@@ -2055,9 +2044,9 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 
 	intel_bios_init_panel(dev_priv, &intel_connector->panel, NULL, NULL);
 
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	intel_panel_add_vbt_lfp_fixed_mode(intel_connector);
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
 	if (!intel_panel_preferred_fixed_mode(intel_connector)) {
 		drm_err(&dev_priv->drm, "DSI fixed mode info missing\n");
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index 18f0a5ae3bac..6621aa245caf 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -252,6 +252,11 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	if (crtc_state->hw.gamma_lut)
 		drm_property_blob_get(crtc_state->hw.gamma_lut);
 
+	if (crtc_state->pre_csc_lut)
+		drm_property_blob_get(crtc_state->pre_csc_lut);
+	if (crtc_state->post_csc_lut)
+		drm_property_blob_get(crtc_state->post_csc_lut);
+
 	crtc_state->update_pipe = false;
 	crtc_state->disable_lp_wm = false;
 	crtc_state->disable_cxsr = false;
@@ -274,6 +279,9 @@ static void intel_crtc_put_color_blobs(struct intel_crtc_state *crtc_state)
 	drm_property_blob_put(crtc_state->hw.degamma_lut);
 	drm_property_blob_put(crtc_state->hw.gamma_lut);
 	drm_property_blob_put(crtc_state->hw.ctm);
+
+	drm_property_blob_put(crtc_state->pre_csc_lut);
+	drm_property_blob_put(crtc_state->post_csc_lut);
 }
 
 void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index aaa6708256d5..bcf0239b9533 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -425,6 +425,47 @@ static bool intel_plane_do_async_flip(struct intel_plane *plane,
 	return DISPLAY_VER(i915) < 13 || old_crtc_state->uapi.async_flip;
 }
 
+static bool i9xx_must_disable_cxsr(const struct intel_crtc_state *new_crtc_state,
+				   const struct intel_plane_state *old_plane_state,
+				   const struct intel_plane_state *new_plane_state)
+{
+	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
+	bool old_visible = old_plane_state->uapi.visible;
+	bool new_visible = new_plane_state->uapi.visible;
+	u32 old_ctl = old_plane_state->ctl;
+	u32 new_ctl = new_plane_state->ctl;
+	bool modeset, turn_on, turn_off;
+
+	if (plane->id == PLANE_CURSOR)
+		return false;
+
+	modeset = intel_crtc_needs_modeset(new_crtc_state);
+	turn_off = old_visible && (!new_visible || modeset);
+	turn_on = new_visible && (!old_visible || modeset);
+
+	/* Must disable CxSR around plane enable/disable */
+	if (turn_on || turn_off)
+		return true;
+
+	if (!old_visible || !new_visible)
+		return false;
+
+	/*
+	 * Most plane control register updates are blocked while in CxSR.
+	 *
+	 * Tiling mode is one exception where the primary plane can
+	 * apparently handle it, whereas the sprites can not (the
+	 * sprite issue being only relevant on VLV/CHV where CxSR
+	 * is actually possible with a sprite enabled).
+	 */
+	if (plane->id == PLANE_PRIMARY) {
+		old_ctl &= ~DISP_TILED;
+		new_ctl &= ~DISP_TILED;
+	}
+
+	return old_ctl != new_ctl;
+}
+
 static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state,
 					   struct intel_crtc_state *new_crtc_state,
 					   const struct intel_plane_state *old_plane_state,
@@ -482,17 +523,9 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr
 	if (turn_on) {
 		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
 			new_crtc_state->update_wm_pre = true;
-
-		/* must disable cxsr around plane enable/disable */
-		if (plane->id != PLANE_CURSOR)
-			new_crtc_state->disable_cxsr = true;
 	} else if (turn_off) {
 		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
 			new_crtc_state->update_wm_post = true;
-
-		/* must disable cxsr around plane enable/disable */
-		if (plane->id != PLANE_CURSOR)
-			new_crtc_state->disable_cxsr = true;
 	} else if (intel_wm_need_update(old_plane_state, new_plane_state)) {
 		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) {
 			/* FIXME bollocks */
@@ -504,6 +537,10 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr
 	if (visible || was_visible)
 		new_crtc_state->fb_bits |= plane->frontbuffer_bit;
 
+	if (HAS_GMCH(dev_priv) &&
+	    i9xx_must_disable_cxsr(new_crtc_state, old_plane_state, new_plane_state))
+		new_crtc_state->disable_cxsr = true;
+
 	/*
 	 * ILK/SNB DVSACNTR/Sprite Enable
 	 * IVB SPR_CTL/Sprite Enable
@@ -1005,7 +1042,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 		 */
 		if (intel_crtc_needs_modeset(crtc_state)) {
 			ret = i915_sw_fence_await_reservation(&state->commit_ready,
-							      old_obj->base.resv, NULL,
+							      old_obj->base.resv,
 							      false, 0,
 							      GFP_KERNEL);
 			if (ret < 0)
@@ -1039,8 +1076,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 		struct dma_fence *fence;
 
 		ret = i915_sw_fence_await_reservation(&state->commit_ready,
-						      obj->base.resv, NULL,
-						      false,
+						      obj->base.resv, false,
 						      i915_fence_timeout(dev_priv),
 						      GFP_KERNEL);
 		if (ret < 0)
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index aacbc6da84ef..c3176c9c89a6 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -250,7 +250,7 @@ static const struct hdmi_aud_ncts hdmi_aud_ncts_36bpp[] = {
 /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */
 static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
 	int i;
@@ -260,17 +260,17 @@ static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_sta
 			break;
 	}
 
-	if (DISPLAY_VER(dev_priv) < 12 && adjusted_mode->crtc_clock > 148500)
+	if (DISPLAY_VER(i915) < 12 && adjusted_mode->crtc_clock > 148500)
 		i = ARRAY_SIZE(hdmi_audio_clock);
 
 	if (i == ARRAY_SIZE(hdmi_audio_clock)) {
-		drm_dbg_kms(&dev_priv->drm,
+		drm_dbg_kms(&i915->drm,
 			    "HDMI audio pixel clock setting for %d not found, falling back to defaults\n",
 			    adjusted_mode->crtc_clock);
 		i = 1;
 	}
 
-	drm_dbg_kms(&dev_priv->drm,
+	drm_dbg_kms(&i915->drm,
 		    "Configuring HDMI audio for pixel clock %d (0x%08x)\n",
 		    hdmi_audio_clock[i].clock,
 		    hdmi_audio_clock[i].config);
@@ -304,96 +304,67 @@ static int audio_config_hdmi_get_n(const struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static bool intel_eld_uptodate(struct drm_connector *connector,
-			       i915_reg_t reg_eldv, u32 bits_eldv,
-			       i915_reg_t reg_elda, u32 bits_elda,
-			       i915_reg_t reg_edid)
+/* ELD buffer size in dwords */
+static int g4x_eld_buffer_size(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	const u8 *eld = connector->eld;
 	u32 tmp;
-	int i;
-
-	tmp = intel_de_read(dev_priv, reg_eldv);
-	tmp &= bits_eldv;
-
-	if (!tmp)
-		return false;
 
-	tmp = intel_de_read(dev_priv, reg_elda);
-	tmp &= ~bits_elda;
-	intel_de_write(dev_priv, reg_elda, tmp);
+	tmp = intel_de_read(i915, G4X_AUD_CNTL_ST);
 
-	for (i = 0; i < drm_eld_size(eld) / 4; i++)
-		if (intel_de_read(dev_priv, reg_edid) != *((const u32 *)eld + i))
-			return false;
-
-	return true;
+	return REG_FIELD_GET(G4X_ELD_BUFFER_SIZE_MASK, tmp);
 }
 
 static void g4x_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *old_crtc_state,
 				    const struct drm_connector_state *old_conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 eldv, tmp;
-
-	tmp = intel_de_read(dev_priv, G4X_AUD_VID_DID);
-	if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL)
-		eldv = G4X_ELDV_DEVCL_DEVBLC;
-	else
-		eldv = G4X_ELDV_DEVCTG;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 
 	/* Invalidate ELD */
-	tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST);
-	tmp &= ~eldv;
-	intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp);
+	intel_de_rmw(i915, G4X_AUD_CNTL_ST,
+		     G4X_ELD_VALID, 0);
+
+	intel_crtc_wait_for_next_vblank(crtc);
+	intel_crtc_wait_for_next_vblank(crtc);
 }
 
 static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
-	const u8 *eld = connector->eld;
-	u32 eldv;
-	u32 tmp;
-	int len, i;
+	const u32 *eld = (const u32 *)connector->eld;
+	int eld_buffer_size, len, i;
 
-	tmp = intel_de_read(dev_priv, G4X_AUD_VID_DID);
-	if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL)
-		eldv = G4X_ELDV_DEVCL_DEVBLC;
-	else
-		eldv = G4X_ELDV_DEVCTG;
+	intel_crtc_wait_for_next_vblank(crtc);
 
-	if (intel_eld_uptodate(connector,
-			       G4X_AUD_CNTL_ST, eldv,
-			       G4X_AUD_CNTL_ST, G4X_ELD_ADDR_MASK,
-			       G4X_HDMIW_HDMIEDID))
-		return;
+	intel_de_rmw(i915, G4X_AUD_CNTL_ST,
+		     G4X_ELD_VALID | G4X_ELD_ADDRESS_MASK, 0);
 
-	tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST);
-	tmp &= ~(eldv | G4X_ELD_ADDR_MASK);
-	len = (tmp >> 9) & 0x1f;		/* ELD buffer size */
-	intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp);
+	eld_buffer_size = g4x_eld_buffer_size(i915);
+	len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size);
 
-	len = min(drm_eld_size(eld) / 4, len);
 	for (i = 0; i < len; i++)
-		intel_de_write(dev_priv, G4X_HDMIW_HDMIEDID,
-			       *((const u32 *)eld + i));
+		intel_de_write(i915, G4X_HDMIW_HDMIEDID, eld[i]);
+	for (; i < eld_buffer_size; i++)
+		intel_de_write(i915, G4X_HDMIW_HDMIEDID, 0);
 
-	tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST);
-	tmp |= eldv;
-	intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp);
+	drm_WARN_ON(&i915->drm,
+		    (intel_de_read(i915, G4X_AUD_CNTL_ST) & G4X_ELD_ADDRESS_MASK) != 0);
+
+	intel_de_rmw(i915, G4X_AUD_CNTL_ST,
+		     0, G4X_ELD_VALID);
 }
 
 static void
 hsw_dp_audio_config_update(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct i915_audio_component *acomp = dev_priv->display.audio.component;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct i915_audio_component *acomp = i915->display.audio.component;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	enum port port = encoder->port;
 	const struct dp_aud_n_m *nm;
@@ -403,12 +374,12 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder,
 	rate = acomp ? acomp->aud_sample_rate[port] : 0;
 	nm = audio_config_dp_get_n_m(crtc_state, rate);
 	if (nm)
-		drm_dbg_kms(&dev_priv->drm, "using Maud %u, Naud %u\n", nm->m,
+		drm_dbg_kms(&i915->drm, "using Maud %u, Naud %u\n", nm->m,
 			    nm->n);
 	else
-		drm_dbg_kms(&dev_priv->drm, "using automatic Maud, Naud\n");
+		drm_dbg_kms(&i915->drm, "using automatic Maud, Naud\n");
 
-	tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder));
+	tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder));
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
 	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
@@ -420,9 +391,9 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder,
 		tmp |= AUD_CONFIG_N_PROG_ENABLE;
 	}
 
-	intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp);
+	intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp);
 
-	tmp = intel_de_read(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder));
+	tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder));
 	tmp &= ~AUD_CONFIG_M_MASK;
 	tmp &= ~AUD_M_CTS_M_VALUE_INDEX;
 	tmp &= ~AUD_M_CTS_M_PROG_ENABLE;
@@ -433,15 +404,15 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder,
 		tmp |= AUD_M_CTS_M_PROG_ENABLE;
 	}
 
-	intel_de_write(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp);
+	intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp);
 }
 
 static void
 hsw_hdmi_audio_config_update(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct i915_audio_component *acomp = dev_priv->display.audio.component;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct i915_audio_component *acomp = i915->display.audio.component;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	enum port port = encoder->port;
 	int n, rate;
@@ -449,7 +420,7 @@ hsw_hdmi_audio_config_update(struct intel_encoder *encoder,
 
 	rate = acomp ? acomp->aud_sample_rate[port] : 0;
 
-	tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder));
+	tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder));
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
 	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
@@ -457,25 +428,25 @@ hsw_hdmi_audio_config_update(struct intel_encoder *encoder,
 
 	n = audio_config_hdmi_get_n(crtc_state, rate);
 	if (n != 0) {
-		drm_dbg_kms(&dev_priv->drm, "using N %d\n", n);
+		drm_dbg_kms(&i915->drm, "using N %d\n", n);
 
 		tmp &= ~AUD_CONFIG_N_MASK;
 		tmp |= AUD_CONFIG_N(n);
 		tmp |= AUD_CONFIG_N_PROG_ENABLE;
 	} else {
-		drm_dbg_kms(&dev_priv->drm, "using automatic N\n");
+		drm_dbg_kms(&i915->drm, "using automatic N\n");
 	}
 
-	intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp);
+	intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp);
 
 	/*
 	 * Let's disable "Enable CTS or M Prog bit"
 	 * and let HW calculate the value
 	 */
-	tmp = intel_de_read(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder));
+	tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder));
 	tmp &= ~AUD_M_CTS_M_PROG_ENABLE;
 	tmp &= ~AUD_M_CTS_M_VALUE_INDEX;
-	intel_de_write(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp);
+	intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp);
 }
 
 static void
@@ -488,33 +459,48 @@ hsw_audio_config_update(struct intel_encoder *encoder,
 		hsw_hdmi_audio_config_update(encoder, crtc_state);
 }
 
+/* ELD buffer size in dwords */
+static int hsw_eld_buffer_size(struct drm_i915_private *i915,
+			       enum transcoder cpu_transcoder)
+{
+	u32 tmp;
+
+	tmp = intel_de_read(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder));
+
+	return REG_FIELD_GET(IBX_ELD_BUFFER_SIZE_MASK, tmp);
+}
+
 static void hsw_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *old_crtc_state,
 				    const struct drm_connector_state *old_conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
-	u32 tmp;
 
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 
 	/* Disable timestamps */
-	tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder));
-	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
-	tmp |= AUD_CONFIG_N_PROG_ENABLE;
-	tmp &= ~AUD_CONFIG_UPPER_N_MASK;
-	tmp &= ~AUD_CONFIG_LOWER_N_MASK;
-	if (intel_crtc_has_dp_encoder(old_crtc_state))
-		tmp |= AUD_CONFIG_N_VALUE_INDEX;
-	intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp);
+	intel_de_rmw(i915, HSW_AUD_CFG(cpu_transcoder),
+		     AUD_CONFIG_N_VALUE_INDEX |
+		     AUD_CONFIG_UPPER_N_MASK |
+		     AUD_CONFIG_LOWER_N_MASK,
+		     AUD_CONFIG_N_PROG_ENABLE |
+		     (intel_crtc_has_dp_encoder(old_crtc_state) ?
+		      AUD_CONFIG_N_VALUE_INDEX : 0));
 
 	/* Invalidate ELD */
-	tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD);
-	tmp &= ~AUDIO_ELD_VALID(cpu_transcoder);
-	tmp &= ~AUDIO_OUTPUT_ENABLE(cpu_transcoder);
-	intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp);
+	intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD,
+		     AUDIO_ELD_VALID(cpu_transcoder), 0);
+
+	intel_crtc_wait_for_next_vblank(crtc);
+	intel_crtc_wait_for_next_vblank(crtc);
 
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	/* Disable audio presence detect */
+	intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD,
+		     AUDIO_OUTPUT_ENABLE(cpu_transcoder), 0);
+
+	mutex_unlock(&i915->display.audio.mutex);
 }
 
 static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder,
@@ -626,178 +612,190 @@ static void enable_audio_dsc_wa(struct intel_encoder *encoder,
 	intel_de_write(i915, AUD_CONFIG_BE, val);
 }
 
-#undef ROUNDING_FACTOR
-
 static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	const u8 *eld = connector->eld;
-	u32 tmp;
-	int len, i;
+	const u32 *eld = (const u32 *)connector->eld;
+	int eld_buffer_size, len, i;
 
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 
 	/* Enable Audio WA for 4k DSC usecases */
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP))
 		enable_audio_dsc_wa(encoder, crtc_state);
 
-	/* Enable audio presence detect, invalidate ELD */
-	tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD);
-	tmp |= AUDIO_OUTPUT_ENABLE(cpu_transcoder);
-	tmp &= ~AUDIO_ELD_VALID(cpu_transcoder);
-	intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp);
+	/* Enable audio presence detect */
+	intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD,
+		     0, AUDIO_OUTPUT_ENABLE(cpu_transcoder));
 
-	/*
-	 * FIXME: We're supposed to wait for vblank here, but we have vblanks
-	 * disabled during the mode set. The proper fix would be to push the
-	 * rest of the setup into a vblank work item, queued here, but the
-	 * infrastructure is not there yet.
-	 */
+	intel_crtc_wait_for_next_vblank(crtc);
+
+	/* Invalidate ELD */
+	intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD,
+		     AUDIO_ELD_VALID(cpu_transcoder), 0);
+
+	/* Reset ELD address */
+	intel_de_rmw(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder),
+		     IBX_ELD_ADDRESS_MASK, 0);
 
-	/* Reset ELD write address */
-	tmp = intel_de_read(dev_priv, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder));
-	tmp &= ~IBX_ELD_ADDRESS_MASK;
-	intel_de_write(dev_priv, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder), tmp);
+	eld_buffer_size = hsw_eld_buffer_size(i915, cpu_transcoder);
+	len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size);
 
-	/* Up to 84 bytes of hw ELD buffer */
-	len = min(drm_eld_size(eld), 84);
-	for (i = 0; i < len / 4; i++)
-		intel_de_write(dev_priv, HSW_AUD_EDID_DATA(cpu_transcoder),
-			       *((const u32 *)eld + i));
+	for (i = 0; i < len; i++)
+		intel_de_write(i915, HSW_AUD_EDID_DATA(cpu_transcoder), eld[i]);
+	for (; i < eld_buffer_size; i++)
+		intel_de_write(i915, HSW_AUD_EDID_DATA(cpu_transcoder), 0);
+
+	drm_WARN_ON(&i915->drm,
+		    (intel_de_read(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder)) &
+		     IBX_ELD_ADDRESS_MASK) != 0);
 
 	/* ELD valid */
-	tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD);
-	tmp |= AUDIO_ELD_VALID(cpu_transcoder);
-	intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp);
+	intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD,
+		     0, AUDIO_ELD_VALID(cpu_transcoder));
 
 	/* Enable timestamps */
 	hsw_audio_config_update(encoder, crtc_state);
 
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	mutex_unlock(&i915->display.audio.mutex);
+}
+
+struct ilk_audio_regs {
+	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
+};
+
+static void ilk_audio_regs_init(struct drm_i915_private *i915,
+				enum pipe pipe,
+				struct ilk_audio_regs *regs)
+{
+	if (HAS_PCH_IBX(i915)) {
+		regs->hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID(pipe);
+		regs->aud_config = IBX_AUD_CFG(pipe);
+		regs->aud_cntl_st = IBX_AUD_CNTL_ST(pipe);
+		regs->aud_cntrl_st2 = IBX_AUD_CNTL_ST2;
+	} else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		regs->hdmiw_hdmiedid = VLV_HDMIW_HDMIEDID(pipe);
+		regs->aud_config = VLV_AUD_CFG(pipe);
+		regs->aud_cntl_st = VLV_AUD_CNTL_ST(pipe);
+		regs->aud_cntrl_st2 = VLV_AUD_CNTL_ST2;
+	} else {
+		regs->hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID(pipe);
+		regs->aud_config = CPT_AUD_CFG(pipe);
+		regs->aud_cntl_st = CPT_AUD_CNTL_ST(pipe);
+		regs->aud_cntrl_st2 = CPT_AUD_CNTRL_ST2;
+	}
+}
+
+/* ELD buffer size in dwords */
+static int ilk_eld_buffer_size(struct drm_i915_private *i915,
+			       enum pipe pipe)
+{
+	struct ilk_audio_regs regs;
+	u32 tmp;
+
+	ilk_audio_regs_init(i915, pipe, &regs);
+
+	tmp = intel_de_read(i915, regs.aud_cntl_st);
+
+	return REG_FIELD_GET(IBX_ELD_BUFFER_SIZE_MASK, tmp);
 }
 
 static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *old_crtc_state,
 				    const struct drm_connector_state *old_conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
-	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	u32 tmp, eldv;
-	i915_reg_t aud_config, aud_cntrl_st2;
+	enum pipe pipe = crtc->pipe;
+	struct ilk_audio_regs regs;
 
-	if (drm_WARN_ON(&dev_priv->drm, port == PORT_A))
+	if (drm_WARN_ON(&i915->drm, port == PORT_A))
 		return;
 
-	if (HAS_PCH_IBX(dev_priv)) {
-		aud_config = IBX_AUD_CFG(pipe);
-		aud_cntrl_st2 = IBX_AUD_CNTL_ST2;
-	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		aud_config = VLV_AUD_CFG(pipe);
-		aud_cntrl_st2 = VLV_AUD_CNTL_ST2;
-	} else {
-		aud_config = CPT_AUD_CFG(pipe);
-		aud_cntrl_st2 = CPT_AUD_CNTRL_ST2;
-	}
+	ilk_audio_regs_init(i915, pipe, &regs);
 
-	/* Disable timestamps */
-	tmp = intel_de_read(dev_priv, aud_config);
-	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
-	tmp |= AUD_CONFIG_N_PROG_ENABLE;
-	tmp &= ~AUD_CONFIG_UPPER_N_MASK;
-	tmp &= ~AUD_CONFIG_LOWER_N_MASK;
-	if (intel_crtc_has_dp_encoder(old_crtc_state))
-		tmp |= AUD_CONFIG_N_VALUE_INDEX;
-	intel_de_write(dev_priv, aud_config, tmp);
+	mutex_lock(&i915->display.audio.mutex);
 
-	eldv = IBX_ELD_VALID(port);
+	/* Disable timestamps */
+	intel_de_rmw(i915, regs.aud_config,
+		     AUD_CONFIG_N_VALUE_INDEX |
+		     AUD_CONFIG_UPPER_N_MASK |
+		     AUD_CONFIG_LOWER_N_MASK,
+		     AUD_CONFIG_N_PROG_ENABLE |
+		     (intel_crtc_has_dp_encoder(old_crtc_state) ?
+		      AUD_CONFIG_N_VALUE_INDEX : 0));
 
 	/* Invalidate ELD */
-	tmp = intel_de_read(dev_priv, aud_cntrl_st2);
-	tmp &= ~eldv;
-	intel_de_write(dev_priv, aud_cntrl_st2, tmp);
+	intel_de_rmw(i915, regs.aud_cntrl_st2,
+		     IBX_ELD_VALID(port), 0);
+
+	mutex_unlock(&i915->display.audio.mutex);
+
+	intel_crtc_wait_for_next_vblank(crtc);
+	intel_crtc_wait_for_next_vblank(crtc);
 }
 
 static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
-	enum pipe pipe = crtc->pipe;
+	const u32 *eld = (const u32 *)connector->eld;
 	enum port port = encoder->port;
-	const u8 *eld = connector->eld;
-	u32 tmp, eldv;
-	int len, i;
-	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
+	enum pipe pipe = crtc->pipe;
+	int eld_buffer_size, len, i;
+	struct ilk_audio_regs regs;
 
-	if (drm_WARN_ON(&dev_priv->drm, port == PORT_A))
+	if (drm_WARN_ON(&i915->drm, port == PORT_A))
 		return;
 
-	/*
-	 * FIXME: We're supposed to wait for vblank here, but we have vblanks
-	 * disabled during the mode set. The proper fix would be to push the
-	 * rest of the setup into a vblank work item, queued here, but the
-	 * infrastructure is not there yet.
-	 */
+	intel_crtc_wait_for_next_vblank(crtc);
 
-	if (HAS_PCH_IBX(dev_priv)) {
-		hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID(pipe);
-		aud_config = IBX_AUD_CFG(pipe);
-		aud_cntl_st = IBX_AUD_CNTL_ST(pipe);
-		aud_cntrl_st2 = IBX_AUD_CNTL_ST2;
-	} else if (IS_VALLEYVIEW(dev_priv) ||
-		   IS_CHERRYVIEW(dev_priv)) {
-		hdmiw_hdmiedid = VLV_HDMIW_HDMIEDID(pipe);
-		aud_config = VLV_AUD_CFG(pipe);
-		aud_cntl_st = VLV_AUD_CNTL_ST(pipe);
-		aud_cntrl_st2 = VLV_AUD_CNTL_ST2;
-	} else {
-		hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID(pipe);
-		aud_config = CPT_AUD_CFG(pipe);
-		aud_cntl_st = CPT_AUD_CNTL_ST(pipe);
-		aud_cntrl_st2 = CPT_AUD_CNTRL_ST2;
-	}
+	ilk_audio_regs_init(i915, pipe, &regs);
 
-	eldv = IBX_ELD_VALID(port);
+	mutex_lock(&i915->display.audio.mutex);
 
 	/* Invalidate ELD */
-	tmp = intel_de_read(dev_priv, aud_cntrl_st2);
-	tmp &= ~eldv;
-	intel_de_write(dev_priv, aud_cntrl_st2, tmp);
+	intel_de_rmw(i915, regs.aud_cntrl_st2,
+		     IBX_ELD_VALID(port), 0);
 
-	/* Reset ELD write address */
-	tmp = intel_de_read(dev_priv, aud_cntl_st);
-	tmp &= ~IBX_ELD_ADDRESS_MASK;
-	intel_de_write(dev_priv, aud_cntl_st, tmp);
+	/* Reset ELD address */
+	intel_de_rmw(i915, regs.aud_cntl_st,
+		     IBX_ELD_ADDRESS_MASK, 0);
 
-	/* Up to 84 bytes of hw ELD buffer */
-	len = min(drm_eld_size(eld), 84);
-	for (i = 0; i < len / 4; i++)
-		intel_de_write(dev_priv, hdmiw_hdmiedid,
-			       *((const u32 *)eld + i));
+	eld_buffer_size = ilk_eld_buffer_size(i915, pipe);
+	len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size);
+
+	for (i = 0; i < len; i++)
+		intel_de_write(i915, regs.hdmiw_hdmiedid, eld[i]);
+	for (; i < eld_buffer_size; i++)
+		intel_de_write(i915, regs.hdmiw_hdmiedid, 0);
+
+	drm_WARN_ON(&i915->drm,
+		    (intel_de_read(i915, regs.aud_cntl_st) & IBX_ELD_ADDRESS_MASK) != 0);
 
 	/* ELD valid */
-	tmp = intel_de_read(dev_priv, aud_cntrl_st2);
-	tmp |= eldv;
-	intel_de_write(dev_priv, aud_cntrl_st2, tmp);
+	intel_de_rmw(i915, regs.aud_cntrl_st2,
+		     0, IBX_ELD_VALID(port));
 
 	/* Enable timestamps */
-	tmp = intel_de_read(dev_priv, aud_config);
-	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
-	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
-	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
-	if (intel_crtc_has_dp_encoder(crtc_state))
-		tmp |= AUD_CONFIG_N_VALUE_INDEX;
-	else
-		tmp |= audio_config_hdmi_pixel_clock(crtc_state);
-	intel_de_write(dev_priv, aud_config, tmp);
+	intel_de_rmw(i915, regs.aud_config,
+		     AUD_CONFIG_N_VALUE_INDEX |
+		     AUD_CONFIG_N_PROG_ENABLE |
+		     AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK,
+		     (intel_crtc_has_dp_encoder(crtc_state) ?
+		      AUD_CONFIG_N_VALUE_INDEX :
+		      audio_config_hdmi_pixel_clock(crtc_state)));
+
+	mutex_unlock(&i915->display.audio.mutex);
 }
 
 /**
@@ -813,8 +811,8 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state,
 			      const struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct i915_audio_component *acomp = dev_priv->display.audio.component;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct i915_audio_component *acomp = i915->display.audio.component;
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	const struct drm_display_mode *adjusted_mode =
@@ -825,30 +823,30 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	if (!crtc_state->has_audio)
 		return;
 
-	drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Enable audio codec on pipe %c, %u bytes ELD\n",
+	drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Enable audio codec on pipe %c, %u bytes ELD\n",
 		    connector->base.id, connector->name,
 		    encoder->base.base.id, encoder->base.name,
 		    pipe_name(pipe), drm_eld_size(connector->eld));
 
 	/* FIXME precompute the ELD in .compute_config() */
 	if (!connector->eld[0])
-		drm_dbg_kms(&dev_priv->drm,
+		drm_dbg_kms(&i915->drm,
 			    "Bogus ELD on [CONNECTOR:%d:%s]\n",
 			    connector->base.id, connector->name);
 
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
-	if (dev_priv->display.funcs.audio)
-		dev_priv->display.funcs.audio->audio_codec_enable(encoder,
+	if (i915->display.funcs.audio)
+		i915->display.funcs.audio->audio_codec_enable(encoder,
 								  crtc_state,
 								  conn_state);
 
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 	encoder->audio_connector = connector;
 
 	/* referred in audio callbacks */
-	dev_priv->display.audio.encoder_map[pipe] = encoder;
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	i915->display.audio.encoder_map[pipe] = encoder;
+	mutex_unlock(&i915->display.audio.mutex);
 
 	if (acomp && acomp->base.audio_ops &&
 	    acomp->base.audio_ops->pin_eld_notify) {
@@ -859,7 +857,7 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 						 (int) port, (int) pipe);
 	}
 
-	intel_lpe_audio_notify(dev_priv, pipe, port, connector->eld,
+	intel_lpe_audio_notify(i915, pipe, port, connector->eld,
 			       crtc_state->port_clock,
 			       intel_crtc_has_dp_encoder(crtc_state));
 }
@@ -877,8 +875,8 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *old_crtc_state,
 			       const struct drm_connector_state *old_conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct i915_audio_component *acomp = dev_priv->display.audio.component;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct i915_audio_component *acomp = i915->display.audio.component;
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_connector *connector = old_conn_state->connector;
 	enum port port = encoder->port;
@@ -887,19 +885,19 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 	if (!old_crtc_state->has_audio)
 		return;
 
-	drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Disable audio codec on pipe %c\n",
+	drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Disable audio codec on pipe %c\n",
 		    connector->base.id, connector->name,
 		    encoder->base.base.id, encoder->base.name, pipe_name(pipe));
 
-	if (dev_priv->display.funcs.audio)
-		dev_priv->display.funcs.audio->audio_codec_disable(encoder,
+	if (i915->display.funcs.audio)
+		i915->display.funcs.audio->audio_codec_disable(encoder,
 								   old_crtc_state,
 								   old_conn_state);
 
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 	encoder->audio_connector = NULL;
-	dev_priv->display.audio.encoder_map[pipe] = NULL;
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	i915->display.audio.encoder_map[pipe] = NULL;
+	mutex_unlock(&i915->display.audio.mutex);
 
 	if (acomp && acomp->base.audio_ops &&
 	    acomp->base.audio_ops->pin_eld_notify) {
@@ -910,7 +908,7 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 						 (int) port, (int) pipe);
 	}
 
-	intel_lpe_audio_notify(dev_priv, pipe, port, NULL, 0, false);
+	intel_lpe_audio_notify(i915, pipe, port, NULL, 0, false);
 }
 
 static const struct intel_audio_funcs g4x_audio_funcs = {
@@ -930,19 +928,18 @@ static const struct intel_audio_funcs hsw_audio_funcs = {
 
 /**
  * intel_audio_hooks_init - Set up chip specific audio hooks
- * @dev_priv: device private
+ * @i915: device private
  */
-void intel_audio_hooks_init(struct drm_i915_private *dev_priv)
+void intel_audio_hooks_init(struct drm_i915_private *i915)
 {
-	if (IS_G4X(dev_priv)) {
-		dev_priv->display.funcs.audio = &g4x_audio_funcs;
-	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->display.funcs.audio = &ilk_audio_funcs;
-	} else if (IS_HASWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 8) {
-		dev_priv->display.funcs.audio = &hsw_audio_funcs;
-	} else if (HAS_PCH_SPLIT(dev_priv)) {
-		dev_priv->display.funcs.audio = &ilk_audio_funcs;
-	}
+	if (IS_G4X(i915))
+		i915->display.funcs.audio = &g4x_audio_funcs;
+	else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+		i915->display.funcs.audio = &ilk_audio_funcs;
+	else if (IS_HASWELL(i915) || DISPLAY_VER(i915) >= 8)
+		i915->display.funcs.audio = &hsw_audio_funcs;
+	else if (HAS_PCH_SPLIT(i915))
+		i915->display.funcs.audio = &ilk_audio_funcs;
 }
 
 struct aud_ts_cdclk_m_n {
@@ -1000,7 +997,7 @@ static int glk_force_audio_cdclk_commit(struct intel_atomic_state *state,
 	return drm_atomic_commit(&state->base);
 }
 
-static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv,
+static void glk_force_audio_cdclk(struct drm_i915_private *i915,
 				  bool enable)
 {
 	struct drm_modeset_acquire_ctx ctx;
@@ -1008,13 +1005,13 @@ static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv,
 	struct intel_crtc *crtc;
 	int ret;
 
-	crtc = intel_first_crtc(dev_priv);
+	crtc = intel_first_crtc(i915);
 	if (!crtc)
 		return;
 
 	drm_modeset_acquire_init(&ctx, 0);
-	state = drm_atomic_state_alloc(&dev_priv->drm);
-	if (drm_WARN_ON(&dev_priv->drm, !state))
+	state = drm_atomic_state_alloc(&i915->drm);
+	if (drm_WARN_ON(&i915->drm, !state))
 		return;
 
 	state->acquire_ctx = &ctx;
@@ -1028,7 +1025,7 @@ retry:
 		goto retry;
 	}
 
-	drm_WARN_ON(&dev_priv->drm, ret);
+	drm_WARN_ON(&i915->drm, ret);
 
 	drm_atomic_state_put(state);
 
@@ -1038,30 +1035,30 @@ retry:
 
 static unsigned long i915_audio_component_get_power(struct device *kdev)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
 	intel_wakeref_t ret;
 
 	/* Catch potential impedance mismatches before they occur! */
 	BUILD_BUG_ON(sizeof(intel_wakeref_t) > sizeof(unsigned long));
 
-	ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK);
+	ret = intel_display_power_get(i915, POWER_DOMAIN_AUDIO_PLAYBACK);
 
-	if (dev_priv->display.audio.power_refcount++ == 0) {
-		if (DISPLAY_VER(dev_priv) >= 9) {
-			intel_de_write(dev_priv, AUD_FREQ_CNTRL,
-				       dev_priv->display.audio.freq_cntrl);
-			drm_dbg_kms(&dev_priv->drm,
+	if (i915->display.audio.power_refcount++ == 0) {
+		if (DISPLAY_VER(i915) >= 9) {
+			intel_de_write(i915, AUD_FREQ_CNTRL,
+				       i915->display.audio.freq_cntrl);
+			drm_dbg_kms(&i915->drm,
 				    "restored AUD_FREQ_CNTRL to 0x%x\n",
-				    dev_priv->display.audio.freq_cntrl);
+				    i915->display.audio.freq_cntrl);
 		}
 
 		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
-		if (IS_GEMINILAKE(dev_priv))
-			glk_force_audio_cdclk(dev_priv, true);
+		if (IS_GEMINILAKE(i915))
+			glk_force_audio_cdclk(i915, true);
 
-		if (DISPLAY_VER(dev_priv) >= 10)
-			intel_de_write(dev_priv, AUD_PIN_BUF_CTL,
-				       (intel_de_read(dev_priv, AUD_PIN_BUF_CTL) | AUD_PIN_BUF_ENABLE));
+		if (DISPLAY_VER(i915) >= 10)
+			intel_de_rmw(i915, AUD_PIN_BUF_CTL,
+				     0, AUD_PIN_BUF_ENABLE);
 	}
 
 	return ret;
@@ -1070,24 +1067,23 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 static void i915_audio_component_put_power(struct device *kdev,
 					   unsigned long cookie)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
 
 	/* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
-	if (--dev_priv->display.audio.power_refcount == 0)
-		if (IS_GEMINILAKE(dev_priv))
-			glk_force_audio_cdclk(dev_priv, false);
+	if (--i915->display.audio.power_refcount == 0)
+		if (IS_GEMINILAKE(i915))
+			glk_force_audio_cdclk(i915, false);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK, cookie);
+	intel_display_power_put(i915, POWER_DOMAIN_AUDIO_PLAYBACK, cookie);
 }
 
 static void i915_audio_component_codec_wake_override(struct device *kdev,
 						     bool enable)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
 	unsigned long cookie;
-	u32 tmp;
 
-	if (DISPLAY_VER(dev_priv) < 9)
+	if (DISPLAY_VER(i915) < 9)
 		return;
 
 	cookie = i915_audio_component_get_power(kdev);
@@ -1096,15 +1092,13 @@ static void i915_audio_component_codec_wake_override(struct device *kdev,
 	 * Enable/disable generating the codec wake signal, overriding the
 	 * internal logic to generate the codec wake to controller.
 	 */
-	tmp = intel_de_read(dev_priv, HSW_AUD_CHICKENBIT);
-	tmp &= ~SKL_AUD_CODEC_WAKE_SIGNAL;
-	intel_de_write(dev_priv, HSW_AUD_CHICKENBIT, tmp);
+	intel_de_rmw(i915, HSW_AUD_CHICKENBIT,
+		     SKL_AUD_CODEC_WAKE_SIGNAL, 0);
 	usleep_range(1000, 1500);
 
 	if (enable) {
-		tmp = intel_de_read(dev_priv, HSW_AUD_CHICKENBIT);
-		tmp |= SKL_AUD_CODEC_WAKE_SIGNAL;
-		intel_de_write(dev_priv, HSW_AUD_CHICKENBIT, tmp);
+		intel_de_rmw(i915, HSW_AUD_CHICKENBIT,
+			     0, SKL_AUD_CODEC_WAKE_SIGNAL);
 		usleep_range(1000, 1500);
 	}
 
@@ -1114,12 +1108,12 @@ static void i915_audio_component_codec_wake_override(struct device *kdev,
 /* Get CDCLK in kHz  */
 static int i915_audio_component_get_cdclk_freq(struct device *kdev)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
 
-	if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_DDI(dev_priv)))
+	if (drm_WARN_ON_ONCE(&i915->drm, !HAS_DDI(i915)))
 		return -ENODEV;
 
-	return dev_priv->display.cdclk.hw.cdclk;
+	return i915->display.cdclk.hw.cdclk;
 }
 
 /*
@@ -1132,18 +1126,18 @@ static int i915_audio_component_get_cdclk_freq(struct device *kdev)
  *   will get the right intel_encoder with port matched
  * Non-MST & (pipe < 0): get the right intel_encoder with port matched
  */
-static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv,
-					       int port, int pipe)
+static struct intel_encoder *get_saved_enc(struct drm_i915_private *i915,
+					   int port, int pipe)
 {
 	struct intel_encoder *encoder;
 
 	/* MST */
 	if (pipe >= 0) {
-		if (drm_WARN_ON(&dev_priv->drm,
-				pipe >= ARRAY_SIZE(dev_priv->display.audio.encoder_map)))
+		if (drm_WARN_ON(&i915->drm,
+				pipe >= ARRAY_SIZE(i915->display.audio.encoder_map)))
 			return NULL;
 
-		encoder = dev_priv->display.audio.encoder_map[pipe];
+		encoder = i915->display.audio.encoder_map[pipe];
 		/*
 		 * when bootup, audio driver may not know it is
 		 * MST or not. So it will poll all the port & pipe
@@ -1158,8 +1152,8 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv,
 	if (pipe > 0)
 		return NULL;
 
-	for_each_pipe(dev_priv, pipe) {
-		encoder = dev_priv->display.audio.encoder_map[pipe];
+	for_each_pipe(i915, pipe) {
+		encoder = i915->display.audio.encoder_map[pipe];
 		if (encoder == NULL)
 			continue;
 
@@ -1176,23 +1170,23 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv,
 static int i915_audio_component_sync_audio_rate(struct device *kdev, int port,
 						int pipe, int rate)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
-	struct i915_audio_component *acomp = dev_priv->display.audio.component;
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
+	struct i915_audio_component *acomp = i915->display.audio.component;
 	struct intel_encoder *encoder;
 	struct intel_crtc *crtc;
 	unsigned long cookie;
 	int err = 0;
 
-	if (!HAS_DDI(dev_priv))
+	if (!HAS_DDI(i915))
 		return 0;
 
 	cookie = i915_audio_component_get_power(kdev);
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 
 	/* 1. get the pipe */
-	encoder = get_saved_enc(dev_priv, port, pipe);
+	encoder = get_saved_enc(i915, port, pipe);
 	if (!encoder || !encoder->base.crtc) {
-		drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n",
+		drm_dbg_kms(&i915->drm, "Not valid for port %c\n",
 			    port_name(port));
 		err = -ENODEV;
 		goto unlock;
@@ -1206,7 +1200,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port,
 	hsw_audio_config_update(encoder, crtc->config);
 
  unlock:
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	mutex_unlock(&i915->display.audio.mutex);
 	i915_audio_component_put_power(kdev, cookie);
 	return err;
 }
@@ -1215,18 +1209,18 @@ static int i915_audio_component_get_eld(struct device *kdev, int port,
 					int pipe, bool *enabled,
 					unsigned char *buf, int max_bytes)
 {
-	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(kdev);
 	struct intel_encoder *intel_encoder;
 	const u8 *eld;
 	int ret = -EINVAL;
 
-	mutex_lock(&dev_priv->display.audio.mutex);
+	mutex_lock(&i915->display.audio.mutex);
 
-	intel_encoder = get_saved_enc(dev_priv, port, pipe);
+	intel_encoder = get_saved_enc(i915, port, pipe);
 	if (!intel_encoder) {
-		drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n",
+		drm_dbg_kms(&i915->drm, "Not valid for port %c\n",
 			    port_name(port));
-		mutex_unlock(&dev_priv->display.audio.mutex);
+		mutex_unlock(&i915->display.audio.mutex);
 		return ret;
 	}
 
@@ -1238,7 +1232,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port,
 		memcpy(buf, eld, min(max_bytes, ret));
 	}
 
-	mutex_unlock(&dev_priv->display.audio.mutex);
+	mutex_unlock(&i915->display.audio.mutex);
 	return ret;
 }
 
@@ -1256,25 +1250,25 @@ static int i915_audio_component_bind(struct device *i915_kdev,
 				     struct device *hda_kdev, void *data)
 {
 	struct i915_audio_component *acomp = data;
-	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(i915_kdev);
 	int i;
 
-	if (drm_WARN_ON(&dev_priv->drm, acomp->base.ops || acomp->base.dev))
+	if (drm_WARN_ON(&i915->drm, acomp->base.ops || acomp->base.dev))
 		return -EEXIST;
 
-	if (drm_WARN_ON(&dev_priv->drm,
+	if (drm_WARN_ON(&i915->drm,
 			!device_link_add(hda_kdev, i915_kdev,
 					 DL_FLAG_STATELESS)))
 		return -ENOMEM;
 
-	drm_modeset_lock_all(&dev_priv->drm);
+	drm_modeset_lock_all(&i915->drm);
 	acomp->base.ops = &i915_audio_component_ops;
 	acomp->base.dev = i915_kdev;
 	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
 	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
 		acomp->aud_sample_rate[i] = 0;
-	dev_priv->display.audio.component = acomp;
-	drm_modeset_unlock_all(&dev_priv->drm);
+	i915->display.audio.component = acomp;
+	drm_modeset_unlock_all(&i915->drm);
 
 	return 0;
 }
@@ -1283,19 +1277,19 @@ static void i915_audio_component_unbind(struct device *i915_kdev,
 					struct device *hda_kdev, void *data)
 {
 	struct i915_audio_component *acomp = data;
-	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
+	struct drm_i915_private *i915 = kdev_to_i915(i915_kdev);
 
-	drm_modeset_lock_all(&dev_priv->drm);
+	drm_modeset_lock_all(&i915->drm);
 	acomp->base.ops = NULL;
 	acomp->base.dev = NULL;
-	dev_priv->display.audio.component = NULL;
-	drm_modeset_unlock_all(&dev_priv->drm);
+	i915->display.audio.component = NULL;
+	drm_modeset_unlock_all(&i915->drm);
 
 	device_link_remove(hda_kdev, i915_kdev);
 
-	if (dev_priv->display.audio.power_refcount)
-		drm_err(&dev_priv->drm, "audio power refcount %d after unbind\n",
-			dev_priv->display.audio.power_refcount);
+	if (i915->display.audio.power_refcount)
+		drm_err(&i915->drm, "audio power refcount %d after unbind\n",
+			i915->display.audio.power_refcount);
 }
 
 static const struct component_ops i915_audio_component_bind_ops = {
@@ -1314,7 +1308,7 @@ static const struct component_ops i915_audio_component_bind_ops = {
 
 /**
  * i915_audio_component_init - initialize and register the audio component
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This will register with the component framework a child component which
  * will bind dynamically to the snd_hda_intel driver's corresponding master
@@ -1328,83 +1322,83 @@ static const struct component_ops i915_audio_component_bind_ops = {
  * We ignore any error during registration and continue with reduced
  * functionality (i.e. without HDMI audio).
  */
-static void i915_audio_component_init(struct drm_i915_private *dev_priv)
+static void i915_audio_component_init(struct drm_i915_private *i915)
 {
 	u32 aud_freq, aud_freq_init;
 	int ret;
 
-	ret = component_add_typed(dev_priv->drm.dev,
+	ret = component_add_typed(i915->drm.dev,
 				  &i915_audio_component_bind_ops,
 				  I915_COMPONENT_AUDIO);
 	if (ret < 0) {
-		drm_err(&dev_priv->drm,
+		drm_err(&i915->drm,
 			"failed to add audio component (%d)\n", ret);
 		/* continue with reduced functionality */
 		return;
 	}
 
-	if (DISPLAY_VER(dev_priv) >= 9) {
-		aud_freq_init = intel_de_read(dev_priv, AUD_FREQ_CNTRL);
+	if (DISPLAY_VER(i915) >= 9) {
+		aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL);
 
-		if (DISPLAY_VER(dev_priv) >= 12)
+		if (DISPLAY_VER(i915) >= 12)
 			aud_freq = AUD_FREQ_GEN12;
 		else
 			aud_freq = aud_freq_init;
 
 		/* use BIOS provided value for TGL and RKL unless it is a known bad value */
-		if ((IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv)) &&
+		if ((IS_TIGERLAKE(i915) || IS_ROCKETLAKE(i915)) &&
 		    aud_freq_init != AUD_FREQ_TGL_BROKEN)
 			aud_freq = aud_freq_init;
 
-		drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n",
+		drm_dbg_kms(&i915->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n",
 			    aud_freq, aud_freq_init);
 
-		dev_priv->display.audio.freq_cntrl = aud_freq;
+		i915->display.audio.freq_cntrl = aud_freq;
 	}
 
 	/* init with current cdclk */
-	intel_audio_cdclk_change_post(dev_priv);
+	intel_audio_cdclk_change_post(i915);
 
-	dev_priv->display.audio.component_registered = true;
+	i915->display.audio.component_registered = true;
 }
 
 /**
  * i915_audio_component_cleanup - deregister the audio component
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * Deregisters the audio component, breaking any existing binding to the
  * corresponding snd_hda_intel driver's master component.
  */
-static void i915_audio_component_cleanup(struct drm_i915_private *dev_priv)
+static void i915_audio_component_cleanup(struct drm_i915_private *i915)
 {
-	if (!dev_priv->display.audio.component_registered)
+	if (!i915->display.audio.component_registered)
 		return;
 
-	component_del(dev_priv->drm.dev, &i915_audio_component_bind_ops);
-	dev_priv->display.audio.component_registered = false;
+	component_del(i915->drm.dev, &i915_audio_component_bind_ops);
+	i915->display.audio.component_registered = false;
 }
 
 /**
  * intel_audio_init() - Initialize the audio driver either using
  * component framework or using lpe audio bridge
- * @dev_priv: the i915 drm device private data
+ * @i915: the i915 drm device private data
  *
  */
-void intel_audio_init(struct drm_i915_private *dev_priv)
+void intel_audio_init(struct drm_i915_private *i915)
 {
-	if (intel_lpe_audio_init(dev_priv) < 0)
-		i915_audio_component_init(dev_priv);
+	if (intel_lpe_audio_init(i915) < 0)
+		i915_audio_component_init(i915);
 }
 
 /**
  * intel_audio_deinit() - deinitialize the audio driver
- * @dev_priv: the i915 drm device private data
+ * @i915: the i915 drm device private data
  *
  */
-void intel_audio_deinit(struct drm_i915_private *dev_priv)
+void intel_audio_deinit(struct drm_i915_private *i915)
 {
-	if (dev_priv->display.audio.lpe.platdev != NULL)
-		intel_lpe_audio_teardown(dev_priv);
+	if (i915->display.audio.lpe.platdev != NULL)
+		intel_lpe_audio_teardown(i915);
 	else
-		i915_audio_component_cleanup(dev_priv);
+		i915_audio_component_cleanup(i915);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_audio_regs.h b/drivers/gpu/drm/i915/display/intel_audio_regs.h
index d1e5844e3484..4f432c2eb543 100644
--- a/drivers/gpu/drm/i915/display/intel_audio_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_audio_regs.h
@@ -8,16 +8,11 @@
 
 #include "i915_reg_defs.h"
 
-#define G4X_AUD_VID_DID			_MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x62020)
-#define   INTEL_AUDIO_DEVCL		0x808629FB
-#define   INTEL_AUDIO_DEVBLC		0x80862801
-#define   INTEL_AUDIO_DEVCTG		0x80862802
-
 #define G4X_AUD_CNTL_ST			_MMIO(0x620B4)
-#define   G4X_ELDV_DEVCL_DEVBLC		(1 << 13)
-#define   G4X_ELDV_DEVCTG		(1 << 14)
-#define   G4X_ELD_ADDR_MASK		(0xf << 5)
-#define   G4X_ELD_ACK			(1 << 4)
+#define   G4X_ELD_VALID			REG_BIT(14)
+#define   G4X_ELD_BUFFER_SIZE_MASK	REG_GENMASK(13, 9)
+#define   G4X_ELD_ADDRESS_MASK		REG_GENMASK(8, 5)
+#define   G4X_ELD_ACK			REG_BIT(4)
 #define G4X_HDMIW_HDMIEDID		_MMIO(0x6210C)
 
 #define _IBX_HDMIW_HDMIEDID_A		0xE2050
@@ -28,12 +23,12 @@
 #define _IBX_AUD_CNTL_ST_B		0xE21B4
 #define IBX_AUD_CNTL_ST(pipe)		_MMIO_PIPE(pipe, _IBX_AUD_CNTL_ST_A, \
 						  _IBX_AUD_CNTL_ST_B)
-#define   IBX_ELD_BUFFER_SIZE_MASK	(0x1f << 10)
-#define   IBX_ELD_ADDRESS_MASK		(0x1f << 5)
-#define   IBX_ELD_ACK			(1 << 4)
+#define   IBX_ELD_BUFFER_SIZE_MASK	REG_GENMASK(14, 10)
+#define   IBX_ELD_ADDRESS_MASK		REG_GENMASK(9, 5)
+#define   IBX_ELD_ACK			REG_BIT(4)
 #define IBX_AUD_CNTL_ST2		_MMIO(0xE20C0)
-#define   IBX_CP_READY(port)		((1 << 1) << (((port) - 1) * 4))
-#define   IBX_ELD_VALID(port)		((1 << 0) << (((port) - 1) * 4))
+#define   IBX_CP_READY(port)		REG_BIT(((port) - 1) * 4 + 1)
+#define   IBX_ELD_VALID(port)		REG_BIT(((port) - 1) * 4 + 0)
 
 #define _CPT_HDMIW_HDMIEDID_A		0xE5050
 #define _CPT_HDMIW_HDMIEDID_B		0xE5150
@@ -60,34 +55,30 @@
 #define _VLV_AUD_CONFIG_A		(VLV_DISPLAY_BASE + 0x62000)
 #define _VLV_AUD_CONFIG_B		(VLV_DISPLAY_BASE + 0x62100)
 #define VLV_AUD_CFG(pipe)		_MMIO_PIPE(pipe, _VLV_AUD_CONFIG_A, _VLV_AUD_CONFIG_B)
-
-#define   AUD_CONFIG_N_VALUE_INDEX		(1 << 29)
-#define   AUD_CONFIG_N_PROG_ENABLE		(1 << 28)
-#define   AUD_CONFIG_UPPER_N_SHIFT		20
-#define   AUD_CONFIG_UPPER_N_MASK		(0xff << 20)
-#define   AUD_CONFIG_LOWER_N_SHIFT		4
-#define   AUD_CONFIG_LOWER_N_MASK		(0xfff << 4)
-#define   AUD_CONFIG_N_MASK			(AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK)
-#define   AUD_CONFIG_N(n) \
-	(((((n) >> 12) & 0xff) << AUD_CONFIG_UPPER_N_SHIFT) |	\
-	 (((n) & 0xfff) << AUD_CONFIG_LOWER_N_SHIFT))
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_SHIFT	16
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK	(0xf << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_25175	(0 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_25200	(1 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_27000	(2 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_27027	(3 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_54000	(4 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_54054	(5 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_74176	(6 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_74250	(7 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_148352	(8 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_148500	(9 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_296703	(10 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_297000	(11 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_593407	(12 << 16)
-#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_594000	(13 << 16)
-#define   AUD_CONFIG_DISABLE_NCTS		(1 << 3)
+#define   AUD_CONFIG_N_VALUE_INDEX		REG_BIT(29)
+#define   AUD_CONFIG_N_PROG_ENABLE		REG_BIT(28)
+#define   AUD_CONFIG_UPPER_N_MASK		REG_GENMASK(27, 20)
+#define   AUD_CONFIG_LOWER_N_MASK		REG_GENMASK(15, 4)
+#define   AUD_CONFIG_N_MASK			(AUD_CONFIG_UPPER_N_MASK | \
+						 AUD_CONFIG_LOWER_N_MASK)
+#define   AUD_CONFIG_N(n)			(REG_FIELD_PREP(AUD_CONFIG_UPPER_N_MASK, (n) >> 12) | \
+						 REG_FIELD_PREP(AUD_CONFIG_LOWER_N_MASK, (n) & 0xfff))
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK	REG_GENMASK(19, 16)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_25175	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 0)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_25200	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 1)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_27000	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 2)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_27027	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 3)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_54000	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 4)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_54054	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 5)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_74176	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 6)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_74250	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 7)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_148352	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 8)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_148500	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 9)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_296703	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 10)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_297000	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 11)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_593407	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 12)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_594000	REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 13)
+#define   AUD_CONFIG_DISABLE_NCTS		REG_BIT(3)
 
 #define _HSW_AUD_CONFIG_A		0x65000
 #define _HSW_AUD_CONFIG_B		0x65100
@@ -100,9 +91,9 @@
 #define _HSW_AUD_M_CTS_ENABLE_A		0x65028
 #define _HSW_AUD_M_CTS_ENABLE_B		0x65128
 #define HSW_AUD_M_CTS_ENABLE(trans)	_MMIO_TRANS(trans, _HSW_AUD_M_CTS_ENABLE_A, _HSW_AUD_M_CTS_ENABLE_B)
-#define   AUD_M_CTS_M_VALUE_INDEX	(1 << 21)
-#define   AUD_M_CTS_M_PROG_ENABLE	(1 << 20)
-#define   AUD_CONFIG_M_MASK		0xfffff
+#define   AUD_M_CTS_M_VALUE_INDEX	REG_BIT(21)
+#define   AUD_M_CTS_M_PROG_ENABLE	REG_BIT(20)
+#define   AUD_CONFIG_M_MASK		REG_GENMASK(19, 0)
 
 #define _HSW_AUD_DIP_ELD_CTRL_ST_A	0x650b4
 #define _HSW_AUD_DIP_ELD_CTRL_ST_B	0x651b4
@@ -130,11 +121,11 @@
 #define AUD_DP_2DOT0_CTRL(trans)	_MMIO_TRANS(trans, _AUD_TCA_DP_2DOT0_CTRL, _AUD_TCB_DP_2DOT0_CTRL)
 #define  AUD_ENABLE_SDP_SPLIT		REG_BIT(31)
 
-#define HSW_AUD_CHICKENBIT			_MMIO(0x65f10)
-#define   SKL_AUD_CODEC_WAKE_SIGNAL		(1 << 15)
+#define HSW_AUD_CHICKENBIT		_MMIO(0x65f10)
+#define   SKL_AUD_CODEC_WAKE_SIGNAL	REG_BIT(15)
 
 #define AUD_FREQ_CNTRL			_MMIO(0x65900)
-#define AUD_PIN_BUF_CTL		_MMIO(0x48414)
+#define AUD_PIN_BUF_CTL			_MMIO(0x48414)
 #define   AUD_PIN_BUF_ENABLE		REG_BIT(31)
 
 #define AUD_TS_CDCLK_M			_MMIO(0x65ea0)
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 28bdb936cd1f..c2987f2c2b2e 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -2188,7 +2188,7 @@ static u8 map_ddc_pin(struct drm_i915_private *i915, u8 vbt_pin)
 	const u8 *ddc_pin_map;
 	int n_entries;
 
-	if (IS_ALDERLAKE_P(i915)) {
+	if (HAS_PCH_MTP(i915) || IS_ALDERLAKE_P(i915)) {
 		ddc_pin_map = adlp_ddc_pin_map;
 		n_entries = ARRAY_SIZE(adlp_ddc_pin_map);
 	} else if (IS_ALDERLAKE_S(i915)) {
@@ -2676,6 +2676,14 @@ static void print_ddi_port(const struct intel_bios_encoder_data *devdata,
 		drm_dbg_kms(&i915->drm,
 			    "Port %c VBT DP max link rate: %d\n",
 			    port_name(port), dp_max_link_rate);
+
+	/*
+	 * FIXME need to implement support for VBT
+	 * vswing/preemph tables should this ever trigger.
+	 */
+	drm_WARN(&i915->drm, child->use_vbt_vswing,
+		 "Port %c asks to use VBT vswing/preemph tables\n",
+		 port_name(port));
 }
 
 static void parse_ddi_port(struct intel_bios_encoder_data *devdata)
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ed05070b7307..eada931cb1c8 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1220,11 +1220,6 @@ static void skl_cdclk_uninit_hw(struct drm_i915_private *dev_priv)
 	skl_set_cdclk(dev_priv, &cdclk_config, INVALID_PIPE);
 }
 
-static bool has_cdclk_squasher(struct drm_i915_private *i915)
-{
-	return IS_DG2(i915);
-}
-
 struct intel_cdclk_vals {
 	u32 cdclk;
 	u16 refclk;
@@ -1520,7 +1515,7 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	if (has_cdclk_squasher(dev_priv))
+	if (HAS_CDCLK_SQUASH(dev_priv))
 		squash_ctl = intel_de_read(dev_priv, CDCLK_SQUASH_CTL);
 
 	if (squash_ctl & CDCLK_SQUASH_ENABLE) {
@@ -1689,6 +1684,38 @@ static u32 cdclk_squash_waveform(struct drm_i915_private *dev_priv,
 	return 0xffff;
 }
 
+static void icl_cdclk_pll_update(struct drm_i915_private *i915, int vco)
+{
+	if (i915->display.cdclk.hw.vco != 0 &&
+	    i915->display.cdclk.hw.vco != vco)
+		icl_cdclk_pll_disable(i915);
+
+	if (i915->display.cdclk.hw.vco != vco)
+		icl_cdclk_pll_enable(i915, vco);
+}
+
+static void bxt_cdclk_pll_update(struct drm_i915_private *i915, int vco)
+{
+	if (i915->display.cdclk.hw.vco != 0 &&
+	    i915->display.cdclk.hw.vco != vco)
+		bxt_de_pll_disable(i915);
+
+	if (i915->display.cdclk.hw.vco != vco)
+		bxt_de_pll_enable(i915, vco);
+}
+
+static void dg2_cdclk_squash_program(struct drm_i915_private *i915,
+				     u16 waveform)
+{
+	u32 squash_ctl = 0;
+
+	if (waveform)
+		squash_ctl = CDCLK_SQUASH_ENABLE |
+			     CDCLK_SQUASH_WINDOW_SIZE(0xf) | waveform;
+
+	intel_de_write(i915, CDCLK_SQUASH_CTL, squash_ctl);
+}
+
 static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 			  const struct intel_cdclk_config *cdclk_config,
 			  enum pipe pipe)
@@ -1724,21 +1751,10 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	if (HAS_CDCLK_CRAWL(dev_priv) && dev_priv->display.cdclk.hw.vco > 0 && vco > 0) {
 		if (dev_priv->display.cdclk.hw.vco != vco)
 			adlp_cdclk_pll_crawl(dev_priv, vco);
-	} else if (DISPLAY_VER(dev_priv) >= 11) {
-		if (dev_priv->display.cdclk.hw.vco != 0 &&
-		    dev_priv->display.cdclk.hw.vco != vco)
-			icl_cdclk_pll_disable(dev_priv);
-
-		if (dev_priv->display.cdclk.hw.vco != vco)
-			icl_cdclk_pll_enable(dev_priv, vco);
-	} else {
-		if (dev_priv->display.cdclk.hw.vco != 0 &&
-		    dev_priv->display.cdclk.hw.vco != vco)
-			bxt_de_pll_disable(dev_priv);
-
-		if (dev_priv->display.cdclk.hw.vco != vco)
-			bxt_de_pll_enable(dev_priv, vco);
-	}
+	} else if (DISPLAY_VER(dev_priv) >= 11)
+		icl_cdclk_pll_update(dev_priv, vco);
+	else
+		bxt_cdclk_pll_update(dev_priv, vco);
 
 	waveform = cdclk_squash_waveform(dev_priv, cdclk);
 
@@ -1747,15 +1763,8 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	else
 		clock = cdclk;
 
-	if (has_cdclk_squasher(dev_priv)) {
-		u32 squash_ctl = 0;
-
-		if (waveform)
-			squash_ctl = CDCLK_SQUASH_ENABLE |
-				CDCLK_SQUASH_WINDOW_SIZE(0xf) | waveform;
-
-		intel_de_write(dev_priv, CDCLK_SQUASH_CTL, squash_ctl);
-	}
+	if (HAS_CDCLK_SQUASH(dev_priv))
+		dg2_cdclk_squash_program(dev_priv, waveform);
 
 	val = bxt_cdclk_cd2x_div_sel(dev_priv, clock, vco) |
 		bxt_cdclk_cd2x_pipe(dev_priv, pipe) |
@@ -1845,7 +1854,7 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	expected = skl_cdclk_decimal(cdclk);
 
 	/* Figure out what CD2X divider we should be using for this cdclk */
-	if (has_cdclk_squasher(dev_priv))
+	if (HAS_CDCLK_SQUASH(dev_priv))
 		clock = dev_priv->display.cdclk.hw.vco / 2;
 	else
 		clock = dev_priv->display.cdclk.hw.cdclk;
@@ -1976,7 +1985,7 @@ static bool intel_cdclk_can_squash(struct drm_i915_private *dev_priv,
 	 * the moment all platforms with squasher use a fixed cd2x
 	 * divider.
 	 */
-	if (!has_cdclk_squasher(dev_priv))
+	if (!HAS_CDCLK_SQUASH(dev_priv))
 		return false;
 
 	return a->cdclk != b->cdclk &&
@@ -2028,7 +2037,7 @@ static bool intel_cdclk_can_cd2x_update(struct drm_i915_private *dev_priv,
 	 * the moment all platforms with squasher use a fixed cd2x
 	 * divider.
 	 */
-	if (has_cdclk_squasher(dev_priv))
+	if (HAS_CDCLK_SQUASH(dev_priv))
 		return false;
 
 	return a->cdclk != b->cdclk &&
@@ -2464,10 +2473,6 @@ static int bdw_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state)
 	if (min_cdclk < 0)
 		return min_cdclk;
 
-	/*
-	 * FIXME should also account for plane ratio
-	 * once 64bpp pixel formats are supported.
-	 */
 	cdclk = bdw_calc_cdclk(min_cdclk);
 
 	cdclk_state->logical.cdclk = cdclk;
@@ -2534,10 +2539,6 @@ static int skl_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state)
 
 	vco = skl_dpll0_vco(cdclk_state);
 
-	/*
-	 * FIXME should also account for plane ratio
-	 * once 64bpp pixel formats are supported.
-	 */
 	cdclk = skl_calc_cdclk(min_cdclk, vco);
 
 	cdclk_state->logical.vco = vco;
@@ -2762,12 +2763,12 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 				   &old_cdclk_state->actual,
 				   &new_cdclk_state->actual)) {
 		drm_dbg_kms(&dev_priv->drm,
-			    "Can change cdclk via squasher\n");
+			    "Can change cdclk via squashing\n");
 	} else if (intel_cdclk_can_crawl(dev_priv,
 					 &old_cdclk_state->actual,
 					 &new_cdclk_state->actual)) {
 		drm_dbg_kms(&dev_priv->drm,
-			    "Can change cdclk via crawl\n");
+			    "Can change cdclk via crawling\n");
 	} else if (pipe != INVALID_PIPE) {
 		new_cdclk_state->pipe = pipe;
 
@@ -2777,7 +2778,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 	} else if (intel_cdclk_needs_modeset(&old_cdclk_state->actual,
 					     &new_cdclk_state->actual)) {
 		/* All pipes must be switched off while we change the cdclk. */
-		ret = intel_modeset_all_pipes(state);
+		ret = intel_modeset_all_pipes(state, "CDCLK change");
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 6bda4274eae9..4bb113c39f4b 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -25,9 +25,7 @@
 #include "intel_color.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
-#include "intel_dpll.h"
 #include "intel_dsb.h"
-#include "vlv_dsi_pll.h"
 
 struct intel_color_funcs {
 	int (*color_check)(struct intel_crtc_state *crtc_state);
@@ -559,6 +557,32 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state)
 			  crtc_state->csc_mode);
 }
 
+static struct drm_property_blob *
+create_linear_lut(struct drm_i915_private *i915, int lut_size)
+{
+	struct drm_property_blob *blob;
+	struct drm_color_lut *lut;
+	int i;
+
+	blob = drm_property_create_blob(&i915->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return blob;
+
+	lut = blob->data;
+
+	for (i = 0; i < lut_size; i++) {
+		u16 val = 0xffff * i / (lut_size - 1);
+
+		lut[i].red = val;
+		lut[i].green = val;
+		lut[i].blue = val;
+	}
+
+	return blob;
+}
+
 static void i9xx_load_lut_8(struct intel_crtc *crtc,
 			    const struct drm_property_blob *blob)
 {
@@ -580,12 +604,9 @@ static void i9xx_load_lut_8(struct intel_crtc *crtc,
 static void i9xx_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
 
-	assert_pll_enabled(dev_priv, crtc->pipe);
-
-	i9xx_load_lut_8(crtc, gamma_lut);
+	i9xx_load_lut_8(crtc, post_csc_lut);
 }
 
 static void i965_load_lut_10p6(struct intel_crtc *crtc,
@@ -611,18 +632,12 @@ static void i965_load_lut_10p6(struct intel_crtc *crtc,
 static void i965_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
-
-	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI))
-		assert_dsi_pll_enabled(dev_priv);
-	else
-		assert_pll_enabled(dev_priv, crtc->pipe);
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		i9xx_load_lut_8(crtc, gamma_lut);
+		i9xx_load_lut_8(crtc, post_csc_lut);
 	else
-		i965_load_lut_10p6(crtc, gamma_lut);
+		i965_load_lut_10p6(crtc, post_csc_lut);
 }
 
 static void ilk_load_lut_8(struct intel_crtc *crtc,
@@ -659,14 +674,16 @@ static void ilk_load_lut_10(struct intel_crtc *crtc,
 static void ilk_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut;
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
-		ilk_load_lut_8(crtc, gamma_lut);
+		ilk_load_lut_8(crtc, blob);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		ilk_load_lut_10(crtc, gamma_lut);
+		ilk_load_lut_10(crtc, blob);
 		break;
 	default:
 		MISSING_CASE(crtc_state->gamma_mode);
@@ -773,19 +790,19 @@ static void ivb_load_lut_ext_max(const struct intel_crtc_state *crtc_state)
 static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
-	const struct drm_property_blob *blob = gamma_lut ?: degamma_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut;
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		ilk_load_lut_8(crtc, blob);
 		break;
 	case GAMMA_MODE_MODE_SPLIT:
-		ivb_load_lut_10(crtc, degamma_lut, PAL_PREC_SPLIT_MODE |
+		ivb_load_lut_10(crtc, pre_csc_lut, PAL_PREC_SPLIT_MODE |
 				PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc_state);
-		ivb_load_lut_10(crtc, gamma_lut, PAL_PREC_SPLIT_MODE |
+		ivb_load_lut_10(crtc, post_csc_lut, PAL_PREC_SPLIT_MODE |
 				PAL_PREC_INDEX_VALUE(512));
 		break;
 	case GAMMA_MODE_MODE_10BIT:
@@ -802,19 +819,19 @@ static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 static void bdw_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
-	const struct drm_property_blob *blob = gamma_lut ?: degamma_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut;
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		ilk_load_lut_8(crtc, blob);
 		break;
 	case GAMMA_MODE_MODE_SPLIT:
-		bdw_load_lut_10(crtc, degamma_lut, PAL_PREC_SPLIT_MODE |
+		bdw_load_lut_10(crtc, pre_csc_lut, PAL_PREC_SPLIT_MODE |
 				PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc_state);
-		bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_SPLIT_MODE |
+		bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_SPLIT_MODE |
 				PAL_PREC_INDEX_VALUE(512));
 		break;
 	case GAMMA_MODE_MODE_10BIT:
@@ -837,13 +854,14 @@ static int glk_degamma_lut_size(struct drm_i915_private *i915)
 		return 35;
 }
 
-static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
+static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state,
+				 const struct drm_property_blob *blob)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_color_lut *lut = blob->data;
+	int i, lut_size = drm_color_lut_size(blob);
 	enum pipe pipe = crtc->pipe;
-	int i, lut_size = INTEL_INFO(dev_priv)->display.color.degamma_lut_size;
-	const struct drm_color_lut *lut = crtc_state->hw.degamma_lut->data;
 
 	/*
 	 * When setting the auto-increment bit, the hardware seems to
@@ -879,59 +897,21 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 	intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0);
 }
 
-static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum pipe pipe = crtc->pipe;
-	int i, lut_size = INTEL_INFO(dev_priv)->display.color.degamma_lut_size;
-
-	/*
-	 * When setting the auto-increment bit, the hardware seems to
-	 * ignore the index bits, so we need to reset it to index 0
-	 * separately.
-	 */
-	intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0);
-	intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe),
-			  PRE_CSC_GAMC_AUTO_INCREMENT);
-
-	for (i = 0; i < lut_size; i++) {
-		u32 v = (i << 16) / (lut_size - 1);
-
-		intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), v);
-	}
-
-	/* Clamp values > 1.0. */
-	while (i++ < 35)
-		intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16);
-
-	intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0);
-}
-
 static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
-	/*
-	 * On GLK+ both pipe CSC and degamma LUT are controlled
-	 * by csc_enable. Hence for the cases where the CSC is
-	 * needed but degamma LUT is not we need to load a
-	 * linear degamma LUT. In fact we'll just always load
-	 * the degama LUT so that we don't have to reload
-	 * it every time the pipe CSC is being enabled.
-	 */
-	if (crtc_state->hw.degamma_lut)
-		glk_load_degamma_lut(crtc_state);
-	else
-		glk_load_degamma_lut_linear(crtc_state);
+	if (pre_csc_lut)
+		glk_load_degamma_lut(crtc_state, pre_csc_lut);
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
-		ilk_load_lut_8(crtc, gamma_lut);
+		ilk_load_lut_8(crtc, post_csc_lut);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0));
+		bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc_state);
 		break;
 	default:
@@ -971,7 +951,7 @@ static void
 icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *blob = crtc_state->post_csc_lut;
 	const struct drm_color_lut *lut = blob->data;
 	enum pipe pipe = crtc->pipe;
 	int i;
@@ -1000,7 +980,7 @@ static void
 icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *blob = crtc_state->post_csc_lut;
 	const struct drm_color_lut *lut = blob->data;
 	const struct drm_color_lut *entry;
 	enum pipe pipe = crtc->pipe;
@@ -1054,22 +1034,23 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 
 static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
-	if (crtc_state->hw.degamma_lut)
-		glk_load_degamma_lut(crtc_state);
+	if (pre_csc_lut)
+		glk_load_degamma_lut(crtc_state, pre_csc_lut);
 
 	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
 	case GAMMA_MODE_MODE_8BIT:
-		ilk_load_lut_8(crtc, gamma_lut);
+		ilk_load_lut_8(crtc, post_csc_lut);
 		break;
 	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
 		icl_program_gamma_superfine_segment(crtc_state);
 		icl_program_gamma_multi_segment(crtc_state);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0));
+		bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc_state);
 		break;
 	default:
@@ -1145,18 +1126,18 @@ static void chv_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
-	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut;
+	const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut;
 	const struct drm_property_blob *ctm = crtc_state->hw.ctm;
 
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_CSC)
 		chv_load_cgm_csc(crtc, ctm);
 
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_DEGAMMA)
-		chv_load_cgm_degamma(crtc, degamma_lut);
+		chv_load_cgm_degamma(crtc, pre_csc_lut);
 
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
-		chv_load_cgm_gamma(crtc, gamma_lut);
+		chv_load_cgm_gamma(crtc, post_csc_lut);
 	else
 		i965_load_luts(crtc_state);
 
@@ -1194,8 +1175,8 @@ static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
-	return !old_crtc_state->hw.gamma_lut &&
-		!old_crtc_state->hw.degamma_lut;
+	return !old_crtc_state->post_csc_lut &&
+		!old_crtc_state->pre_csc_lut;
 }
 
 static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
@@ -1214,25 +1195,7 @@ static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 	if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode)
 		return false;
 
-	return !old_crtc_state->hw.gamma_lut;
-}
-
-static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
-	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->uapi.state);
-	const struct intel_crtc_state *old_crtc_state =
-		intel_atomic_get_old_crtc_state(state, crtc);
-
-	/*
-	 * The hardware degamma is active whenever the pipe
-	 * CSC is active. Thus even if the old state has no
-	 * software degamma we need to avoid clobbering the
-	 * linear hardware degamma mid scanout.
-	 */
-	return !old_crtc_state->csc_enable &&
-		!old_crtc_state->hw.gamma_lut;
+	return !old_crtc_state->post_csc_lut;
 }
 
 int intel_color_check(struct intel_crtc_state *crtc_state)
@@ -1295,6 +1258,10 @@ intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state)
 			return PTR_ERR(plane_state);
 
 		new_crtc_state->update_planes |= BIT(plane->id);
+
+		/* plane control register changes blocked by CxSR */
+		if (HAS_GMCH(dev_priv))
+			new_crtc_state->disable_cxsr = true;
 	}
 
 	return 0;
@@ -1361,6 +1328,40 @@ static u32 i9xx_gamma_mode(struct intel_crtc_state *crtc_state)
 		return GAMMA_MODE_MODE_10BIT; /* i965+ only */
 }
 
+void intel_color_assert_luts(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
+
+	/* make sure {pre,post}_csc_lut were correctly assigned */
+	if (DISPLAY_VER(i915) >= 11 || HAS_GMCH(i915)) {
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut);
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->post_csc_lut != crtc_state->hw.gamma_lut);
+	} else if (DISPLAY_VER(i915) == 10) {
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut &&
+			    crtc_state->pre_csc_lut != i915->display.color.glk_linear_degamma_lut);
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->post_csc_lut != crtc_state->hw.gamma_lut);
+	} else {
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut &&
+			    crtc_state->pre_csc_lut != crtc_state->hw.gamma_lut);
+		drm_WARN_ON(&i915->drm,
+			    crtc_state->post_csc_lut != crtc_state->hw.degamma_lut &&
+			    crtc_state->post_csc_lut != crtc_state->hw.gamma_lut);
+	}
+}
+
+static void intel_assign_luts(struct intel_crtc_state *crtc_state)
+{
+	drm_property_replace_blob(&crtc_state->pre_csc_lut,
+				  crtc_state->hw.degamma_lut);
+	drm_property_replace_blob(&crtc_state->post_csc_lut,
+				  crtc_state->hw.gamma_lut);
+}
+
 static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 {
 	int ret;
@@ -1379,6 +1380,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	intel_assign_luts(crtc_state);
+
 	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
 
 	return 0;
@@ -1433,6 +1436,8 @@ static int chv_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	intel_assign_luts(crtc_state);
+
 	crtc_state->preload_luts = chv_can_preload_luts(crtc_state);
 
 	return 0;
@@ -1458,10 +1463,29 @@ static u32 ilk_csc_mode(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
 		return CSC_BLACK_SCREEN_OFFSET;
 
+	if (crtc_state->hw.degamma_lut)
+		return CSC_MODE_YUV_TO_RGB;
+
 	return CSC_MODE_YUV_TO_RGB |
 		CSC_POSITION_BEFORE_GAMMA;
 }
 
+static void ilk_assign_luts(struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->hw.degamma_lut ||
+	    crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) {
+		drm_property_replace_blob(&crtc_state->pre_csc_lut,
+					  crtc_state->hw.degamma_lut);
+		drm_property_replace_blob(&crtc_state->post_csc_lut,
+					  crtc_state->hw.gamma_lut);
+	} else {
+		drm_property_replace_blob(&crtc_state->pre_csc_lut,
+					  crtc_state->hw.gamma_lut);
+		drm_property_replace_blob(&crtc_state->post_csc_lut,
+					  NULL);
+	}
+}
+
 static int ilk_color_check(struct intel_crtc_state *crtc_state)
 {
 	int ret;
@@ -1489,6 +1513,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	ilk_assign_luts(crtc_state);
+
 	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
 
 	return 0;
@@ -1556,6 +1582,8 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	ilk_assign_luts(crtc_state);
+
 	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
 
 	return 0;
@@ -1570,6 +1598,23 @@ static u32 glk_gamma_mode(const struct intel_crtc_state *crtc_state)
 		return GAMMA_MODE_MODE_10BIT;
 }
 
+static void glk_assign_luts(struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
+
+	intel_assign_luts(crtc_state);
+
+	/*
+	 * On GLK+ both pipe CSC and degamma LUT are controlled
+	 * by csc_enable. Hence for the cases where the CSC is
+	 * needed but degamma LUT is not we need to load a
+	 * linear degamma LUT.
+	 */
+	if (crtc_state->csc_enable && !crtc_state->pre_csc_lut)
+		drm_property_replace_blob(&crtc_state->pre_csc_lut,
+					  i915->display.color.glk_linear_degamma_lut);
+}
+
 static int glk_color_check(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
@@ -1604,7 +1649,9 @@ static int glk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
-	crtc_state->preload_luts = glk_can_preload_luts(crtc_state);
+	glk_assign_luts(crtc_state);
+
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
 
 	return 0;
 }
@@ -1664,6 +1711,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 	crtc_state->csc_mode = icl_csc_mode(crtc_state);
 
+	intel_assign_luts(crtc_state);
+
 	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
 
 	return 0;
@@ -1869,7 +1918,7 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 	if (!crtc_state->gamma_enable)
 		return;
 
-	crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc);
+	crtc_state->post_csc_lut = i9xx_read_lut_8(crtc);
 }
 
 static struct drm_property_blob *i965_read_lut_10p6(struct intel_crtc *crtc)
@@ -1910,9 +1959,9 @@ static void i965_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc);
+		crtc_state->post_csc_lut = i9xx_read_lut_8(crtc);
 	else
-		crtc_state->hw.gamma_lut = i965_read_lut_10p6(crtc);
+		crtc_state->post_csc_lut = i965_read_lut_10p6(crtc);
 }
 
 static struct drm_property_blob *chv_read_cgm_gamma(struct intel_crtc *crtc)
@@ -1946,7 +1995,7 @@ static void chv_read_luts(struct intel_crtc_state *crtc_state)
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
-		crtc_state->hw.gamma_lut = chv_read_cgm_gamma(crtc);
+		crtc_state->post_csc_lut = chv_read_cgm_gamma(crtc);
 	else
 		i965_read_luts(crtc_state);
 }
@@ -2013,10 +2062,10 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state)
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
-		crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc);
+		crtc_state->post_csc_lut = ilk_read_lut_8(crtc);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		crtc_state->hw.gamma_lut = ilk_read_lut_10(crtc);
+		crtc_state->post_csc_lut = ilk_read_lut_10(crtc);
 		break;
 	default:
 		MISSING_CASE(crtc_state->gamma_mode);
@@ -2068,10 +2117,10 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
-		crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc);
+		crtc_state->post_csc_lut = ilk_read_lut_8(crtc);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		crtc_state->hw.gamma_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
+		crtc_state->post_csc_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
 		break;
 	default:
 		MISSING_CASE(crtc_state->gamma_mode);
@@ -2126,13 +2175,13 @@ static void icl_read_luts(struct intel_crtc_state *crtc_state)
 
 	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
 	case GAMMA_MODE_MODE_8BIT:
-		crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc);
+		crtc_state->post_csc_lut = ilk_read_lut_8(crtc);
 		break;
 	case GAMMA_MODE_MODE_10BIT:
-		crtc_state->hw.gamma_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
+		crtc_state->post_csc_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
 		break;
 	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
-		crtc_state->hw.gamma_lut = icl_read_lut_multi_segment(crtc);
+		crtc_state->post_csc_lut = icl_read_lut_multi_segment(crtc);
 		break;
 	default:
 		MISSING_CASE(crtc_state->gamma_mode);
@@ -2217,41 +2266,58 @@ static const struct intel_color_funcs ilk_color_funcs = {
 	.read_luts = ilk_read_luts,
 };
 
-void intel_color_init(struct intel_crtc *crtc)
+void intel_color_crtc_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	bool has_ctm = INTEL_INFO(dev_priv)->display.color.degamma_lut_size != 0;
 
 	drm_mode_crtc_set_gamma_size(&crtc->base, 256);
 
-	if (HAS_GMCH(dev_priv)) {
-		if (IS_CHERRYVIEW(dev_priv)) {
-			dev_priv->display.funcs.color = &chv_color_funcs;
-		} else if (DISPLAY_VER(dev_priv) >= 4) {
-			dev_priv->display.funcs.color = &i965_color_funcs;
-		} else {
-			dev_priv->display.funcs.color = &i9xx_color_funcs;
-		}
-	} else {
-		if (DISPLAY_VER(dev_priv) >= 11)
-			dev_priv->display.funcs.color = &icl_color_funcs;
-		else if (DISPLAY_VER(dev_priv) == 10)
-			dev_priv->display.funcs.color = &glk_color_funcs;
-		else if (DISPLAY_VER(dev_priv) == 9)
-			dev_priv->display.funcs.color = &skl_color_funcs;
-		else if (DISPLAY_VER(dev_priv) == 8)
-			dev_priv->display.funcs.color = &bdw_color_funcs;
-		else if (DISPLAY_VER(dev_priv) == 7) {
-			if (IS_HASWELL(dev_priv))
-				dev_priv->display.funcs.color = &hsw_color_funcs;
-			else
-				dev_priv->display.funcs.color = &ivb_color_funcs;
-		} else
-			dev_priv->display.funcs.color = &ilk_color_funcs;
-	}
-
 	drm_crtc_enable_color_mgmt(&crtc->base,
 				   INTEL_INFO(dev_priv)->display.color.degamma_lut_size,
 				   has_ctm,
 				   INTEL_INFO(dev_priv)->display.color.gamma_lut_size);
 }
+
+int intel_color_init(struct drm_i915_private *i915)
+{
+	struct drm_property_blob *blob;
+
+	if (DISPLAY_VER(i915) != 10)
+		return 0;
+
+	blob = create_linear_lut(i915, INTEL_INFO(i915)->display.color.degamma_lut_size);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	i915->display.color.glk_linear_degamma_lut = blob;
+
+	return 0;
+}
+
+void intel_color_init_hooks(struct drm_i915_private *i915)
+{
+	if (HAS_GMCH(i915)) {
+		if (IS_CHERRYVIEW(i915))
+			i915->display.funcs.color = &chv_color_funcs;
+		else if (DISPLAY_VER(i915) >= 4)
+			i915->display.funcs.color = &i965_color_funcs;
+		else
+			i915->display.funcs.color = &i9xx_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;
+		else if (DISPLAY_VER(i915) == 9)
+			i915->display.funcs.color = &skl_color_funcs;
+		else if (DISPLAY_VER(i915) == 8)
+			i915->display.funcs.color = &bdw_color_funcs;
+		else if (IS_HASWELL(i915))
+			i915->display.funcs.color = &hsw_color_funcs;
+		else if (DISPLAY_VER(i915) == 7)
+			i915->display.funcs.color = &ivb_color_funcs;
+		else
+			i915->display.funcs.color = &ilk_color_funcs;
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h
index fd873425e082..2a5ada67774d 100644
--- a/drivers/gpu/drm/i915/display/intel_color.h
+++ b/drivers/gpu/drm/i915/display/intel_color.h
@@ -10,9 +10,12 @@
 
 struct intel_crtc_state;
 struct intel_crtc;
+struct drm_i915_private;
 struct drm_property_blob;
 
-void intel_color_init(struct intel_crtc *crtc);
+void intel_color_init_hooks(struct drm_i915_private *i915);
+int intel_color_init(struct drm_i915_private *i915);
+void intel_color_crtc_init(struct intel_crtc *crtc);
 int intel_color_check(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);
@@ -22,5 +25,6 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat
 bool intel_color_lut_equal(struct drm_property_blob *blob1,
 			   struct drm_property_blob *blob2,
 			   u32 gamma_mode, u32 bit_precision);
+void intel_color_assert_luts(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_COLOR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c
index 64890f39c3cc..71d7aece1dc6 100644
--- a/drivers/gpu/drm/i915/display/intel_combo_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c
@@ -53,7 +53,6 @@ static const struct icl_procmon {
 static const struct icl_procmon *
 icl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
 {
-	const struct icl_procmon *procmon;
 	u32 val;
 
 	val = intel_de_read(dev_priv, ICL_PORT_COMP_DW3(phy));
@@ -62,23 +61,16 @@ icl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy)
 		MISSING_CASE(val);
 		fallthrough;
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
-		procmon = &icl_procmon_values[PROCMON_0_85V_DOT_0];
-		break;
+		return &icl_procmon_values[PROCMON_0_85V_DOT_0];
 	case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_0:
-		procmon = &icl_procmon_values[PROCMON_0_95V_DOT_0];
-		break;
+		return &icl_procmon_values[PROCMON_0_95V_DOT_0];
 	case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_1:
-		procmon = &icl_procmon_values[PROCMON_0_95V_DOT_1];
-		break;
+		return &icl_procmon_values[PROCMON_0_95V_DOT_1];
 	case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_0:
-		procmon = &icl_procmon_values[PROCMON_1_05V_DOT_0];
-		break;
+		return &icl_procmon_values[PROCMON_1_05V_DOT_0];
 	case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_1:
-		procmon = &icl_procmon_values[PROCMON_1_05V_DOT_1];
-		break;
+		return &icl_procmon_values[PROCMON_1_05V_DOT_1];
 	}
-
-	return procmon;
 }
 
 static void icl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c
index 6d5cbeb8df4d..6205ddd3ded0 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.c
+++ b/drivers/gpu/drm/i915/display/intel_connector.c
@@ -293,3 +293,21 @@ intel_attach_dp_colorspace_property(struct drm_connector *connector)
 	if (!drm_mode_create_dp_colorspace_property(connector))
 		drm_connector_attach_colorspace_property(connector);
 }
+
+void
+intel_attach_scaling_mode_property(struct drm_connector *connector)
+{
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+	u32 scaling_modes;
+
+	scaling_modes = BIT(DRM_MODE_SCALE_ASPECT) |
+		BIT(DRM_MODE_SCALE_FULLSCREEN);
+
+	/* On GMCH platforms borders are only possible on the LVDS port */
+	if (!HAS_GMCH(i915) || connector->connector_type == DRM_MODE_CONNECTOR_LVDS)
+		scaling_modes |= BIT(DRM_MODE_SCALE_CENTER);
+
+	drm_connector_attach_scaling_mode_property(connector, scaling_modes);
+
+	connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_connector.h b/drivers/gpu/drm/i915/display/intel_connector.h
index 661a37a3c6d8..7d7b588d2286 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.h
+++ b/drivers/gpu/drm/i915/display/intel_connector.h
@@ -32,5 +32,6 @@ void intel_attach_broadcast_rgb_property(struct drm_connector *connector);
 void intel_attach_aspect_ratio_property(struct drm_connector *connector);
 void intel_attach_hdmi_colorspace_property(struct drm_connector *connector);
 void intel_attach_dp_colorspace_property(struct drm_connector *connector);
+void intel_attach_scaling_mode_property(struct drm_connector *connector);
 
 #endif /* __INTEL_CONNECTOR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 4a8ff2f97608..94d0a5e1dd03 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -1044,17 +1044,14 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 	intel_connector_attach_encoder(intel_connector, &crt->base);
 
 	crt->base.type = INTEL_OUTPUT_ANALOG;
-	crt->base.cloneable = (1 << INTEL_OUTPUT_DVO) | (1 << INTEL_OUTPUT_HDMI);
+	crt->base.cloneable = BIT(INTEL_OUTPUT_DVO) | BIT(INTEL_OUTPUT_HDMI);
 	if (IS_I830(dev_priv))
 		crt->base.pipe_mask = BIT(PIPE_A);
 	else
 		crt->base.pipe_mask = ~0;
 
-	if (DISPLAY_VER(dev_priv) == 2)
-		connector->interlace_allowed = 0;
-	else
-		connector->interlace_allowed = 1;
-	connector->doublescan_allowed = 0;
+	if (DISPLAY_VER(dev_priv) != 2)
+		connector->interlace_allowed = true;
 
 	crt->adpa_reg = adpa_reg;
 
diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c
index 6792a9056f46..037fc140b585 100644
--- a/drivers/gpu/drm/i915/display/intel_crtc.c
+++ b/drivers/gpu/drm/i915/display/intel_crtc.c
@@ -365,9 +365,8 @@ int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 						BIT(DRM_SCALING_FILTER_DEFAULT) |
 						BIT(DRM_SCALING_FILTER_NEAREST_NEIGHBOR));
 
-	intel_color_init(crtc);
-
-	intel_crtc_drrs_init(crtc);
+	intel_color_crtc_init(crtc);
+	intel_drrs_crtc_init(crtc);
 	intel_crtc_crc_init(crtc);
 
 	cpu_latency_qos_add_request(&crtc->vblank_pm_qos, PM_QOS_DEFAULT_VALUE);
@@ -387,8 +386,7 @@ static bool intel_crtc_needs_vblank_work(const struct intel_crtc_state *crtc_sta
 	return crtc_state->hw.active &&
 		!intel_crtc_needs_modeset(crtc_state) &&
 		!crtc_state->preload_luts &&
-		(crtc_state->uapi.color_mgmt_changed ||
-		 crtc_state->update_pipe);
+		intel_crtc_needs_color_update(crtc_state);
 }
 
 static void intel_crtc_vblank_work(struct kthread_work *base)
diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
index e9212f69c360..e3273fe8ddac 100644
--- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
+++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
@@ -298,11 +298,13 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config,
 			    pipe_config->csc_mode, pipe_config->gamma_mode,
 			    pipe_config->gamma_enable, pipe_config->csc_enable);
 
-	drm_dbg_kms(&i915->drm, "degamma lut: %d entries, gamma lut: %d entries\n",
-		    pipe_config->hw.degamma_lut ?
-		    drm_color_lut_size(pipe_config->hw.degamma_lut) : 0,
-		    pipe_config->hw.gamma_lut ?
-		    drm_color_lut_size(pipe_config->hw.gamma_lut) : 0);
+	drm_dbg_kms(&i915->drm, "pre csc lut: %s%d entries, post csc lut: %d entries\n",
+		    pipe_config->pre_csc_lut && pipe_config->pre_csc_lut ==
+		    i915->display.color.glk_linear_degamma_lut ? "(linear) " : "",
+		    pipe_config->pre_csc_lut ?
+		    drm_color_lut_size(pipe_config->pre_csc_lut) : 0,
+		    pipe_config->post_csc_lut ?
+		    drm_color_lut_size(pipe_config->post_csc_lut) : 0);
 
 dump_planes:
 	if (!state)
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 87899e89b3a7..96422c98656a 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -631,8 +631,10 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 *
 	 * FIXME bigjoiner fastpath would be good
 	 */
-	if (!crtc_state->hw.active || intel_crtc_needs_modeset(crtc_state) ||
-	    crtc_state->update_pipe || crtc_state->bigjoiner_pipes)
+	if (!crtc_state->hw.active ||
+	    intel_crtc_needs_modeset(crtc_state) ||
+	    intel_crtc_needs_fastset(crtc_state) ||
+	    crtc_state->bigjoiner_pipes)
 		goto slow;
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index da8472cdc135..e95bde5cf060 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -43,6 +43,8 @@
 #include "intel_de.h"
 #include "intel_display_power.h"
 #include "intel_display_types.h"
+#include "intel_dkl_phy.h"
+#include "intel_dkl_phy_regs.h"
 #include "intel_dp.h"
 #include "intel_dp_link_training.h"
 #include "intel_dp_mst.h"
@@ -55,13 +57,13 @@
 #include "intel_hdmi.h"
 #include "intel_hotplug.h"
 #include "intel_lspcon.h"
+#include "intel_mg_phy_regs.h"
 #include "intel_pps.h"
 #include "intel_psr.h"
 #include "intel_quirks.h"
 #include "intel_snps_phy.h"
 #include "intel_sprite.h"
 #include "intel_tc.h"
-#include "intel_tc_phy_regs.h"
 #include "intel_vdsc.h"
 #include "intel_vrr.h"
 #include "skl_scaler.h"
@@ -1262,33 +1264,30 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder,
 	for (ln = 0; ln < 2; ln++) {
 		int level;
 
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, ln));
-
-		intel_de_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), 0);
+		intel_dkl_phy_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port, ln), 0);
 
 		level = intel_ddi_level(encoder, crtc_state, 2*ln+0);
 
-		intel_de_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port),
-			     DKL_TX_PRESHOOT_COEFF_MASK |
-			     DKL_TX_DE_EMPAHSIS_COEFF_MASK |
-			     DKL_TX_VSWING_CONTROL_MASK,
-			     DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
-			     DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
-			     DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
+		intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port, ln),
+				  DKL_TX_PRESHOOT_COEFF_MASK |
+				  DKL_TX_DE_EMPAHSIS_COEFF_MASK |
+				  DKL_TX_VSWING_CONTROL_MASK,
+				  DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
+				  DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
+				  DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
 
 		level = intel_ddi_level(encoder, crtc_state, 2*ln+1);
 
-		intel_de_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port),
-			     DKL_TX_PRESHOOT_COEFF_MASK |
-			     DKL_TX_DE_EMPAHSIS_COEFF_MASK |
-			     DKL_TX_VSWING_CONTROL_MASK,
-			     DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
-			     DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
-			     DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
+		intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port, ln),
+				  DKL_TX_PRESHOOT_COEFF_MASK |
+				  DKL_TX_DE_EMPAHSIS_COEFF_MASK |
+				  DKL_TX_VSWING_CONTROL_MASK,
+				  DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
+				  DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
+				  DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
 
-		intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
-			     DKL_TX_DP20BITMODE, 0);
+		intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port, ln),
+				  DKL_TX_DP20BITMODE, 0);
 
 		if (IS_ALDERLAKE_P(dev_priv)) {
 			u32 val;
@@ -1306,10 +1305,10 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder,
 				val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(0);
 			}
 
-			intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
-				     DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK |
-				     DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK,
-				     val);
+			intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port, ln),
+					  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK |
+					  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK,
+					  val);
 		}
 	}
 }
@@ -2019,12 +2018,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 		return;
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, 0x0));
-		ln0 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port));
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, 0x1));
-		ln1 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port));
+		ln0 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port, 0));
+		ln1 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port, 1));
 	} else {
 		ln0 = intel_de_read(dev_priv, MG_DP_MODE(0, tc_port));
 		ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port));
@@ -2085,12 +2080,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 	}
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, 0x0));
-		intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln0);
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, 0x1));
-		intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln1);
+		intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port, 0), ln0);
+		intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port, 1), ln1);
 	} else {
 		intel_de_write(dev_priv, MG_DP_MODE(0, tc_port), ln0);
 		intel_de_write(dev_priv, MG_DP_MODE(1, tc_port), ln1);
@@ -3094,10 +3085,8 @@ static void adlp_tbt_to_dp_alt_switch_wa(struct intel_encoder *encoder)
 	enum tc_port tc_port = intel_port_to_tc(i915, encoder->port);
 	int ln;
 
-	for (ln = 0; ln < 2; ln++) {
-		intel_de_write(i915, HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
-		intel_de_rmw(i915, DKL_PCS_DW5(tc_port), DKL_PCS_DW5_CORE_SOFTRESET, 0);
-	}
+	for (ln = 0; ln < 2; ln++)
+		intel_dkl_phy_rmw(i915, DKL_PCS_DW5(tc_port, ln), DKL_PCS_DW5_CORE_SOFTRESET, 0);
 }
 
 static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp,
@@ -3536,7 +3525,7 @@ static void icl_ddi_tc_get_clock(struct intel_encoder *encoder,
 	if (drm_WARN_ON(&i915->drm, !pll))
 		return;
 
-	if (intel_get_shared_dpll_id(i915, pll) == DPLL_ID_ICL_TBTPLL)
+	if (pll->info->id == DPLL_ID_ICL_TBTPLL)
 		port_dpll_id = ICL_PORT_DPLL_DEFAULT;
 	else
 		port_dpll_id = ICL_PORT_DPLL_MG_PHY;
@@ -3549,7 +3538,7 @@ static void icl_ddi_tc_get_clock(struct intel_encoder *encoder,
 
 	icl_set_active_port_dpll(crtc_state, port_dpll_id);
 
-	if (intel_get_shared_dpll_id(i915, crtc_state->shared_dpll) == DPLL_ID_ICL_TBTPLL)
+	if (crtc_state->shared_dpll->info->id == DPLL_ID_ICL_TBTPLL)
 		crtc_state->port_clock = icl_calc_tbt_pll_link(i915, encoder->port);
 	else
 		crtc_state->port_clock = intel_dpll_get_freq(i915, crtc_state->shared_dpll,
@@ -3591,7 +3580,7 @@ static void intel_ddi_sync_state(struct intel_encoder *encoder,
 	enum phy phy = intel_port_to_phy(i915, encoder->port);
 
 	if (intel_phy_is_tc(i915, phy))
-		intel_tc_port_sanitize(enc_to_dig_port(encoder));
+		intel_tc_port_sanitize_mode(enc_to_dig_port(encoder));
 
 	if (crtc_state && intel_crtc_has_dp_encoder(crtc_state))
 		intel_dp_sync_state(encoder, crtc_state);
@@ -3801,11 +3790,17 @@ static void intel_ddi_encoder_destroy(struct drm_encoder *encoder)
 
 static void intel_ddi_encoder_reset(struct drm_encoder *encoder)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(encoder));
+	struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
+	enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
 
 	intel_dp->reset_link_params = true;
 
 	intel_pps_encoder_reset(intel_dp);
+
+	if (intel_phy_is_tc(i915, phy))
+		intel_tc_port_init_mode(dig_port);
 }
 
 static const struct drm_encoder_funcs intel_ddi_funcs = {
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 461c62c88413..b9393f9fc764 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -831,13 +831,27 @@ intel_plane_fence_y_offset(const struct intel_plane_state *plane_state)
 }
 
 static int
+intel_display_commit_duplicated_state(struct intel_atomic_state *state,
+				      struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	int ret;
+
+	ret = drm_atomic_helper_commit_duplicated_state(&state->base, ctx);
+
+	drm_WARN_ON(&i915->drm, ret == -EDEADLK);
+
+	return ret;
+}
+
+static int
 __intel_display_resume(struct drm_i915_private *i915,
 		       struct drm_atomic_state *state,
 		       struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	int i, ret;
+	int i;
 
 	intel_modeset_setup_hw_state(i915, ctx);
 	intel_vga_redisable(i915);
@@ -863,11 +877,7 @@ __intel_display_resume(struct drm_i915_private *i915,
 	if (!HAS_GMCH(i915))
 		to_intel_atomic_state(state)->skip_intermediate_wm = true;
 
-	ret = drm_atomic_helper_commit_duplicated_state(state, ctx);
-
-	drm_WARN_ON(&i915->drm, ret == -EDEADLK);
-
-	return ret;
+	return intel_display_commit_duplicated_state(to_intel_atomic_state(state), ctx);
 }
 
 static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv)
@@ -878,7 +888,6 @@ static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv)
 
 void intel_display_prepare_reset(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
 	struct drm_atomic_state *state;
 	int ret;
@@ -906,10 +915,10 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv)
 	 * Need mode_config.mutex so that we don't
 	 * trample ongoing ->detect() and whatnot.
 	 */
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	drm_modeset_acquire_init(ctx, 0);
 	while (1) {
-		ret = drm_modeset_lock_all_ctx(dev, ctx);
+		ret = drm_modeset_lock_all_ctx(&dev_priv->drm, ctx);
 		if (ret != -EDEADLK)
 			break;
 
@@ -919,7 +928,7 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv)
 	 * Disabling the crtcs gracefully seems nicer. Also the
 	 * g33 docs say we should at least disable all the planes.
 	 */
-	state = drm_atomic_helper_duplicate_state(dev, ctx);
+	state = drm_atomic_helper_duplicate_state(&dev_priv->drm, ctx);
 	if (IS_ERR(state)) {
 		ret = PTR_ERR(state);
 		drm_err(&dev_priv->drm, "Duplicating state failed with %i\n",
@@ -927,7 +936,7 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv)
 		return;
 	}
 
-	ret = drm_atomic_helper_disable_all(dev, ctx);
+	ret = drm_atomic_helper_disable_all(&dev_priv->drm, ctx);
 	if (ret) {
 		drm_err(&dev_priv->drm, "Suspending crtc's failed with %i\n",
 			ret);
@@ -959,7 +968,7 @@ void intel_display_finish_reset(struct drm_i915_private *i915)
 	/* reset doesn't touch the display */
 	if (!gpu_reset_clobbers_display(i915)) {
 		/* for testing only restore the display */
-		ret = __intel_display_resume(i915, state, ctx);
+		ret = intel_display_commit_duplicated_state(to_intel_atomic_state(state), ctx);
 		if (ret)
 			drm_err(&i915->drm,
 				"Restoring old state failed with %i\n", ret);
@@ -1252,8 +1261,6 @@ 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);
-
-	intel_drrs_activate(new_crtc_state);
 }
 
 static void intel_crtc_enable_flip_done(struct intel_atomic_state *state,
@@ -4572,8 +4579,8 @@ static bool encoders_cloneable(const struct intel_encoder *a,
 			       const struct intel_encoder *b)
 {
 	/* masks could be asymmetric, so check both ways */
-	return a == b || (a->cloneable & (1 << b->type) &&
-			  b->cloneable & (1 << a->type));
+	return a == b || (a->cloneable & BIT(b->type) &&
+			  b->cloneable & BIT(a->type));
 }
 
 static bool check_single_encoder_cloning(struct intel_atomic_state *state,
@@ -4824,14 +4831,14 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
-	bool mode_changed = intel_crtc_needs_modeset(crtc_state);
 	int ret;
 
 	if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv) &&
-	    mode_changed && !crtc_state->hw.active)
+	    intel_crtc_needs_modeset(crtc_state) &&
+	    !crtc_state->hw.active)
 		crtc_state->update_wm_post = true;
 
-	if (mode_changed) {
+	if (intel_crtc_needs_modeset(crtc_state)) {
 		ret = intel_dpll_crtc_get_shared_dpll(state, crtc);
 		if (ret)
 			return ret;
@@ -4844,8 +4851,7 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	if (c8_planes_changed(crtc_state))
 		crtc_state->uapi.color_mgmt_changed = true;
 
-	if (mode_changed || crtc_state->update_pipe ||
-	    crtc_state->uapi.color_mgmt_changed) {
+	if (intel_crtc_needs_color_update(crtc_state)) {
 		ret = intel_color_check(crtc_state);
 		if (ret)
 			return ret;
@@ -4871,7 +4877,8 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	}
 
 	if (DISPLAY_VER(dev_priv) >= 9) {
-		if (mode_changed || crtc_state->update_pipe) {
+		if (intel_crtc_needs_modeset(crtc_state) ||
+		    intel_crtc_needs_fastset(crtc_state)) {
 			ret = skl_update_scaler_crtc(crtc_state);
 			if (ret)
 				return ret;
@@ -5637,39 +5644,6 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_I(name.y2); \
 } while (0)
 
-/* This is required for BDW+ where there is only one set of registers for
- * switching between high and low RR.
- * This macro can be used whenever a comparison has to be made between one
- * hw state and multiple sw state variables.
- */
-#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) do { \
-	if (!intel_compare_link_m_n(&current_config->name, \
-				    &pipe_config->name) && \
-	    !intel_compare_link_m_n(&current_config->alt_name, \
-				    &pipe_config->name)) { \
-		pipe_config_mismatch(fastset, crtc, __stringify(name), \
-				     "(expected tu %i data %i/%i link %i/%i, " \
-				     "or tu %i data %i/%i link %i/%i, " \
-				     "found tu %i, data %i/%i link %i/%i)", \
-				     current_config->name.tu, \
-				     current_config->name.data_m, \
-				     current_config->name.data_n, \
-				     current_config->name.link_m, \
-				     current_config->name.link_n, \
-				     current_config->alt_name.tu, \
-				     current_config->alt_name.data_m, \
-				     current_config->alt_name.data_n, \
-				     current_config->alt_name.link_m, \
-				     current_config->alt_name.link_n, \
-				     pipe_config->name.tu, \
-				     pipe_config->name.data_m, \
-				     pipe_config->name.data_n, \
-				     pipe_config->name.link_m, \
-				     pipe_config->name.link_n); \
-		ret = false; \
-	} \
-} while (0)
-
 #define PIPE_CONF_CHECK_FLAGS(name, mask) do { \
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
 		pipe_config_mismatch(fastset, crtc, __stringify(name), \
@@ -5738,7 +5712,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	if (HAS_DOUBLE_BUFFERED_M_N(dev_priv)) {
 		if (!fastset || !pipe_config->seamless_m_n)
-			PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2);
+			PIPE_CONF_CHECK_M_N(dp_m_n);
 	} else {
 		PIPE_CONF_CHECK_M_N(dp_m_n);
 		PIPE_CONF_CHECK_M_N(dp_m2_n2);
@@ -5815,7 +5789,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 		bp_gamma = intel_color_get_gamma_bit_precision(pipe_config);
 		if (bp_gamma)
-			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma);
+			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, post_csc_lut, bp_gamma);
 
 		if (current_config->active_planes) {
 			PIPE_CONF_CHECK_BOOL(has_psr);
@@ -5937,7 +5911,8 @@ intel_verify_planes(struct intel_atomic_state *state)
 			     plane_state->uapi.visible);
 }
 
-int intel_modeset_all_pipes(struct intel_atomic_state *state)
+int intel_modeset_all_pipes(struct intel_atomic_state *state,
+			    const char *reason)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
@@ -5958,7 +5933,11 @@ int intel_modeset_all_pipes(struct intel_atomic_state *state)
 		    drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
 			continue;
 
+		drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s] Full modeset due to %s\n",
+			    crtc->base.base.id, crtc->base.name, reason);
+
 		crtc_state->uapi.mode_changed = true;
+		crtc_state->update_pipe = false;
 
 		ret = drm_atomic_add_affected_connectors(&state->base,
 							 &crtc->base);
@@ -6134,7 +6113,8 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta
 		return;
 
 	new_crtc_state->uapi.mode_changed = false;
-	new_crtc_state->update_pipe = true;
+	if (!intel_crtc_needs_modeset(new_crtc_state))
+		new_crtc_state->update_pipe = true;
 }
 
 static int intel_crtc_add_planes_to_state(struct intel_atomic_state *state,
@@ -6906,12 +6886,19 @@ static int intel_atomic_check(struct drm_device *dev,
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
+		intel_color_assert_luts(new_crtc_state);
+
 		ret = intel_async_flip_check_hw(state, crtc);
 		if (ret)
 			goto fail;
 
+		/* Either full modeset or fastset (or neither), never both */
+		drm_WARN_ON(&dev_priv->drm,
+			    intel_crtc_needs_modeset(new_crtc_state) &&
+			    intel_crtc_needs_fastset(new_crtc_state));
+
 		if (!intel_crtc_needs_modeset(new_crtc_state) &&
-		    !new_crtc_state->update_pipe)
+		    !intel_crtc_needs_fastset(new_crtc_state))
 			continue;
 
 		intel_crtc_state_dump(new_crtc_state, state,
@@ -6947,12 +6934,8 @@ static int intel_atomic_prepare_commit(struct intel_atomic_state *state)
 		return ret;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		bool mode_changed = intel_crtc_needs_modeset(crtc_state);
-
-		if (mode_changed || crtc_state->update_pipe ||
-		    crtc_state->uapi.color_mgmt_changed) {
+		if (intel_crtc_needs_color_update(crtc_state))
 			intel_dsb_prepare(crtc_state);
-		}
 	}
 
 	return 0;
@@ -7033,14 +7016,13 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state,
 	 * CRTC was enabled.
 	 */
 	if (!modeset) {
-		if (new_crtc_state->uapi.color_mgmt_changed ||
-		    new_crtc_state->update_pipe)
+		if (intel_crtc_needs_color_update(new_crtc_state))
 			intel_color_commit_arm(new_crtc_state);
 
 		if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
 			bdw_set_pipemisc(new_crtc_state);
 
-		if (new_crtc_state->update_pipe)
+		if (intel_crtc_needs_fastset(new_crtc_state))
 			intel_pipe_fastset(old_crtc_state, new_crtc_state);
 	}
 
@@ -7099,25 +7081,23 @@ static void intel_update_crtc(struct intel_atomic_state *state,
 
 	if (!modeset) {
 		if (new_crtc_state->preload_luts &&
-		    (new_crtc_state->uapi.color_mgmt_changed ||
-		     new_crtc_state->update_pipe))
+		    intel_crtc_needs_color_update(new_crtc_state))
 			intel_color_load_luts(new_crtc_state);
 
 		intel_pre_plane_update(state, crtc);
 
-		if (new_crtc_state->update_pipe)
+		if (intel_crtc_needs_fastset(new_crtc_state))
 			intel_encoders_update_pipe(state, crtc);
 
 		if (DISPLAY_VER(i915) >= 11 &&
-		    new_crtc_state->update_pipe)
+		    intel_crtc_needs_fastset(new_crtc_state))
 			icl_set_pipe_chicken(new_crtc_state);
 	}
 
 	intel_fbc_update(state, crtc);
 
 	if (!modeset &&
-	    (new_crtc_state->uapi.color_mgmt_changed ||
-	     new_crtc_state->update_pipe))
+	    intel_crtc_needs_color_update(new_crtc_state))
 		intel_color_commit_noarm(new_crtc_state);
 
 	intel_crtc_planes_update_noarm(state, crtc);
@@ -7139,7 +7119,7 @@ static void intel_update_crtc(struct intel_atomic_state *state,
 	 * valid pipe configuration from the BIOS we need to take care
 	 * of enabling them on the CRTC's first fastset.
 	 */
-	if (new_crtc_state->update_pipe && !modeset &&
+	if (intel_crtc_needs_fastset(new_crtc_state) && !modeset &&
 	    old_crtc_state->inherited)
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
@@ -7162,9 +7142,7 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 	intel_fbc_disable(crtc);
 	intel_disable_shared_dpll(old_crtc_state);
 
-	/* FIXME unify this for all platforms */
-	if (!new_crtc_state->hw.active &&
-	    !HAS_GMCH(dev_priv))
+	if (!new_crtc_state->hw.active)
 		intel_initial_watermarks(state, crtc);
 }
 
@@ -7499,9 +7477,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
 		if (intel_crtc_needs_modeset(new_crtc_state) ||
-		    new_crtc_state->update_pipe) {
+		    intel_crtc_needs_fastset(new_crtc_state))
 			intel_modeset_get_crtc_power_domains(new_crtc_state, &put_domains[crtc->pipe]);
-		}
 	}
 
 	intel_commit_modeset_disables(state);
@@ -7605,6 +7582,12 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_modeset_verify_crtc(crtc, state, old_crtc_state, new_crtc_state);
 
 		/*
+		 * Activate DRRS after state readout to avoid
+		 * dp_m_n vs. dp_m2_n2 confusion on BDW+.
+		 */
+		intel_drrs_activate(new_crtc_state);
+
+		/*
 		 * DSB cleanup is done in cleanup_work aligning with framebuffer
 		 * cleanup. So copy and reset the dsb structure to sync with
 		 * commit_done and later do dsb cleanup in cleanup_work.
@@ -8344,6 +8327,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
+	intel_color_init_hooks(dev_priv);
 	intel_init_cdclk_hooks(dev_priv);
 	intel_audio_hooks_init(dev_priv);
 
@@ -8674,6 +8658,10 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915)
 	if (ret)
 		goto cleanup_vga_client_pw_domain_dmc;
 
+	ret = intel_color_init(i915);
+	if (ret)
+		goto cleanup_vga_client_pw_domain_dmc;
+
 	ret = intel_dbuf_init(i915);
 	if (ret)
 		goto cleanup_vga_client_pw_domain_dmc;
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 884e8e67b17c..c803330a276d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -469,10 +469,6 @@ enum hpd_pin {
 	list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
 		for_each_if((intel_encoder)->base.crtc == (__crtc))
 
-#define for_each_connector_on_encoder(dev, __encoder, intel_connector) \
-	list_for_each_entry((intel_connector), &(dev)->mode_config.connector_list, base.head) \
-		for_each_if((intel_connector)->base.encoder == (__encoder))
-
 #define for_each_old_intel_plane_in_state(__state, plane, old_plane_state, __i) \
 	for ((__i) = 0; \
 	     (__i) < (__state)->base.dev->mode_config.num_total_plane && \
@@ -683,7 +679,8 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915);
 void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915);
 void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915);
 void intel_display_resume(struct drm_device *dev);
-int intel_modeset_all_pipes(struct intel_atomic_state *state);
+int intel_modeset_all_pipes(struct intel_atomic_state *state,
+			    const char *reason);
 void intel_modeset_get_crtc_power_domains(struct intel_crtc_state *crtc_state,
 					  struct intel_power_domain_mask *old_domains);
 void intel_modeset_put_crtc_power_domains(struct intel_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h
index 96cf994b0ad1..337d8e08ba43 100644
--- a/drivers/gpu/drm/i915/display/intel_display_core.h
+++ b/drivers/gpu/drm/i915/display/intel_display_core.h
@@ -28,6 +28,7 @@
 
 struct drm_i915_private;
 struct drm_property;
+struct drm_property_blob;
 struct i915_audio_component;
 struct i915_hdcp_comp_master;
 struct intel_atomic_state;
@@ -309,6 +310,10 @@ struct intel_display {
 	} cdclk;
 
 	struct {
+		struct drm_property_blob *glk_linear_degamma_lut;
+	} color;
+
+	struct {
 		/* The current hardware dbuf configuration */
 		u8 enabled_slices;
 
@@ -316,6 +321,14 @@ struct intel_display {
 	} dbuf;
 
 	struct {
+		/*
+		 * dkl.phy_lock protects against concurrent access of the
+		 * Dekel TypeC PHYs.
+		 */
+		spinlock_t phy_lock;
+	} dkl;
+
+	struct {
 		/* VLV/CHV/BXT/GLK DSI MMIO register base address */
 		u32 mmio_base;
 	} dsi;
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 7c7253a2541c..cfc056a05bbf 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -22,6 +22,7 @@
 #include "intel_fbdev.h"
 #include "intel_hdcp.h"
 #include "intel_hdmi.h"
+#include "intel_hotplug.h"
 #include "intel_panel.h"
 #include "intel_pm.h"
 #include "intel_psr.h"
@@ -127,7 +128,6 @@ static int i915_vbt(struct seq_file *m, void *unused)
 static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_framebuffer *fbdev_fb = NULL;
 	struct drm_framebuffer *drm_fb;
 
@@ -146,8 +146,8 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 	}
 #endif
 
-	mutex_lock(&dev->mode_config.fb_lock);
-	drm_for_each_fb(drm_fb, dev) {
+	mutex_lock(&dev_priv->drm.mode_config.fb_lock);
+	drm_for_each_fb(drm_fb, &dev_priv->drm) {
 		struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb);
 		if (fb == fbdev_fb)
 			continue;
@@ -162,7 +162,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		i915_debugfs_describe_obj(m, intel_fb_obj(&fb->base));
 		seq_putc(m, '\n');
 	}
-	mutex_unlock(&dev->mode_config.fb_lock);
+	mutex_unlock(&dev_priv->drm.mode_config.fb_lock);
 
 	return 0;
 }
@@ -897,7 +897,6 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc)
 static int i915_display_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
@@ -905,22 +904,22 @@ static int i915_display_info(struct seq_file *m, void *unused)
 
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
-	for_each_intel_crtc(dev, crtc)
+	for_each_intel_crtc(&dev_priv->drm, crtc)
 		intel_crtc_info(m, crtc);
 
 	seq_printf(m, "\n");
 	seq_printf(m, "Connector info\n");
 	seq_printf(m, "--------------\n");
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter)
 		intel_connector_info(m, connector);
 	drm_connector_list_iter_end(&conn_iter);
 
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
@@ -930,10 +929,9 @@ static int i915_display_info(struct seq_file *m, void *unused)
 static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	int i;
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 
 	seq_printf(m, "PLL refclks: non-SSC: %d kHz, SSC: %d kHz\n",
 		   dev_priv->display.dpll.ref_clks.nssc,
@@ -978,7 +976,7 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 		seq_printf(m, " mg_pll_tdc_coldst_bias: 0x%08x\n",
 			   pll->state.hw_state.mg_pll_tdc_coldst_bias);
 	}
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	return 0;
 }
@@ -986,14 +984,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 static int i915_ddb_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	struct skl_ddb_entry *entry;
 	struct intel_crtc *crtc;
 
 	if (DISPLAY_VER(dev_priv) < 9)
 		return -ENODEV;
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 
 	seq_printf(m, "%-15s%8s%8s%8s\n", "", "Start", "End", "Size");
 
@@ -1017,53 +1014,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 			   entry->end, skl_ddb_entry_size(entry));
 	}
 
-	drm_modeset_unlock_all(dev);
-
-	return 0;
-}
-
-static int i915_drrs_status(struct seq_file *m, void *unused)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_connector_list_iter conn_iter;
-	struct intel_connector *connector;
-	struct intel_crtc *crtc;
-
-	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
-	for_each_intel_connector_iter(connector, &conn_iter) {
-		seq_printf(m, "[CONNECTOR:%d:%s] DRRS type: %s\n",
-			   connector->base.base.id, connector->base.name,
-			   intel_drrs_type_str(intel_panel_drrs_type(connector)));
-	}
-	drm_connector_list_iter_end(&conn_iter);
-
-	seq_puts(m, "\n");
-
-	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		const struct intel_crtc_state *crtc_state =
-			to_intel_crtc_state(crtc->base.state);
-
-		seq_printf(m, "[CRTC:%d:%s]:\n",
-			   crtc->base.base.id, crtc->base.name);
-
-		mutex_lock(&crtc->drrs.mutex);
-
-		/* DRRS Supported */
-		seq_printf(m, "\tDRRS Enabled: %s\n",
-			   str_yes_no(crtc_state->has_drrs));
-
-		seq_printf(m, "\tDRRS Active: %s\n",
-			   str_yes_no(intel_drrs_is_active(crtc)));
-
-		seq_printf(m, "\tBusy_frontbuffer_bits: 0x%X\n",
-			   crtc->drrs.busy_frontbuffer_bits);
-
-		seq_printf(m, "\tDRRS refresh rate: %s\n",
-			   crtc->drrs.refresh_rate == DRRS_REFRESH_RATE_LOW ?
-			   "low" : "high");
-
-		mutex_unlock(&crtc->drrs.mutex);
-	}
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	return 0;
 }
@@ -1107,13 +1058,12 @@ static int i915_lpsp_status(struct seq_file *m, void *unused)
 static int i915_dp_mst_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *intel_encoder;
 	struct intel_digital_port *dig_port;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
 		if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
 			continue;
@@ -1200,12 +1150,11 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 static int i915_displayport_test_active_show(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = m->private;
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
 		struct intel_encoder *encoder;
 
@@ -1250,12 +1199,11 @@ static const struct file_operations i915_displayport_test_active_fops = {
 static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = m->private;
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
 		struct intel_encoder *encoder;
 
@@ -1304,12 +1252,11 @@ DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_data);
 static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = m->private;
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
 		struct intel_encoder *encoder;
 
@@ -1336,7 +1283,6 @@ DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_type);
 static void wm_latency_show(struct seq_file *m, const u16 wm[8])
 {
 	struct drm_i915_private *dev_priv = m->private;
-	struct drm_device *dev = &dev_priv->drm;
 	int level;
 	int num_levels;
 
@@ -1349,7 +1295,7 @@ static void wm_latency_show(struct seq_file *m, const u16 wm[8])
 	else
 		num_levels = ilk_wm_max_level(dev_priv) + 1;
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 
 	for (level = 0; level < num_levels; level++) {
 		unsigned int latency = wm[level];
@@ -1370,7 +1316,7 @@ static void wm_latency_show(struct seq_file *m, const u16 wm[8])
 			   level, wm[level], latency / 10, latency % 10);
 	}
 
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 }
 
 static int pri_wm_latency_show(struct seq_file *m, void *data)
@@ -1453,7 +1399,6 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf,
 {
 	struct seq_file *m = file->private_data;
 	struct drm_i915_private *dev_priv = m->private;
-	struct drm_device *dev = &dev_priv->drm;
 	u16 new[8] = { 0 };
 	int num_levels;
 	int level;
@@ -1483,12 +1428,12 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf,
 	if (ret != num_levels)
 		return -EINVAL;
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 
 	for (level = 0; level < num_levels; level++)
 		wm[level] = new[level];
 
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	return len;
 }
@@ -1566,209 +1511,6 @@ static const struct file_operations i915_cur_wm_latency_fops = {
 	.write = cur_wm_latency_write
 };
 
-static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = m->private;
-	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
-
-	/* Synchronize with everything first in case there's been an HPD
-	 * storm, but we haven't finished handling it in the kernel yet
-	 */
-	intel_synchronize_irq(dev_priv);
-	flush_work(&dev_priv->display.hotplug.dig_port_work);
-	flush_delayed_work(&dev_priv->display.hotplug.hotplug_work);
-
-	seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold);
-	seq_printf(m, "Detected: %s\n",
-		   str_yes_no(delayed_work_pending(&hotplug->reenable_work)));
-
-	return 0;
-}
-
-static ssize_t i915_hpd_storm_ctl_write(struct file *file,
-					const char __user *ubuf, size_t len,
-					loff_t *offp)
-{
-	struct seq_file *m = file->private_data;
-	struct drm_i915_private *dev_priv = m->private;
-	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
-	unsigned int new_threshold;
-	int i;
-	char *newline;
-	char tmp[16];
-
-	if (len >= sizeof(tmp))
-		return -EINVAL;
-
-	if (copy_from_user(tmp, ubuf, len))
-		return -EFAULT;
-
-	tmp[len] = '\0';
-
-	/* Strip newline, if any */
-	newline = strchr(tmp, '\n');
-	if (newline)
-		*newline = '\0';
-
-	if (strcmp(tmp, "reset") == 0)
-		new_threshold = HPD_STORM_DEFAULT_THRESHOLD;
-	else if (kstrtouint(tmp, 10, &new_threshold) != 0)
-		return -EINVAL;
-
-	if (new_threshold > 0)
-		drm_dbg_kms(&dev_priv->drm,
-			    "Setting HPD storm detection threshold to %d\n",
-			    new_threshold);
-	else
-		drm_dbg_kms(&dev_priv->drm, "Disabling HPD storm detection\n");
-
-	spin_lock_irq(&dev_priv->irq_lock);
-	hotplug->hpd_storm_threshold = new_threshold;
-	/* Reset the HPD storm stats so we don't accidentally trigger a storm */
-	for_each_hpd_pin(i)
-		hotplug->stats[i].count = 0;
-	spin_unlock_irq(&dev_priv->irq_lock);
-
-	/* Re-enable hpd immediately if we were in an irq storm */
-	flush_delayed_work(&dev_priv->display.hotplug.reenable_work);
-
-	return len;
-}
-
-static int i915_hpd_storm_ctl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, i915_hpd_storm_ctl_show, inode->i_private);
-}
-
-static const struct file_operations i915_hpd_storm_ctl_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_hpd_storm_ctl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.write = i915_hpd_storm_ctl_write
-};
-
-static int i915_hpd_short_storm_ctl_show(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = m->private;
-
-	seq_printf(m, "Enabled: %s\n",
-		   str_yes_no(dev_priv->display.hotplug.hpd_short_storm_enabled));
-
-	return 0;
-}
-
-static int
-i915_hpd_short_storm_ctl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, i915_hpd_short_storm_ctl_show,
-			   inode->i_private);
-}
-
-static ssize_t i915_hpd_short_storm_ctl_write(struct file *file,
-					      const char __user *ubuf,
-					      size_t len, loff_t *offp)
-{
-	struct seq_file *m = file->private_data;
-	struct drm_i915_private *dev_priv = m->private;
-	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
-	char *newline;
-	char tmp[16];
-	int i;
-	bool new_state;
-
-	if (len >= sizeof(tmp))
-		return -EINVAL;
-
-	if (copy_from_user(tmp, ubuf, len))
-		return -EFAULT;
-
-	tmp[len] = '\0';
-
-	/* Strip newline, if any */
-	newline = strchr(tmp, '\n');
-	if (newline)
-		*newline = '\0';
-
-	/* Reset to the "default" state for this system */
-	if (strcmp(tmp, "reset") == 0)
-		new_state = !HAS_DP_MST(dev_priv);
-	else if (kstrtobool(tmp, &new_state) != 0)
-		return -EINVAL;
-
-	drm_dbg_kms(&dev_priv->drm, "%sabling HPD short storm detection\n",
-		    new_state ? "En" : "Dis");
-
-	spin_lock_irq(&dev_priv->irq_lock);
-	hotplug->hpd_short_storm_enabled = new_state;
-	/* Reset the HPD storm stats so we don't accidentally trigger a storm */
-	for_each_hpd_pin(i)
-		hotplug->stats[i].count = 0;
-	spin_unlock_irq(&dev_priv->irq_lock);
-
-	/* Re-enable hpd immediately if we were in an irq storm */
-	flush_delayed_work(&dev_priv->display.hotplug.reenable_work);
-
-	return len;
-}
-
-static const struct file_operations i915_hpd_short_storm_ctl_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_hpd_short_storm_ctl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.write = i915_hpd_short_storm_ctl_write,
-};
-
-static int i915_drrs_ctl_set(void *data, u64 val)
-{
-	struct drm_i915_private *dev_priv = data;
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_crtc *crtc;
-
-	for_each_intel_crtc(dev, crtc) {
-		struct intel_crtc_state *crtc_state;
-		struct drm_crtc_commit *commit;
-		int ret;
-
-		ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex);
-		if (ret)
-			return ret;
-
-		crtc_state = to_intel_crtc_state(crtc->base.state);
-
-		if (!crtc_state->hw.active ||
-		    !crtc_state->has_drrs)
-			goto out;
-
-		commit = crtc_state->uapi.commit;
-		if (commit) {
-			ret = wait_for_completion_interruptible(&commit->hw_done);
-			if (ret)
-				goto out;
-		}
-
-		drm_dbg(&dev_priv->drm,
-			"Manually %sactivating DRRS\n", val ? "" : "de");
-
-		if (val)
-			intel_drrs_activate(crtc_state);
-		else
-			intel_drrs_deactivate(crtc_state);
-
-out:
-		drm_modeset_unlock(&crtc->base.mutex);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(i915_drrs_ctl_fops, NULL, i915_drrs_ctl_set, "%llu\n");
-
 static ssize_t
 i915_fifo_underrun_reset_write(struct file *filp,
 			       const char __user *ubuf,
@@ -1776,7 +1518,6 @@ i915_fifo_underrun_reset_write(struct file *filp,
 {
 	struct drm_i915_private *dev_priv = filp->private_data;
 	struct intel_crtc *crtc;
-	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 	bool reset;
 
@@ -1787,7 +1528,7 @@ i915_fifo_underrun_reset_write(struct file *filp,
 	if (!reset)
 		return cnt;
 
-	for_each_intel_crtc(dev, crtc) {
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		struct drm_crtc_commit *commit;
 		struct intel_crtc_state *crtc_state;
 
@@ -1842,7 +1583,6 @@ static const struct drm_info_list intel_display_debugfs_list[] = {
 	{"i915_shared_dplls_info", i915_shared_dplls_info, 0},
 	{"i915_dp_mst_info", i915_dp_mst_info, 0},
 	{"i915_ddb_info", i915_ddb_info, 0},
-	{"i915_drrs_status", i915_drrs_status, 0},
 	{"i915_lpsp_status", i915_lpsp_status, 0},
 };
 
@@ -1857,9 +1597,6 @@ static const struct {
 	{"i915_dp_test_data", &i915_displayport_test_data_fops},
 	{"i915_dp_test_type", &i915_displayport_test_type_fops},
 	{"i915_dp_test_active", &i915_displayport_test_active_fops},
-	{"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops},
-	{"i915_hpd_short_storm_ctl", &i915_hpd_short_storm_ctl_fops},
-	{"i915_drrs_ctl", &i915_drrs_ctl_fops},
 	{"i915_edp_psr_debug", &i915_edp_psr_debug_fops},
 };
 
@@ -1882,6 +1619,7 @@ void intel_display_debugfs_register(struct drm_i915_private *i915)
 
 	intel_dmc_debugfs_register(i915);
 	intel_fbc_debugfs_register(i915);
+	intel_hpd_debugfs_register(i915);
 	skl_watermark_ipc_debugfs_register(i915);
 }
 
@@ -2195,6 +1933,8 @@ void intel_connector_debugfs_add(struct intel_connector *intel_connector)
 	if (!root)
 		return;
 
+	intel_drrs_connector_debugfs_add(intel_connector);
+
 	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		debugfs_create_file("i915_panel_timings", S_IRUGO, root,
 				    connector, &i915_panel_fops);
@@ -2247,6 +1987,7 @@ void intel_crtc_debugfs_add(struct drm_crtc *crtc)
 		return;
 
 	crtc_updates_add(crtc);
+	intel_drrs_crtc_debugfs_add(to_intel_crtc(crtc));
 	intel_fbc_crtc_debugfs_add(to_intel_crtc(crtc));
 
 	debugfs_create_file("i915_current_bpc", 0444, crtc->debugfs_entry, crtc,
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 1e608b9e5055..4c1de91e56ff 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -1148,10 +1148,9 @@ static void hsw_assert_cdclk(struct drm_i915_private *dev_priv)
 
 static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 
-	for_each_intel_crtc(dev, crtc)
+	for_each_intel_crtc(&dev_priv->drm, crtc)
 		I915_STATE_WARN(crtc->active, "CRTC for pipe %c enabled\n",
 				pipe_name(crtc->pipe));
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index df7ee4969ef1..8710dd41ffd4 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -12,6 +12,8 @@
 #include "intel_de.h"
 #include "intel_display_power_well.h"
 #include "intel_display_types.h"
+#include "intel_dkl_phy.h"
+#include "intel_dkl_phy_regs.h"
 #include "intel_dmc.h"
 #include "intel_dpio_phy.h"
 #include "intel_dpll.h"
@@ -529,11 +531,9 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 		enum tc_port tc_port;
 
 		tc_port = TGL_AUX_PW_TO_TC_PORT(i915_power_well_instance(power_well)->hsw.idx);
-		intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-			       HIP_INDEX_VAL(tc_port, 0x2));
 
-		if (intel_de_wait_for_set(dev_priv, DKL_CMN_UC_DW_27(tc_port),
-					  DKL_CMN_UC_DW27_UC_HEALTH, 1))
+		if (wait_for(intel_dkl_phy_read(dev_priv, DKL_CMN_UC_DW_27(tc_port)) &
+			     DKL_CMN_UC_DW27_UC_HEALTH, 1))
 			drm_warn(&dev_priv->drm,
 				 "Timeout waiting TC uC health\n");
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 298d00a11f47..7f18c052ec16 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1001,11 +1001,15 @@ struct intel_crtc_state {
 	 */
 	struct {
 		bool active, enable;
+		/* logical state of LUTs */
 		struct drm_property_blob *degamma_lut, *gamma_lut, *ctm;
 		struct drm_display_mode mode, pipe_mode, adjusted_mode;
 		enum drm_scaling_filter scaling_filter;
 	} hw;
 
+	/* actual state of LUTs */
+	struct drm_property_blob *pre_csc_lut, *post_csc_lut;
+
 	/**
 	 * quirks - bitfield with hw state readout quirks
 	 *
@@ -2040,15 +2044,16 @@ static inline bool
 intel_crtc_has_type(const struct intel_crtc_state *crtc_state,
 		    enum intel_output_type type)
 {
-	return crtc_state->output_types & (1 << type);
+	return crtc_state->output_types & BIT(type);
 }
+
 static inline bool
 intel_crtc_has_dp_encoder(const struct intel_crtc_state *crtc_state)
 {
 	return crtc_state->output_types &
-		((1 << INTEL_OUTPUT_DP) |
-		 (1 << INTEL_OUTPUT_DP_MST) |
-		 (1 << INTEL_OUTPUT_EDP));
+		(BIT(INTEL_OUTPUT_DP) |
+		 BIT(INTEL_OUTPUT_DP_MST) |
+		 BIT(INTEL_OUTPUT_EDP));
 }
 
 static inline bool
@@ -2057,6 +2062,20 @@ intel_crtc_needs_modeset(const struct intel_crtc_state *crtc_state)
 	return drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
 }
 
+static inline bool
+intel_crtc_needs_fastset(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->update_pipe;
+}
+
+static inline bool
+intel_crtc_needs_color_update(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->uapi.color_mgmt_changed ||
+		intel_crtc_needs_fastset(crtc_state) ||
+		intel_crtc_needs_modeset(crtc_state);
+}
+
 static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state)
 {
 	return i915_ggtt_offset(plane_state->ggtt_vma);
diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.c b/drivers/gpu/drm/i915/display/intel_dkl_phy.c
new file mode 100644
index 000000000000..57cc3edba016
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_reg.h"
+
+#include "intel_de.h"
+#include "intel_display.h"
+#include "intel_dkl_phy.h"
+#include "intel_dkl_phy_regs.h"
+
+static void
+dkl_phy_set_hip_idx(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg)
+{
+	enum tc_port tc_port = DKL_REG_TC_PORT(reg);
+
+	drm_WARN_ON(&i915->drm, tc_port < TC_PORT_1 || tc_port >= I915_MAX_TC_PORTS);
+
+	intel_de_write(i915,
+		       HIP_INDEX_REG(tc_port),
+		       HIP_INDEX_VAL(tc_port, reg.bank_idx));
+}
+
+/**
+ * intel_dkl_phy_read - read a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ *
+ * Read the @reg Dekel PHY register.
+ *
+ * Returns the read value.
+ */
+u32
+intel_dkl_phy_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg)
+{
+	u32 val;
+
+	spin_lock(&i915->display.dkl.phy_lock);
+
+	dkl_phy_set_hip_idx(i915, reg);
+	val = intel_de_read(i915, DKL_REG_MMIO(reg));
+
+	spin_unlock(&i915->display.dkl.phy_lock);
+
+	return val;
+}
+
+/**
+ * intel_dkl_phy_write - write a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @val: value to write
+ *
+ * Write @val to the @reg Dekel PHY register.
+ */
+void
+intel_dkl_phy_write(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 val)
+{
+	spin_lock(&i915->display.dkl.phy_lock);
+
+	dkl_phy_set_hip_idx(i915, reg);
+	intel_de_write(i915, DKL_REG_MMIO(reg), val);
+
+	spin_unlock(&i915->display.dkl.phy_lock);
+}
+
+/**
+ * intel_dkl_phy_rmw - read-modify-write a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @clear: mask to clear
+ * @set: mask to set
+ *
+ * Read the @reg Dekel PHY register, clearing then setting the @clear/@set bits in it, and writing
+ * this value back to the register if the value differs from the read one.
+ */
+void
+intel_dkl_phy_rmw(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 clear, u32 set)
+{
+	spin_lock(&i915->display.dkl.phy_lock);
+
+	dkl_phy_set_hip_idx(i915, reg);
+	intel_de_rmw(i915, DKL_REG_MMIO(reg), clear, set);
+
+	spin_unlock(&i915->display.dkl.phy_lock);
+}
+
+/**
+ * intel_dkl_phy_posting_read - do a posting read from a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ *
+ * Read the @reg Dekel PHY register without returning the read value.
+ */
+void
+intel_dkl_phy_posting_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg)
+{
+	spin_lock(&i915->display.dkl.phy_lock);
+
+	dkl_phy_set_hip_idx(i915, reg);
+	intel_de_posting_read(i915, DKL_REG_MMIO(reg));
+
+	spin_unlock(&i915->display.dkl.phy_lock);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.h b/drivers/gpu/drm/i915/display/intel_dkl_phy.h
new file mode 100644
index 000000000000..570ee36f9386
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_DKL_PHY_H__
+#define __INTEL_DKL_PHY_H__
+
+#include <linux/types.h>
+
+#include "intel_dkl_phy_regs.h"
+
+struct drm_i915_private;
+
+u32
+intel_dkl_phy_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg);
+void
+intel_dkl_phy_write(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 val);
+void
+intel_dkl_phy_rmw(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 clear, u32 set);
+void
+intel_dkl_phy_posting_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg);
+
+#endif /* __INTEL_DKL_PHY_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h b/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h
new file mode 100644
index 000000000000..56085b32956d
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_DKL_PHY_REGS__
+#define __INTEL_DKL_PHY_REGS__
+
+#include <linux/types.h>
+
+struct intel_dkl_phy_reg {
+	u32 reg:24;
+	u32 bank_idx:4;
+};
+
+#define _DKL_PHY1_BASE					0x168000
+#define _DKL_PHY2_BASE					0x169000
+#define _DKL_PHY3_BASE					0x16A000
+#define _DKL_PHY4_BASE					0x16B000
+#define _DKL_PHY5_BASE					0x16C000
+#define _DKL_PHY6_BASE					0x16D000
+
+#define DKL_REG_TC_PORT(__reg) \
+	(TC_PORT_1 + ((__reg).reg - _DKL_PHY1_BASE) / (_DKL_PHY2_BASE - _DKL_PHY1_BASE))
+
+/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */
+#define DKL_REG_MMIO(__reg)				_MMIO((__reg).reg)
+
+#define _DKL_REG_PHY_BASE(tc_port)			_PORT(tc_port, \
+							      _DKL_PHY1_BASE, \
+							      _DKL_PHY2_BASE)
+
+#define _DKL_BANK_SHIFT					12
+#define _DKL_REG_BANK_OFFSET(phy_offset) \
+	((phy_offset) & ((1 << _DKL_BANK_SHIFT) - 1))
+#define _DKL_REG_BANK_IDX(phy_offset) \
+	(((phy_offset) >> _DKL_BANK_SHIFT) & 0xf)
+
+#define _DKL_REG(tc_port, phy_offset)	\
+	((const struct intel_dkl_phy_reg) { \
+		.reg = _DKL_REG_PHY_BASE(tc_port) + \
+		       _DKL_REG_BANK_OFFSET(phy_offset), \
+		.bank_idx = _DKL_REG_BANK_IDX(phy_offset), \
+	})
+
+#define _DKL_REG_LN(tc_port, ln_idx, ln0_offs, ln1_offs) \
+	_DKL_REG(tc_port, (ln0_offs) + (ln_idx) * ((ln1_offs) - (ln0_offs)))
+
+#define _DKL_PCS_DW5_LN0				0x0014
+#define _DKL_PCS_DW5_LN1				0x1014
+#define DKL_PCS_DW5(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_PCS_DW5_LN0, \
+								    _DKL_PCS_DW5_LN1)
+#define   DKL_PCS_DW5_CORE_SOFTRESET			REG_BIT(11)
+
+#define _DKL_PLL_DIV0					0x2200
+#define DKL_PLL_DIV0(tc_port)				_DKL_REG(tc_port, \
+								 _DKL_PLL_DIV0)
+#define   DKL_PLL_DIV0_AFC_STARTUP_MASK			REG_GENMASK(27, 25)
+#define   DKL_PLL_DIV0_AFC_STARTUP(val)			REG_FIELD_PREP(DKL_PLL_DIV0_AFC_STARTUP_MASK, (val))
+#define   DKL_PLL_DIV0_INTEG_COEFF(x)			((x) << 16)
+#define   DKL_PLL_DIV0_INTEG_COEFF_MASK			(0x1F << 16)
+#define   DKL_PLL_DIV0_PROP_COEFF(x)			((x) << 12)
+#define   DKL_PLL_DIV0_PROP_COEFF_MASK			(0xF << 12)
+#define   DKL_PLL_DIV0_FBPREDIV_SHIFT			(8)
+#define   DKL_PLL_DIV0_FBPREDIV(x)			((x) << DKL_PLL_DIV0_FBPREDIV_SHIFT)
+#define   DKL_PLL_DIV0_FBPREDIV_MASK			(0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT)
+#define   DKL_PLL_DIV0_FBDIV_INT(x)			((x) << 0)
+#define   DKL_PLL_DIV0_FBDIV_INT_MASK			(0xFF << 0)
+#define   DKL_PLL_DIV0_MASK				(DKL_PLL_DIV0_INTEG_COEFF_MASK | \
+							 DKL_PLL_DIV0_PROP_COEFF_MASK | \
+							 DKL_PLL_DIV0_FBPREDIV_MASK | \
+							 DKL_PLL_DIV0_FBDIV_INT_MASK)
+
+#define _DKL_PLL_DIV1					0x2204
+#define DKL_PLL_DIV1(tc_port)				_DKL_REG(tc_port, \
+								 _DKL_PLL_DIV1)
+#define   DKL_PLL_DIV1_IREF_TRIM(x)			((x) << 16)
+#define   DKL_PLL_DIV1_IREF_TRIM_MASK			(0x1F << 16)
+#define   DKL_PLL_DIV1_TDC_TARGET_CNT(x)		((x) << 0)
+#define   DKL_PLL_DIV1_TDC_TARGET_CNT_MASK		(0xFF << 0)
+
+#define _DKL_PLL_SSC					0x2210
+#define DKL_PLL_SSC(tc_port)				_DKL_REG(tc_port, \
+								 _DKL_PLL_SSC)
+#define   DKL_PLL_SSC_IREF_NDIV_RATIO(x)		((x) << 29)
+#define   DKL_PLL_SSC_IREF_NDIV_RATIO_MASK		(0x7 << 29)
+#define   DKL_PLL_SSC_STEP_LEN(x)			((x) << 16)
+#define   DKL_PLL_SSC_STEP_LEN_MASK			(0xFF << 16)
+#define   DKL_PLL_SSC_STEP_NUM(x)			((x) << 11)
+#define   DKL_PLL_SSC_STEP_NUM_MASK			(0x7 << 11)
+#define   DKL_PLL_SSC_EN				(1 << 9)
+
+#define _DKL_PLL_BIAS					0x2214
+#define DKL_PLL_BIAS(tc_port)				_DKL_REG(tc_port, \
+								 _DKL_PLL_BIAS)
+#define   DKL_PLL_BIAS_FRAC_EN_H			(1 << 30)
+#define   DKL_PLL_BIAS_FBDIV_SHIFT			(8)
+#define   DKL_PLL_BIAS_FBDIV_FRAC(x)			((x) << DKL_PLL_BIAS_FBDIV_SHIFT)
+#define   DKL_PLL_BIAS_FBDIV_FRAC_MASK			(0x3FFFFF << DKL_PLL_BIAS_FBDIV_SHIFT)
+
+#define _DKL_PLL_TDC_COLDST_BIAS			0x2218
+#define DKL_PLL_TDC_COLDST_BIAS(tc_port)		_DKL_REG(tc_port, \
+								 _DKL_PLL_TDC_COLDST_BIAS)
+#define   DKL_PLL_TDC_SSC_STEP_SIZE(x)			((x) << 8)
+#define   DKL_PLL_TDC_SSC_STEP_SIZE_MASK		(0xFF << 8)
+#define   DKL_PLL_TDC_FEED_FWD_GAIN(x)			((x) << 0)
+#define   DKL_PLL_TDC_FEED_FWD_GAIN_MASK		(0xFF << 0)
+
+#define _DKL_REFCLKIN_CTL				0x212C
+#define DKL_REFCLKIN_CTL(tc_port)			_DKL_REG(tc_port, \
+								 _DKL_REFCLKIN_CTL)
+/* Bits are the same as MG_REFCLKIN_CTL */
+
+#define _DKL_CLKTOP2_HSCLKCTL				0x20D4
+#define DKL_CLKTOP2_HSCLKCTL(rc_port)			_DKL_REG(tc_port, \
+								 _DKL_CLKTOP2_HSCLKCTL)
+/* Bits are the same as MG_CLKTOP2_HSCLKCTL */
+
+#define _DKL_CLKTOP2_CORECLKCTL1			0x20D8
+#define DKL_CLKTOP2_CORECLKCTL1(tc_port)		_DKL_REG(tc_port, \
+								 _DKL_CLKTOP2_CORECLKCTL1)
+/* Bits are the same as MG_CLKTOP2_CORECLKCTL1 */
+
+#define _DKL_TX_DPCNTL0_LN0				0x02C0
+#define _DKL_TX_DPCNTL0_LN1				0x12C0
+#define DKL_TX_DPCNTL0(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_DPCNTL0_LN0, \
+								    _DKL_TX_DPCNTL0_LN1)
+#define  DKL_TX_PRESHOOT_COEFF(x)			((x) << 13)
+#define  DKL_TX_PRESHOOT_COEFF_MASK			(0x1f << 13)
+#define  DKL_TX_DE_EMPHASIS_COEFF(x)			((x) << 8)
+#define  DKL_TX_DE_EMPAHSIS_COEFF_MASK			(0x1f << 8)
+#define  DKL_TX_VSWING_CONTROL(x)			((x) << 0)
+#define  DKL_TX_VSWING_CONTROL_MASK			(0x7 << 0)
+
+#define _DKL_TX_DPCNTL1_LN0				0x02C4
+#define _DKL_TX_DPCNTL1_LN1				0x12C4
+#define DKL_TX_DPCNTL1(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_DPCNTL1_LN0, \
+								    _DKL_TX_DPCNTL1_LN1)
+/* Bits are the same as DKL_TX_DPCNTRL0 */
+
+#define _DKL_TX_DPCNTL2_LN0				0x02C8
+#define _DKL_TX_DPCNTL2_LN1				0x12C8
+#define DKL_TX_DPCNTL2(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_DPCNTL2_LN0, \
+								    _DKL_TX_DPCNTL2_LN1)
+#define  DKL_TX_DP20BITMODE				REG_BIT(2)
+#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK	REG_GENMASK(4, 3)
+#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(val)	REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK, (val))
+#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK	REG_GENMASK(6, 5)
+#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(val)	REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, (val))
+
+#define _DKL_TX_FW_CALIB_LN0				0x02F8
+#define _DKL_TX_FW_CALIB_LN1				0x12F8
+#define DKL_TX_FW_CALIB(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_FW_CALIB_LN0, \
+								    _DKL_TX_FW_CALIB_LN1)
+#define  DKL_TX_CFG_DISABLE_WAIT_INIT			(1 << 7)
+
+#define _DKL_TX_PMD_LANE_SUS_LN0			0x0D00
+#define _DKL_TX_PMD_LANE_SUS_LN1			0x1D00
+#define DKL_TX_PMD_LANE_SUS(tc_port, ln)		_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_PMD_LANE_SUS_LN0, \
+								    _DKL_TX_PMD_LANE_SUS_LN1)
+
+#define _DKL_TX_DW17_LN0				0x0DC4
+#define _DKL_TX_DW17_LN1				0x1DC4
+#define DKL_TX_DW17(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_DW17_LN0, \
+								    _DKL_TX_DW17_LN1)
+
+#define _DKL_TX_DW18_LN0				0x0DC8
+#define _DKL_TX_DW18_LN1				0x1DC8
+#define DKL_TX_DW18(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_TX_DW18_LN0, \
+								    _DKL_TX_DW18_LN1)
+
+#define _DKL_DP_MODE_LN0				0x00A0
+#define _DKL_DP_MODE_LN1				0x10A0
+#define DKL_DP_MODE(tc_port, ln)			_DKL_REG_LN(tc_port, ln, \
+								    _DKL_DP_MODE_LN0, \
+								    _DKL_DP_MODE_LN1)
+
+#define _DKL_CMN_UC_DW27				0x236C
+#define DKL_CMN_UC_DW_27(tc_port)			_DKL_REG(tc_port, \
+								 _DKL_CMN_UC_DW27)
+#define  DKL_CMN_UC_DW27_UC_HEALTH			(0x1 << 15)
+
+/*
+ * Each Dekel PHY is addressed through a 4KB aperture. Each PHY has more than
+ * 4KB of register space, so a separate index is programmed in HIP_INDEX_REG0
+ * or HIP_INDEX_REG1, based on the port number, to set the upper 2 address
+ * bits that point the 4KB window into the full PHY register space.
+ */
+#define _HIP_INDEX_REG0					0x1010A0
+#define _HIP_INDEX_REG1					0x1010A4
+#define HIP_INDEX_REG(tc_port)				_MMIO((tc_port) < 4 ? _HIP_INDEX_REG0 \
+							      : _HIP_INDEX_REG1)
+#define _HIP_INDEX_SHIFT(tc_port)			(8 * ((tc_port) % 4))
+#define HIP_INDEX_VAL(tc_port, val)			((val) << _HIP_INDEX_SHIFT(tc_port))
+
+#endif /* __INTEL_DKL_PHY_REGS__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index e52ecc0738a6..081a4d0083b1 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -1065,12 +1065,13 @@ static int intel_dmc_debugfs_status_show(struct seq_file *m, void *unused)
 	seq_printf(m, "fw loaded: %s\n",
 		   str_yes_no(intel_dmc_has_payload(i915)));
 	seq_printf(m, "path: %s\n", dmc->fw_path);
-	seq_printf(m, "Pipe A fw support: %s\n",
+	seq_printf(m, "Pipe A fw needed: %s\n",
 		   str_yes_no(GRAPHICS_VER(i915) >= 12));
 	seq_printf(m, "Pipe A fw loaded: %s\n",
 		   str_yes_no(dmc->dmc_info[DMC_FW_PIPEA].payload));
-	seq_printf(m, "Pipe B fw support: %s\n",
-		   str_yes_no(IS_ALDERLAKE_P(i915)));
+	seq_printf(m, "Pipe B fw needed: %s\n",
+		   str_yes_no(IS_ALDERLAKE_P(i915) ||
+			      DISPLAY_VER(i915) >= 14));
 	seq_printf(m, "Pipe B fw loaded: %s\n",
 		   str_yes_no(dmc->dmc_info[DMC_FW_PIPEB].payload));
 
@@ -1081,22 +1082,19 @@ static int intel_dmc_debugfs_status_show(struct seq_file *m, void *unused)
 		   DMC_VERSION_MINOR(dmc->version));
 
 	if (DISPLAY_VER(i915) >= 12) {
-		if (IS_DGFX(i915)) {
+		i915_reg_t dc3co_reg;
+
+		if (IS_DGFX(i915) || DISPLAY_VER(i915) >= 14) {
+			dc3co_reg = DG1_DMC_DEBUG3;
 			dc5_reg = DG1_DMC_DEBUG_DC5_COUNT;
 		} else {
+			dc3co_reg = TGL_DMC_DEBUG3;
 			dc5_reg = TGL_DMC_DEBUG_DC5_COUNT;
 			dc6_reg = TGL_DMC_DEBUG_DC6_COUNT;
 		}
 
-		/*
-		 * NOTE: DMC_DEBUG3 is a general purpose reg.
-		 * According to B.Specs:49196 DMC f/w reuses DC5/6 counter
-		 * reg for DC3CO debugging and validation,
-		 * but TGL DMC f/w is using DMC_DEBUG3 reg for DC3CO counter.
-		 */
 		seq_printf(m, "DC3CO count: %d\n",
-			   intel_de_read(i915, IS_DGFX(i915) ?
-					 DG1_DMC_DEBUG3 : TGL_DMC_DEBUG3));
+			   intel_de_read(i915, dc3co_reg));
 	} else {
 		dc5_reg = IS_BROXTON(i915) ? BXT_DMC_DC3_DC5_COUNT :
 			SKL_DMC_DC3_DC5_COUNT;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c9be61d2348e..7400d6b4c587 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2306,6 +2306,7 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	bool fastset = true;
 
 	/*
 	 * If BIOS has set an unsupported or non-standard link rate for some
@@ -2313,9 +2314,10 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder,
 	 */
 	if (intel_dp_rate_index(intel_dp->source_rates, intel_dp->num_source_rates,
 				crtc_state->port_clock) < 0) {
-		drm_dbg_kms(&i915->drm, "Forcing full modeset due to unsupported link rate\n");
+		drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset due to unsupported link rate\n",
+			    encoder->base.base.id, encoder->base.name);
 		crtc_state->uapi.connectors_changed = true;
-		return false;
+		fastset = false;
 	}
 
 	/*
@@ -2326,18 +2328,20 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder,
 	 * Remove once we have readout for DSC.
 	 */
 	if (crtc_state->dsc.compression_enable) {
-		drm_dbg_kms(&i915->drm, "Forcing full modeset due to DSC being enabled\n");
+		drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset due to DSC being enabled\n",
+			    encoder->base.base.id, encoder->base.name);
 		crtc_state->uapi.mode_changed = true;
-		return false;
+		fastset = false;
 	}
 
 	if (CAN_PSR(intel_dp)) {
-		drm_dbg_kms(&i915->drm, "Forcing full modeset to compute PSR state\n");
+		drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset to compute PSR state\n",
+			    encoder->base.base.id, encoder->base.name);
 		crtc_state->uapi.mode_changed = true;
-		return false;
+		fastset = false;
 	}
 
-	return true;
+	return fastset;
 }
 
 static void intel_dp_get_pcon_dsc_cap(struct intel_dp *intel_dp)
@@ -2686,7 +2690,6 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp,
 			   str_enable_disable(tmp));
 }
 
-
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 {
 	u8 dprx = 0;
@@ -3957,6 +3960,8 @@ intel_dp_handle_hdmi_link_status_change(struct intel_dp *intel_dp)
 
 		drm_dp_pcon_hdmi_frl_link_error_count(&intel_dp->aux, &intel_dp->attached_connector->base);
 
+		intel_dp->frl.is_trained = false;
+
 		/* Restart FRL training or fall back to TMDS mode */
 		intel_dp_check_frl_training(intel_dp);
 	}
@@ -5172,19 +5177,6 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 	if (has_gamut_metadata_dip(dev_priv, port))
 		drm_connector_attach_hdr_output_metadata_property(connector);
 
-	if (intel_dp_is_edp(intel_dp)) {
-		u32 allowed_scalers;
-
-		allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
-		if (!HAS_GMCH(dev_priv))
-			allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
-
-		drm_connector_attach_scaling_mode_property(connector, allowed_scalers);
-
-		connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT;
-
-	}
-
 	if (HAS_VRR(dev_priv))
 		drm_connector_attach_vrr_capable_property(connector);
 }
@@ -5197,8 +5189,7 @@ intel_edp_add_properties(struct intel_dp *intel_dp)
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_preferred_fixed_mode(connector);
 
-	if (!fixed_mode)
-		return;
+	intel_attach_scaling_mode_property(&connector->base);
 
 	drm_connector_set_panel_orientation_with_quirk(&connector->base,
 						       i915->display.vbt.orientation,
@@ -5206,16 +5197,43 @@ intel_edp_add_properties(struct intel_dp *intel_dp)
 						       fixed_mode->vdisplay);
 }
 
+static void intel_edp_backlight_setup(struct intel_dp *intel_dp,
+				      struct intel_connector *connector)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	enum pipe pipe = INVALID_PIPE;
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		/*
+		 * Figure out the current pipe for the initial backlight setup.
+		 * If the current pipe isn't valid, try the PPS pipe, and if that
+		 * fails just assume pipe A.
+		 */
+		pipe = vlv_active_pipe(intel_dp);
+
+		if (pipe != PIPE_A && pipe != PIPE_B)
+			pipe = intel_dp->pps.pps_pipe;
+
+		if (pipe != PIPE_A && pipe != PIPE_B)
+			pipe = PIPE_A;
+
+		drm_dbg_kms(&i915->drm,
+			    "[CONNECTOR:%d:%s] using pipe %c for initial backlight setup\n",
+			    connector->base.base.id, connector->base.name,
+			    pipe_name(pipe));
+	}
+
+	intel_backlight_setup(connector, pipe);
+}
+
 static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 				     struct intel_connector *intel_connector)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector = &intel_connector->base;
 	struct drm_display_mode *fixed_mode;
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	bool has_dpcd;
-	enum pipe pipe = INVALID_PIPE;
 	struct edid *edid;
 
 	if (!intel_dp_is_edp(intel_dp))
@@ -5228,7 +5246,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	 * with an already powered-on LVDS power sequencer.
 	 */
 	if (intel_get_lvds_encoder(dev_priv)) {
-		drm_WARN_ON(dev,
+		drm_WARN_ON(&dev_priv->drm,
 			    !(HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)));
 		drm_info(&dev_priv->drm,
 			 "LVDS was detected, not registering eDP\n");
@@ -5244,11 +5262,12 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	if (!has_dpcd) {
 		/* if this fails, presume the device is a ghost */
 		drm_info(&dev_priv->drm,
-			 "failed to retrieve link info, disabling eDP\n");
+			 "[ENCODER:%d:%s] failed to retrieve link info, disabling eDP\n",
+			 encoder->base.base.id, encoder->base.name);
 		goto out_vdd_off;
 	}
 
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (!edid) {
 		/* Fallback to EDID from ACPI OpRegion, if any */
@@ -5273,9 +5292,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	intel_bios_init_panel(dev_priv, &intel_connector->panel,
 			      encoder->devdata, IS_ERR(edid) ? NULL : edid);
 
-	intel_panel_add_edid_fixed_modes(intel_connector,
-					 intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE,
-					 intel_vrr_is_capable(intel_connector));
+	intel_panel_add_edid_fixed_modes(intel_connector, true);
 
 	/* MSO requires information from the EDID */
 	intel_edp_mso_init(intel_dp);
@@ -5288,30 +5305,18 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	if (!intel_panel_preferred_fixed_mode(intel_connector))
 		intel_panel_add_vbt_lfp_fixed_mode(intel_connector);
 
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		/*
-		 * Figure out the current pipe for the initial backlight setup.
-		 * If the current pipe isn't valid, try the PPS pipe, and if that
-		 * fails just assume pipe A.
-		 */
-		pipe = vlv_active_pipe(intel_dp);
-
-		if (pipe != PIPE_A && pipe != PIPE_B)
-			pipe = intel_dp->pps.pps_pipe;
-
-		if (pipe != PIPE_A && pipe != PIPE_B)
-			pipe = PIPE_A;
-
-		drm_dbg_kms(&dev_priv->drm,
-			    "using pipe %c for initial backlight setup\n",
-			    pipe_name(pipe));
+	if (!intel_panel_preferred_fixed_mode(intel_connector)) {
+		drm_info(&dev_priv->drm,
+			 "[ENCODER:%d:%s] failed to find fixed mode for the panel, disabling eDP\n",
+			 encoder->base.base.id, encoder->base.name);
+		goto out_vdd_off;
 	}
 
 	intel_panel_init(intel_connector);
 
-	intel_backlight_setup(intel_connector, pipe);
+	intel_edp_backlight_setup(intel_dp, intel_connector);
 
 	intel_edp_add_properties(intel_dp);
 
@@ -5413,7 +5418,6 @@ intel_dp_init_connector(struct intel_digital_port *dig_port,
 
 	if (!HAS_GMCH(dev_priv))
 		connector->interlace_allowed = true;
-	connector->doublescan_allowed = 0;
 
 	intel_connector->polled = DRM_CONNECTOR_POLL_HPD;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index 88689124c013..35360dd543ac 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -19,28 +19,20 @@
 #include "intel_hdcp.h"
 #include "intel_hdcp_regs.h"
 
-static unsigned int transcoder_to_stream_enc_status(enum transcoder cpu_transcoder)
+static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder)
 {
-	u32 stream_enc_mask;
-
 	switch (cpu_transcoder) {
 	case TRANSCODER_A:
-		stream_enc_mask = HDCP_STATUS_STREAM_A_ENC;
-		break;
+		return HDCP_STATUS_STREAM_A_ENC;
 	case TRANSCODER_B:
-		stream_enc_mask = HDCP_STATUS_STREAM_B_ENC;
-		break;
+		return HDCP_STATUS_STREAM_B_ENC;
 	case TRANSCODER_C:
-		stream_enc_mask = HDCP_STATUS_STREAM_C_ENC;
-		break;
+		return HDCP_STATUS_STREAM_C_ENC;
 	case TRANSCODER_D:
-		stream_enc_mask = HDCP_STATUS_STREAM_D_ENC;
-		break;
+		return HDCP_STATUS_STREAM_D_ENC;
 	default:
-		stream_enc_mask = 0;
+		return 0;
 	}
-
-	return stream_enc_mask;
 }
 
 static void intel_dp_hdcp_wait_for_cp_irq(struct intel_hdcp *hdcp, int timeout)
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 03604a37931c..cd4e61026d98 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -793,7 +793,35 @@ static bool intel_dp_mst_get_hw_state(struct intel_connector *connector)
 	return false;
 }
 
-static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *pathprop)
+static int intel_dp_mst_add_properties(struct intel_dp *intel_dp,
+				       struct drm_connector *connector,
+				       const char *pathprop)
+{
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.path_property, 0);
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tile_property, 0);
+
+	intel_attach_force_audio_property(connector);
+	intel_attach_broadcast_rgb_property(connector);
+
+	/*
+	 * Reuse the prop from the SST connector because we're
+	 * not allowed to create new props after device registration.
+	 */
+	connector->max_bpc_property =
+		intel_dp->attached_connector->base.max_bpc_property;
+	if (connector->max_bpc_property)
+		drm_connector_attach_max_bpc_property(connector, 6, 12);
+
+	return drm_connector_set_path_property(connector, pathprop);
+}
+
+static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
+							struct drm_dp_mst_port *port,
+							const char *pathprop)
 {
 	struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst_mgr);
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -833,28 +861,14 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 			goto err;
 	}
 
-	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
-	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
-
-	ret = drm_connector_set_path_property(connector, pathprop);
+	ret = intel_dp_mst_add_properties(intel_dp, connector, pathprop);
 	if (ret)
 		goto err;
 
-	intel_attach_force_audio_property(connector);
-	intel_attach_broadcast_rgb_property(connector);
-
 	ret = intel_dp_hdcp_init(dig_port, intel_connector);
 	if (ret)
 		drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP MST init failed, skipping.\n",
 			    connector->name, connector->base.id);
-	/*
-	 * Reuse the prop from the SST connector because we're
-	 * not allowed to create new props after device registration.
-	 */
-	connector->max_bpc_property =
-		intel_dp->attached_connector->base.max_bpc_property;
-	if (connector->max_bpc_property)
-		drm_connector_attach_max_bpc_property(connector, 6, 12);
 
 	return connector;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index e5fb66a5dd02..7c6c094a0a01 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -25,12 +25,14 @@
 
 #include "intel_de.h"
 #include "intel_display_types.h"
+#include "intel_dkl_phy.h"
+#include "intel_dkl_phy_regs.h"
 #include "intel_dpio_phy.h"
 #include "intel_dpll.h"
 #include "intel_dpll_mgr.h"
+#include "intel_mg_phy_regs.h"
 #include "intel_pch_refclk.h"
 #include "intel_tc.h"
-#include "intel_tc_phy_regs.h"
 
 /**
  * DOC: Display PLLs
@@ -152,28 +154,6 @@ intel_get_shared_dpll_by_id(struct drm_i915_private *dev_priv,
 	return &dev_priv->display.dpll.shared_dplls[id];
 }
 
-/**
- * intel_get_shared_dpll_id - get the id of a DPLL
- * @dev_priv: i915 device instance
- * @pll: the DPLL
- *
- * Returns:
- * The id of @pll
- */
-enum intel_dpll_id
-intel_get_shared_dpll_id(struct drm_i915_private *dev_priv,
-			 struct intel_shared_dpll *pll)
-{
-	long pll_idx = pll - dev_priv->display.dpll.shared_dplls;
-
-	if (drm_WARN_ON(&dev_priv->drm,
-			pll_idx < 0 ||
-			pll_idx >= dev_priv->display.dpll.num_shared_dpll))
-		return -1;
-
-	return pll_idx;
-}
-
 /* For ILK+ */
 void assert_shared_dpll(struct drm_i915_private *dev_priv,
 			struct intel_shared_dpll *pll,
@@ -384,20 +364,30 @@ intel_reference_shared_dpll(struct intel_atomic_state *state,
 	if (shared_dpll[id].pipe_mask == 0)
 		shared_dpll[id].hw_state = *pll_state;
 
-	drm_dbg(&i915->drm, "using %s for pipe %c\n", pll->info->name,
-		pipe_name(crtc->pipe));
+	drm_WARN_ON(&i915->drm, (shared_dpll[id].pipe_mask & BIT(crtc->pipe)) != 0);
 
 	shared_dpll[id].pipe_mask |= BIT(crtc->pipe);
+
+	drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] reserving %s\n",
+		    crtc->base.base.id, crtc->base.name, pll->info->name);
 }
 
 static void intel_unreference_shared_dpll(struct intel_atomic_state *state,
 					  const struct intel_crtc *crtc,
 					  const struct intel_shared_dpll *pll)
 {
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	struct intel_shared_dpll_state *shared_dpll;
+	const enum intel_dpll_id id = pll->info->id;
 
 	shared_dpll = intel_atomic_get_shared_dpll_state(&state->base);
-	shared_dpll[pll->info->id].pipe_mask &= ~BIT(crtc->pipe);
+
+	drm_WARN_ON(&i915->drm, (shared_dpll[id].pipe_mask & BIT(crtc->pipe)) == 0);
+
+	shared_dpll[id].pipe_mask &= ~BIT(crtc->pipe);
+
+	drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] releasing %s\n",
+		    crtc->base.base.id, crtc->base.name, pll->info->name);
 }
 
 static void intel_put_dpll(struct intel_atomic_state *state,
@@ -708,8 +698,6 @@ struct hsw_wrpll_rnp {
 
 static unsigned hsw_wrpll_get_budget_for_freq(int clock)
 {
-	unsigned budget;
-
 	switch (clock) {
 	case 25175000:
 	case 25200000:
@@ -742,21 +730,18 @@ static unsigned hsw_wrpll_get_budget_for_freq(int clock)
 	case 222750000:
 	case 296703000:
 	case 297000000:
-		budget = 0;
-		break;
+		return 0;
 	case 233500000:
 	case 245250000:
 	case 247750000:
 	case 253250000:
 	case 298000000:
-		budget = 1500;
-		break;
+		return 1500;
 	case 169128000:
 	case 169500000:
 	case 179500000:
 	case 202000000:
-		budget = 2000;
-		break;
+		return 2000;
 	case 256250000:
 	case 262500000:
 	case 270000000:
@@ -766,18 +751,13 @@ static unsigned hsw_wrpll_get_budget_for_freq(int clock)
 	case 281250000:
 	case 286000000:
 	case 291750000:
-		budget = 4000;
-		break;
+		return 4000;
 	case 267250000:
 	case 268500000:
-		budget = 5000;
-		break;
+		return 5000;
 	default:
-		budget = 1000;
-		break;
+		return 1000;
 	}
-
-	return budget;
 }
 
 static void hsw_wrpll_update_rnp(u64 freq2k, unsigned int budget,
@@ -3508,15 +3488,12 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	 * All registers read here have the same HIP_INDEX_REG even though
 	 * they are on different building blocks
 	 */
-	intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-		       HIP_INDEX_VAL(tc_port, 0x2));
-
-	hw_state->mg_refclkin_ctl = intel_de_read(dev_priv,
-						  DKL_REFCLKIN_CTL(tc_port));
+	hw_state->mg_refclkin_ctl = intel_dkl_phy_read(dev_priv,
+						       DKL_REFCLKIN_CTL(tc_port));
 	hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
 
 	hw_state->mg_clktop2_hsclkctl =
-		intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
+		intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
 	hw_state->mg_clktop2_hsclkctl &=
 		MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
 		MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
@@ -3524,32 +3501,32 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 		MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
 
 	hw_state->mg_clktop2_coreclkctl1 =
-		intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
+		intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
 	hw_state->mg_clktop2_coreclkctl1 &=
 		MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
 
-	hw_state->mg_pll_div0 = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port));
+	hw_state->mg_pll_div0 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV0(tc_port));
 	val = DKL_PLL_DIV0_MASK;
 	if (dev_priv->display.vbt.override_afc_startup)
 		val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
 	hw_state->mg_pll_div0 &= val;
 
-	hw_state->mg_pll_div1 = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
+	hw_state->mg_pll_div1 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port));
 	hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK |
 				  DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
 
-	hw_state->mg_pll_ssc = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port));
+	hw_state->mg_pll_ssc = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port));
 	hw_state->mg_pll_ssc &= (DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
 				 DKL_PLL_SSC_STEP_LEN_MASK |
 				 DKL_PLL_SSC_STEP_NUM_MASK |
 				 DKL_PLL_SSC_EN);
 
-	hw_state->mg_pll_bias = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port));
+	hw_state->mg_pll_bias = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port));
 	hw_state->mg_pll_bias &= (DKL_PLL_BIAS_FRAC_EN_H |
 				  DKL_PLL_BIAS_FBDIV_FRAC_MASK);
 
 	hw_state->mg_pll_tdc_coldst_bias =
-		intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+		intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
 	hw_state->mg_pll_tdc_coldst_bias &= (DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
 					     DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
 
@@ -3737,61 +3714,58 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv,
 	 * All registers programmed here have the same HIP_INDEX_REG even
 	 * though on different building block
 	 */
-	intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
-		       HIP_INDEX_VAL(tc_port, 0x2));
-
 	/* All the registers are RMW */
-	val = intel_de_read(dev_priv, DKL_REFCLKIN_CTL(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_REFCLKIN_CTL(tc_port));
 	val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
 	val |= hw_state->mg_refclkin_ctl;
-	intel_de_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
 	val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
 	val |= hw_state->mg_clktop2_coreclkctl1;
-	intel_de_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
 	val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
 		 MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
 		 MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
 		 MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
 	val |= hw_state->mg_clktop2_hsclkctl;
-	intel_de_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val);
 
 	val = DKL_PLL_DIV0_MASK;
 	if (dev_priv->display.vbt.override_afc_startup)
 		val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
-	intel_de_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val,
-		     hw_state->mg_pll_div0);
+	intel_dkl_phy_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val,
+			  hw_state->mg_pll_div0);
 
-	val = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port));
 	val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK |
 		 DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
 	val |= hw_state->mg_pll_div1;
-	intel_de_write(dev_priv, DKL_PLL_DIV1(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_PLL_DIV1(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port));
 	val &= ~(DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
 		 DKL_PLL_SSC_STEP_LEN_MASK |
 		 DKL_PLL_SSC_STEP_NUM_MASK |
 		 DKL_PLL_SSC_EN);
 	val |= hw_state->mg_pll_ssc;
-	intel_de_write(dev_priv, DKL_PLL_SSC(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_PLL_SSC(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port));
 	val &= ~(DKL_PLL_BIAS_FRAC_EN_H |
 		 DKL_PLL_BIAS_FBDIV_FRAC_MASK);
 	val |= hw_state->mg_pll_bias;
-	intel_de_write(dev_priv, DKL_PLL_BIAS(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_PLL_BIAS(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+	val = intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
 	val &= ~(DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
 		 DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
 	val |= hw_state->mg_pll_tdc_coldst_bias;
-	intel_de_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), val);
+	intel_dkl_phy_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), val);
 
-	intel_de_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+	intel_dkl_phy_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
 }
 
 static void icl_pll_power_enable(struct drm_i915_private *dev_priv,
@@ -4193,6 +4167,8 @@ void intel_shared_dpll_init(struct drm_i915_private *dev_priv)
 	const struct dpll_info *dpll_info;
 	int i;
 
+	mutex_init(&dev_priv->display.dpll.lock);
+
 	if (IS_DG2(dev_priv))
 		/* No shared DPLLs on DG2; port PLLs are part of the PHY */
 		dpll_mgr = NULL;
@@ -4237,7 +4213,6 @@ void intel_shared_dpll_init(struct drm_i915_private *dev_priv)
 
 	dev_priv->display.dpll.mgr = dpll_mgr;
 	dev_priv->display.dpll.num_shared_dpll = i;
-	mutex_init(&dev_priv->display.dpll.lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index 3247dc300ae4..3854f1b4299a 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -328,9 +328,6 @@ struct intel_shared_dpll {
 struct intel_shared_dpll *
 intel_get_shared_dpll_by_id(struct drm_i915_private *dev_priv,
 			    enum intel_dpll_id id);
-enum intel_dpll_id
-intel_get_shared_dpll_id(struct drm_i915_private *dev_priv,
-			 struct intel_shared_dpll *pll);
 void assert_shared_dpll(struct drm_i915_private *dev_priv,
 			struct intel_shared_dpll *pll,
 			bool state);
diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index ac587647e1f5..ad1a37b515fb 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -5,6 +5,7 @@
 
 #include "gem/i915_gem_domain.h"
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_lmem.h"
 #include "gt/gen8_ppgtt.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.c b/drivers/gpu/drm/i915/display/intel_drrs.c
index 7da4a9cbe4ba..e27408efaae2 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.c
+++ b/drivers/gpu/drm/i915/display/intel_drrs.c
@@ -284,16 +284,124 @@ void intel_drrs_flush(struct drm_i915_private *dev_priv,
 }
 
 /**
- * intel_crtc_drrs_init - Init DRRS for CRTC
+ * intel_drrs_crtc_init - Init DRRS for CRTC
  * @crtc: crtc
  *
  * This function is called only once at driver load to initialize basic
  * DRRS stuff.
  *
  */
-void intel_crtc_drrs_init(struct intel_crtc *crtc)
+void intel_drrs_crtc_init(struct intel_crtc *crtc)
 {
 	INIT_DELAYED_WORK(&crtc->drrs.work, intel_drrs_downclock_work);
 	mutex_init(&crtc->drrs.mutex);
 	crtc->drrs.cpu_transcoder = INVALID_TRANSCODER;
 }
+
+static int intel_drrs_debugfs_status_show(struct seq_file *m, void *unused)
+{
+	struct intel_crtc *crtc = m->private;
+	const struct intel_crtc_state *crtc_state;
+	int ret;
+
+	ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex);
+	if (ret)
+		return ret;
+
+	crtc_state = to_intel_crtc_state(crtc->base.state);
+
+	mutex_lock(&crtc->drrs.mutex);
+
+	seq_printf(m, "DRRS enabled: %s\n",
+		   str_yes_no(crtc_state->has_drrs));
+
+	seq_printf(m, "DRRS active: %s\n",
+		   str_yes_no(intel_drrs_is_active(crtc)));
+
+	seq_printf(m, "DRRS refresh rate: %s\n",
+		   crtc->drrs.refresh_rate == DRRS_REFRESH_RATE_LOW ?
+		   "low" : "high");
+
+	seq_printf(m, "DRRS busy frontbuffer bits: 0x%x\n",
+		   crtc->drrs.busy_frontbuffer_bits);
+
+	mutex_unlock(&crtc->drrs.mutex);
+
+	drm_modeset_unlock(&crtc->base.mutex);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(intel_drrs_debugfs_status);
+
+static int intel_drrs_debugfs_ctl_set(void *data, u64 val)
+{
+	struct intel_crtc *crtc = data;
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	struct intel_crtc_state *crtc_state;
+	struct drm_crtc_commit *commit;
+	int ret;
+
+	ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex);
+	if (ret)
+		return ret;
+
+	crtc_state = to_intel_crtc_state(crtc->base.state);
+
+	if (!crtc_state->hw.active ||
+	    !crtc_state->has_drrs)
+		goto out;
+
+	commit = crtc_state->uapi.commit;
+	if (commit) {
+		ret = wait_for_completion_interruptible(&commit->hw_done);
+		if (ret)
+			goto out;
+	}
+
+	drm_dbg(&i915->drm,
+		"Manually %sactivating DRRS\n", val ? "" : "de");
+
+	if (val)
+		intel_drrs_activate(crtc_state);
+	else
+		intel_drrs_deactivate(crtc_state);
+
+out:
+	drm_modeset_unlock(&crtc->base.mutex);
+
+	return ret;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(intel_drrs_debugfs_ctl_fops,
+			NULL, intel_drrs_debugfs_ctl_set, "%llu\n");
+
+void intel_drrs_crtc_debugfs_add(struct intel_crtc *crtc)
+{
+	debugfs_create_file("i915_drrs_status", 0444, crtc->base.debugfs_entry,
+			    crtc, &intel_drrs_debugfs_status_fops);
+
+	debugfs_create_file("i915_drrs_ctl", 0644, crtc->base.debugfs_entry,
+			    crtc, &intel_drrs_debugfs_ctl_fops);
+}
+
+static int intel_drrs_debugfs_type_show(struct seq_file *m, void *unused)
+{
+	struct intel_connector *connector = m->private;
+
+	seq_printf(m, "DRRS type: %s\n",
+		   intel_drrs_type_str(intel_panel_drrs_type(connector)));
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(intel_drrs_debugfs_type);
+
+void intel_drrs_connector_debugfs_add(struct intel_connector *connector)
+{
+	if (intel_panel_drrs_type(connector) == DRRS_TYPE_NONE)
+		return;
+
+	debugfs_create_file("i915_drrs_type", 0444, connector->base.debugfs_entry,
+			    connector, &intel_drrs_debugfs_type_fops);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.h b/drivers/gpu/drm/i915/display/intel_drrs.h
index 3ad1be1ad9c1..8ef5f93a80ff 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.h
+++ b/drivers/gpu/drm/i915/display/intel_drrs.h
@@ -23,6 +23,8 @@ void intel_drrs_invalidate(struct drm_i915_private *dev_priv,
 			   unsigned int frontbuffer_bits);
 void intel_drrs_flush(struct drm_i915_private *dev_priv,
 		      unsigned int frontbuffer_bits);
-void intel_crtc_drrs_init(struct intel_crtc *crtc);
+void intel_drrs_crtc_init(struct intel_crtc *crtc);
+void intel_drrs_crtc_debugfs_add(struct intel_crtc *crtc);
+void intel_drrs_connector_debugfs_add(struct intel_connector *connector);
 
 #endif /* __INTEL_DRRS_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 5572e43026e4..595087288922 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -491,8 +491,8 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		intel_encoder->pipe_mask = ~0;
 
 		if (dvo->type != INTEL_DVO_CHIP_LVDS)
-			intel_encoder->cloneable = (1 << INTEL_OUTPUT_ANALOG) |
-				(1 << INTEL_OUTPUT_DVO);
+			intel_encoder->cloneable = BIT(INTEL_OUTPUT_ANALOG) |
+				BIT(INTEL_OUTPUT_DVO);
 
 		switch (dvo->type) {
 		case INTEL_DVO_CHIP_TMDS:
@@ -515,8 +515,6 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		drm_connector_helper_add(connector,
 					 &intel_dvo_connector_helper_funcs);
 		connector->display_info.subpixel_order = SubPixelHorizontalRGB;
-		connector->interlace_allowed = false;
-		connector->doublescan_allowed = false;
 
 		intel_connector_attach_encoder(intel_connector, intel_encoder);
 		if (dvo->type == INTEL_DVO_CHIP_LVDS) {
diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index eefa33c555ac..63137ae5ab21 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -301,6 +301,19 @@ static bool plane_caps_contain_all(u8 caps, u8 mask)
 }
 
 /**
+ * intel_fb_is_tiled_modifier: Check if a modifier is a tiled modifier type
+ * @modifier: Modifier to check
+ *
+ * Returns:
+ * Returns %true if @modifier is a tiled modifier.
+ */
+bool intel_fb_is_tiled_modifier(u64 modifier)
+{
+	return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps,
+				      INTEL_PLANE_CAP_TILING_MASK);
+}
+
+/**
  * intel_fb_is_ccs_modifier: Check if a modifier is a CCS modifier type
  * @modifier: Modifier to check
  *
diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h
index 12386f13a4e0..4662b812b934 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.h
+++ b/drivers/gpu/drm/i915/display/intel_fb.h
@@ -29,6 +29,7 @@ struct intel_plane_state;
 #define INTEL_PLANE_CAP_TILING_Yf	BIT(5)
 #define INTEL_PLANE_CAP_TILING_4	BIT(6)
 
+bool intel_fb_is_tiled_modifier(u64 modifier);
 bool intel_fb_is_ccs_modifier(u64 modifier);
 bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier);
 bool intel_fb_is_mc_ccs_modifier(u64 modifier);
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 1dddd6abd77b..6900acbb1381 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -167,7 +167,6 @@ retry:
 		ret = i915_gem_object_attach_phys(obj, alignment);
 	else if (!ret && HAS_LMEM(dev_priv))
 		ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0);
-	/* TODO: Do we need to sync when migration becomes async? */
 	if (!ret)
 		ret = i915_gem_object_pin_pages(obj);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index f38175304928..3f24f326b989 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -670,6 +670,7 @@ static void intel_fbc_nuke(struct intel_fbc *fbc)
 {
 	struct drm_i915_private *i915 = fbc->i915;
 
+	lockdep_assert_held(&fbc->lock);
 	drm_WARN_ON(&i915->drm, fbc->flip_pending);
 
 	trace_intel_fbc_nuke(fbc->state.plane);
@@ -679,6 +680,8 @@ static void intel_fbc_nuke(struct intel_fbc *fbc)
 
 static void intel_fbc_activate(struct intel_fbc *fbc)
 {
+	lockdep_assert_held(&fbc->lock);
+
 	intel_fbc_hw_activate(fbc);
 	intel_fbc_nuke(fbc);
 
@@ -687,9 +690,7 @@ static void intel_fbc_activate(struct intel_fbc *fbc)
 
 static void intel_fbc_deactivate(struct intel_fbc *fbc, const char *reason)
 {
-	struct drm_i915_private *i915 = fbc->i915;
-
-	drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock));
+	lockdep_assert_held(&fbc->lock);
 
 	if (fbc->active)
 		intel_fbc_hw_deactivate(fbc);
@@ -1009,7 +1010,8 @@ static bool intel_fbc_is_fence_ok(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev);
 
-	/* The use of a CPU fence is one of two ways to detect writes by the
+	/*
+	 * The use of a CPU fence is one of two ways to detect writes by the
 	 * CPU to the scanout and trigger updates to the FBC.
 	 *
 	 * The other method is by software tracking (see
@@ -1019,12 +1021,6 @@ static bool intel_fbc_is_fence_ok(const struct intel_plane_state *plane_state)
 	 * Note that is possible for a tiled surface to be unmappable (and
 	 * so have no fence associated with it) due to aperture constraints
 	 * at the time of pinning.
-	 *
-	 * FIXME with 90/270 degree rotation we should use the fence on
-	 * the normal GTT view (the rotated view doesn't even have a
-	 * fence). Would need changes to the FBC fence Y offset as well.
-	 * For now this will effectively disable FBC with 90/270 degree
-	 * rotation.
 	 */
 	return DISPLAY_VER(i915) >= 9 ||
 		(plane_state->flags & PLANE_HAS_FENCE &&
@@ -1227,6 +1223,8 @@ static bool __intel_fbc_pre_update(struct intel_atomic_state *state,
 	struct intel_fbc *fbc = plane->fbc;
 	bool need_vblank_wait = false;
 
+	lockdep_assert_held(&fbc->lock);
+
 	fbc->flip_pending = true;
 
 	if (intel_fbc_can_flip_nuke(state, crtc, plane))
@@ -1284,7 +1282,7 @@ static void __intel_fbc_disable(struct intel_fbc *fbc)
 	struct drm_i915_private *i915 = fbc->i915;
 	struct intel_plane *plane = fbc->state.plane;
 
-	drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock));
+	lockdep_assert_held(&fbc->lock);
 	drm_WARN_ON(&i915->drm, fbc->active);
 
 	drm_dbg_kms(&i915->drm, "Disabling FBC on [PLANE:%d:%s]\n",
@@ -1299,9 +1297,9 @@ static void __intel_fbc_disable(struct intel_fbc *fbc)
 
 static void __intel_fbc_post_update(struct intel_fbc *fbc)
 {
-	struct drm_i915_private *i915 = fbc->i915;
+	lockdep_assert_held(&fbc->lock);
 
-	drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock));
+	fbc->flip_pending = false;
 
 	if (!fbc->busy_bits)
 		intel_fbc_activate(fbc);
@@ -1324,10 +1322,8 @@ void intel_fbc_post_update(struct intel_atomic_state *state,
 
 		mutex_lock(&fbc->lock);
 
-		if (fbc->state.plane == plane) {
-			fbc->flip_pending = false;
+		if (fbc->state.plane == plane)
 			__intel_fbc_post_update(fbc);
-		}
 
 		mutex_unlock(&fbc->lock);
 	}
@@ -1437,6 +1433,8 @@ static void __intel_fbc_enable(struct intel_atomic_state *state,
 		intel_atomic_get_new_plane_state(state, plane);
 	struct intel_fbc *fbc = plane->fbc;
 
+	lockdep_assert_held(&fbc->lock);
+
 	if (fbc->state.plane) {
 		if (fbc->state.plane != plane)
 			return;
@@ -1522,7 +1520,8 @@ void intel_fbc_update(struct intel_atomic_state *state,
 
 		mutex_lock(&fbc->lock);
 
-		if (crtc_state->update_pipe && plane_state->no_fbc_reason) {
+		if (intel_crtc_needs_fastset(crtc_state) &&
+		    plane_state->no_fbc_reason) {
 			if (fbc->state.plane == plane)
 				__intel_fbc_disable(fbc);
 		} else {
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 112aa0447a0d..ab385d18ddcc 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -175,7 +175,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	}
 
 	if (IS_ERR(obj)) {
-		drm_err(&dev_priv->drm, "failed to allocate framebuffer\n");
+		drm_err(&dev_priv->drm, "failed to allocate framebuffer (%pe)\n", obj);
 		return PTR_ERR(obj);
 	}
 
@@ -256,7 +256,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	info = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(info)) {
-		drm_err(&dev_priv->drm, "Failed to allocate fb_info\n");
+		drm_err(&dev_priv->drm, "Failed to allocate fb_info (%pe)\n", info);
 		ret = PTR_ERR(info);
 		goto out_unpin;
 	}
@@ -291,7 +291,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	vaddr = i915_vma_pin_iomap(vma);
 	if (IS_ERR(vaddr)) {
 		drm_err(&dev_priv->drm,
-			"Failed to remap framebuffer into virtual memory\n");
+			"Failed to remap framebuffer into virtual memory (%pe)\n", vaddr);
 		ret = PTR_ERR(vaddr);
 		goto out_unpin;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 18451f5d2548..02f8374ea51f 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2950,9 +2950,8 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 				    ddc);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
 
-	connector->interlace_allowed = 1;
-	connector->doublescan_allowed = 0;
-	connector->stereo_allowed = 1;
+	connector->interlace_allowed = true;
+	connector->stereo_allowed = true;
 
 	if (DISPLAY_VER(dev_priv) >= 10)
 		connector->ycbcr_420_allowed = true;
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index f7a2f485b177..907ab7526cb4 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -90,6 +90,9 @@ enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 	return HPD_PORT_A + port - PORT_A;
 }
 
+/* Threshold == 5 for long IRQs, 50 for short */
+#define HPD_STORM_DEFAULT_THRESHOLD	50
+
 #define HPD_STORM_DETECT_PERIOD		1000
 #define HPD_STORM_REENABLE_DELAY	(2 * 60 * 1000)
 #define HPD_RETRY_DELAY			1000
@@ -175,14 +178,13 @@ static bool intel_hpd_irq_storm_detect(struct drm_i915_private *dev_priv,
 static void
 intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	bool hpd_disabled = false;
 
 	lockdep_assert_held(&dev_priv->irq_lock);
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		enum hpd_pin pin;
 
@@ -208,7 +210,7 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv)
 
 	/* Enable polling and queue hotplug re-enabling. */
 	if (hpd_disabled) {
-		drm_kms_helper_poll_enable(dev);
+		drm_kms_helper_poll_enable(&dev_priv->drm);
 		mod_delayed_work(system_wq, &dev_priv->display.hotplug.reenable_work,
 				 msecs_to_jiffies(HPD_STORM_REENABLE_DELAY));
 	}
@@ -219,7 +221,6 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv),
 			     display.hotplug.reenable_work.work);
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	intel_wakeref_t wakeref;
@@ -229,7 +230,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		pin = intel_connector_hpd_pin(connector);
 		if (pin == HPD_NONE ||
@@ -367,14 +368,13 @@ static void i915_hotplug_work_func(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private,
 			     display.hotplug.hotplug_work.work);
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	u32 changed = 0, retry = 0;
 	u32 hpd_event_bits;
 	u32 hpd_retry_bits;
 
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	drm_dbg_kms(&dev_priv->drm, "running encoder hotplug functions\n");
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -389,7 +389,7 @@ static void i915_hotplug_work_func(struct work_struct *work)
 
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		enum hpd_pin pin;
 		u32 hpd_bit;
@@ -426,10 +426,10 @@ static void i915_hotplug_work_func(struct work_struct *work)
 		}
 	}
 	drm_connector_list_iter_end(&conn_iter);
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
 	if (changed)
-		drm_kms_helper_hotplug_event(dev);
+		drm_kms_helper_hotplug_event(&dev_priv->drm);
 
 	/* Remove shared HPD pins that have changed */
 	retry &= ~changed;
@@ -612,16 +612,15 @@ static void i915_hpd_poll_init_work(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private,
 			     display.hotplug.poll_init_work);
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	bool enabled;
 
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 
 	enabled = READ_ONCE(dev_priv->display.hotplug.poll_enabled);
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		enum hpd_pin pin;
 
@@ -638,16 +637,16 @@ static void i915_hpd_poll_init_work(struct work_struct *work)
 	drm_connector_list_iter_end(&conn_iter);
 
 	if (enabled)
-		drm_kms_helper_poll_enable(dev);
+		drm_kms_helper_poll_enable(&dev_priv->drm);
 
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
 	/*
 	 * We might have missed any hotplugs that happened while we were
 	 * in the middle of disabling polling
 	 */
 	if (!enabled)
-		drm_helper_hpd_irq_event(dev);
+		drm_helper_hpd_irq_event(&dev_priv->drm);
 }
 
 /**
@@ -711,14 +710,23 @@ void intel_hpd_poll_disable(struct drm_i915_private *dev_priv)
 	schedule_work(&dev_priv->display.hotplug.poll_init_work);
 }
 
-void intel_hpd_init_work(struct drm_i915_private *dev_priv)
+void intel_hpd_init_early(struct drm_i915_private *i915)
 {
-	INIT_DELAYED_WORK(&dev_priv->display.hotplug.hotplug_work,
+	INIT_DELAYED_WORK(&i915->display.hotplug.hotplug_work,
 			  i915_hotplug_work_func);
-	INIT_WORK(&dev_priv->display.hotplug.dig_port_work, i915_digport_work_func);
-	INIT_WORK(&dev_priv->display.hotplug.poll_init_work, i915_hpd_poll_init_work);
-	INIT_DELAYED_WORK(&dev_priv->display.hotplug.reenable_work,
+	INIT_WORK(&i915->display.hotplug.dig_port_work, i915_digport_work_func);
+	INIT_WORK(&i915->display.hotplug.poll_init_work, i915_hpd_poll_init_work);
+	INIT_DELAYED_WORK(&i915->display.hotplug.reenable_work,
 			  intel_hpd_irq_storm_reenable_work);
+
+	i915->display.hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD;
+	/* If we have MST support, we want to avoid doing short HPD IRQ storm
+	 * detection, as short HPD storms will occur as a natural part of
+	 * sideband messaging with MST.
+	 * On older platforms however, IRQ storms can occur with both long and
+	 * short pulses, as seen on some G4x systems.
+	 */
+	i915->display.hotplug.hpd_short_storm_enabled = !HAS_DP_MST(i915);
 }
 
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv)
@@ -767,3 +775,169 @@ void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin)
 	dev_priv->display.hotplug.stats[pin].state = HPD_ENABLED;
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
+
+static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data)
+{
+	struct drm_i915_private *dev_priv = m->private;
+	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
+
+	/* Synchronize with everything first in case there's been an HPD
+	 * storm, but we haven't finished handling it in the kernel yet
+	 */
+	intel_synchronize_irq(dev_priv);
+	flush_work(&dev_priv->display.hotplug.dig_port_work);
+	flush_delayed_work(&dev_priv->display.hotplug.hotplug_work);
+
+	seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold);
+	seq_printf(m, "Detected: %s\n",
+		   str_yes_no(delayed_work_pending(&hotplug->reenable_work)));
+
+	return 0;
+}
+
+static ssize_t i915_hpd_storm_ctl_write(struct file *file,
+					const char __user *ubuf, size_t len,
+					loff_t *offp)
+{
+	struct seq_file *m = file->private_data;
+	struct drm_i915_private *dev_priv = m->private;
+	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
+	unsigned int new_threshold;
+	int i;
+	char *newline;
+	char tmp[16];
+
+	if (len >= sizeof(tmp))
+		return -EINVAL;
+
+	if (copy_from_user(tmp, ubuf, len))
+		return -EFAULT;
+
+	tmp[len] = '\0';
+
+	/* Strip newline, if any */
+	newline = strchr(tmp, '\n');
+	if (newline)
+		*newline = '\0';
+
+	if (strcmp(tmp, "reset") == 0)
+		new_threshold = HPD_STORM_DEFAULT_THRESHOLD;
+	else if (kstrtouint(tmp, 10, &new_threshold) != 0)
+		return -EINVAL;
+
+	if (new_threshold > 0)
+		drm_dbg_kms(&dev_priv->drm,
+			    "Setting HPD storm detection threshold to %d\n",
+			    new_threshold);
+	else
+		drm_dbg_kms(&dev_priv->drm, "Disabling HPD storm detection\n");
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	hotplug->hpd_storm_threshold = new_threshold;
+	/* Reset the HPD storm stats so we don't accidentally trigger a storm */
+	for_each_hpd_pin(i)
+		hotplug->stats[i].count = 0;
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/* Re-enable hpd immediately if we were in an irq storm */
+	flush_delayed_work(&dev_priv->display.hotplug.reenable_work);
+
+	return len;
+}
+
+static int i915_hpd_storm_ctl_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, i915_hpd_storm_ctl_show, inode->i_private);
+}
+
+static const struct file_operations i915_hpd_storm_ctl_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_hpd_storm_ctl_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.write = i915_hpd_storm_ctl_write
+};
+
+static int i915_hpd_short_storm_ctl_show(struct seq_file *m, void *data)
+{
+	struct drm_i915_private *dev_priv = m->private;
+
+	seq_printf(m, "Enabled: %s\n",
+		   str_yes_no(dev_priv->display.hotplug.hpd_short_storm_enabled));
+
+	return 0;
+}
+
+static int
+i915_hpd_short_storm_ctl_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, i915_hpd_short_storm_ctl_show,
+			   inode->i_private);
+}
+
+static ssize_t i915_hpd_short_storm_ctl_write(struct file *file,
+					      const char __user *ubuf,
+					      size_t len, loff_t *offp)
+{
+	struct seq_file *m = file->private_data;
+	struct drm_i915_private *dev_priv = m->private;
+	struct intel_hotplug *hotplug = &dev_priv->display.hotplug;
+	char *newline;
+	char tmp[16];
+	int i;
+	bool new_state;
+
+	if (len >= sizeof(tmp))
+		return -EINVAL;
+
+	if (copy_from_user(tmp, ubuf, len))
+		return -EFAULT;
+
+	tmp[len] = '\0';
+
+	/* Strip newline, if any */
+	newline = strchr(tmp, '\n');
+	if (newline)
+		*newline = '\0';
+
+	/* Reset to the "default" state for this system */
+	if (strcmp(tmp, "reset") == 0)
+		new_state = !HAS_DP_MST(dev_priv);
+	else if (kstrtobool(tmp, &new_state) != 0)
+		return -EINVAL;
+
+	drm_dbg_kms(&dev_priv->drm, "%sabling HPD short storm detection\n",
+		    new_state ? "En" : "Dis");
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	hotplug->hpd_short_storm_enabled = new_state;
+	/* Reset the HPD storm stats so we don't accidentally trigger a storm */
+	for_each_hpd_pin(i)
+		hotplug->stats[i].count = 0;
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/* Re-enable hpd immediately if we were in an irq storm */
+	flush_delayed_work(&dev_priv->display.hotplug.reenable_work);
+
+	return len;
+}
+
+static const struct file_operations i915_hpd_short_storm_ctl_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_hpd_short_storm_ctl_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.write = i915_hpd_short_storm_ctl_write,
+};
+
+void intel_hpd_debugfs_register(struct drm_i915_private *i915)
+{
+	struct drm_minor *minor = i915->drm.primary;
+
+	debugfs_create_file("i915_hpd_storm_ctl", 0644, minor->debugfs_root,
+			    i915, &i915_hpd_storm_ctl_fops);
+	debugfs_create_file("i915_hpd_short_storm_ctl", 0644, minor->debugfs_root,
+			    i915, &i915_hpd_short_storm_ctl_fops);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.h b/drivers/gpu/drm/i915/display/intel_hotplug.h
index b87e95d606e6..424ae5dbf5a0 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.h
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.h
@@ -22,11 +22,12 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask);
 void intel_hpd_trigger_irq(struct intel_digital_port *dig_port);
 void intel_hpd_init(struct drm_i915_private *dev_priv);
-void intel_hpd_init_work(struct drm_i915_private *dev_priv);
+void intel_hpd_init_early(struct drm_i915_private *i915);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
 enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 				   enum port port);
 bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
 void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
+void intel_hpd_debugfs_register(struct drm_i915_private *i915);
 
 #endif /* __INTEL_HOTPLUG_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
index dca6003ccac8..22ca8754ea96 100644
--- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
@@ -80,8 +80,7 @@
 static struct platform_device *
 lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
 	struct platform_device_info pinfo = {};
 	struct resource *rsc;
 	struct platform_device *platdev;
@@ -101,14 +100,14 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 	rsc[0].flags    = IORESOURCE_IRQ;
 	rsc[0].name     = "hdmi-lpe-audio-irq";
 
-	rsc[1].start    = pci_resource_start(pdev, GTTMMADR_BAR) +
+	rsc[1].start    = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) +
 		I915_HDMI_LPE_AUDIO_BASE;
-	rsc[1].end      = pci_resource_start(pdev, GTTMMADR_BAR) +
+	rsc[1].end      = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) +
 		I915_HDMI_LPE_AUDIO_BASE + I915_HDMI_LPE_AUDIO_SIZE - 1;
 	rsc[1].flags    = IORESOURCE_MEM;
 	rsc[1].name     = "hdmi-lpe-audio-mmio";
 
-	pinfo.parent = dev->dev;
+	pinfo.parent = dev_priv->drm.dev;
 	pinfo.name = "hdmi-lpe-audio";
 	pinfo.id = -1;
 	pinfo.res = rsc;
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 9aa38e8141b5..246787bbf5ef 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -78,9 +78,9 @@ struct intel_lvds_encoder {
 	struct intel_connector *attached_connector;
 };
 
-static struct intel_lvds_encoder *to_lvds_encoder(struct drm_encoder *encoder)
+static struct intel_lvds_encoder *to_lvds_encoder(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_lvds_encoder, base.base);
+	return container_of(encoder, struct intel_lvds_encoder, base);
 }
 
 bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv,
@@ -103,7 +103,7 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder);
 	intel_wakeref_t wakeref;
 	bool ret;
 
@@ -123,7 +123,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder);
 	u32 tmp, flags = 0;
 
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_LVDS);
@@ -229,7 +229,7 @@ static void intel_pre_enable_lvds(struct intel_atomic_state *state,
 				  const struct intel_crtc_state *pipe_config,
 				  const struct drm_connector_state *conn_state)
 {
-	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
@@ -312,7 +312,7 @@ static void intel_enable_lvds(struct intel_atomic_state *state,
 			      const struct drm_connector_state *conn_state)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder);
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_de_write(dev_priv, lvds_encoder->reg,
@@ -334,7 +334,7 @@ static void intel_disable_lvds(struct intel_atomic_state *state,
 			       const struct intel_crtc_state *old_crtc_state,
 			       const struct drm_connector_state *old_conn_state)
 {
-	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	intel_de_write(dev_priv, PP_CONTROL(0),
@@ -413,7 +413,7 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
 	struct intel_lvds_encoder *lvds_encoder =
-		to_lvds_encoder(&intel_encoder->base);
+		to_lvds_encoder(intel_encoder);
 	struct intel_connector *intel_connector =
 		lvds_encoder->attached_connector;
 	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
@@ -775,7 +775,7 @@ bool intel_is_dual_link_lvds(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder = intel_get_lvds_encoder(dev_priv);
 
-	return encoder && to_lvds_encoder(&encoder->base)->is_dual_link;
+	return encoder && to_lvds_encoder(encoder)->is_dual_link;
 }
 
 static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
@@ -814,6 +814,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
 	return (val & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP;
 }
 
+static void intel_lvds_add_properties(struct drm_connector *connector)
+{
+	intel_attach_scaling_mode_property(connector);
+}
+
 /**
  * intel_lvds_init - setup LVDS connectors on this device
  * @dev_priv: i915 device
@@ -823,7 +828,6 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
  */
 void intel_lvds_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_lvds_encoder *lvds_encoder;
 	struct intel_encoder *intel_encoder;
 	struct intel_connector *intel_connector;
@@ -833,11 +837,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	i915_reg_t lvds_reg;
 	u32 lvds;
 	u8 pin;
-	u32 allowed_scalers;
 
 	/* Skip init on machines we know falsely report LVDS */
 	if (dmi_check_system(intel_no_lvds)) {
-		drm_WARN(dev, !dev_priv->display.vbt.int_lvds_support,
+		drm_WARN(&dev_priv->drm, !dev_priv->display.vbt.int_lvds_support,
 			 "Useless DMI match. Internal LVDS support disabled by VBT\n");
 		return;
 	}
@@ -886,10 +889,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	intel_encoder = &lvds_encoder->base;
 	encoder = &intel_encoder->base;
 	connector = &intel_connector->base;
-	drm_connector_init(dev, &intel_connector->base, &intel_lvds_connector_funcs,
+	drm_connector_init(&dev_priv->drm, &intel_connector->base, &intel_lvds_connector_funcs,
 			   DRM_MODE_CONNECTOR_LVDS);
 
-	drm_encoder_init(dev, &intel_encoder->base, &intel_lvds_enc_funcs,
+	drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_lvds_enc_funcs,
 			 DRM_MODE_ENCODER_LVDS, "LVDS");
 
 	intel_encoder->enable = intel_enable_lvds;
@@ -920,17 +923,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 
 	drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
 
 	lvds_encoder->reg = lvds_reg;
 
-	/* create the scaling mode property */
-	allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT);
-	allowed_scalers |= BIT(DRM_MODE_SCALE_FULLSCREEN);
-	allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
-	drm_connector_attach_scaling_mode_property(connector, allowed_scalers);
-	connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT;
+	intel_lvds_add_properties(connector);
 
 	intel_lvds_pps_get_hw_state(dev_priv, &lvds_encoder->init_pps);
 	lvds_encoder->init_lvds_val = lvds;
@@ -947,7 +943,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	 * Attempt to get the fixed panel mode from DDC.  Assume that the
 	 * preferred mode is the right one.
 	 */
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	if (vga_switcheroo_handler_flags() & VGA_SWITCHEROO_CAN_SWITCH_DDC)
 		edid = drm_get_edid_switcheroo(connector,
 				    intel_gmbus_get_adapter(dev_priv, pin));
@@ -971,9 +967,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 			      IS_ERR(edid) ? NULL : edid);
 
 	/* Try EDID first */
-	intel_panel_add_edid_fixed_modes(intel_connector,
-					 intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE,
-					 false);
+	intel_panel_add_edid_fixed_modes(intel_connector, true);
 
 	/* Failed to get EDID, what about VBT? */
 	if (!intel_panel_preferred_fixed_mode(intel_connector))
@@ -987,7 +981,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	if (!intel_panel_preferred_fixed_mode(intel_connector))
 		intel_panel_add_encoder_fixed_mode(intel_connector, intel_encoder);
 
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
 	/* If we still don't have a mode after all that, give up. */
 	if (!intel_panel_preferred_fixed_mode(intel_connector))
diff --git a/drivers/gpu/drm/i915/display/intel_tc_phy_regs.h b/drivers/gpu/drm/i915/display/intel_mg_phy_regs.h
index 5a545086f959..07978f8d5fb7 100644
--- a/drivers/gpu/drm/i915/display/intel_tc_phy_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_mg_phy_regs.h
@@ -3,8 +3,8 @@
  * Copyright © 2022 Intel Corporation
  */
 
-#ifndef __INTEL_TC_PHY_REGS__
-#define __INTEL_TC_PHY_REGS__
+#ifndef __INTEL_MG_PHY_REGS__
+#define __INTEL_MG_PHY_REGS__
 
 #include "i915_reg_defs.h"
 
@@ -277,4 +277,4 @@
 						   _MG_PLL_TDC_COLDST_BIAS_PORT1, \
 						   _MG_PLL_TDC_COLDST_BIAS_PORT2)
 
-#endif /* __INTEL_TC_PHY_REGS__ */
+#endif /* __INTEL_MG_PHY_REGS__ */
diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
index cbfabd58b75a..9d8ca230be39 100644
--- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c
+++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
@@ -155,6 +155,12 @@ static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state
 	crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode;
 	crtc_state->uapi.scaling_filter = crtc_state->hw.scaling_filter;
 
+	/* assume 1:1 mapping */
+	drm_property_replace_blob(&crtc_state->hw.degamma_lut,
+				  crtc_state->pre_csc_lut);
+	drm_property_replace_blob(&crtc_state->hw.gamma_lut,
+				  crtc_state->post_csc_lut);
+
 	drm_property_replace_blob(&crtc_state->uapi.degamma_lut,
 				  crtc_state->hw.degamma_lut);
 	drm_property_replace_blob(&crtc_state->uapi.gamma_lut,
@@ -205,13 +211,21 @@ static bool intel_crtc_has_encoders(struct intel_crtc *crtc)
 
 static struct intel_connector *intel_encoder_find_connector(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
+	struct intel_connector *found_connector = NULL;
 
-	for_each_connector_on_encoder(dev, &encoder->base, connector)
-		return connector;
+	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
+	for_each_intel_connector_iter(connector, &conn_iter) {
+		if (&encoder->base == connector->base.encoder) {
+			found_connector = connector;
+			break;
+		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
 
-	return NULL;
+	return found_connector;
 }
 
 static void intel_sanitize_fifo_underrun_reporting(const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_modeset_verify.c b/drivers/gpu/drm/i915/display/intel_modeset_verify.c
index 0fdcf2e6d57f..842d70f0dfd2 100644
--- a/drivers/gpu/drm/i915/display/intel_modeset_verify.c
+++ b/drivers/gpu/drm/i915/display/intel_modeset_verify.c
@@ -227,7 +227,8 @@ void intel_modeset_verify_crtc(struct intel_crtc *crtc,
 			       struct intel_crtc_state *old_crtc_state,
 			       struct intel_crtc_state *new_crtc_state)
 {
-	if (!intel_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->update_pipe)
+	if (!intel_crtc_needs_modeset(new_crtc_state) &&
+	    !intel_crtc_needs_fastset(new_crtc_state))
 		return;
 
 	intel_wm_state_verify(crtc, new_crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index caa07ef34f21..e0184745632c 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -463,7 +463,6 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp)
 	struct intel_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct opregion_asle *asle = dev_priv->display.opregion.asle;
-	struct drm_device *dev = &dev_priv->drm;
 
 	drm_dbg(&dev_priv->drm, "bclp = 0x%08x\n", bclp);
 
@@ -480,7 +479,7 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp)
 	if (bclp > 255)
 		return ASLC_BACKLIGHT_FAILED;
 
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+	drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex, NULL);
 
 	/*
 	 * Update backlight on all connectors that support backlight (usually
@@ -488,13 +487,13 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp)
 	 */
 	drm_dbg_kms(&dev_priv->drm, "updating opregion backlight %d/255\n",
 		    bclp);
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter)
 		intel_backlight_set_acpi(connector->base.state, bclp, 255);
 	drm_connector_list_iter_end(&conn_iter);
 	asle->cblv = DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID;
 
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	drm_modeset_unlock(&dev_priv->drm.mode_config.connection_mutex);
 
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index a3a3f9fe4342..69ce77711b7c 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -85,9 +85,10 @@ static bool is_alt_drrs_mode(const struct drm_display_mode *mode,
 static bool is_alt_fixed_mode(const struct drm_display_mode *mode,
 			      const struct drm_display_mode *preferred_mode)
 {
-	return drm_mode_match(mode, preferred_mode,
-			      DRM_MODE_MATCH_FLAGS |
-			      DRM_MODE_MATCH_3D_FLAGS) &&
+	u32 sync_flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC |
+		DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC;
+
+	return (mode->flags & ~sync_flags) == (preferred_mode->flags & ~sync_flags) &&
 		mode->hdisplay == preferred_mode->hdisplay &&
 		mode->vdisplay == preferred_mode->vdisplay;
 }
@@ -147,12 +148,24 @@ int intel_panel_get_modes(struct intel_connector *connector)
 	return num_modes;
 }
 
-enum drrs_type intel_panel_drrs_type(struct intel_connector *connector)
+static bool has_drrs_modes(struct intel_connector *connector)
 {
-	if (list_empty(&connector->panel.fixed_modes) ||
-	    list_is_singular(&connector->panel.fixed_modes))
-		return DRRS_TYPE_NONE;
+	const struct drm_display_mode *mode1;
+
+	list_for_each_entry(mode1, &connector->panel.fixed_modes, head) {
+		const struct drm_display_mode *mode2 = mode1;
+
+		list_for_each_entry_continue(mode2, &connector->panel.fixed_modes, head) {
+			if (is_alt_drrs_mode(mode1, mode2))
+				return true;
+		}
+	}
+
+	return false;
+}
 
+enum drrs_type intel_panel_drrs_type(struct intel_connector *connector)
+{
 	return connector->panel.vbt.drrs_type;
 }
 
@@ -254,10 +267,10 @@ static void intel_panel_destroy_probed_modes(struct intel_connector *connector)
 }
 
 void intel_panel_add_edid_fixed_modes(struct intel_connector *connector,
-				      bool has_drrs, bool has_vrr)
+				      bool use_alt_fixed_modes)
 {
 	intel_panel_add_edid_preferred_mode(connector);
-	if (intel_panel_preferred_fixed_mode(connector) && (has_drrs || has_vrr))
+	if (intel_panel_preferred_fixed_mode(connector) && use_alt_fixed_modes)
 		intel_panel_add_edid_alt_fixed_modes(connector);
 	intel_panel_destroy_probed_modes(connector);
 }
@@ -653,6 +666,9 @@ int intel_panel_init(struct intel_connector *connector)
 
 	intel_backlight_init_funcs(panel);
 
+	if (!has_drrs_modes(connector))
+		connector->panel.vbt.drrs_type = DRRS_TYPE_NONE;
+
 	drm_dbg_kms(connector->base.dev,
 		    "[CONNECTOR:%d:%s] DRRS type: %s\n",
 		    connector->base.base.id, connector->base.name,
diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h
index eff3ffd3d082..5c5b5b7f95b6 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.h
+++ b/drivers/gpu/drm/i915/display/intel_panel.h
@@ -44,7 +44,7 @@ int intel_panel_fitting(struct intel_crtc_state *crtc_state,
 int intel_panel_compute_config(struct intel_connector *connector,
 			       struct drm_display_mode *adjusted_mode);
 void intel_panel_add_edid_fixed_modes(struct intel_connector *connector,
-				      bool has_drrs, bool has_vrr);
+				      bool use_alt_fixed_modes);
 void intel_panel_add_vbt_lfp_fixed_mode(struct intel_connector *connector);
 void intel_panel_add_vbt_sdvo_fixed_mode(struct intel_connector *connector);
 void intel_panel_add_encoder_fixed_mode(struct intel_connector *connector,
diff --git a/drivers/gpu/drm/i915/display/intel_pipe_crc.c b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
index 8ac263f471be..1c74388c60d7 100644
--- a/drivers/gpu/drm/i915/display/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
@@ -75,7 +75,6 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 				     enum pipe pipe,
 				     enum intel_pipe_crc_source *source)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *encoder;
 	struct intel_crtc *crtc;
 	struct intel_digital_port *dig_port;
@@ -83,8 +82,8 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 
 	*source = INTEL_PIPE_CRC_SOURCE_PIPE;
 
-	drm_modeset_lock_all(dev);
-	for_each_intel_encoder(dev, encoder) {
+	drm_modeset_lock_all(&dev_priv->drm);
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
 		if (!encoder->base.crtc)
 			continue;
 
@@ -111,7 +110,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 				*source = INTEL_PIPE_CRC_SOURCE_DP_D;
 				break;
 			default:
-				drm_WARN(dev, 1, "nonexisting DP port %c\n",
+				drm_WARN(&dev_priv->drm, 1, "nonexisting DP port %c\n",
 					 port_name(dig_port->base.port));
 				break;
 			}
@@ -120,7 +119,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 			break;
 		}
 	}
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index d4cce627d7a8..904a1049eff3 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -533,7 +533,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 
 	val |= psr_compute_idle_frames(intel_dp) << EDP_PSR2_IDLE_FRAME_SHIFT;
 
-	if (!IS_ALDERLAKE_P(dev_priv))
+	if (DISPLAY_VER(dev_priv) <= 13 && !IS_ALDERLAKE_P(dev_priv))
 		val |= EDP_SU_TRACK_ENABLE;
 
 	if (DISPLAY_VER(dev_priv) >= 10 && DISPLAY_VER(dev_priv) <= 12)
@@ -616,7 +616,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 static bool
 transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
 {
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14)
 		return trans == TRANSCODER_A || trans == TRANSCODER_B;
 	else if (DISPLAY_VER(dev_priv) >= 12)
 		return trans == TRANSCODER_A;
@@ -696,7 +696,7 @@ dc3co_is_pipe_port_compatible(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	enum port port = dig_port->base.port;
 
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14)
 		return pipe <= PIPE_B && port <= PORT_B;
 	else
 		return pipe == PIPE_A && port == PORT_A;
@@ -795,11 +795,11 @@ static bool psr2_granularity_check(struct intel_dp *intel_dp,
 		return intel_dp->psr.su_y_granularity == 4;
 
 	/*
-	 * adl_p has 1 line granularity. For other platforms with SW tracking we
-	 * can adjust the y coordinates to match sink requirement if multiple of
-	 * 4.
+	 * adl_p and display 14+ platforms has 1 line granularity.
+	 * For other platforms with SW tracking we can adjust the y coordinates
+	 * to match sink requirement if multiple of 4.
 	 */
-	if (IS_ALDERLAKE_P(dev_priv))
+	if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14)
 		y_granularity = intel_dp->psr.su_y_granularity;
 	else if (intel_dp->psr.su_y_granularity <= 2)
 		y_granularity = 4;
@@ -883,7 +883,8 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	 * resolution requires DSC to be enabled, priority is given to DSC
 	 * over PSR2.
 	 */
-	if (crtc_state->dsc.compression_enable) {
+	if (crtc_state->dsc.compression_enable &&
+	    (DISPLAY_VER(dev_priv) <= 13 && !IS_ALDERLAKE_P(dev_priv))) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "PSR2 cannot be enabled since DSC is enabled\n");
 		return false;
@@ -1474,7 +1475,7 @@ static u32 man_trk_ctl_enable_bit_get(struct drm_i915_private *dev_priv)
 
 static u32 man_trk_ctl_single_full_frame_bit_get(struct drm_i915_private *dev_priv)
 {
-	return IS_ALDERLAKE_P(dev_priv) ?
+	return IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14 ?
 	       ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME :
 	       PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
 }
@@ -1627,7 +1628,7 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
 	if (clip->y1 == -1)
 		goto exit;
 
-	if (IS_ALDERLAKE_P(dev_priv)) {
+	if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) {
 		val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1);
 		val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 - 1);
 	} else {
@@ -1664,7 +1665,15 @@ static void intel_psr2_sel_fetch_pipe_alignment(const struct intel_crtc_state *c
 						struct drm_rect *pipe_clip)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
-	const u16 y_alignment = crtc_state->su_y_granularity;
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	u16 y_alignment;
+
+	/* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */
+	if (crtc_state->dsc.compression_enable &&
+	    (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14))
+		y_alignment = vdsc_cfg->slice_height;
+	else
+		y_alignment = crtc_state->su_y_granularity;
 
 	pipe_clip->y1 -= pipe_clip->y1 % y_alignment;
 	if (pipe_clip->y2 % y_alignment)
@@ -2054,13 +2063,12 @@ static bool __psr_wait_for_idle_locked(struct intel_dp *intel_dp)
 static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 {
 	struct drm_connector_list_iter conn_iter;
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_modeset_acquire_ctx ctx;
 	struct drm_atomic_state *state;
 	struct drm_connector *conn;
 	int err = 0;
 
-	state = drm_atomic_state_alloc(dev);
+	state = drm_atomic_state_alloc(&dev_priv->drm);
 	if (!state)
 		return -ENOMEM;
 
@@ -2069,7 +2077,7 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 
 retry:
 
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
 	drm_for_each_connector_iter(conn, &conn_iter) {
 		struct drm_connector_state *conn_state;
 		struct drm_crtc_state *crtc_state;
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index f5b744bef18f..48b7b1aa37b2 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -199,7 +199,7 @@ to_intel_sdvo_connector(struct drm_connector *connector)
 	container_of((conn_state), struct intel_sdvo_connector_state, base.base)
 
 static bool
-intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags);
+intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo);
 static bool
 intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
 			      struct intel_sdvo_connector *intel_sdvo_connector,
@@ -1297,13 +1297,28 @@ static bool intel_sdvo_limited_color_range(struct intel_encoder *encoder,
 	return intel_hdmi_limited_color_range(crtc_state, conn_state);
 }
 
+static bool intel_sdvo_has_audio(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state)
+{
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
+	const struct intel_digital_connector_state *intel_conn_state =
+		to_intel_digital_connector_state(conn_state);
+
+	if (!crtc_state->has_hdmi_sink)
+		return false;
+
+	if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
+		return intel_sdvo->has_hdmi_audio;
+	else
+		return intel_conn_state->force_audio == HDMI_AUDIO_ON;
+}
+
 static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config,
 				     struct drm_connector_state *conn_state)
 {
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_sdvo_connector_state *intel_sdvo_state =
-		to_intel_sdvo_connector_state(conn_state);
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(conn_state->connector);
 	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
@@ -1362,13 +1377,7 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 
 	pipe_config->has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo, conn_state);
 
-	if (pipe_config->has_hdmi_sink) {
-		if (intel_sdvo_state->base.force_audio == HDMI_AUDIO_AUTO)
-			pipe_config->has_audio = intel_sdvo->has_hdmi_audio;
-		else
-			pipe_config->has_audio =
-				intel_sdvo_state->base.force_audio == HDMI_AUDIO_ON;
-	}
+	pipe_config->has_audio = intel_sdvo_has_audio(encoder, pipe_config, conn_state);
 
 	pipe_config->limited_color_range =
 		intel_sdvo_limited_color_range(encoder, pipe_config,
@@ -2290,17 +2299,12 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector)
 
 static int intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	int num_modes = 0;
 
 	drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s]\n",
 		    connector->base.id, connector->name);
 
-	num_modes += intel_panel_get_modes(to_intel_connector(connector));
-	num_modes += intel_ddc_get_modes(connector, &intel_sdvo->ddc);
-
-	return num_modes;
+	return intel_panel_get_modes(to_intel_connector(connector));
 }
 
 static int intel_sdvo_get_modes(struct drm_connector *connector)
@@ -2627,7 +2631,7 @@ intel_sdvo_unselect_i2c_bus(struct intel_sdvo *sdvo)
 }
 
 static bool
-intel_sdvo_is_hdmi_connector(struct intel_sdvo *intel_sdvo, int device)
+intel_sdvo_is_hdmi_connector(struct intel_sdvo *intel_sdvo)
 {
 	return intel_sdvo_check_supp_encode(intel_sdvo);
 }
@@ -2689,9 +2693,8 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 	drm_connector_helper_add(drm_connector,
 				 &intel_sdvo_connector_helper_funcs);
 
-	connector->base.base.interlace_allowed = 1;
-	connector->base.base.doublescan_allowed = 0;
 	connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB;
+	connector->base.base.interlace_allowed = true;
 	connector->base.get_hw_state = intel_sdvo_connector_get_hw_state;
 
 	intel_connector_attach_encoder(&connector->base, &encoder->base);
@@ -2733,7 +2736,7 @@ static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void)
 }
 
 static bool
-intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
+intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, u16 type)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_connector *connector;
@@ -2741,19 +2744,13 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
-	DRM_DEBUG_KMS("initialising DVI device %d\n", device);
+	DRM_DEBUG_KMS("initialising DVI type 0x%x\n", type);
 
 	intel_sdvo_connector = intel_sdvo_connector_alloc();
 	if (!intel_sdvo_connector)
 		return false;
 
-	if (device == 0) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS0;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0;
-	} else if (device == 1) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS1;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1;
-	}
+	intel_sdvo_connector->output_flag = type;
 
 	intel_connector = &intel_sdvo_connector->base;
 	connector = &intel_connector->base;
@@ -2773,7 +2770,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 	encoder->encoder_type = DRM_MODE_ENCODER_TMDS;
 	connector->connector_type = DRM_MODE_CONNECTOR_DVID;
 
-	if (intel_sdvo_is_hdmi_connector(intel_sdvo, device)) {
+	if (intel_sdvo_is_hdmi_connector(intel_sdvo)) {
 		connector->connector_type = DRM_MODE_CONNECTOR_HDMIA;
 		intel_sdvo_connector->is_hdmi = true;
 	}
@@ -2790,14 +2787,14 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 }
 
 static bool
-intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type)
+intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, u16 type)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_connector *connector;
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
-	DRM_DEBUG_KMS("initialising TV type %d\n", type);
+	DRM_DEBUG_KMS("initialising TV type 0x%x\n", type);
 
 	intel_sdvo_connector = intel_sdvo_connector_alloc();
 	if (!intel_sdvo_connector)
@@ -2808,7 +2805,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type)
 	encoder->encoder_type = DRM_MODE_ENCODER_TVDAC;
 	connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO;
 
-	intel_sdvo->controlled_output |= type;
 	intel_sdvo_connector->output_flag = type;
 
 	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
@@ -2830,14 +2826,14 @@ err:
 }
 
 static bool
-intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
+intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, u16 type)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_connector *connector;
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
-	DRM_DEBUG_KMS("initialising analog device %d\n", device);
+	DRM_DEBUG_KMS("initialising analog type 0x%x\n", type);
 
 	intel_sdvo_connector = intel_sdvo_connector_alloc();
 	if (!intel_sdvo_connector)
@@ -2849,13 +2845,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
 	encoder->encoder_type = DRM_MODE_ENCODER_DAC;
 	connector->connector_type = DRM_MODE_CONNECTOR_VGA;
 
-	if (device == 0) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB0;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0;
-	} else if (device == 1) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB1;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1;
-	}
+	intel_sdvo_connector->output_flag = type;
 
 	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
 		kfree(intel_sdvo_connector);
@@ -2866,7 +2856,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
 }
 
 static bool
-intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
+intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, u16 type)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_i915_private *i915 = to_i915(encoder->dev);
@@ -2874,7 +2864,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
-	DRM_DEBUG_KMS("initialising LVDS device %d\n", device);
+	DRM_DEBUG_KMS("initialising LVDS type 0x%x\n", type);
 
 	intel_sdvo_connector = intel_sdvo_connector_alloc();
 	if (!intel_sdvo_connector)
@@ -2885,13 +2875,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
 	encoder->encoder_type = DRM_MODE_ENCODER_LVDS;
 	connector->connector_type = DRM_MODE_CONNECTOR_LVDS;
 
-	if (device == 0) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS0;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0;
-	} else if (device == 1) {
-		intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS1;
-		intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1;
-	}
+	intel_sdvo_connector->output_flag = type;
 
 	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
 		kfree(intel_sdvo_connector);
@@ -2910,8 +2894,12 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
 	intel_panel_add_vbt_sdvo_fixed_mode(intel_connector);
 
 	if (!intel_panel_preferred_fixed_mode(intel_connector)) {
+		mutex_lock(&i915->drm.mode_config.mutex);
+
 		intel_ddc_get_modes(connector, &intel_sdvo->ddc);
-		intel_panel_add_edid_fixed_modes(intel_connector, false, false);
+		intel_panel_add_edid_fixed_modes(intel_connector, false);
+
+		mutex_unlock(&i915->drm.mode_config.mutex);
 	}
 
 	intel_panel_init(intel_connector);
@@ -2926,58 +2914,78 @@ err:
 	return false;
 }
 
-static bool
-intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
+static u16 intel_sdvo_filter_output_flags(u16 flags)
 {
+	flags &= SDVO_OUTPUT_MASK;
+
 	/* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/
+	if (!(flags & SDVO_OUTPUT_TMDS0))
+		flags &= ~SDVO_OUTPUT_TMDS1;
 
-	if (flags & SDVO_OUTPUT_TMDS0)
-		if (!intel_sdvo_dvi_init(intel_sdvo, 0))
-			return false;
+	if (!(flags & SDVO_OUTPUT_RGB0))
+		flags &= ~SDVO_OUTPUT_RGB1;
 
-	if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK)
-		if (!intel_sdvo_dvi_init(intel_sdvo, 1))
-			return false;
+	if (!(flags & SDVO_OUTPUT_LVDS0))
+		flags &= ~SDVO_OUTPUT_LVDS1;
 
-	/* TV has no XXX1 function block */
-	if (flags & SDVO_OUTPUT_SVID0)
-		if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_SVID0))
-			return false;
+	return flags;
+}
 
-	if (flags & SDVO_OUTPUT_CVBS0)
-		if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_CVBS0))
-			return false;
+static bool intel_sdvo_output_init(struct intel_sdvo *sdvo, u16 type)
+{
+	if (type & SDVO_TMDS_MASK)
+		return intel_sdvo_dvi_init(sdvo, type);
+	else if (type & SDVO_TV_MASK)
+		return intel_sdvo_tv_init(sdvo, type);
+	else if (type & SDVO_RGB_MASK)
+		return intel_sdvo_analog_init(sdvo, type);
+	else if (type & SDVO_LVDS_MASK)
+		return intel_sdvo_lvds_init(sdvo, type);
+	else
+		return false;
+}
 
-	if (flags & SDVO_OUTPUT_YPRPB0)
-		if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_YPRPB0))
-			return false;
+static bool
+intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo)
+{
+	static const u16 probe_order[] = {
+		SDVO_OUTPUT_TMDS0,
+		SDVO_OUTPUT_TMDS1,
+		/* TV has no XXX1 function block */
+		SDVO_OUTPUT_SVID0,
+		SDVO_OUTPUT_CVBS0,
+		SDVO_OUTPUT_YPRPB0,
+		SDVO_OUTPUT_RGB0,
+		SDVO_OUTPUT_RGB1,
+		SDVO_OUTPUT_LVDS0,
+		SDVO_OUTPUT_LVDS1,
+	};
+	struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev);
+	u16 flags;
+	int i;
 
-	if (flags & SDVO_OUTPUT_RGB0)
-		if (!intel_sdvo_analog_init(intel_sdvo, 0))
-			return false;
+	flags = intel_sdvo_filter_output_flags(intel_sdvo->caps.output_flags);
 
-	if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK)
-		if (!intel_sdvo_analog_init(intel_sdvo, 1))
-			return false;
+	if (flags == 0) {
+		DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%04x)\n",
+			      SDVO_NAME(intel_sdvo), intel_sdvo->caps.output_flags);
+		return false;
+	}
 
-	if (flags & SDVO_OUTPUT_LVDS0)
-		if (!intel_sdvo_lvds_init(intel_sdvo, 0))
-			return false;
+	intel_sdvo->controlled_output = flags;
 
-	if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK)
-		if (!intel_sdvo_lvds_init(intel_sdvo, 1))
-			return false;
+	intel_sdvo_select_ddc_bus(i915, intel_sdvo);
 
-	if ((flags & SDVO_OUTPUT_MASK) == 0) {
-		unsigned char bytes[2];
+	for (i = 0; i < ARRAY_SIZE(probe_order); i++) {
+		u16 type = flags & probe_order[i];
 
-		intel_sdvo->controlled_output = 0;
-		memcpy(bytes, &intel_sdvo->caps.output_flags, 2);
-		DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n",
-			      SDVO_NAME(intel_sdvo),
-			      bytes[0], bytes[1]);
-		return false;
+		if (!type)
+			continue;
+
+		if (!intel_sdvo_output_init(intel_sdvo, type))
+			return false;
 	}
+
 	intel_sdvo->base.pipe_mask = ~0;
 
 	return true;
@@ -3353,8 +3361,7 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 	intel_sdvo->colorimetry_cap =
 		intel_sdvo_get_colorimetry_cap(intel_sdvo);
 
-	if (intel_sdvo_output_setup(intel_sdvo,
-				    intel_sdvo->caps.output_flags) != true) {
+	if (!intel_sdvo_output_setup(intel_sdvo)) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "SDVO output failed to setup on %s\n",
 			    SDVO_NAME(intel_sdvo));
@@ -3383,8 +3390,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 	 */
 	intel_sdvo->base.cloneable = 0;
 
-	intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo);
-
 	/* Set the input timing to the screen. Assume always input 0. */
 	if (!intel_sdvo_set_target_input(intel_sdvo))
 		goto err_output;
@@ -3407,9 +3412,12 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 			(intel_sdvo->caps.sdvo_inputs_mask & 0x2) ? 'Y' : 'N',
 			/* check currently supported outputs */
 			intel_sdvo->caps.output_flags &
-			(SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_RGB0) ? 'Y' : 'N',
+			(SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_RGB0 |
+			 SDVO_OUTPUT_LVDS0 | SDVO_OUTPUT_SVID0 |
+			 SDVO_OUTPUT_CVBS0 | SDVO_OUTPUT_YPRPB0) ? 'Y' : 'N',
 			intel_sdvo->caps.output_flags &
-			(SDVO_OUTPUT_TMDS1 | SDVO_OUTPUT_RGB1) ? 'Y' : 'N');
+			(SDVO_OUTPUT_TMDS1 | SDVO_OUTPUT_RGB1 |
+			 SDVO_OUTPUT_LVDS1) ? 'Y' : 'N');
 	return true;
 
 err_output:
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index e5af955b5600..70624b4b2d38 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -8,9 +8,10 @@
 #include "intel_display.h"
 #include "intel_display_power_map.h"
 #include "intel_display_types.h"
+#include "intel_dkl_phy_regs.h"
 #include "intel_dp_mst.h"
+#include "intel_mg_phy_regs.h"
 #include "intel_tc.h"
-#include "intel_tc_phy_regs.h"
 
 static const char *tc_port_mode_name(enum tc_port_mode mode)
 {
@@ -408,14 +409,9 @@ static bool adl_tc_phy_take_ownership(struct intel_digital_port *dig_port,
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	struct intel_uncore *uncore = &i915->uncore;
 	enum port port = dig_port->base.port;
-	u32 val;
 
-	val = intel_uncore_read(uncore, DDI_BUF_CTL(port));
-	if (take)
-		val |= DDI_BUF_CTL_TC_PHY_OWNERSHIP;
-	else
-		val &= ~DDI_BUF_CTL_TC_PHY_OWNERSHIP;
-	intel_uncore_write(uncore, DDI_BUF_CTL(port), val);
+	intel_uncore_rmw(uncore, DDI_BUF_CTL(port), DDI_BUF_CTL_TC_PHY_OWNERSHIP,
+			 take ? DDI_BUF_CTL_TC_PHY_OWNERSHIP : 0);
 
 	return true;
 }
@@ -687,18 +683,58 @@ static void
 intel_tc_port_link_init_refcount(struct intel_digital_port *dig_port,
 				 int refcount)
 {
+	dig_port->tc_link_refcount = refcount;
+}
+
+/**
+ * intel_tc_port_init_mode: Read out HW state and init the given port's TypeC mode
+ * @dig_port: digital port
+ *
+ * Read out the HW state and initialize the TypeC mode of @dig_port. The mode
+ * will be locked until intel_tc_port_sanitize_mode() is called.
+ */
+void intel_tc_port_init_mode(struct intel_digital_port *dig_port)
+{
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	intel_wakeref_t tc_cold_wref;
+	enum intel_display_power_domain domain;
+
+	mutex_lock(&dig_port->tc_lock);
 
+	drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED);
+	drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref);
 	drm_WARN_ON(&i915->drm, dig_port->tc_link_refcount);
-	dig_port->tc_link_refcount = refcount;
+
+	tc_cold_wref = tc_cold_block(dig_port, &domain);
+
+	dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port);
+	/* Prevent changing dig_port->tc_mode until intel_tc_port_sanitize_mode() is called. */
+	intel_tc_port_link_init_refcount(dig_port, 1);
+	dig_port->tc_lock_wakeref = tc_cold_block(dig_port, &dig_port->tc_lock_power_domain);
+
+	tc_cold_unblock(dig_port, domain, tc_cold_wref);
+
+	drm_dbg_kms(&i915->drm, "Port %s: init mode (%s)\n",
+		    dig_port->tc_port_name,
+		    tc_port_mode_name(dig_port->tc_mode));
+
+	mutex_unlock(&dig_port->tc_lock);
 }
 
-void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
+/**
+ * intel_tc_port_sanitize_mode: Sanitize the given port's TypeC mode
+ * @dig_port: digital port
+ *
+ * Sanitize @dig_port's TypeC mode wrt. the encoder's state right after driver
+ * loading and system resume:
+ * If the encoder is enabled keep the TypeC mode/PHY connected state locked until
+ * the encoder is disabled.
+ * If the encoder is disabled make sure the PHY is disconnected.
+ */
+void intel_tc_port_sanitize_mode(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	struct intel_encoder *encoder = &dig_port->base;
-	intel_wakeref_t tc_cold_wref;
-	enum intel_display_power_domain domain;
 	int active_links = 0;
 
 	mutex_lock(&dig_port->tc_lock);
@@ -708,21 +744,14 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 	else if (encoder->base.crtc)
 		active_links = to_intel_crtc(encoder->base.crtc)->active;
 
-	drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED);
-	drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref);
-
-	tc_cold_wref = tc_cold_block(dig_port, &domain);
+	drm_WARN_ON(&i915->drm, dig_port->tc_link_refcount != 1);
+	intel_tc_port_link_init_refcount(dig_port, active_links);
 
-	dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port);
 	if (active_links) {
 		if (!icl_tc_phy_is_connected(dig_port))
 			drm_dbg_kms(&i915->drm,
 				    "Port %s: PHY disconnected with %d active link(s)\n",
 				    dig_port->tc_port_name, active_links);
-		intel_tc_port_link_init_refcount(dig_port, active_links);
-
-		dig_port->tc_lock_wakeref = tc_cold_block(dig_port,
-							  &dig_port->tc_lock_power_domain);
 	} else {
 		/*
 		 * TBT-alt is the default mode in any case the PHY ownership is not
@@ -736,9 +765,10 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 				    dig_port->tc_port_name,
 				    tc_port_mode_name(dig_port->tc_mode));
 		icl_tc_phy_disconnect(dig_port);
-	}
 
-	tc_cold_unblock(dig_port, domain, tc_cold_wref);
+		tc_cold_unblock(dig_port, dig_port->tc_lock_power_domain,
+				fetch_and_zero(&dig_port->tc_lock_wakeref));
+	}
 
 	drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n",
 		    dig_port->tc_port_name,
@@ -923,4 +953,6 @@ void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy)
 	dig_port->tc_mode = TC_PORT_DISCONNECTED;
 	dig_port->tc_link_refcount = 0;
 	tc_port_load_fia_params(i915, dig_port);
+
+	intel_tc_port_init_mode(dig_port);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 6b47b29f551c..d54082e2d5e8 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -24,7 +24,8 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port);
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes);
 
-void intel_tc_port_sanitize(struct intel_digital_port *dig_port);
+void intel_tc_port_init_mode(struct intel_digital_port *dig_port);
+void intel_tc_port_sanitize_mode(struct intel_digital_port *dig_port);
 void intel_tc_port_lock(struct intel_digital_port *dig_port);
 void intel_tc_port_unlock(struct intel_digital_port *dig_port);
 void intel_tc_port_flush_work(struct intel_digital_port *dig_port);
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index dcf89d701f0f..cf7d5c1ab406 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -1880,18 +1880,56 @@ static const struct drm_encoder_funcs intel_tv_enc_funcs = {
 	.destroy = intel_encoder_destroy,
 };
 
+static void intel_tv_add_properties(struct drm_connector *connector)
+{
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+	struct drm_connector_state *conn_state = connector->state;
+	const char *tv_format_names[ARRAY_SIZE(tv_modes)];
+	int i;
+
+	/* BIOS margin values */
+	conn_state->tv.margins.left = 54;
+	conn_state->tv.margins.top = 36;
+	conn_state->tv.margins.right = 46;
+	conn_state->tv.margins.bottom = 37;
+
+	conn_state->tv.mode = 0;
+
+	/* Create TV properties then attach current values */
+	for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
+		/* 1080p50/1080p60 not supported on gen3 */
+		if (DISPLAY_VER(i915) == 3 && tv_modes[i].oversample == 1)
+			break;
+
+		tv_format_names[i] = tv_modes[i].name;
+	}
+	drm_mode_create_tv_properties(&i915->drm, i, tv_format_names);
+
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tv_mode_property,
+				   conn_state->tv.mode);
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tv_left_margin_property,
+				   conn_state->tv.margins.left);
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tv_top_margin_property,
+				   conn_state->tv.margins.top);
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tv_right_margin_property,
+				   conn_state->tv.margins.right);
+	drm_object_attach_property(&connector->base,
+				   i915->drm.mode_config.tv_bottom_margin_property,
+				   conn_state->tv.margins.bottom);
+}
+
 void
 intel_tv_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct intel_tv *intel_tv;
 	struct intel_encoder *intel_encoder;
 	struct intel_connector *intel_connector;
 	u32 tv_dac_on, tv_dac_off, save_tv_dac;
-	const char *tv_format_names[ARRAY_SIZE(tv_modes)];
-	int i, initial_mode = 0;
-	struct drm_connector_state *state;
 
 	if ((intel_de_read(dev_priv, TV_CTL) & TV_FUSE_STATE_MASK) == TV_FUSE_STATE_DISABLED)
 		return;
@@ -1937,7 +1975,6 @@ intel_tv_init(struct drm_i915_private *dev_priv)
 
 	intel_encoder = &intel_tv->base;
 	connector = &intel_connector->base;
-	state = connector->state;
 
 	/*
 	 * The documentation, for the older chipsets at least, recommend
@@ -1951,10 +1988,10 @@ intel_tv_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
-	drm_connector_init(dev, connector, &intel_tv_connector_funcs,
+	drm_connector_init(&dev_priv->drm, connector, &intel_tv_connector_funcs,
 			   DRM_MODE_CONNECTOR_SVIDEO);
 
-	drm_encoder_init(dev, &intel_encoder->base, &intel_tv_enc_funcs,
+	drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_tv_enc_funcs,
 			 DRM_MODE_ENCODER_TVDAC, "TV");
 
 	intel_encoder->compute_config = intel_tv_compute_config;
@@ -1974,41 +2011,7 @@ intel_tv_init(struct drm_i915_private *dev_priv)
 	intel_encoder->cloneable = 0;
 	intel_tv->type = DRM_MODE_CONNECTOR_Unknown;
 
-	/* BIOS margin values */
-	state->tv.margins.left = 54;
-	state->tv.margins.top = 36;
-	state->tv.margins.right = 46;
-	state->tv.margins.bottom = 37;
-
-	state->tv.mode = initial_mode;
-
 	drm_connector_helper_add(connector, &intel_tv_connector_helper_funcs);
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
 
-	/* Create TV properties then attach current values */
-	for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
-		/* 1080p50/1080p60 not supported on gen3 */
-		if (DISPLAY_VER(dev_priv) == 3 &&
-		    tv_modes[i].oversample == 1)
-			break;
-
-		tv_format_names[i] = tv_modes[i].name;
-	}
-	drm_mode_create_tv_properties(dev, i, tv_format_names);
-
-	drm_object_attach_property(&connector->base, dev->mode_config.tv_mode_property,
-				   state->tv.mode);
-	drm_object_attach_property(&connector->base,
-				   dev->mode_config.tv_left_margin_property,
-				   state->tv.margins.left);
-	drm_object_attach_property(&connector->base,
-				   dev->mode_config.tv_top_margin_property,
-				   state->tv.margins.top);
-	drm_object_attach_property(&connector->base,
-				   dev->mode_config.tv_right_margin_property,
-				   state->tv.margins.right);
-	drm_object_attach_property(&connector->base,
-				   dev->mode_config.tv_bottom_margin_property,
-				   state->tv.margins.bottom);
+	intel_tv_add_properties(connector);
 }
diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index 18178b01375e..d58e667016e4 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -1706,26 +1706,10 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED ||
-		      modifier == I915_FORMAT_MOD_4_TILED ||
-		      modifier == I915_FORMAT_MOD_Yf_TILED ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
-		      modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
-		      modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS ||
-		      modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
-	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
-			 modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
-			 modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS ||
-			 modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC;
+	wp->y_tiled = modifier != I915_FORMAT_MOD_X_TILED &&
+		intel_fb_is_tiled_modifier(modifier);
+	wp->rc_surface = intel_fb_is_ccs_modifier(modifier);
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;
@@ -2498,7 +2482,7 @@ skl_compute_ddb(struct intel_atomic_state *state)
 
 		if (old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) {
 			/* TODO: Implement vblank synchronized MBUS joining changes */
-			ret = intel_modeset_all_pipes(state);
+			ret = intel_modeset_all_pipes(state, "MBUS joining change");
 			if (ret)
 				return ret;
 		}
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index b3f5ca280ef2..5a741ea4505f 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1659,19 +1659,10 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = {
 
 static void vlv_dsi_add_properties(struct intel_connector *connector)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_preferred_fixed_mode(connector);
-	u32 allowed_scalers;
 
-	allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
-	if (!HAS_GMCH(dev_priv))
-		allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
-
-	drm_connector_attach_scaling_mode_property(&connector->base,
-						   allowed_scalers);
-
-	connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT;
+	intel_attach_scaling_mode_property(&connector->base);
 
 	drm_connector_set_panel_orientation_with_quirk(&connector->base,
 						       intel_dsi_get_panel_orientation(connector),
@@ -1854,7 +1845,6 @@ static void vlv_dphy_param_init(struct intel_dsi *intel_dsi)
 
 void vlv_dsi_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_dsi *intel_dsi;
 	struct intel_encoder *intel_encoder;
 	struct drm_encoder *encoder;
@@ -1891,7 +1881,7 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 
 	connector = &intel_connector->base;
 
-	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI,
+	drm_encoder_init(&dev_priv->drm, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI,
 			 "DSI %c", port_name(port));
 
 	intel_encoder->compute_config = intel_dsi_compute_config;
@@ -1974,20 +1964,18 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	intel_dsi_vbt_gpio_init(intel_dsi,
 				intel_dsi_get_hw_state(intel_encoder, &pipe));
 
-	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
+	drm_connector_init(&dev_priv->drm, connector, &intel_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 
 	drm_connector_helper_add(connector, &intel_dsi_connector_helper_funcs);
 
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB; /*XXX*/
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 
-	mutex_lock(&dev->mode_config.mutex);
+	mutex_lock(&dev_priv->drm.mode_config.mutex);
 	intel_panel_add_vbt_lfp_fixed_mode(intel_connector);
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev_priv->drm.mode_config.mutex);
 
 	if (!intel_panel_preferred_fixed_mode(intel_connector)) {
 		drm_dbg_kms(&dev_priv->drm, "no fixed mode\n");
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 0512afdd20d8..b3b398fe689c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -113,7 +113,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 		clflush = clflush_work_create(obj);
 	if (clflush) {
 		i915_sw_fence_await_reservation(&clflush->base.chain,
-						obj->base.resv, NULL, true,
+						obj->base.resv, true,
 						i915_fence_timeout(i915),
 						I915_FENCE_GFP);
 		dma_resv_add_fence(obj->base.resv, &clflush->base.dma,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1e29b1e6d186..01402f3c58f6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1452,7 +1452,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 		int err;
 
 		/* serialises with execbuf */
-		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
+		intel_context_close(ce);
 		if (!intel_context_pin_if_active(ce))
 			continue;
 
@@ -2298,7 +2298,6 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	}
 
 	args->ctx_id = id;
-	drm_dbg(&i915->drm, "HW context %d created\n", args->ctx_id);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 07eee1c09aaf..ec6f7ae47783 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -25,43 +25,44 @@ static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
 	return to_intel_bo(buf->priv);
 }
 
-static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment,
+static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attach,
 					     enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
-	struct sg_table *st;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attach->dmabuf);
+	struct sg_table *sgt;
 	struct scatterlist *src, *dst;
 	int ret, i;
 
-	/* Copy sg so that we make an independent mapping */
-	st = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
-	if (st == NULL) {
+	/*
+	 * Make a copy of the object's sgt, so that we can make an independent
+	 * mapping
+	 */
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL);
+	ret = sg_alloc_table(sgt, obj->mm.pages->orig_nents, GFP_KERNEL);
 	if (ret)
 		goto err_free;
 
-	src = obj->mm.pages->sgl;
-	dst = st->sgl;
-	for (i = 0; i < obj->mm.pages->nents; i++) {
+	dst = sgt->sgl;
+	for_each_sg(obj->mm.pages->sgl, src, obj->mm.pages->orig_nents, i) {
 		sg_set_page(dst, sg_page(src), src->length, 0);
 		dst = sg_next(dst);
-		src = sg_next(src);
 	}
 
-	ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC);
+	ret = dma_map_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC);
 	if (ret)
 		goto err_free_sg;
 
-	return st;
+	return sgt;
 
 err_free_sg:
-	sg_free_table(st);
+	sg_free_table(sgt);
 err_free:
-	kfree(st);
+	kfree(sgt);
 err:
 	return ERR_PTR(ret);
 }
@@ -236,15 +237,15 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct sg_table *pages;
+	struct sg_table *sgt;
 	unsigned int sg_page_sizes;
 
 	assert_object_held(obj);
 
-	pages = dma_buf_map_attachment(obj->base.import_attach,
-				       DMA_BIDIRECTIONAL);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
+	sgt = dma_buf_map_attachment(obj->base.import_attach,
+				     DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt))
+		return PTR_ERR(sgt);
 
 	/*
 	 * DG1 is special here since it still snoops transactions even with
@@ -261,16 +262,16 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	    (!HAS_LLC(i915) && !IS_DG1(i915)))
 		wbinvd_on_all_cpus();
 
-	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);
-	__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
+	sg_page_sizes = i915_sg_dma_sizes(sgt->sgl);
+	__i915_gem_object_set_pages(obj, sgt, sg_page_sizes);
 
 	return 0;
 }
 
 static void i915_gem_object_put_pages_dmabuf(struct drm_i915_gem_object *obj,
-					     struct sg_table *pages)
+					     struct sg_table *sgt)
 {
-	dma_buf_unmap_attachment(obj->base.import_attach, pages,
+	dma_buf_unmap_attachment(obj->base.import_attach, sgt,
 				 DMA_BIDIRECTIONAL);
 }
 
@@ -313,7 +314,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	get_dma_buf(dma_buf);
 
 	obj = i915_gem_object_alloc();
-	if (obj == NULL) {
+	if (!obj) {
 		ret = -ENOMEM;
 		goto fail_detach;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 845023c14eb3..1160723c9d2d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2954,11 +2954,6 @@ await_fence_array(struct i915_execbuffer *eb,
 	int err;
 
 	for (n = 0; n < eb->num_fences; n++) {
-		struct drm_syncobj *syncobj;
-		unsigned int flags;
-
-		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
-
 		if (!eb->fences[n].dma_fence)
 			continue;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index c698f95af15f..629acb403a2c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -6,7 +6,6 @@
 
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
-#include <linux/swiotlb.h>
 
 #include "i915_drv.h"
 #include "i915_gem.h"
@@ -38,22 +37,12 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 	struct scatterlist *sg;
 	unsigned int sg_page_sizes;
 	unsigned int npages;
-	int max_order;
+	int max_order = MAX_ORDER;
+	unsigned int max_segment;
 	gfp_t gfp;
 
-	max_order = MAX_ORDER;
-#ifdef CONFIG_SWIOTLB
-	if (is_swiotlb_active(obj->base.dev->dev)) {
-		unsigned int max_segment;
-
-		max_segment = swiotlb_max_segment();
-		if (max_segment) {
-			max_segment = max_t(unsigned int, max_segment,
-					    PAGE_SIZE) >> PAGE_SHIFT;
-			max_order = min(max_order, ilog2(max_segment));
-		}
-	}
-#endif
+	max_segment = i915_sg_segment_size(i915->drm.dev) >> PAGE_SHIFT;
+	max_order = min(max_order, get_order(max_segment));
 
 	gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
 	if (IS_I965GM(i915) || IS_I965G(i915)) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 73d9eda1d6b7..e63329bc8065 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -413,7 +413,7 @@ retry:
 	vma->mmo = mmo;
 
 	if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)
-		intel_wakeref_auto(&to_gt(i915)->userfault_wakeref,
+		intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
 	if (write) {
@@ -557,11 +557,13 @@ void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *
 
 	drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping);
 
-	if (obj->userfault_count) {
-		/* rpm wakeref provide exclusive access */
-		list_del(&obj->userfault_link);
-		obj->userfault_count = 0;
-	}
+	/*
+	 * We have exclusive access here via runtime suspend. All other callers
+	 * must first grab the rpm wakeref.
+	 */
+	GEM_BUG_ON(!obj->userfault_count);
+	list_del(&obj->userfault_link);
+	obj->userfault_count = 0;
 }
 
 void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
@@ -587,13 +589,6 @@ void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
 		spin_lock(&obj->mmo.lock);
 	}
 	spin_unlock(&obj->mmo.lock);
-
-	if (obj->userfault_count) {
-		mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
-		list_del(&obj->userfault_link);
-		mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
-		obj->userfault_count = 0;
-	}
 }
 
 static struct i915_mmap_offset *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 6b8710ba8ded..733696057761 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -458,6 +458,16 @@ i915_gem_object_read_from_page_iomap(struct drm_i915_gem_object *obj, u64 offset
 	io_mapping_unmap(src_map);
 }
 
+static bool object_has_mappable_iomem(struct drm_i915_gem_object *obj)
+{
+	GEM_BUG_ON(!i915_gem_object_has_iomem(obj));
+
+	if (IS_DGFX(to_i915(obj->base.dev)))
+		return i915_ttm_resource_mappable(i915_gem_to_ttm(obj)->resource);
+
+	return true;
+}
+
 /**
  * i915_gem_object_read_from_page - read data from the page of a GEM object
  * @obj: GEM object to read from
@@ -480,7 +490,7 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset,
 
 	if (i915_gem_object_has_struct_page(obj))
 		i915_gem_object_read_from_page_kmap(obj, offset, dst, size);
-	else if (i915_gem_object_has_iomem(obj))
+	else if (i915_gem_object_has_iomem(obj) && object_has_mappable_iomem(obj))
 		i915_gem_object_read_from_page_iomap(obj, offset, dst, size);
 	else
 		return -ENODEV;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 1723af9b0f6a..6b9ecff42bb5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -482,6 +482,10 @@ void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 void *__must_check i915_gem_object_pin_map_unlocked(struct drm_i915_gem_object *obj,
 						    enum i915_map_type type);
 
+enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915,
+					  struct drm_i915_gem_object *obj,
+					  bool always_coherent);
+
 void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj,
 				 unsigned long offset,
 				 unsigned long size);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 4df50b049cea..16f845663ff2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -466,6 +466,18 @@ void *i915_gem_object_pin_map_unlocked(struct drm_i915_gem_object *obj,
 	return ret;
 }
 
+enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915,
+					  struct drm_i915_gem_object *obj,
+					  bool always_coherent)
+{
+	if (i915_gem_object_is_lmem(obj))
+		return I915_MAP_WC;
+	if (HAS_LLC(i915) || always_coherent)
+		return I915_MAP_WB;
+	else
+		return I915_MAP_WC;
+}
+
 void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj,
 				 unsigned long offset,
 				 unsigned long size)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 3428f735e786..0d812f4d787d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -22,9 +22,12 @@
 
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
+	struct intel_gt *gt;
+	unsigned int i;
+
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
-	intel_wakeref_auto(&to_gt(i915)->userfault_wakeref, 0);
+	intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
 
 	/*
@@ -36,7 +39,8 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	intel_gt_suspend_prepare(to_gt(i915));
+	for_each_gt(gt, i915, i)
+		intel_gt_suspend_prepare(gt);
 
 	i915_gem_drain_freed_objects(i915);
 }
@@ -131,7 +135,9 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 		&i915->mm.purge_list,
 		NULL
 	}, **phase;
+	struct intel_gt *gt;
 	unsigned long flags;
+	unsigned int i;
 	bool flush = false;
 
 	/*
@@ -154,7 +160,8 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 	 * machine in an unusable condition.
 	 */
 
-	intel_gt_suspend_late(to_gt(i915));
+	for_each_gt(gt, i915, i)
+		intel_gt_suspend_late(gt);
 
 	spin_lock_irqsave(&i915->mm.obj_lock, flags);
 	for (phase = phases; *phase; phase++) {
@@ -212,7 +219,8 @@ int i915_gem_freeze_late(struct drm_i915_private *i915)
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
-	int ret;
+	struct intel_gt *gt;
+	int ret, i, j;
 
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
@@ -224,8 +232,25 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	 * guarantee that the context image is complete. So let's just reset
 	 * it and start again.
 	 */
-	intel_gt_resume(to_gt(i915));
+	for_each_gt(gt, i915, i)
+		if (intel_gt_resume(gt))
+			goto err_wedged;
 
 	ret = lmem_restore(i915, I915_TTM_BACKUP_ALLOW_GPU);
 	GEM_WARN_ON(ret);
+
+	return;
+
+err_wedged:
+	for_each_gt(gt, i915, j) {
+		if (!intel_gt_is_wedged(gt)) {
+			dev_err(i915->drm.dev,
+				"Failed to re-initialize GPU[%u], declaring it wedged!\n",
+				j);
+			intel_gt_set_wedged(gt);
+		}
+
+		if (j == i)
+			break;
+	}
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index f42ca1179f37..2f7804492cd5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -194,7 +194,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	struct intel_memory_region *mem = obj->mm.region;
 	struct address_space *mapping = obj->base.filp->f_mapping;
 	const unsigned long page_count = obj->base.size / PAGE_SIZE;
-	unsigned int max_segment = i915_sg_segment_size();
+	unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
 	struct sg_table *st;
 	struct sgt_iter sgt_iter;
 	struct page *page;
@@ -369,14 +369,14 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
 
 	__start_cpu_write(obj);
 	/*
-	 * On non-LLC platforms, force the flush-on-acquire if this is ever
+	 * On non-LLC igfx platforms, force the flush-on-acquire if this is ever
 	 * swapped-in. Our async flush path is not trust worthy enough yet(and
 	 * happens in the wrong order), and with some tricks it's conceivable
 	 * for userspace to change the cache-level to I915_CACHE_NONE after the
 	 * pages are swapped-in, and since execbuf binds the object before doing
 	 * the async flush, we have a race window.
 	 */
-	if (!HAS_LLC(i915))
+	if (!HAS_LLC(i915) && !IS_DGFX(i915))
 		obj->cache_dirty = true;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index acc561c0f0aa..0c70711818ed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -77,22 +77,26 @@ void i915_gem_stolen_remove_node(struct drm_i915_private *i915,
 	mutex_unlock(&i915->mm.stolen_lock);
 }
 
-static int i915_adjust_stolen(struct drm_i915_private *i915,
-			      struct resource *dsm)
+static bool valid_stolen_size(struct drm_i915_private *i915, struct resource *dsm)
+{
+	return (dsm->start != 0 || HAS_LMEMBAR_SMEM_STOLEN(i915)) && dsm->end > dsm->start;
+}
+
+static int adjust_stolen(struct drm_i915_private *i915,
+			 struct resource *dsm)
 {
 	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
 	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
-	struct resource *r;
 
-	if (dsm->start == 0 || dsm->end <= dsm->start)
+	if (!valid_stolen_size(i915, dsm))
 		return -EINVAL;
 
 	/*
+	 * Make sure we don't clobber the GTT if it's within stolen memory
+	 *
 	 * TODO: We have yet too encounter the case where the GTT wasn't at the
 	 * end of stolen. With that assumption we could simplify this.
 	 */
-
-	/* Make sure we don't clobber the GTT if it's within stolen memory */
 	if (GRAPHICS_VER(i915) <= 4 &&
 	    !IS_G33(i915) && !IS_PINEVIEW(i915) && !IS_G4X(i915)) {
 		struct resource stolen[2] = {*dsm, *dsm};
@@ -131,12 +135,25 @@ static int i915_adjust_stolen(struct drm_i915_private *i915,
 		}
 	}
 
+	if (!valid_stolen_size(i915, dsm))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int request_smem_stolen(struct drm_i915_private *i915,
+			       struct resource *dsm)
+{
+	struct resource *r;
+
 	/*
-	 * With stolen lmem, we don't need to check if the address range
-	 * overlaps with the non-stolen system memory range, since lmem is local
-	 * to the gpu.
+	 * With stolen lmem, we don't need to request system memory for the
+	 * address range since it's local to the gpu.
+	 *
+	 * Starting MTL, in IGFX devices the stolen memory is exposed via
+	 * LMEMBAR and shall be considered similar to stolen lmem.
 	 */
-	if (HAS_LMEM(i915))
+	if (HAS_LMEM(i915) || HAS_LMEMBAR_SMEM_STOLEN(i915))
 		return 0;
 
 	/*
@@ -371,8 +388,6 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 
 	drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
 
-	*base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
-
 	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
 	case GEN8_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
@@ -390,41 +405,30 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 		*size = 8 * 1024 * 1024;
 		MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK);
 	}
+
+	if (HAS_LMEMBAR_SMEM_STOLEN(i915))
+		/* the base is initialized to stolen top so subtract size to get base */
+		*base -= *size;
+	else
+		*base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
 }
 
-static int i915_gem_init_stolen(struct intel_memory_region *mem)
+/*
+ * Initialize i915->dsm_reserved to contain the reserved space within the Data
+ * Stolen Memory. This is a range on the top of DSM that is reserved, not to
+ * be used by driver, so must be excluded from the region passed to the
+ * allocator later. In the spec this is also called as WOPCM.
+ *
+ * Our expectation is that the reserved space is at the top of the stolen
+ * region, as it has been the case for every platform, and *never* at the
+ * bottom, so the calculation here can be simplified.
+ */
+static int init_reserved_stolen(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *i915 = mem->i915;
 	struct intel_uncore *uncore = &i915->uncore;
 	resource_size_t reserved_base, stolen_top;
-	resource_size_t reserved_total, reserved_size;
-
-	mutex_init(&i915->mm.stolen_lock);
-
-	if (intel_vgpu_active(i915)) {
-		drm_notice(&i915->drm,
-			   "%s, disabling use of stolen memory\n",
-			   "iGVT-g active");
-		return 0;
-	}
-
-	if (i915_vtd_active(i915) && GRAPHICS_VER(i915) < 8) {
-		drm_notice(&i915->drm,
-			   "%s, disabling use of stolen memory\n",
-			   "DMAR active");
-		return 0;
-	}
-
-	if (resource_size(&mem->region) == 0)
-		return 0;
-
-	i915->dsm = mem->region;
-
-	if (i915_adjust_stolen(i915, &i915->dsm))
-		return 0;
-
-	GEM_BUG_ON(i915->dsm.start == 0);
-	GEM_BUG_ON(i915->dsm.end <= i915->dsm.start);
+	resource_size_t reserved_size;
+	int ret = 0;
 
 	stolen_top = i915->dsm.end + 1;
 	reserved_base = stolen_top;
@@ -455,17 +459,16 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 					&reserved_base, &reserved_size);
 	}
 
-	/*
-	 * Our expectation is that the reserved space is at the top of the
-	 * stolen region and *never* at the bottom. If we see !reserved_base,
-	 * it likely means we failed to read the registers correctly.
-	 */
+	/* No reserved stolen */
+	if (reserved_base == stolen_top)
+		goto bail_out;
+
 	if (!reserved_base) {
 		drm_err(&i915->drm,
 			"inconsistent reservation %pa + %pa; ignoring\n",
 			&reserved_base, &reserved_size);
-		reserved_base = stolen_top;
-		reserved_size = 0;
+		ret = -EINVAL;
+		goto bail_out;
 	}
 
 	i915->dsm_reserved =
@@ -475,19 +478,55 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 		drm_err(&i915->drm,
 			"Stolen reserved area %pR outside stolen memory %pR\n",
 			&i915->dsm_reserved, &i915->dsm);
-		return 0;
+		ret = -EINVAL;
+		goto bail_out;
 	}
 
+	return 0;
+
+bail_out:
+	i915->dsm_reserved =
+		(struct resource)DEFINE_RES_MEM(reserved_base, 0);
+
+	return ret;
+}
+
+static int i915_gem_init_stolen(struct intel_memory_region *mem)
+{
+	struct drm_i915_private *i915 = mem->i915;
+
+	mutex_init(&i915->mm.stolen_lock);
+
+	if (intel_vgpu_active(i915)) {
+		drm_notice(&i915->drm,
+			   "%s, disabling use of stolen memory\n",
+			   "iGVT-g active");
+		return -ENOSPC;
+	}
+
+	if (i915_vtd_active(i915) && GRAPHICS_VER(i915) < 8) {
+		drm_notice(&i915->drm,
+			   "%s, disabling use of stolen memory\n",
+			   "DMAR active");
+		return -ENOSPC;
+	}
+
+	if (adjust_stolen(i915, &mem->region))
+		return -ENOSPC;
+
+	if (request_smem_stolen(i915, &mem->region))
+		return -ENOSPC;
+
+	i915->dsm = mem->region;
+
+	if (init_reserved_stolen(i915))
+		return -ENOSPC;
+
 	/* Exclude the reserved region from driver use */
-	mem->region.end = reserved_base - 1;
+	mem->region.end = i915->dsm_reserved.start - 1;
 	mem->io_size = min(mem->io_size, resource_size(&mem->region));
 
-	/* It is possible for the reserved area to end before the end of stolen
-	 * memory, so just consider the start. */
-	reserved_total = stolen_top - reserved_base;
-
-	i915->stolen_usable_size =
-		resource_size(&i915->dsm) - reserved_total;
+	i915->stolen_usable_size = resource_size(&mem->region);
 
 	drm_dbg(&i915->drm,
 		"Memory reserved for graphics device: %lluK, usable: %lluK\n",
@@ -495,7 +534,7 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 		(u64)i915->stolen_usable_size >> 10);
 
 	if (i915->stolen_usable_size == 0)
-		return 0;
+		return -ENOSPC;
 
 	/* Basic memrange allocator for stolen space. */
 	drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size);
@@ -733,11 +772,17 @@ i915_gem_object_create_stolen(struct drm_i915_private *i915,
 
 static int init_stolen_smem(struct intel_memory_region *mem)
 {
+	int err;
+
 	/*
 	 * Initialise stolen early so that we may reserve preallocated
 	 * objects for the BIOS to KMS transition.
 	 */
-	return i915_gem_init_stolen(mem);
+	err = i915_gem_init_stolen(mem);
+	if (err)
+		drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n");
+
+	return 0;
 }
 
 static int release_stolen_smem(struct intel_memory_region *mem)
@@ -754,26 +799,25 @@ static const struct intel_memory_region_ops i915_region_stolen_smem_ops = {
 
 static int init_stolen_lmem(struct intel_memory_region *mem)
 {
+	struct drm_i915_private *i915 = mem->i915;
 	int err;
 
 	if (GEM_WARN_ON(resource_size(&mem->region) == 0))
-		return -ENODEV;
+		return 0;
 
-	/*
-	 * TODO: For stolen lmem we mostly just care about populating the dsm
-	 * related bits and setting up the drm_mm allocator for the range.
-	 * Perhaps split up i915_gem_init_stolen() for this.
-	 */
 	err = i915_gem_init_stolen(mem);
-	if (err)
-		return err;
+	if (err) {
+		drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n");
+		return 0;
+	}
 
-	if (mem->io_size && !io_mapping_init_wc(&mem->iomap,
-						mem->io_start,
-						mem->io_size)) {
-		err = -EIO;
+	if (mem->io_size &&
+	    !io_mapping_init_wc(&mem->iomap, mem->io_start, mem->io_size))
 		goto err_cleanup;
-	}
+
+	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
+		&mem->io_start);
+	drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &mem->region.start);
 
 	return 0;
 
@@ -796,6 +840,29 @@ static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = {
 	.init_object = _i915_gem_object_stolen_init,
 };
 
+static int mtl_get_gms_size(struct intel_uncore *uncore)
+{
+	u16 ggc, gms;
+
+	ggc = intel_uncore_read16(uncore, GGC);
+
+	/* check GGMS, should be fixed 0x3 (8MB) */
+	if ((ggc & GGMS_MASK) != GGMS_MASK)
+		return -EIO;
+
+	/* return valid GMS value, -EIO if invalid */
+	gms = REG_FIELD_GET(GMS_MASK, ggc);
+	switch (gms) {
+	case 0x0 ... 0x04:
+		return gms * 32;
+	case 0xf0 ... 0xfe:
+		return (gms - 0xf0 + 1) * 4;
+	default:
+		MISSING_CASE(gms);
+		return -EIO;
+	}
+}
+
 struct intel_memory_region *
 i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 			   u16 instance)
@@ -806,6 +873,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 	struct intel_memory_region *mem;
 	resource_size_t io_start, io_size;
 	resource_size_t min_page_size;
+	int ret;
 
 	if (WARN_ON_ONCE(instance))
 		return ERR_PTR(-ENODEV);
@@ -813,12 +881,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 	if (!i915_pci_resource_valid(pdev, GEN12_LMEM_BAR))
 		return ERR_PTR(-ENXIO);
 
-	/* Use DSM base address instead for stolen memory */
-	dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE);
-	if (IS_DG1(uncore->i915)) {
+	if (HAS_LMEMBAR_SMEM_STOLEN(i915) || IS_DG1(i915)) {
 		lmem_size = pci_resource_len(pdev, GEN12_LMEM_BAR);
-		if (WARN_ON(lmem_size < dsm_base))
-			return ERR_PTR(-ENODEV);
 	} else {
 		resource_size_t lmem_range;
 
@@ -827,13 +891,39 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 		lmem_size *= SZ_1G;
 	}
 
-	dsm_size = lmem_size - dsm_base;
-	if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
+	if (HAS_LMEMBAR_SMEM_STOLEN(i915)) {
+		/*
+		 * MTL dsm size is in GGC register.
+		 * Also MTL uses offset to DSMBASE in ptes, so i915
+		 * uses dsm_base = 0 to setup stolen region.
+		 */
+		ret = mtl_get_gms_size(uncore);
+		if (ret < 0) {
+			drm_err(&i915->drm, "invalid MTL GGC register setting\n");
+			return ERR_PTR(ret);
+		}
+
+		dsm_base = 0;
+		dsm_size = (resource_size_t)(ret * SZ_1M);
+
+		GEM_BUG_ON(pci_resource_len(pdev, GEN12_LMEM_BAR) != SZ_256M);
+		GEM_BUG_ON((dsm_size + SZ_8M) > lmem_size);
+	} else {
+		/* Use DSM base address instead for stolen memory */
+		dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK;
+		if (WARN_ON(lmem_size < dsm_base))
+			return ERR_PTR(-ENODEV);
+		dsm_size = lmem_size - dsm_base;
+	}
+
+	io_size = dsm_size;
+	if (HAS_LMEMBAR_SMEM_STOLEN(i915)) {
+		io_start = pci_resource_start(pdev, GEN12_LMEM_BAR) + SZ_8M;
+	} else if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
 		io_start = 0;
 		io_size = 0;
 	} else {
 		io_start = pci_resource_start(pdev, GEN12_LMEM_BAR) + dsm_base;
-		io_size = dsm_size;
 	}
 
 	min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K :
@@ -847,16 +937,6 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 	if (IS_ERR(mem))
 		return mem;
 
-	/*
-	 * TODO: consider creating common helper to just print all the
-	 * interesting stuff from intel_memory_region, which we can use for all
-	 * our probed regions.
-	 */
-
-	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
-		&mem->io_start);
-	drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &dsm_base);
-
 	intel_memory_region_set_name(mem, "stolen-local");
 
 	mem->private = true;
@@ -881,6 +961,7 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type,
 	intel_memory_region_set_name(mem, "stolen-system");
 
 	mem->private = true;
+
 	return mem;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 7a1e92c11946..25129af70f70 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -189,7 +189,7 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
 	struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev);
 	struct intel_memory_region *mr = i915->mm.regions[INTEL_MEMORY_SYSTEM];
 	struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
-	const unsigned int max_segment = i915_sg_segment_size();
+	const unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
 	const size_t size = (size_t)ttm->num_pages << PAGE_SHIFT;
 	struct file *filp = i915_tt->filp;
 	struct sgt_iter sgt_iter;
@@ -279,7 +279,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 	struct i915_ttm_tt *i915_tt;
 	int ret;
 
-	if (!obj)
+	if (i915_ttm_is_ghost_object(bo))
 		return NULL;
 
 	i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL);
@@ -362,7 +362,7 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
 {
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 
-	if (!obj)
+	if (i915_ttm_is_ghost_object(bo))
 		return false;
 
 	/*
@@ -509,18 +509,9 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags)
 static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
 {
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
-	intel_wakeref_t wakeref = 0;
-
-	if (bo->resource && likely(obj)) {
-		/* ttm_bo_release() already has dma_resv_lock */
-		if (i915_ttm_cpu_maps_iomem(bo->resource))
-			wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm);
 
+	if (bo->resource && !i915_ttm_is_ghost_object(bo)) {
 		__i915_gem_object_pages_fini(obj);
-
-		if (wakeref)
-			intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref);
-
 		i915_ttm_free_cached_io_rsgt(obj);
 	}
 }
@@ -538,7 +529,7 @@ static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm)
 	ret = sg_alloc_table_from_pages_segment(st,
 			ttm->pages, ttm->num_pages,
 			0, (unsigned long)ttm->num_pages << PAGE_SHIFT,
-			i915_sg_segment_size(), GFP_KERNEL);
+			i915_sg_segment_size(i915_tt->dev), GFP_KERNEL);
 	if (ret) {
 		st->sgl = NULL;
 		return ERR_PTR(ret);
@@ -624,7 +615,7 @@ static void i915_ttm_swap_notify(struct ttm_buffer_object *bo)
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 	int ret;
 
-	if (!obj)
+	if (i915_ttm_is_ghost_object(bo))
 		return;
 
 	ret = i915_ttm_move_notify(bo);
@@ -657,7 +648,7 @@ static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(mem->bo);
 	bool unknown_state;
 
-	if (!obj)
+	if (i915_ttm_is_ghost_object(mem->bo))
 		return -EINVAL;
 
 	if (!kref_get_unless_zero(&obj->base.refcount))
@@ -690,7 +681,7 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
 	unsigned long base;
 	unsigned int ofs;
 
-	GEM_BUG_ON(!obj);
+	GEM_BUG_ON(i915_ttm_is_ghost_object(bo));
 	GEM_WARN_ON(bo->ttm);
 
 	base = obj->mm.region->iomap.base - obj->mm.region->region.start;
@@ -699,6 +690,50 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
 	return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs;
 }
 
+static int i915_ttm_access_memory(struct ttm_buffer_object *bo,
+				  unsigned long offset, void *buf,
+				  int len, int write)
+{
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+	resource_size_t iomap = obj->mm.region->iomap.base -
+		obj->mm.region->region.start;
+	unsigned long page = offset >> PAGE_SHIFT;
+	unsigned long bytes_left = len;
+
+	/*
+	 * TODO: For now just let it fail if the resource is non-mappable,
+	 * otherwise we need to perform the memcpy from the gpu here, without
+	 * interfering with the object (like moving the entire thing).
+	 */
+	if (!i915_ttm_resource_mappable(bo->resource))
+		return -EIO;
+
+	offset -= page << PAGE_SHIFT;
+	do {
+		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
+		void __iomem *ptr;
+		dma_addr_t daddr;
+
+		daddr = i915_gem_object_get_dma_address(obj, page);
+		ptr = ioremap_wc(iomap + daddr + offset, bytes);
+		if (!ptr)
+			return -EIO;
+
+		if (write)
+			memcpy_toio(ptr, buf, bytes);
+		else
+			memcpy_fromio(buf, ptr, bytes);
+		iounmap(ptr);
+
+		page++;
+		buf += bytes;
+		bytes_left -= bytes;
+		offset = 0;
+	} while (bytes_left);
+
+	return len;
+}
+
 /*
  * All callbacks need to take care not to downcast a struct ttm_buffer_object
  * without checking its subclass, since it might be a TTM ghost object.
@@ -715,6 +750,7 @@ static struct ttm_device_funcs i915_ttm_bo_driver = {
 	.delete_mem_notify = i915_ttm_delete_mem_notify,
 	.io_mem_reserve = i915_ttm_io_mem_reserve,
 	.io_mem_pfn = i915_ttm_io_mem_pfn,
+	.access_memory = i915_ttm_access_memory,
 };
 
 /**
@@ -990,13 +1026,12 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 	struct vm_area_struct *area = vmf->vma;
 	struct ttm_buffer_object *bo = area->vm_private_data;
 	struct drm_device *dev = bo->base.dev;
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 	intel_wakeref_t wakeref = 0;
 	vm_fault_t ret;
 	int idx;
 
-	obj = i915_ttm_to_gem(bo);
-	if (!obj)
+	if (i915_ttm_is_ghost_object(bo))
 		return VM_FAULT_SIGBUS;
 
 	/* Sanity check that we allow writing into this object */
@@ -1035,7 +1070,8 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 		}
 
 		if (err) {
-			drm_dbg(dev, "Unable to make resource CPU accessible\n");
+			drm_dbg(dev, "Unable to make resource CPU accessible(err = %pe)\n",
+				ERR_PTR(err));
 			dma_resv_unlock(bo->base.resv);
 			ret = VM_FAULT_SIGBUS;
 			goto out_rpm;
@@ -1053,16 +1089,19 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		goto out_rpm;
 
-	/* ttm_bo_vm_reserve() already has dma_resv_lock */
+	/*
+	 * ttm_bo_vm_reserve() already has dma_resv_lock.
+	 * userfault_count is protected by dma_resv lock and rpm wakeref.
+	 */
 	if (ret == VM_FAULT_NOPAGE && wakeref && !obj->userfault_count) {
 		obj->userfault_count = 1;
-		mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
-		list_add(&obj->userfault_link, &to_gt(to_i915(obj->base.dev))->lmem_userfault_list);
-		mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
+		spin_lock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock);
+		list_add(&obj->userfault_link, &to_i915(obj->base.dev)->runtime_pm.lmem_userfault_list);
+		spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock);
 	}
 
 	if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)
-		intel_wakeref_auto(&to_gt(to_i915(obj->base.dev))->userfault_wakeref,
+		intel_wakeref_auto(&to_i915(obj->base.dev)->runtime_pm.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
 	i915_ttm_adjust_lru(obj);
@@ -1094,7 +1133,7 @@ static void ttm_vm_open(struct vm_area_struct *vma)
 	struct drm_i915_gem_object *obj =
 		i915_ttm_to_gem(vma->vm_private_data);
 
-	GEM_BUG_ON(!obj);
+	GEM_BUG_ON(i915_ttm_is_ghost_object(vma->vm_private_data));
 	i915_gem_object_get(obj);
 }
 
@@ -1103,7 +1142,7 @@ static void ttm_vm_close(struct vm_area_struct *vma)
 	struct drm_i915_gem_object *obj =
 		i915_ttm_to_gem(vma->vm_private_data);
 
-	GEM_BUG_ON(!obj);
+	GEM_BUG_ON(i915_ttm_is_ghost_object(vma->vm_private_data));
 	i915_gem_object_put(obj);
 }
 
@@ -1124,7 +1163,27 @@ static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj)
 
 static void i915_ttm_unmap_virtual(struct drm_i915_gem_object *obj)
 {
+	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+	intel_wakeref_t wakeref = 0;
+
+	assert_object_held_shared(obj);
+
+	if (i915_ttm_cpu_maps_iomem(bo->resource)) {
+		wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm);
+
+		/* userfault_count is protected by obj lock and rpm wakeref. */
+		if (obj->userfault_count) {
+			spin_lock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock);
+			list_del(&obj->userfault_link);
+			spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock);
+			obj->userfault_count = 0;
+		}
+	}
+
 	ttm_bo_unmap_virtual(i915_gem_to_ttm(obj));
+
+	if (wakeref)
+		intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
index e4842b4296fc..2a94a99ef76b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
@@ -28,18 +28,26 @@ i915_gem_to_ttm(struct drm_i915_gem_object *obj)
 void i915_ttm_bo_destroy(struct ttm_buffer_object *bo);
 
 /**
+ * i915_ttm_is_ghost_object - Check if the ttm bo is a ghost object.
+ * @bo: Pointer to the ttm buffer object
+ *
+ * Return: True if the ttm bo is not a i915 object but a ghost ttm object,
+ * False otherwise.
+ */
+static inline bool i915_ttm_is_ghost_object(struct ttm_buffer_object *bo)
+{
+	return bo->destroy != i915_ttm_bo_destroy;
+}
+
+/**
  * i915_ttm_to_gem - Convert a struct ttm_buffer_object to an embedding
  * struct drm_i915_gem_object.
  *
- * Return: Pointer to the embedding struct ttm_buffer_object, or NULL
- * if the object was not an i915 ttm object.
+ * Return: Pointer to the embedding struct ttm_buffer_object.
  */
 static inline struct drm_i915_gem_object *
 i915_ttm_to_gem(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy != i915_ttm_bo_destroy)
-		return NULL;
-
 	return container_of(bo, struct drm_i915_gem_object, __do_not_access);
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index 9a7e50534b84..f59f812dc6d2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -560,7 +560,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 	bool clear;
 	int ret;
 
-	if (GEM_WARN_ON(!obj)) {
+	if (GEM_WARN_ON(i915_ttm_is_ghost_object(bo))) {
 		ttm_bo_move_null(bo, dst_mem);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index d4398948f016..1b1a22716722 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -129,7 +129,7 @@ static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj)
 static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 {
 	const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
-	unsigned int max_segment = i915_sg_segment_size();
+	unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev);
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
 	struct page **pvec;
@@ -292,7 +292,7 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 	if (!i915_gem_object_is_readonly(obj))
 		gup_flags |= FOLL_WRITE;
 
-	pinned = ret = 0;
+	pinned = 0;
 	while (pinned < num_pages) {
 		ret = pin_user_pages_fast(obj->userptr.ptr + pinned * PAGE_SIZE,
 					  num_pages - pinned, gup_flags,
@@ -302,7 +302,6 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj)
 
 		pinned += ret;
 	}
-	ret = 0;
 
 	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index c570cf780079..0cb99e75b0bc 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1161,7 +1161,8 @@ static int igt_write_huge(struct drm_i915_private *i915,
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
 
 	size = obj->base.size;
-	if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K)
+	if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
+	    !HAS_64K_PAGES(i915))
 		size = round_up(size, I915_GTT_PAGE_SIZE_2M);
 
 	n = 0;
@@ -1214,6 +1215,10 @@ static int igt_write_huge(struct drm_i915_private *i915,
 		 * size and ensure the vma offset is at the start of the pt
 		 * boundary, however to improve coverage we opt for testing both
 		 * aligned and unaligned offsets.
+		 *
+		 * With PS64 this is no longer the case, but to ensure we
+		 * sometimes get the compact layout for smaller objects, apply
+		 * the round_up anyway.
 		 */
 		if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K)
 			offset_low = round_down(offset_low,
@@ -1411,6 +1416,7 @@ static int igt_ppgtt_sanity_check(void *arg)
 		{ SZ_2M + SZ_4K,	SZ_64K | SZ_4K	},
 		{ SZ_2M + SZ_4K,	SZ_2M  | SZ_4K	},
 		{ SZ_2M + SZ_64K,	SZ_2M  | SZ_64K },
+		{ SZ_2M + SZ_64K,	SZ_64K		},
 	};
 	int i, j;
 	int err;
@@ -1540,6 +1546,154 @@ out_put:
 	return err;
 }
 
+static int igt_ppgtt_mixed(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	const unsigned long flags = PIN_OFFSET_FIXED | PIN_USER;
+	struct drm_i915_gem_object *obj, *on;
+	struct i915_gem_engines *engines;
+	struct i915_gem_engines_iter it;
+	struct i915_address_space *vm;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct file *file;
+	I915_RND_STATE(prng);
+	LIST_HEAD(objects);
+	struct intel_memory_region *mr;
+	struct i915_vma *vma;
+	unsigned int count;
+	u32 i, addr;
+	int *order;
+	int n, err;
+
+	/*
+	 * Sanity check mixing 4K and 64K pages within the same page-table via
+	 * the new PS64 TLB hint.
+	 */
+
+	if (!HAS_64K_PAGES(i915)) {
+		pr_info("device lacks PS64, skipping\n");
+		return 0;
+	}
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = hugepage_ctx(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out;
+	}
+	vm = i915_gem_context_get_eb_vm(ctx);
+
+	i = 0;
+	addr = 0;
+	do {
+		u32 sz;
+
+		sz = i915_prandom_u32_max_state(SZ_4M, &prng);
+		sz = max_t(u32, sz, SZ_4K);
+
+		mr = i915->mm.regions[INTEL_REGION_LMEM_0];
+		if (i & 1)
+			mr = i915->mm.regions[INTEL_REGION_SMEM];
+
+		obj = i915_gem_object_create_region(mr, sz, 0, 0);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			goto out_vm;
+		}
+
+		list_add_tail(&obj->st_link, &objects);
+
+		vma = i915_vma_instance(obj, vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto err_put;
+		}
+
+		addr = round_up(addr, mr->min_page_size);
+		err = i915_vma_pin(vma, 0, 0, addr | flags);
+		if (err)
+			goto err_put;
+
+		if (mr->type == INTEL_MEMORY_LOCAL &&
+		    (vma->resource->page_sizes_gtt & I915_GTT_PAGE_SIZE_4K)) {
+			err = -EINVAL;
+			goto err_put;
+		}
+
+		addr += obj->base.size;
+		i++;
+	} while (addr <= SZ_16M);
+
+	n = 0;
+	count = 0;
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		count++;
+		if (!intel_engine_can_store_dword(ce->engine))
+			continue;
+
+		n++;
+	}
+	i915_gem_context_unlock_engines(ctx);
+	if (!n)
+		goto err_put;
+
+	order = i915_random_order(count * count, &prng);
+	if (!order) {
+		err = -ENOMEM;
+		goto err_put;
+	}
+
+	i = 0;
+	addr = 0;
+	engines = i915_gem_context_lock_engines(ctx);
+	list_for_each_entry(obj, &objects, st_link) {
+		u32 rnd = i915_prandom_u32_max_state(UINT_MAX, &prng);
+
+		addr = round_up(addr, obj->mm.region->min_page_size);
+
+		ce = engines->engines[order[i] % engines->num_engines];
+		i = (i + 1) % (count * count);
+		if (!ce || !intel_engine_can_store_dword(ce->engine))
+			continue;
+
+		err = __igt_write_huge(ce, obj, obj->base.size, addr, 0, rnd);
+		if (err)
+			break;
+
+		err = __igt_write_huge(ce, obj, obj->base.size, addr,
+				       offset_in_page(rnd) / sizeof(u32), rnd + 1);
+		if (err)
+			break;
+
+		err = __igt_write_huge(ce, obj, obj->base.size, addr,
+				       (PAGE_SIZE / sizeof(u32)) - 1,
+				       rnd + 2);
+		if (err)
+			break;
+
+		addr += obj->base.size;
+
+		cond_resched();
+	}
+
+	i915_gem_context_unlock_engines(ctx);
+	kfree(order);
+err_put:
+	list_for_each_entry_safe(obj, on, &objects, st_link) {
+		list_del(&obj->st_link);
+		i915_gem_object_put(obj);
+	}
+out_vm:
+	i915_vm_put(vm);
+out:
+	fput(file);
+	return err;
+}
+
 static int igt_tmpfs_fallback(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -1803,6 +1957,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_smoke_huge),
 		SUBTEST(igt_ppgtt_sanity_check),
 		SUBTEST(igt_ppgtt_compact),
+		SUBTEST(igt_ppgtt_mixed),
 	};
 
 	if (!HAS_PPGTT(i915)) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index c6ad67b90e8a..d8864444432b 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -179,97 +179,108 @@ out_file:
 }
 
 struct parallel_switch {
-	struct task_struct *tsk;
+	struct kthread_worker *worker;
+	struct kthread_work work;
 	struct intel_context *ce[2];
+	int result;
 };
 
-static int __live_parallel_switch1(void *data)
+static void __live_parallel_switch1(struct kthread_work *work)
 {
-	struct parallel_switch *arg = data;
+	struct parallel_switch *arg =
+		container_of(work, typeof(*arg), work);
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 
 	count = 0;
+	arg->result = 0;
 	do {
 		struct i915_request *rq = NULL;
-		int err, n;
+		int n;
 
-		err = 0;
-		for (n = 0; !err && n < ARRAY_SIZE(arg->ce); n++) {
+		for (n = 0; !arg->result && n < ARRAY_SIZE(arg->ce); n++) {
 			struct i915_request *prev = rq;
 
 			rq = i915_request_create(arg->ce[n]);
 			if (IS_ERR(rq)) {
 				i915_request_put(prev);
-				return PTR_ERR(rq);
+				arg->result = PTR_ERR(rq);
+				break;
 			}
 
 			i915_request_get(rq);
 			if (prev) {
-				err = i915_request_await_dma_fence(rq, &prev->fence);
+				arg->result =
+					i915_request_await_dma_fence(rq,
+								     &prev->fence);
 				i915_request_put(prev);
 			}
 
 			i915_request_add(rq);
 		}
+
+		if (IS_ERR_OR_NULL(rq))
+			break;
+
 		if (i915_request_wait(rq, 0, HZ) < 0)
-			err = -ETIME;
+			arg->result = -ETIME;
+
 		i915_request_put(rq);
-		if (err)
-			return err;
 
 		count++;
-	} while (!__igt_timeout(end_time, NULL));
+	} while (!arg->result && !__igt_timeout(end_time, NULL));
 
-	pr_info("%s: %lu switches (sync)\n", arg->ce[0]->engine->name, count);
-	return 0;
+	pr_info("%s: %lu switches (sync) <%d>\n",
+		arg->ce[0]->engine->name, count, arg->result);
 }
 
-static int __live_parallel_switchN(void *data)
+static void __live_parallel_switchN(struct kthread_work *work)
 {
-	struct parallel_switch *arg = data;
+	struct parallel_switch *arg =
+		container_of(work, typeof(*arg), work);
 	struct i915_request *rq = NULL;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 	int n;
 
 	count = 0;
+	arg->result = 0;
 	do {
-		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
+		for (n = 0; !arg->result && n < ARRAY_SIZE(arg->ce); n++) {
 			struct i915_request *prev = rq;
-			int err = 0;
 
 			rq = i915_request_create(arg->ce[n]);
 			if (IS_ERR(rq)) {
 				i915_request_put(prev);
-				return PTR_ERR(rq);
+				arg->result = PTR_ERR(rq);
+				break;
 			}
 
 			i915_request_get(rq);
 			if (prev) {
-				err = i915_request_await_dma_fence(rq, &prev->fence);
+				arg->result =
+					i915_request_await_dma_fence(rq,
+								     &prev->fence);
 				i915_request_put(prev);
 			}
 
 			i915_request_add(rq);
-			if (err) {
-				i915_request_put(rq);
-				return err;
-			}
 		}
 
 		count++;
-	} while (!__igt_timeout(end_time, NULL));
-	i915_request_put(rq);
+	} while (!arg->result && !__igt_timeout(end_time, NULL));
 
-	pr_info("%s: %lu switches (many)\n", arg->ce[0]->engine->name, count);
-	return 0;
+	if (!IS_ERR_OR_NULL(rq))
+		i915_request_put(rq);
+
+	pr_info("%s: %lu switches (many) <%d>\n",
+		arg->ce[0]->engine->name, count, arg->result);
 }
 
 static int live_parallel_switch(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	static int (* const func[])(void *arg) = {
+	static void (* const func[])(struct kthread_work *) = {
 		__live_parallel_switch1,
 		__live_parallel_switchN,
 		NULL,
@@ -277,7 +288,7 @@ static int live_parallel_switch(void *arg)
 	struct parallel_switch *data = NULL;
 	struct i915_gem_engines *engines;
 	struct i915_gem_engines_iter it;
-	int (* const *fn)(void *arg);
+	void (* const *fn)(struct kthread_work *);
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct file *file;
@@ -348,9 +359,22 @@ static int live_parallel_switch(void *arg)
 		}
 	}
 
+	for (n = 0; n < count; n++) {
+		struct kthread_worker *worker;
+
+		if (!data[n].ce[0])
+			continue;
+
+		worker = kthread_create_worker(0, "igt/parallel:%s",
+					       data[n].ce[0]->engine->name);
+		if (IS_ERR(worker))
+			goto out;
+
+		data[n].worker = worker;
+	}
+
 	for (fn = func; !err && *fn; fn++) {
 		struct igt_live_test t;
-		int n;
 
 		err = igt_live_test_begin(&t, i915, __func__, "");
 		if (err)
@@ -360,30 +384,17 @@ static int live_parallel_switch(void *arg)
 			if (!data[n].ce[0])
 				continue;
 
-			data[n].tsk = kthread_run(*fn, &data[n],
-						  "igt/parallel:%s",
-						  data[n].ce[0]->engine->name);
-			if (IS_ERR(data[n].tsk)) {
-				err = PTR_ERR(data[n].tsk);
-				break;
-			}
-			get_task_struct(data[n].tsk);
+			data[n].result = 0;
+			kthread_init_work(&data[n].work, *fn);
+			kthread_queue_work(data[n].worker, &data[n].work);
 		}
 
-		yield(); /* start all threads before we kthread_stop() */
-
 		for (n = 0; n < count; n++) {
-			int status;
-
-			if (IS_ERR_OR_NULL(data[n].tsk))
-				continue;
-
-			status = kthread_stop(data[n].tsk);
-			if (status && !err)
-				err = status;
-
-			put_task_struct(data[n].tsk);
-			data[n].tsk = NULL;
+			if (data[n].ce[0]) {
+				kthread_flush_work(&data[n].work);
+				if (data[n].result && !err)
+					err = data[n].result;
+			}
 		}
 
 		if (igt_live_test_end(&t))
@@ -399,6 +410,9 @@ out:
 			intel_context_unpin(data[n].ce[m]);
 			intel_context_put(data[n].ce[m]);
 		}
+
+		if (data[n].worker)
+			kthread_destroy_worker(data[n].worker);
 	}
 	kfree(data);
 out_file:
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index f2f3cfad807b..e57f9390076c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -6,8 +6,12 @@
 
 #include "i915_drv.h"
 #include "i915_selftest.h"
+#include "gem/i915_gem_context.h"
 
+#include "mock_context.h"
 #include "mock_dmabuf.h"
+#include "igt_gem_utils.h"
+#include "selftests/mock_drm.h"
 #include "selftests/mock_gem_device.h"
 
 static int igt_dmabuf_export(void *arg)
@@ -140,6 +144,75 @@ out_ret:
 	return err;
 }
 
+static int verify_access(struct drm_i915_private *i915,
+			 struct drm_i915_gem_object *native_obj,
+			 struct drm_i915_gem_object *import_obj)
+{
+	struct i915_gem_engines_iter it;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct i915_vma *vma;
+	struct file *file;
+	u32 *vaddr;
+	int err = 0, i;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_file;
+	}
+
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		if (intel_engine_can_store_dword(ce->engine))
+			break;
+	}
+	i915_gem_context_unlock_engines(ctx);
+	if (!ce)
+		goto out_file;
+
+	vma = i915_vma_instance(import_obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_file;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto out_file;
+
+	err = igt_gpu_fill_dw(ce, vma, 0,
+			      vma->size >> PAGE_SHIFT, 0xdeadbeaf);
+	i915_vma_unpin(vma);
+	if (err)
+		goto out_file;
+
+	err = i915_gem_object_wait(import_obj, 0, MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		goto out_file;
+
+	vaddr = i915_gem_object_pin_map_unlocked(native_obj, I915_MAP_WB);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto out_file;
+	}
+
+	for (i = 0; i < native_obj->base.size / sizeof(u32); i += PAGE_SIZE / sizeof(u32)) {
+		if (vaddr[i] != 0xdeadbeaf) {
+			pr_err("Data mismatch [%d]=%u\n", i, vaddr[i]);
+			err = -EINVAL;
+			goto out_file;
+		}
+	}
+
+out_file:
+	fput(file);
+	return err;
+}
+
 static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 					 struct intel_memory_region **regions,
 					 unsigned int num_regions)
@@ -154,7 +227,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 
 	force_different_devices = true;
 
-	obj = __i915_gem_object_create_user(i915, PAGE_SIZE,
+	obj = __i915_gem_object_create_user(i915, SZ_8M,
 					    regions, num_regions);
 	if (IS_ERR(obj)) {
 		pr_err("__i915_gem_object_create_user failed with err=%ld\n",
@@ -206,6 +279,10 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 
 	i915_gem_object_unlock(import_obj);
 
+	err = verify_access(i915, obj, import_obj);
+	if (err)
+		goto out_import;
+
 	/* Now try a fake an importer */
 	import_attach = dma_buf_attach(dmabuf, obj->base.dev->dev);
 	if (IS_ERR(import_attach)) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index b73c91aa5450..1cae24349a96 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -8,6 +8,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_ttm.h"
 #include "gem/i915_gem_ttm_move.h"
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index e49fa6fa6aee..e1c76e5bfa82 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -396,15 +396,17 @@ int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	return 0;
 }
 
-static int __gen125_emit_bb_start(struct i915_request *rq,
-				  u64 offset, u32 len,
-				  const unsigned int flags,
-				  u32 arb)
+static int __xehp_emit_bb_start(struct i915_request *rq,
+				u64 offset, u32 len,
+				const unsigned int flags,
+				u32 arb)
 {
 	struct intel_context *ce = rq->context;
 	u32 wa_offset = lrc_indirect_bb(ce);
 	u32 *cs;
 
+	GEM_BUG_ON(!ce->wa_bb_page);
+
 	cs = intel_ring_begin(rq, 12);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
@@ -435,18 +437,18 @@ static int __gen125_emit_bb_start(struct i915_request *rq,
 	return 0;
 }
 
-int gen125_emit_bb_start_noarb(struct i915_request *rq,
-			       u64 offset, u32 len,
-			       const unsigned int flags)
+int xehp_emit_bb_start_noarb(struct i915_request *rq,
+			     u64 offset, u32 len,
+			     const unsigned int flags)
 {
-	return __gen125_emit_bb_start(rq, offset, len, flags, MI_ARB_DISABLE);
+	return __xehp_emit_bb_start(rq, offset, len, flags, MI_ARB_DISABLE);
 }
 
-int gen125_emit_bb_start(struct i915_request *rq,
-			 u64 offset, u32 len,
-			 const unsigned int flags)
+int xehp_emit_bb_start(struct i915_request *rq,
+		       u64 offset, u32 len,
+		       const unsigned int flags)
 {
-	return __gen125_emit_bb_start(rq, offset, len, flags, MI_ARB_ENABLE);
+	return __xehp_emit_bb_start(rq, offset, len, flags, MI_ARB_ENABLE);
 }
 
 int gen8_emit_bb_start_noarb(struct i915_request *rq,
@@ -583,6 +585,8 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
 	cs = gen8_emit_pipe_control(cs,
+				    PIPE_CONTROL_CS_STALL |
+				    PIPE_CONTROL_TLB_INVALIDATE |
 				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
 				    PIPE_CONTROL_DC_FLUSH_ENABLE,
@@ -600,15 +604,21 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
+	cs = gen8_emit_pipe_control(cs,
+				    PIPE_CONTROL_CS_STALL |
+				    PIPE_CONTROL_TLB_INVALIDATE |
+				    PIPE_CONTROL_TILE_CACHE_FLUSH |
+				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+				    PIPE_CONTROL_DC_FLUSH_ENABLE,
+				    0);
+
+	/*XXX: Look at gen8_emit_fini_breadcrumb_rcs */
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      rq->fence.seqno,
 				      hwsp_offset(rq),
-				      PIPE_CONTROL_CS_STALL |
-				      PIPE_CONTROL_TILE_CACHE_FLUSH |
-				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				      PIPE_CONTROL_DC_FLUSH_ENABLE |
-				      PIPE_CONTROL_FLUSH_ENABLE);
+				      PIPE_CONTROL_FLUSH_ENABLE |
+				      PIPE_CONTROL_CS_STALL);
 
 	return gen8_emit_fini_breadcrumb_tail(rq, cs);
 }
@@ -715,6 +725,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
 	struct drm_i915_private *i915 = rq->engine->i915;
 	u32 flags = (PIPE_CONTROL_CS_STALL |
+		     PIPE_CONTROL_TLB_INVALIDATE |
 		     PIPE_CONTROL_TILE_CACHE_FLUSH |
 		     PIPE_CONTROL_FLUSH_L3 |
 		     PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -731,11 +742,15 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 	else if (rq->engine->class == COMPUTE_CLASS)
 		flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
+	cs = gen12_emit_pipe_control(cs, PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags, 0);
+
+	/*XXX: Look at gen8_emit_fini_breadcrumb_rcs */
 	cs = gen12_emit_ggtt_write_rcs(cs,
 				       rq->fence.seqno,
 				       hwsp_offset(rq),
-				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
-				       flags);
+				       0,
+				       PIPE_CONTROL_FLUSH_ENABLE |
+				       PIPE_CONTROL_CS_STALL);
 
 	return gen12_emit_fini_breadcrumb_tail(rq, cs);
 }
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
index e4d24c811dd6..655e5c00ddc2 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
@@ -32,12 +32,12 @@ int gen8_emit_bb_start(struct i915_request *rq,
 		       u64 offset, u32 len,
 		       const unsigned int flags);
 
-int gen125_emit_bb_start_noarb(struct i915_request *rq,
-			       u64 offset, u32 len,
-			       const unsigned int flags);
-int gen125_emit_bb_start(struct i915_request *rq,
-			 u64 offset, u32 len,
-			 const unsigned int flags);
+int xehp_emit_bb_start_noarb(struct i915_request *rq,
+			     u64 offset, u32 len,
+			     const unsigned int flags);
+int xehp_emit_bb_start(struct i915_request *rq,
+		       u64 offset, u32 len,
+		       const unsigned int flags);
 
 u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs);
 u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 2128b7a72a25..4daaa6f55668 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -476,6 +476,7 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 	const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags);
 	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma_res->start;
+	u64 end = start + vma_res->vma_size;
 
 	GEM_BUG_ON(!i915_vm_is_4lvl(vm));
 
@@ -489,9 +490,10 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 		gen8_pte_t encode = pte_encode;
 		unsigned int page_size;
 		gen8_pte_t *vaddr;
-		u16 index, max;
+		u16 index, max, nent, i;
 
 		max = I915_PDES;
+		nent = 1;
 
 		if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
 		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
@@ -503,25 +505,37 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 
 			vaddr = px_vaddr(pd);
 		} else {
-			if (encode & GEN12_PPGTT_PTE_LM) {
-				GEM_BUG_ON(__gen8_pte_index(start, 0) % 16);
-				GEM_BUG_ON(rem < I915_GTT_PAGE_SIZE_64K);
-				GEM_BUG_ON(!IS_ALIGNED(iter->dma,
-						       I915_GTT_PAGE_SIZE_64K));
-
-				index = __gen8_pte_index(start, 0) / 16;
-				page_size = I915_GTT_PAGE_SIZE_64K;
-
-				max /= 16;
-
-				vaddr = px_vaddr(pd);
-				vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K;
+			index =  __gen8_pte_index(start, 0);
+			page_size = I915_GTT_PAGE_SIZE;
 
-				pt->is_compact = true;
-			} else {
-				GEM_BUG_ON(pt->is_compact);
-				index =  __gen8_pte_index(start, 0);
-				page_size = I915_GTT_PAGE_SIZE;
+			if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_64K) {
+				/*
+				 * Device local-memory on these platforms should
+				 * always use 64K pages or larger (including GTT
+				 * alignment), therefore if we know the whole
+				 * page-table needs to be filled we can always
+				 * safely use the compact-layout. Otherwise fall
+				 * back to the TLB hint with PS64. If this is
+				 * system memory we only bother with PS64.
+				 */
+				if ((encode & GEN12_PPGTT_PTE_LM) &&
+				    end - start >= SZ_2M && !index) {
+					index = __gen8_pte_index(start, 0) / 16;
+					page_size = I915_GTT_PAGE_SIZE_64K;
+
+					max /= 16;
+
+					vaddr = px_vaddr(pd);
+					vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K;
+
+					pt->is_compact = true;
+				} else if (IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
+					   rem >= I915_GTT_PAGE_SIZE_64K &&
+					   !(index % 16)) {
+					encode |= GEN12_PTE_PS64;
+					page_size = I915_GTT_PAGE_SIZE_64K;
+					nent = 16;
+				}
 			}
 
 			vaddr = px_vaddr(pt);
@@ -529,7 +543,12 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 
 		do {
 			GEM_BUG_ON(rem < page_size);
-			vaddr[index++] = encode | iter->dma;
+
+			for (i = 0; i < nent; i++) {
+				vaddr[index++] =
+					encode | (iter->dma + i *
+						  I915_GTT_PAGE_SIZE);
+			}
 
 			start += page_size;
 			iter->dma += page_size;
@@ -745,6 +764,8 @@ static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
 	GEM_BUG_ON(!IS_ALIGNED(addr, SZ_64K));
 	GEM_BUG_ON(!IS_ALIGNED(offset, SZ_64K));
 
+	/* XXX: we don't strictly need to use this layout */
+
 	if (!pt->is_compact) {
 		vaddr = px_vaddr(pd);
 		vaddr[gen8_pd_index(idx, 1)] |= GEN12_PDE_64K;
@@ -929,29 +950,18 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 	 */
 	ppgtt->vm.has_read_only = !IS_GRAPHICS_VER(gt->i915, 11, 12);
 
-	if (HAS_LMEM(gt->i915)) {
+	if (HAS_LMEM(gt->i915))
 		ppgtt->vm.alloc_pt_dma = alloc_pt_lmem;
-
-		/*
-		 * On some platforms the hw has dropped support for 4K GTT pages
-		 * when dealing with LMEM, and due to the design of 64K GTT
-		 * pages in the hw, we can only mark the *entire* page-table as
-		 * operating in 64K GTT mode, since the enable bit is still on
-		 * the pde, and not the pte. And since we still need to allow
-		 * 4K GTT pages for SMEM objects, we can't have a "normal" 4K
-		 * page-table with scratch pointing to LMEM, since that's
-		 * undefined from the hw pov. The simplest solution is to just
-		 * move the 64K scratch page to SMEM on such platforms and call
-		 * it a day, since that should work for all configurations.
-		 */
-		if (HAS_64K_PAGES(gt->i915))
-			ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
-		else
-			ppgtt->vm.alloc_scratch_dma = alloc_pt_lmem;
-	} else {
+	else
 		ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
-		ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
-	}
+
+	/*
+	 * Using SMEM here instead of LMEM has the advantage of not reserving
+	 * high performance memory for a "never" used filler page. It also
+	 * removes the device access that would be required to initialise the
+	 * scratch page, reducing pressure on an even scarcer resource.
+	 */
+	ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
 
 	ppgtt->vm.pte_encode = gen8_pte_encode;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index be09fb2e883a..fb62b7b8cbcd 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -276,6 +276,14 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce)
 	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 }
 
+static inline void intel_context_close(struct intel_context *ce)
+{
+	set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
+
+	if (ce->ops->close)
+		ce->ops->close(ce);
+}
+
 static inline bool intel_context_is_closed(const struct intel_context *ce)
 {
 	return test_bit(CONTEXT_CLOSED_BIT, &ce->flags);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 04eacae1aca5..e36670f2e626 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -43,6 +43,8 @@ struct intel_context_ops {
 	void (*revoke)(struct intel_context *ce, struct i915_request *rq,
 		       unsigned int preempt_timeout_ms);
 
+	void (*close)(struct intel_context *ce);
+
 	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
 	int (*pin)(struct intel_context *ce, void *vaddr);
 	void (*unpin)(struct intel_context *ce);
@@ -197,8 +199,6 @@ struct intel_context {
 		 * context's submissions is complete.
 		 */
 		struct i915_sw_fence blocked;
-		/** @number_committed_requests: number of committed requests */
-		int number_committed_requests;
 		/** @requests: list of active requests on this context */
 		struct list_head requests;
 		/** @prio: the context's current guc priority */
@@ -208,6 +208,11 @@ struct intel_context {
 		 * each priority bucket
 		 */
 		u32 prio_count[GUC_CLIENT_PRIORITY_NUM];
+		/**
+		 * @sched_disable_delay_work: worker to disable scheduling on this
+		 * context
+		 */
+		struct delayed_work sched_disable_delay_work;
 	} guc_state;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 04e435bce79b..cbc8b857d5f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -348,4 +348,10 @@ intel_engine_get_hung_context(struct intel_engine_cs *engine)
 	return engine->hung_ce;
 }
 
+u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value);
+u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value);
+u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value);
+u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value);
+u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value);
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 1f7188129cd1..3b7d750ad054 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -486,6 +486,17 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	engine->logical_mask = BIT(logical_instance);
 	__sprint_engine_name(engine);
 
+	if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) &&
+	     __ffs(CCS_MASK(engine->gt)) == engine->instance) ||
+	     engine->class == RENDER_CLASS)
+		engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE;
+
+	/* features common between engines sharing EUs */
+	if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) {
+		engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
+		engine->flags |= I915_ENGINE_HAS_EU_PRIORITY;
+	}
+
 	engine->props.heartbeat_interval_ms =
 		CONFIG_DRM_I915_HEARTBEAT_INTERVAL;
 	engine->props.max_busywait_duration_ns =
@@ -497,20 +508,34 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	engine->props.timeslice_duration_ms =
 		CONFIG_DRM_I915_TIMESLICE_DURATION;
 
-	/* Override to uninterruptible for OpenCL workloads. */
-	if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS)
-		engine->props.preempt_timeout_ms = 0;
-
-	if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) &&
-	     __ffs(CCS_MASK(engine->gt)) == engine->instance) ||
-	     engine->class == RENDER_CLASS)
-		engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE;
-
-	/* features common between engines sharing EUs */
-	if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) {
-		engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
-		engine->flags |= I915_ENGINE_HAS_EU_PRIORITY;
-	}
+	/*
+	 * Mid-thread pre-emption is not available in Gen12. Unfortunately,
+	 * some compute workloads run quite long threads. That means they get
+	 * reset due to not pre-empting in a timely manner. So, bump the
+	 * pre-emption timeout value to be much higher for compute engines.
+	 */
+	if (GRAPHICS_VER(i915) == 12 && (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
+		engine->props.preempt_timeout_ms = CONFIG_DRM_I915_PREEMPT_TIMEOUT_COMPUTE;
+
+	/* Cap properties according to any system limits */
+#define CLAMP_PROP(field) \
+	do { \
+		u64 clamp = intel_clamp_##field(engine, engine->props.field); \
+		if (clamp != engine->props.field) { \
+			drm_notice(&engine->i915->drm, \
+				   "Warning, clamping %s to %lld to prevent overflow\n", \
+				   #field, clamp); \
+			engine->props.field = clamp; \
+		} \
+	} while (0)
+
+	CLAMP_PROP(heartbeat_interval_ms);
+	CLAMP_PROP(max_busywait_duration_ns);
+	CLAMP_PROP(preempt_timeout_ms);
+	CLAMP_PROP(stop_timeout_ms);
+	CLAMP_PROP(timeslice_duration_ms);
+
+#undef CLAMP_PROP
 
 	engine->defaults = engine->props; /* never to change again */
 
@@ -534,6 +559,55 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	return 0;
 }
 
+u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value)
+{
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value)
+{
+	value = min(value, jiffies_to_nsecs(2));
+
+	return value;
+}
+
+u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value)
+{
+	/*
+	 * NB: The GuC API only supports 32bit values. However, the limit is further
+	 * reduced due to internal calculations which would otherwise overflow.
+	 */
+	if (intel_guc_submission_is_wanted(&engine->gt->uc.guc))
+		value = min_t(u64, value, guc_policy_max_preempt_timeout_ms());
+
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value)
+{
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value)
+{
+	/*
+	 * NB: The GuC API only supports 32bit values. However, the limit is further
+	 * reduced due to internal calculations which would otherwise overflow.
+	 */
+	if (intel_guc_submission_is_wanted(&engine->gt->uc.guc))
+		value = min_t(u64, value, guc_policy_max_exec_quantum_ms());
+
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
 static void __setup_engine_capabilities(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
@@ -1274,8 +1348,13 @@ int intel_engines_init(struct intel_gt *gt)
 			return err;
 
 		err = setup(engine);
-		if (err)
+		if (err) {
+			intel_engine_cleanup_common(engine);
 			return err;
+		}
+
+		/* The backend should now be responsible for cleanup */
+		GEM_BUG_ON(engine->release == NULL);
 
 		err = engine_init_common(engine);
 		if (err)
@@ -1554,11 +1633,11 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 		for_each_ss_steering(iter, engine->gt, slice, subslice) {
 			instdone->sampler[slice][subslice] =
 				intel_gt_mcr_read(engine->gt,
-						  GEN7_SAMPLER_INSTDONE,
+						  GEN8_SAMPLER_INSTDONE,
 						  slice, subslice);
 			instdone->row[slice][subslice] =
 				intel_gt_mcr_read(engine->gt,
-						  GEN7_ROW_INSTDONE,
+						  GEN8_ROW_INSTDONE,
 						  slice, subslice);
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index a3698f611f45..9a527e1f5be6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -22,9 +22,37 @@
 
 static bool next_heartbeat(struct intel_engine_cs *engine)
 {
+	struct i915_request *rq;
 	long delay;
 
 	delay = READ_ONCE(engine->props.heartbeat_interval_ms);
+
+	rq = engine->heartbeat.systole;
+
+	/*
+	 * FIXME: The final period extension is disabled if the period has been
+	 * modified from the default. This is to prevent issues with certain
+	 * selftests which override the value and expect specific behaviour.
+	 * Once the selftests have been updated to either cope with variable
+	 * heartbeat periods (or to override the pre-emption timeout as well,
+	 * or just to add a selftest specific override of the extension), the
+	 * generic override can be removed.
+	 */
+	if (rq && rq->sched.attr.priority >= I915_PRIORITY_BARRIER &&
+	    delay == engine->defaults.heartbeat_interval_ms) {
+		long longer;
+
+		/*
+		 * The final try is at the highest priority possible. Up until now
+		 * a pre-emption might not even have been attempted. So make sure
+		 * this last attempt allows enough time for a pre-emption to occur.
+		 */
+		longer = READ_ONCE(engine->props.preempt_timeout_ms) * 2;
+		longer = intel_clamp_heartbeat_interval_ms(engine, longer);
+		if (longer > delay)
+			delay = longer;
+	}
+
 	if (!delay)
 		return false;
 
@@ -288,6 +316,17 @@ int intel_engine_set_heartbeat(struct intel_engine_cs *engine,
 	if (!delay && !intel_engine_has_preempt_reset(engine))
 		return -ENODEV;
 
+	/* FIXME: Remove together with equally marked hack in next_heartbeat. */
+	if (delay != engine->defaults.heartbeat_interval_ms &&
+	    delay < 2 * engine->props.preempt_timeout_ms) {
+		if (intel_engine_uses_guc(engine))
+			drm_notice(&engine->i915->drm, "%s heartbeat interval adjusted to a non-default value which may downgrade individual engine resets to full GPU resets!\n",
+				   engine->name);
+		else
+			drm_notice(&engine->i915->drm, "%s heartbeat interval adjusted to a non-default value which may cause engine resets to target innocent contexts!\n",
+				   engine->name);
+	}
+
 	intel_engine_pm_get(engine);
 
 	err = mutex_lock_interruptible(&ce->timeline->mutex);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index fe1a0d5fd4b1..ee3efd06ee54 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -201,6 +201,7 @@
 #define RING_CONTEXT_STATUS_PTR(base)		_MMIO((base) + 0x3a0)
 #define RING_CTX_TIMESTAMP(base)		_MMIO((base) + 0x3a8) /* gen8+ */
 #define RING_PREDICATE_RESULT(base)		_MMIO((base) + 0x3b8)
+#define MI_PREDICATE_RESULT_2_ENGINE(base)	_MMIO((base) + 0x3bc)
 #define RING_FORCE_TO_NONPRIV(base, i)		_MMIO(((base) + 0x4D0) + (i) * 4)
 #define   RING_FORCE_TO_NONPRIV_DENY		REG_BIT(30)
 #define   RING_FORCE_TO_NONPRIV_ADDRESS_MASK	REG_GENMASK(25, 2)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index c718e6dc40b5..0187bc72310d 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3471,9 +3471,9 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 
 	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) {
 		if (intel_engine_has_preemption(engine))
-			engine->emit_bb_start = gen125_emit_bb_start;
+			engine->emit_bb_start = xehp_emit_bb_start;
 		else
-			engine->emit_bb_start = gen125_emit_bb_start_noarb;
+			engine->emit_bb_start = xehp_emit_bb_start_noarb;
 	} else {
 		if (intel_engine_has_preemption(engine))
 			engine->emit_bb_start = gen8_emit_bb_start;
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 2049a00417af..2518cebbf931 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -871,8 +871,8 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	u32 pte_flags;
 	int ret;
 
-	GEM_WARN_ON(pci_resource_len(pdev, GTTMMADR_BAR) != gen6_gttmmadr_size(i915));
-	phys_addr = pci_resource_start(pdev, GTTMMADR_BAR) + gen6_gttadr_offset(i915);
+	GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915));
+	phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
 
 	/*
 	 * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
@@ -931,11 +931,11 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	unsigned int size;
 	u16 snb_gmch_ctl;
 
-	if (!HAS_LMEM(i915)) {
-		if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR))
+	if (!HAS_LMEM(i915) && !HAS_LMEMBAR_SMEM_STOLEN(i915)) {
+		if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR))
 			return -ENXIO;
 
-		ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR);
+		ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR);
 		ggtt->mappable_end = resource_size(&ggtt->gmadr);
 	}
 
@@ -986,7 +986,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
 
-	setup_private_pat(ggtt->vm.gt->uncore);
+	setup_private_pat(ggtt->vm.gt);
 
 	return ggtt_probe_common(ggtt, size);
 }
@@ -1089,10 +1089,10 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	unsigned int size;
 	u16 snb_gmch_ctl;
 
-	if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR))
+	if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR))
 		return -ENXIO;
 
-	ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR);
+	ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR);
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 
 	/*
@@ -1308,7 +1308,7 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
 		wbinvd_on_all_cpus();
 
 	if (GRAPHICS_VER(ggtt->vm.i915) >= 8)
-		setup_private_pat(ggtt->vm.gt->uncore);
+		setup_private_pat(ggtt->vm.gt);
 
 	intel_ggtt_restore_fences(ggtt);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index d4e9702d3c8e..f50ea92910d9 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -187,6 +187,10 @@
 #define   MI_BATCH_RESOURCE_STREAMER REG_BIT(10)
 #define   MI_BATCH_PREDICATE         REG_BIT(15) /* HSW+ on RCS only*/
 
+#define MI_OPCODE(x)		(((x) >> 23) & 0x3f)
+#define IS_MI_LRI_CMD(x)	(MI_OPCODE(x) == MI_OPCODE(MI_INSTR(0x22, 0)))
+#define MI_LRI_LEN(x)		(((x) & 0xff) + 1)
+
 /*
  * 3D instructions used by the kernel
  */
diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c
index 7af6db3194dd..976fdf27e790 100644
--- a/drivers/gpu/drm/i915/gt/intel_gsc.c
+++ b/drivers/gpu/drm/i915/gt/intel_gsc.c
@@ -7,6 +7,7 @@
 #include <linux/mei_aux.h>
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 #include "gt/intel_gsc.h"
 #include "gt/intel_gt.h"
@@ -142,8 +143,14 @@ static void gsc_destroy_one(struct drm_i915_private *i915,
 	struct intel_gsc_intf *intf = &gsc->intf[intf_id];
 
 	if (intf->adev) {
-		auxiliary_device_delete(&intf->adev->aux_dev);
-		auxiliary_device_uninit(&intf->adev->aux_dev);
+		struct auxiliary_device *aux_dev = &intf->adev->aux_dev;
+
+		if (intf_id == 0)
+			intel_huc_unregister_gsc_notifier(&gsc_to_gt(gsc)->uc.huc,
+							  aux_dev->dev.bus);
+
+		auxiliary_device_delete(aux_dev);
+		auxiliary_device_uninit(aux_dev);
 		intf->adev = NULL;
 	}
 
@@ -242,14 +249,24 @@ add_device:
 		goto fail;
 	}
 
+	intf->adev = adev; /* needed by the notifier */
+
+	if (intf_id == 0)
+		intel_huc_register_gsc_notifier(&gsc_to_gt(gsc)->uc.huc,
+						aux_dev->dev.bus);
+
 	ret = auxiliary_device_add(aux_dev);
 	if (ret < 0) {
 		drm_err(&i915->drm, "gsc aux add failed %d\n", ret);
+		if (intf_id == 0)
+			intel_huc_unregister_gsc_notifier(&gsc_to_gt(gsc)->uc.huc,
+							  aux_dev->dev.bus);
+		intf->adev = NULL;
+
 		/* adev will be freed with the put_device() and .release sequence */
 		auxiliary_device_uninit(aux_dev);
 		goto fail;
 	}
-	intf->adev = adev;
 
 	return;
 fail:
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index d0b03a928b9a..8e914c4066ed 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -40,8 +40,6 @@ void intel_gt_common_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(gt->irq_lock);
 
-	INIT_LIST_HEAD(&gt->lmem_userfault_list);
-	mutex_init(&gt->lmem_userfault_lock);
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -231,6 +229,16 @@ static void gen6_clear_engine_error_register(struct intel_engine_cs *engine)
 	GEN6_RING_FAULT_REG_POSTING_READ(engine);
 }
 
+i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt)
+{
+	/* GT0_PERF_LIMIT_REASONS is available only for Gen11+ */
+	if (GRAPHICS_VER(gt->i915) < 11)
+		return INVALID_MMIO_REG;
+
+	return gt->type == GT_MEDIA ?
+		MTL_MEDIA_PERF_LIMIT_REASONS : GT0_PERF_LIMIT_REASONS;
+}
+
 void
 intel_gt_clear_error_registers(struct intel_gt *gt,
 			       intel_engine_mask_t engine_mask)
@@ -260,7 +268,11 @@ intel_gt_clear_error_registers(struct intel_gt *gt,
 				   I915_MASTER_ERROR_INTERRUPT);
 	}
 
-	if (GRAPHICS_VER(i915) >= 12) {
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+		intel_gt_mcr_multicast_rmw(gt, XEHP_RING_FAULT_REG,
+					   RING_FAULT_VALID, 0);
+		intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG);
+	} else if (GRAPHICS_VER(i915) >= 12) {
 		rmw_clear(uncore, GEN12_RING_FAULT_REG, RING_FAULT_VALID);
 		intel_uncore_posting_read(uncore, GEN12_RING_FAULT_REG);
 	} else if (GRAPHICS_VER(i915) >= 8) {
@@ -298,6 +310,42 @@ static void gen6_check_faults(struct intel_gt *gt)
 	}
 }
 
+static void xehp_check_faults(struct intel_gt *gt)
+{
+	u32 fault;
+
+	/*
+	 * Although the fault register now lives in an MCR register range,
+	 * the GAM registers are special and we only truly need to read
+	 * the "primary" GAM instance rather than handling each instance
+	 * individually.  intel_gt_mcr_read_any() will automatically steer
+	 * toward the primary instance.
+	 */
+	fault = intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG);
+	if (fault & RING_FAULT_VALID) {
+		u32 fault_data0, fault_data1;
+		u64 fault_addr;
+
+		fault_data0 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA0);
+		fault_data1 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA1);
+
+		fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) |
+			     ((u64)fault_data0 << 12);
+
+		drm_dbg(&gt->i915->drm, "Unexpected fault\n"
+			"\tAddr: 0x%08x_%08x\n"
+			"\tAddress space: %s\n"
+			"\tEngine ID: %d\n"
+			"\tSource ID: %d\n"
+			"\tType: %d\n",
+			upper_32_bits(fault_addr), lower_32_bits(fault_addr),
+			fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT",
+			GEN8_RING_FAULT_ENGINE_ID(fault),
+			RING_FAULT_SRCID(fault),
+			RING_FAULT_FAULT_TYPE(fault));
+	}
+}
+
 static void gen8_check_faults(struct intel_gt *gt)
 {
 	struct intel_uncore *uncore = gt->uncore;
@@ -344,7 +392,9 @@ void intel_gt_check_and_clear_faults(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 
 	/* From GEN8 onwards we only have one 'All Engine Fault Register' */
-	if (GRAPHICS_VER(i915) >= 8)
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+		xehp_check_faults(gt);
+	else if (GRAPHICS_VER(i915) >= 8)
 		gen8_check_faults(gt);
 	else if (GRAPHICS_VER(i915) >= 6)
 		gen6_check_faults(gt);
@@ -807,7 +857,6 @@ static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr)
 	}
 
 	intel_uncore_init_early(gt->uncore, gt);
-	intel_wakeref_auto_init(&gt->userfault_wakeref, gt->uncore->rpm);
 
 	ret = intel_uncore_setup_mmio(gt->uncore, phys_addr);
 	if (ret)
@@ -828,7 +877,7 @@ int intel_gt_probe_all(struct drm_i915_private *i915)
 	unsigned int i;
 	int ret;
 
-	mmio_bar = GRAPHICS_VER(i915) == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR;
+	mmio_bar = intel_mmio_bar(GRAPHICS_VER(i915));
 	phys_addr = pci_resource_start(pdev, mmio_bar);
 
 	/*
@@ -939,7 +988,10 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 }
 
 struct reg_and_bit {
-	i915_reg_t reg;
+	union {
+		i915_reg_t reg;
+		i915_mcr_reg_t mcr_reg;
+	};
 	u32 bit;
 };
 
@@ -965,6 +1017,32 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 	return rb;
 }
 
+/*
+ * HW architecture suggest typical invalidation time at 40us,
+ * with pessimistic cases up to 100us and a recommendation to
+ * cap at 1ms. We go a bit higher just in case.
+ */
+#define TLB_INVAL_TIMEOUT_US 100
+#define TLB_INVAL_TIMEOUT_MS 4
+
+/*
+ * On Xe_HP the TLB invalidation registers are located at the same MMIO offsets
+ * but are now considered MCR registers.  Since they exist within a GAM range,
+ * the primary instance of the register rolls up the status from each unit.
+ */
+static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
+{
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+		return intel_gt_mcr_wait_for_reg_fw(gt, rb.mcr_reg, rb.bit, 0,
+						    TLB_INVAL_TIMEOUT_US,
+						    TLB_INVAL_TIMEOUT_MS);
+	else
+		return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0,
+						    TLB_INVAL_TIMEOUT_US,
+						    TLB_INVAL_TIMEOUT_MS,
+						    NULL);
+}
+
 static void mmio_invalidate_full(struct intel_gt *gt)
 {
 	static const i915_reg_t gen8_regs[] = {
@@ -980,6 +1058,13 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 		[COPY_ENGINE_CLASS]		= GEN12_BLT_TLB_INV_CR,
 		[COMPUTE_CLASS]			= GEN12_COMPCTX_TLB_INV_CR,
 	};
+	static const i915_mcr_reg_t xehp_regs[] = {
+		[RENDER_CLASS]			= XEHP_GFX_TLB_INV_CR,
+		[VIDEO_DECODE_CLASS]		= XEHP_VD_TLB_INV_CR,
+		[VIDEO_ENHANCEMENT_CLASS]	= XEHP_VE_TLB_INV_CR,
+		[COPY_ENGINE_CLASS]		= XEHP_BLT_TLB_INV_CR,
+		[COMPUTE_CLASS]			= XEHP_COMPCTX_TLB_INV_CR,
+	};
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
@@ -988,7 +1073,10 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	const i915_reg_t *regs;
 	unsigned int num = 0;
 
-	if (GRAPHICS_VER(i915) == 12) {
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+		regs = NULL;
+		num = ARRAY_SIZE(xehp_regs);
+	} else if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
 	} else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) {
@@ -1013,11 +1101,17 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 		if (!intel_engine_pm_is_awake(engine))
 			continue;
 
-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (!i915_mmio_reg_offset(rb.reg))
-			continue;
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			intel_gt_mcr_multicast_write_fw(gt,
+							xehp_regs[engine->class],
+							BIT(engine->instance));
+		} else {
+			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+			if (!i915_mmio_reg_offset(rb.reg))
+				continue;
 
-		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+			intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		}
 		awake |= engine->mask;
 	}
 
@@ -1037,22 +1131,17 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	for_each_engine_masked(engine, gt, awake, tmp) {
 		struct reg_and_bit rb;
 
-		/*
-		 * HW architecture suggest typical invalidation time at 40us,
-		 * with pessimistic cases up to 100us and a recommendation to
-		 * cap at 1ms. We go a bit higher just in case.
-		 */
-		const unsigned int timeout_us = 100;
-		const unsigned int timeout_ms = 4;
-
-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (__intel_wait_for_register_fw(uncore,
-						 rb.reg, rb.bit, 0,
-						 timeout_us, timeout_ms,
-						 NULL))
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			rb.mcr_reg = xehp_regs[engine->class];
+			rb.bit = BIT(engine->instance);
+		} else {
+			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		}
+
+		if (wait_for_invalidate(gt, rb))
 			drm_err_ratelimited(&gt->i915->drm,
 					    "%s TLB invalidation did not complete in %ums!\n",
-					    engine->name, timeout_ms);
+					    engine->name, TLB_INVAL_TIMEOUT_MS);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 2ee582e287c8..e0365d556248 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -60,6 +60,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915);
 int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 
 void intel_gt_check_and_clear_faults(struct intel_gt *gt);
+i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt);
 void intel_gt_clear_error_registers(struct intel_gt *gt,
 				    intel_engine_mask_t engine_mask);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 3f656d3dba9a..2a6a4ca7fdad 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -107,7 +107,7 @@ static u32 gen9_read_clock_frequency(struct intel_uncore *uncore)
 	return freq;
 }
 
-static u32 gen5_read_clock_frequency(struct intel_uncore *uncore)
+static u32 gen6_read_clock_frequency(struct intel_uncore *uncore)
 {
 	/*
 	 * PRMs say:
@@ -119,7 +119,27 @@ static u32 gen5_read_clock_frequency(struct intel_uncore *uncore)
 	return 12500000;
 }
 
-static u32 gen2_read_clock_frequency(struct intel_uncore *uncore)
+static u32 gen5_read_clock_frequency(struct intel_uncore *uncore)
+{
+	/*
+	 * 63:32 increments every 1000 ns
+	 * 31:0 mbz
+	 */
+	return 1000000000 / 1000;
+}
+
+static u32 g4x_read_clock_frequency(struct intel_uncore *uncore)
+{
+	/*
+	 * 63:20 increments every 1/4 ns
+	 * 19:0 mbz
+	 *
+	 * -> 63:32 increments every 1024 ns
+	 */
+	return 1000000000 / 1024;
+}
+
+static u32 gen4_read_clock_frequency(struct intel_uncore *uncore)
 {
 	/*
 	 * PRMs say:
@@ -127,8 +147,10 @@ static u32 gen2_read_clock_frequency(struct intel_uncore *uncore)
 	 *     "The value in this register increments once every 16
 	 *      hclks." (through the “Clocking Configuration”
 	 *      (“CLKCFG”) MCHBAR register)
+	 *
+	 * Testing on actual hardware has shown there is no /16.
 	 */
-	return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16;
+	return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000;
 }
 
 static u32 read_clock_frequency(struct intel_uncore *uncore)
@@ -137,10 +159,16 @@ static u32 read_clock_frequency(struct intel_uncore *uncore)
 		return gen11_read_clock_frequency(uncore);
 	else if (GRAPHICS_VER(uncore->i915) >= 9)
 		return gen9_read_clock_frequency(uncore);
-	else if (GRAPHICS_VER(uncore->i915) >= 5)
+	else if (GRAPHICS_VER(uncore->i915) >= 6)
+		return gen6_read_clock_frequency(uncore);
+	else if (GRAPHICS_VER(uncore->i915) == 5)
 		return gen5_read_clock_frequency(uncore);
+	else if (IS_G4X(uncore->i915))
+		return g4x_read_clock_frequency(uncore);
+	else if (GRAPHICS_VER(uncore->i915) == 4)
+		return gen4_read_clock_frequency(uncore);
 	else
-		return gen2_read_clock_frequency(uncore);
+		return 0;
 }
 
 void intel_gt_init_clock_frequency(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index e79405a45312..830edffe88cc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -40,6 +40,9 @@ static const char * const intel_steering_types[] = {
 	"L3BANK",
 	"MSLICE",
 	"LNCF",
+	"GAM",
+	"DSS",
+	"OADDRM",
 	"INSTANCE 0",
 };
 
@@ -48,14 +51,23 @@ static const struct intel_mmio_range icl_l3bank_steering_table[] = {
 	{},
 };
 
+/*
+ * Although the bspec lists more "MSLICE" ranges than shown here, some of those
+ * are of a "GAM" subclass that has special rules.  Thus we use a separate
+ * GAM table farther down for those.
+ */
 static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = {
-	{ 0x004000, 0x004AFF },
-	{ 0x00C800, 0x00CFFF },
 	{ 0x00DD00, 0x00DDFF },
 	{ 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */
 	{},
 };
 
+static const struct intel_mmio_range xehpsdv_gam_steering_table[] = {
+	{ 0x004000, 0x004AFF },
+	{ 0x00C800, 0x00CFFF },
+	{},
+};
+
 static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = {
 	{ 0x00B000, 0x00B0FF },
 	{ 0x00D800, 0x00D8FF },
@@ -89,9 +101,47 @@ static const struct intel_mmio_range pvc_instance0_steering_table[] = {
 	{},
 };
 
+static const struct intel_mmio_range xelpg_instance0_steering_table[] = {
+	{ 0x000B00, 0x000BFF },         /* SQIDI */
+	{ 0x001000, 0x001FFF },         /* SQIDI */
+	{ 0x004000, 0x0048FF },         /* GAM */
+	{ 0x008700, 0x0087FF },         /* SQIDI */
+	{ 0x00B000, 0x00B0FF },         /* NODE */
+	{ 0x00C800, 0x00CFFF },         /* GAM */
+	{ 0x00D880, 0x00D8FF },         /* NODE */
+	{ 0x00DD00, 0x00DDFF },         /* OAAL2 */
+	{},
+};
+
+static const struct intel_mmio_range xelpg_l3bank_steering_table[] = {
+	{ 0x00B100, 0x00B3FF },
+	{},
+};
+
+/* DSS steering is used for SLICE ranges as well */
+static const struct intel_mmio_range xelpg_dss_steering_table[] = {
+	{ 0x005200, 0x0052FF },		/* SLICE */
+	{ 0x005500, 0x007FFF },		/* SLICE */
+	{ 0x008140, 0x00815F },		/* SLICE (0x8140-0x814F), DSS (0x8150-0x815F) */
+	{ 0x0094D0, 0x00955F },		/* SLICE (0x94D0-0x951F), DSS (0x9520-0x955F) */
+	{ 0x009680, 0x0096FF },		/* DSS */
+	{ 0x00D800, 0x00D87F },		/* SLICE */
+	{ 0x00DC00, 0x00DCFF },		/* SLICE */
+	{ 0x00DE80, 0x00E8FF },		/* DSS (0xE000-0xE0FF reserved) */
+	{},
+};
+
+static const struct intel_mmio_range xelpmp_oaddrm_steering_table[] = {
+	{ 0x393200, 0x39323F },
+	{ 0x393400, 0x3934FF },
+	{},
+};
+
 void intel_gt_mcr_init(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
+	unsigned long fuse;
+	int i;
 
 	/*
 	 * An mslice is unavailable only if both the meml3 for the slice is
@@ -109,14 +159,36 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 			drm_warn(&i915->drm, "mslice mask all zero!\n");
 	}
 
-	if (IS_PONTEVECCHIO(i915)) {
+	if (MEDIA_VER(i915) >= 13 && gt->type == GT_MEDIA) {
+		gt->steering_table[OADDRM] = xelpmp_oaddrm_steering_table;
+	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) {
+		fuse = REG_FIELD_GET(GT_L3_EXC_MASK,
+				     intel_uncore_read(gt->uncore, XEHP_FUSE4));
+
+		/*
+		 * Despite the register field being named "exclude mask" the
+		 * bits actually represent enabled banks (two banks per bit).
+		 */
+		for_each_set_bit(i, &fuse, 3)
+			gt->info.l3bank_mask |= 0x3 << 2 * i;
+
+		gt->steering_table[INSTANCE0] = xelpg_instance0_steering_table;
+		gt->steering_table[L3BANK] = xelpg_l3bank_steering_table;
+		gt->steering_table[DSS] = xelpg_dss_steering_table;
+	} else if (IS_PONTEVECCHIO(i915)) {
 		gt->steering_table[INSTANCE0] = pvc_instance0_steering_table;
 	} else if (IS_DG2(i915)) {
 		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
 		gt->steering_table[LNCF] = dg2_lncf_steering_table;
+		/*
+		 * No need to hook up the GAM table since it has a dedicated
+		 * steering control register on DG2 and can use implicit
+		 * steering.
+		 */
 	} else if (IS_XEHPSDV(i915)) {
 		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
 		gt->steering_table[LNCF] = xehpsdv_lncf_steering_table;
+		gt->steering_table[GAM] = xehpsdv_gam_steering_table;
 	} else if (GRAPHICS_VER(i915) >= 11 &&
 		   GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) {
 		gt->steering_table[L3BANK] = icl_l3bank_steering_table;
@@ -135,6 +207,19 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 }
 
 /*
+ * Although the rest of the driver should use MCR-specific functions to
+ * read/write MCR registers, we still use the regular intel_uncore_* functions
+ * internally to implement those, so we need a way for the functions in this
+ * file to "cast" an i915_mcr_reg_t into an i915_reg_t.
+ */
+static i915_reg_t mcr_reg_cast(const i915_mcr_reg_t mcr)
+{
+	i915_reg_t r = { .reg = mcr.reg };
+
+	return r;
+}
+
+/*
  * rw_with_mcr_steering_fw - Access a register with specific MCR steering
  * @uncore: pointer to struct intel_uncore
  * @reg: register being accessed
@@ -148,14 +233,26 @@ void intel_gt_mcr_init(struct intel_gt *gt)
  * Caller needs to make sure the relevant forcewake wells are up.
  */
 static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
-				   i915_reg_t reg, u8 rw_flag,
+				   i915_mcr_reg_t reg, u8 rw_flag,
 				   int group, int instance, u32 value)
 {
 	u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0;
 
 	lockdep_assert_held(&uncore->lock);
 
-	if (GRAPHICS_VER(uncore->i915) >= 11) {
+	if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70)) {
+		/*
+		 * Always leave the hardware in multicast mode when doing reads
+		 * (see comment about Wa_22013088509 below) and only change it
+		 * to unicast mode when doing writes of a specific instance.
+		 *
+		 * No need to save old steering reg value.
+		 */
+		intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR,
+				      REG_FIELD_PREP(MTL_MCR_GROUPID, group) |
+				      REG_FIELD_PREP(MTL_MCR_INSTANCEID, instance) |
+				      (rw_flag == FW_REG_READ ? GEN11_MCR_MULTICAST : 0));
+	} else if (GRAPHICS_VER(uncore->i915) >= 11) {
 		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN11_MCR_SLICE(group) | GEN11_MCR_SUBSLICE(instance);
 
@@ -173,39 +270,53 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 		 */
 		if (rw_flag == FW_REG_WRITE)
 			mcr_mask |= GEN11_MCR_MULTICAST;
+
+		mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		old_mcr = mcr;
+
+		mcr &= ~mcr_mask;
+		mcr |= mcr_ss;
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 	} else {
 		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN8_MCR_SLICE(group) | GEN8_MCR_SUBSLICE(instance);
-	}
 
-	old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		old_mcr = mcr;
 
-	mcr &= ~mcr_mask;
-	mcr |= mcr_ss;
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+		mcr &= ~mcr_mask;
+		mcr |= mcr_ss;
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+	}
 
 	if (rw_flag == FW_REG_READ)
-		val = intel_uncore_read_fw(uncore, reg);
+		val = intel_uncore_read_fw(uncore, mcr_reg_cast(reg));
 	else
-		intel_uncore_write_fw(uncore, reg, value);
-
-	mcr &= ~mcr_mask;
-	mcr |= old_mcr & mcr_mask;
+		intel_uncore_write_fw(uncore, mcr_reg_cast(reg), value);
 
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+	/*
+	 * For pre-MTL platforms, we need to restore the old value of the
+	 * steering control register to ensure that implicit steering continues
+	 * to behave as expected.  For MTL and beyond, we need only reinstate
+	 * the 'multicast' bit (and only if we did a write that cleared it).
+	 */
+	if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70) && rw_flag == FW_REG_WRITE)
+		intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+	else if (GRAPHICS_VER_FULL(uncore->i915) < IP_VER(12, 70))
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, old_mcr);
 
 	return val;
 }
 
 static u32 rw_with_mcr_steering(struct intel_uncore *uncore,
-				i915_reg_t reg, u8 rw_flag,
+				i915_mcr_reg_t reg, u8 rw_flag,
 				int group, int instance,
 				u32 value)
 {
 	enum forcewake_domains fw_domains;
 	u32 val;
 
-	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, mcr_reg_cast(reg),
 						    rw_flag);
 	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
 						     GEN8_MCR_SELECTOR,
@@ -233,7 +344,7 @@ static u32 rw_with_mcr_steering(struct intel_uncore *uncore,
  * group/instance.
  */
 u32 intel_gt_mcr_read(struct intel_gt *gt,
-		      i915_reg_t reg,
+		      i915_mcr_reg_t reg,
 		      int group, int instance)
 {
 	return rw_with_mcr_steering(gt->uncore, reg, FW_REG_READ, group, instance, 0);
@@ -250,7 +361,7 @@ u32 intel_gt_mcr_read(struct intel_gt *gt,
  * Write an MCR register in unicast mode after steering toward a specific
  * group/instance.
  */
-void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value,
+void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value,
 				int group, int instance)
 {
 	rw_with_mcr_steering(gt->uncore, reg, FW_REG_WRITE, group, instance, value);
@@ -265,9 +376,16 @@ void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value,
  * Write an MCR register in multicast mode to update all instances.
  */
 void intel_gt_mcr_multicast_write(struct intel_gt *gt,
-				i915_reg_t reg, u32 value)
+				  i915_mcr_reg_t reg, u32 value)
 {
-	intel_uncore_write(gt->uncore, reg, value);
+	/*
+	 * Ensure we have multicast behavior, just in case some non-i915 agent
+	 * left the hardware in unicast mode.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+		intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+
+	intel_uncore_write(gt->uncore, mcr_reg_cast(reg), value);
 }
 
 /**
@@ -281,9 +399,44 @@ void intel_gt_mcr_multicast_write(struct intel_gt *gt,
  * domains; use intel_gt_mcr_multicast_write() in cases where forcewake should
  * be obtained automatically.
  */
-void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 value)
+void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value)
+{
+	/*
+	 * Ensure we have multicast behavior, just in case some non-i915 agent
+	 * left the hardware in unicast mode.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+		intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+
+	intel_uncore_write_fw(gt->uncore, mcr_reg_cast(reg), value);
+}
+
+/**
+ * intel_gt_mcr_multicast_rmw - Performs a multicast RMW operations
+ * @gt: GT structure
+ * @reg: the MCR register to read and write
+ * @clear: bits to clear during RMW
+ * @set: bits to set during RMW
+ *
+ * Performs a read-modify-write on an MCR register in a multicast manner.
+ * This operation only makes sense on MCR registers where all instances are
+ * expected to have the same value.  The read will target any non-terminated
+ * instance and the write will be applied to all instances.
+ *
+ * This function assumes the caller is already holding any necessary forcewake
+ * domains; use intel_gt_mcr_multicast_rmw() in cases where forcewake should
+ * be obtained automatically.
+ *
+ * Returns the old (unmodified) value read.
+ */
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg,
+			       u32 clear, u32 set)
 {
-	intel_uncore_write_fw(gt->uncore, reg, value);
+	u32 val = intel_gt_mcr_read_any(gt, reg);
+
+	intel_gt_mcr_multicast_write(gt, reg, (val & ~clear) | set);
+
+	return val;
 }
 
 /*
@@ -301,7 +454,7 @@ void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 va
  * for @type steering too.
  */
 static bool reg_needs_read_steering(struct intel_gt *gt,
-				    i915_reg_t reg,
+				    i915_mcr_reg_t reg,
 				    enum intel_steering_type type)
 {
 	const u32 offset = i915_mmio_reg_offset(reg);
@@ -332,6 +485,8 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 				       enum intel_steering_type type,
 				       u8 *group, u8 *instance)
 {
+	u32 dss;
+
 	switch (type) {
 	case L3BANK:
 		*group = 0;		/* unused */
@@ -351,6 +506,15 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 		*group = __ffs(gt->info.mslice_mask) << 1;
 		*instance = 0;	/* unused */
 		break;
+	case GAM:
+		*group = IS_DG2(gt->i915) ? 1 : 0;
+		*instance = 0;
+		break;
+	case DSS:
+		dss = intel_sseu_find_first_xehp_dss(&gt->info.sseu, 0, 0);
+		*group = dss / GEN_DSS_PER_GSLICE;
+		*instance = dss % GEN_DSS_PER_GSLICE;
+		break;
 	case INSTANCE0:
 		/*
 		 * There are a lot of MCR types for which instance (0, 0)
@@ -359,6 +523,13 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 		*group = 0;
 		*instance = 0;
 		break;
+	case OADDRM:
+		if ((VDBOX_MASK(gt) | VEBOX_MASK(gt) | gt->info.sfc_mask) & BIT(0))
+			*group = 0;
+		else
+			*group = 1;
+		*instance = 0;
+		break;
 	default:
 		MISSING_CASE(type);
 		*group = 0;
@@ -380,7 +551,7 @@ static void get_nonterminated_steering(struct intel_gt *gt,
  * steering.
  */
 void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
-					     i915_reg_t reg,
+					     i915_mcr_reg_t reg,
 					     u8 *group, u8 *instance)
 {
 	int type;
@@ -409,7 +580,7 @@ void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
  *
  * Returns the value from a non-terminated instance of @reg.
  */
-u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg)
 {
 	int type;
 	u8 group, instance;
@@ -423,7 +594,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
 		}
 	}
 
-	return intel_uncore_read_fw(gt->uncore, reg);
+	return intel_uncore_read_fw(gt->uncore, mcr_reg_cast(reg));
 }
 
 /**
@@ -436,7 +607,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
  *
  * Returns the value from a non-terminated instance of @reg.
  */
-u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg)
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg)
 {
 	int type;
 	u8 group, instance;
@@ -450,7 +621,7 @@ u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg)
 		}
 	}
 
-	return intel_uncore_read(gt->uncore, reg);
+	return intel_uncore_read(gt->uncore, mcr_reg_cast(reg));
 }
 
 static void report_steering_type(struct drm_printer *p,
@@ -483,11 +654,20 @@ static void report_steering_type(struct drm_printer *p,
 void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 				  bool dump_table)
 {
-	drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n",
-		   gt->default_steering.groupid,
-		   gt->default_steering.instanceid);
-
-	if (IS_PONTEVECCHIO(gt->i915)) {
+	/*
+	 * Starting with MTL we no longer have default steering;
+	 * all ranges are explicitly steered.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70))
+		drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n",
+			   gt->default_steering.groupid,
+			   gt->default_steering.instanceid);
+
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) {
+		for (int i = 0; i < NUM_STEERING_TYPES; i++)
+			if (gt->steering_table[i])
+				report_steering_type(p, gt, i, dump_table);
+	} else if (IS_PONTEVECCHIO(gt->i915)) {
 		report_steering_type(p, gt, INSTANCE0, dump_table);
 	} else if (HAS_MSLICE_STEERING(gt->i915)) {
 		report_steering_type(p, gt, MSLICE, dump_table);
@@ -520,3 +700,58 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 		return;
 	}
 }
+
+/**
+ * intel_gt_mcr_wait_for_reg_fw - wait until MCR register matches expected state
+ * @gt: GT structure
+ * @reg: the register to read
+ * @mask: mask to apply to register value
+ * @value: value to wait for
+ * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait
+ * @slow_timeout_ms: slow timeout in millisecond
+ *
+ * This routine waits until the target register @reg contains the expected
+ * @value after applying the @mask, i.e. it waits until ::
+ *
+ *     (intel_gt_mcr_read_any_fw(gt, reg) & mask) == value
+ *
+ * Otherwise, the wait will timeout after @slow_timeout_ms milliseconds.
+ * For atomic context @slow_timeout_ms must be zero and @fast_timeout_us
+ * must be not larger than 20,0000 microseconds.
+ *
+ * This function is basically an MCR-friendly version of
+ * __intel_wait_for_register_fw().  Generally this function will only be used
+ * on GAM registers which are a bit special --- although they're MCR registers,
+ * reads (e.g., waiting for status updates) are always directed to the primary
+ * instance.
+ *
+ * Note that this routine assumes the caller holds forcewake asserted, it is
+ * not suitable for very long waits.
+ *
+ * Return: 0 if the register matches the desired condition, or -ETIMEDOUT.
+ */
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_mcr_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms)
+{
+	u32 reg_value = 0;
+#define done (((reg_value = intel_gt_mcr_read_any_fw(gt, reg)) & mask) == value)
+	int ret;
+
+	/* Catch any overuse of this function */
+	might_sleep_if(slow_timeout_ms);
+	GEM_BUG_ON(fast_timeout_us > 20000);
+	GEM_BUG_ON(!fast_timeout_us && !slow_timeout_ms);
+
+	ret = -ETIMEDOUT;
+	if (fast_timeout_us && fast_timeout_us <= 20000)
+		ret = _wait_for_atomic(done, fast_timeout_us, 0);
+	if (ret && slow_timeout_ms)
+		ret = wait_for(done, slow_timeout_ms);
+
+	return ret;
+#undef done
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
index 77a8b11c287d..3fb0502bff22 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -11,21 +11,24 @@
 void intel_gt_mcr_init(struct intel_gt *gt);
 
 u32 intel_gt_mcr_read(struct intel_gt *gt,
-		      i915_reg_t reg,
+		      i915_mcr_reg_t reg,
 		      int group, int instance);
-u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg);
-u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg);
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg);
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg);
 
 void intel_gt_mcr_unicast_write(struct intel_gt *gt,
-				i915_reg_t reg, u32 value,
+				i915_mcr_reg_t reg, u32 value,
 				int group, int instance);
 void intel_gt_mcr_multicast_write(struct intel_gt *gt,
-				  i915_reg_t reg, u32 value);
+				  i915_mcr_reg_t reg, u32 value);
 void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt,
-				     i915_reg_t reg, u32 value);
+				     i915_mcr_reg_t reg, u32 value);
+
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg,
+			       u32 clear, u32 set);
 
 void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
-					     i915_reg_t reg,
+					     i915_mcr_reg_t reg,
 					     u8 *group, u8 *instance);
 
 void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
@@ -34,6 +37,13 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 				  unsigned int *group, unsigned int *instance);
 
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_mcr_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms);
+
 /*
  * Helper for for_each_ss_steering loop.  On pre-Xe_HP platforms, subslice
  * presence is determined by using the group/instance as direct lookups in the
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
index 108b9e76c32e..40d0a3be42ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
@@ -344,162 +344,7 @@ void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p)
 		drm_printf(p, "efficient (RPe) frequency: %d MHz\n",
 			   intel_gpu_freq(rps, rps->efficient_freq));
 	} else if (GRAPHICS_VER(i915) >= 6) {
-		u32 rp_state_limits;
-		u32 gt_perf_status;
-		struct intel_rps_freq_caps caps;
-		u32 rpmodectl, rpinclimit, rpdeclimit;
-		u32 rpstat, cagf, reqf;
-		u32 rpcurupei, rpcurup, rpprevup;
-		u32 rpcurdownei, rpcurdown, rpprevdown;
-		u32 rpupei, rpupt, rpdownei, rpdownt;
-		u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
-
-		rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
-		gen6_rps_get_freq_caps(rps, &caps);
-		if (IS_GEN9_LP(i915))
-			gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
-		else
-			gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS);
-
-		/* RPSTAT1 is in the GT power well */
-		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
-
-		reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ);
-		if (GRAPHICS_VER(i915) >= 9) {
-			reqf >>= 23;
-		} else {
-			reqf &= ~GEN6_TURBO_DISABLE;
-			if (IS_HASWELL(i915) || IS_BROADWELL(i915))
-				reqf >>= 24;
-			else
-				reqf >>= 25;
-		}
-		reqf = intel_gpu_freq(rps, reqf);
-
-		rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
-		rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
-		rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
-
-		rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1);
-		rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
-		rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK;
-		rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK;
-		rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
-		rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
-		rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-
-		rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI);
-		rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
-
-		rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI);
-		rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
-
-		cagf = intel_rps_read_actual_frequency(rps);
-
-		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
-
-		if (GRAPHICS_VER(i915) >= 11) {
-			pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE);
-			pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK);
-			/*
-			 * The equivalent to the PM ISR & IIR cannot be read
-			 * without affecting the current state of the system
-			 */
-			pm_isr = 0;
-			pm_iir = 0;
-		} else if (GRAPHICS_VER(i915) >= 8) {
-			pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2));
-			pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2));
-			pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2));
-			pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2));
-		} else {
-			pm_ier = intel_uncore_read(uncore, GEN6_PMIER);
-			pm_imr = intel_uncore_read(uncore, GEN6_PMIMR);
-			pm_isr = intel_uncore_read(uncore, GEN6_PMISR);
-			pm_iir = intel_uncore_read(uncore, GEN6_PMIIR);
-		}
-		pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK);
-
-		drm_printf(p, "Video Turbo Mode: %s\n",
-			   str_yes_no(rpmodectl & GEN6_RP_MEDIA_TURBO));
-		drm_printf(p, "HW control enabled: %s\n",
-			   str_yes_no(rpmodectl & GEN6_RP_ENABLE));
-		drm_printf(p, "SW control enabled: %s\n",
-			   str_yes_no((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE));
-
-		drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
-			   pm_ier, pm_imr, pm_mask);
-		if (GRAPHICS_VER(i915) <= 10)
-			drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n",
-				   pm_isr, pm_iir);
-		drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n",
-			   rps->pm_intrmsk_mbz);
-		drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
-		drm_printf(p, "Render p-state ratio: %d\n",
-			   (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8);
-		drm_printf(p, "Render p-state VID: %d\n",
-			   gt_perf_status & 0xff);
-		drm_printf(p, "Render p-state limit: %d\n",
-			   rp_state_limits & 0xff);
-		drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat);
-		drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl);
-		drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit);
-		drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
-		drm_printf(p, "RPNSWREQ: %dMHz\n", reqf);
-		drm_printf(p, "CAGF: %dMHz\n", cagf);
-		drm_printf(p, "RP CUR UP EI: %d (%lldns)\n",
-			   rpcurupei,
-			   intel_gt_pm_interval_to_ns(gt, rpcurupei));
-		drm_printf(p, "RP CUR UP: %d (%lldns)\n",
-			   rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup));
-		drm_printf(p, "RP PREV UP: %d (%lldns)\n",
-			   rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup));
-		drm_printf(p, "Up threshold: %d%%\n",
-			   rps->power.up_threshold);
-		drm_printf(p, "RP UP EI: %d (%lldns)\n",
-			   rpupei, intel_gt_pm_interval_to_ns(gt, rpupei));
-		drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n",
-			   rpupt, intel_gt_pm_interval_to_ns(gt, rpupt));
-
-		drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n",
-			   rpcurdownei,
-			   intel_gt_pm_interval_to_ns(gt, rpcurdownei));
-		drm_printf(p, "RP CUR DOWN: %d (%lldns)\n",
-			   rpcurdown,
-			   intel_gt_pm_interval_to_ns(gt, rpcurdown));
-		drm_printf(p, "RP PREV DOWN: %d (%lldns)\n",
-			   rpprevdown,
-			   intel_gt_pm_interval_to_ns(gt, rpprevdown));
-		drm_printf(p, "Down threshold: %d%%\n",
-			   rps->power.down_threshold);
-		drm_printf(p, "RP DOWN EI: %d (%lldns)\n",
-			   rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei));
-		drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n",
-			   rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt));
-
-		drm_printf(p, "Lowest (RPN) frequency: %dMHz\n",
-			   intel_gpu_freq(rps, caps.min_freq));
-		drm_printf(p, "Nominal (RP1) frequency: %dMHz\n",
-			   intel_gpu_freq(rps, caps.rp1_freq));
-		drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n",
-			   intel_gpu_freq(rps, caps.rp0_freq));
-		drm_printf(p, "Max overclocked frequency: %dMHz\n",
-			   intel_gpu_freq(rps, rps->max_freq));
-
-		drm_printf(p, "Current freq: %d MHz\n",
-			   intel_gpu_freq(rps, rps->cur_freq));
-		drm_printf(p, "Actual freq: %d MHz\n", cagf);
-		drm_printf(p, "Idle freq: %d MHz\n",
-			   intel_gpu_freq(rps, rps->idle_freq));
-		drm_printf(p, "Min freq: %d MHz\n",
-			   intel_gpu_freq(rps, rps->min_freq));
-		drm_printf(p, "Boost freq: %d MHz\n",
-			   intel_gpu_freq(rps, rps->boost_freq));
-		drm_printf(p, "Max freq: %d MHz\n",
-			   intel_gpu_freq(rps, rps->max_freq));
-		drm_printf(p,
-			   "efficient (RPe) frequency: %d MHz\n",
-			   intel_gpu_freq(rps, rps->efficient_freq));
+		gen6_rps_frequency_dump(rps, p);
 	} else {
 		drm_puts(p, "no P-state info available\n");
 	}
@@ -655,6 +500,44 @@ static bool rps_eval(void *data)
 
 DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rps_boost);
 
+static int perf_limit_reasons_get(void *data, u64 *val)
+{
+	struct intel_gt *gt = data;
+	intel_wakeref_t wakeref;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		*val = intel_uncore_read(gt->uncore, intel_gt_perf_limit_reasons_reg(gt));
+
+	return 0;
+}
+
+static int perf_limit_reasons_clear(void *data, u64 val)
+{
+	struct intel_gt *gt = data;
+	intel_wakeref_t wakeref;
+
+	/*
+	 * Clear the upper 16 "log" bits, the lower 16 "status" bits are
+	 * read-only. The upper 16 "log" bits are identical to the lower 16
+	 * "status" bits except that the "log" bits remain set until cleared.
+	 */
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		intel_uncore_rmw(gt->uncore, intel_gt_perf_limit_reasons_reg(gt),
+				 GT0_PERF_LIMIT_REASONS_LOG_MASK, 0);
+
+	return 0;
+}
+
+static bool perf_limit_reasons_eval(void *data)
+{
+	struct intel_gt *gt = data;
+
+	return i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt));
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(perf_limit_reasons_fops, perf_limit_reasons_get,
+			perf_limit_reasons_clear, "%llu\n");
+
 void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root)
 {
 	static const struct intel_gt_debugfs_file files[] = {
@@ -664,6 +547,7 @@ void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root)
 		{ "forcewake_user", &forcewake_user_fops, NULL},
 		{ "llc", &llc_fops, llc_eval },
 		{ "rps_boost", &rps_boost_fops, rps_eval },
+		{ "perf_limit_reasons", &perf_limit_reasons_fops, perf_limit_reasons_eval },
 	};
 
 	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 2275ee47da95..70177d3f2e94 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -8,6 +8,19 @@
 
 #include "i915_reg_defs.h"
 
+#define MCR_REG(offset)	((const i915_mcr_reg_t){ .reg = (offset) })
+
+/*
+ * The perf control registers are technically multicast registers, but the
+ * driver never needs to read/write them directly; we only use them to build
+ * lists of registers (where they're mixed in with other non-MCR registers)
+ * and then operate on the offset directly.  For now we'll just define them
+ * as non-multicast so we can place them on the same list, but we may want
+ * to try to come up with a better way to handle heterogeneous lists of
+ * registers in the future.
+ */
+#define PERF_REG(offset)			_MMIO(offset)
+
 /* RPM unit config (Gen8+) */
 #define RPM_CONFIG0				_MMIO(0xd00)
 #define   GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
@@ -39,9 +52,17 @@
 #define FORCEWAKE_ACK_RENDER_GEN9		_MMIO(0xd84)
 #define FORCEWAKE_ACK_MEDIA_GEN9		_MMIO(0xd88)
 
+#define FORCEWAKE_ACK_GSC			_MMIO(0xdf8)
+#define FORCEWAKE_ACK_GT_MTL			_MMIO(0xdfc)
+
+#define GMD_ID_GRAPHICS				_MMIO(0xd8c)
+#define GMD_ID_MEDIA				_MMIO(MTL_MEDIA_GSI_BASE + 0xd8c)
+
 #define MCFG_MCR_SELECTOR			_MMIO(0xfd0)
+#define MTL_MCR_SELECTOR			_MMIO(0xfd4)
 #define SF_MCR_SELECTOR				_MMIO(0xfd8)
 #define GEN8_MCR_SELECTOR			_MMIO(0xfdc)
+#define GAM_MCR_SELECTOR			_MMIO(0xfe0)
 #define   GEN8_MCR_SLICE(slice)			(((slice) & 3) << 26)
 #define   GEN8_MCR_SLICE_MASK			GEN8_MCR_SLICE(3)
 #define   GEN8_MCR_SUBSLICE(subslice)		(((subslice) & 3) << 24)
@@ -51,6 +72,8 @@
 #define   GEN11_MCR_SLICE_MASK			GEN11_MCR_SLICE(0xf)
 #define   GEN11_MCR_SUBSLICE(subslice)		(((subslice) & 0x7) << 24)
 #define   GEN11_MCR_SUBSLICE_MASK		GEN11_MCR_SUBSLICE(0x7)
+#define   MTL_MCR_GROUPID			REG_GENMASK(11, 8)
+#define   MTL_MCR_INSTANCEID			REG_GENMASK(3, 0)
 
 #define IPEIR_I965				_MMIO(0x2064)
 #define IPEHR_I965				_MMIO(0x2068)
@@ -326,11 +349,12 @@
 #define GEN7_TLB_RD_ADDR			_MMIO(0x4700)
 
 #define GEN12_PAT_INDEX(index)			_MMIO(0x4800 + (index) * 4)
+#define XEHP_PAT_INDEX(index)			MCR_REG(0x4800 + (index) * 4)
 
-#define XEHP_TILE0_ADDR_RANGE			_MMIO(0x4900)
+#define XEHP_TILE0_ADDR_RANGE			MCR_REG(0x4900)
 #define   XEHP_TILE_LMEM_RANGE_SHIFT		8
 
-#define XEHP_FLAT_CCS_BASE_ADDR			_MMIO(0x4910)
+#define XEHP_FLAT_CCS_BASE_ADDR			MCR_REG(0x4910)
 #define   XEHP_CCS_BASE_SHIFT			8
 
 #define GAMTARBMODE				_MMIO(0x4a08)
@@ -380,17 +404,18 @@
 #define CHICKEN_RASTER_2			_MMIO(0x6208)
 #define   TBIMR_FAST_CLIP			REG_BIT(5)
 
-#define VFLSKPD					_MMIO(0x62a8)
+#define VFLSKPD					MCR_REG(0x62a8)
 #define   DIS_OVER_FETCH_CACHE			REG_BIT(1)
 #define   DIS_MULT_MISS_RD_SQUASH		REG_BIT(0)
 
-#define FF_MODE2				_MMIO(0x6604)
+#define GEN12_FF_MODE2				_MMIO(0x6604)
+#define XEHP_FF_MODE2				MCR_REG(0x6604)
 #define   FF_MODE2_GS_TIMER_MASK		REG_GENMASK(31, 24)
 #define   FF_MODE2_GS_TIMER_224			REG_FIELD_PREP(FF_MODE2_GS_TIMER_MASK, 224)
 #define   FF_MODE2_TDS_TIMER_MASK		REG_GENMASK(23, 16)
 #define   FF_MODE2_TDS_TIMER_128		REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
 
-#define XEHPG_INSTDONE_GEOM_SVG			_MMIO(0x666c)
+#define XEHPG_INSTDONE_GEOM_SVG			MCR_REG(0x666c)
 
 #define CACHE_MODE_0_GEN7			_MMIO(0x7000) /* IVB+ */
 #define   RC_OP_FLUSH_ENABLE			(1 << 0)
@@ -418,6 +443,7 @@
 #define HIZ_CHICKEN				_MMIO(0x7018)
 #define   CHV_HZ_8X8_MODE_IN_1X			REG_BIT(15)
 #define   DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE	REG_BIT(14)
+#define   HZ_DEPTH_TEST_LE_GE_OPT_DISABLE	REG_BIT(13)
 #define   BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	REG_BIT(3)
 
 #define GEN8_L3CNTLREG				_MMIO(0x7034)
@@ -439,23 +465,16 @@
 #define GEN8_HDC_CHICKEN1			_MMIO(0x7304)
 
 #define GEN11_COMMON_SLICE_CHICKEN3		_MMIO(0x7304)
+#define XEHP_COMMON_SLICE_CHICKEN3		MCR_REG(0x7304)
 #define   DG1_FLOAT_POINT_BLEND_OPT_STRICT_MODE_EN	REG_BIT(12)
 #define   XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE	REG_BIT(12)
 #define   GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	REG_BIT(11)
 #define   GEN12_DISABLE_CPS_AWARE_COLOR_PIPE	REG_BIT(9)
 
-/* GEN9 chicken */
-#define SLICE_ECO_CHICKEN0			_MMIO(0x7308)
-#define   PIXEL_MASK_CAMMING_DISABLE		(1 << 14)
-
-#define GEN9_SLICE_COMMON_ECO_CHICKEN0		_MMIO(0x7308)
-#define   DISABLE_PIXEL_MASK_CAMMING		(1 << 14)
-
 #define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
-#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
-
-#define SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
+#define XEHP_SLICE_COMMON_ECO_CHICKEN1		MCR_REG(0x731c)
 #define   MSC_MSAA_REODER_BUF_BYPASS_DISABLE	REG_BIT(14)
+#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
 
 #define GEN9_SLICE_PGCTL_ACK(slice)		_MMIO(0x804c + (slice) * 0x4)
 #define GEN10_SLICE_PGCTL_ACK(slice)		_MMIO(0x804c + ((slice) / 3) * 0x34 + \
@@ -482,9 +501,12 @@
 #define VF_PREEMPTION				_MMIO(0x83a4)
 #define   PREEMPTION_VERTEX_COUNT		REG_GENMASK(15, 0)
 
+#define VFG_PREEMPTION_CHICKEN			_MMIO(0x83b4)
+#define   POLYGON_TRIFAN_LINELOOP_DISABLE	REG_BIT(4)
+
 #define GEN8_RC6_CTX_INFO			_MMIO(0x8504)
 
-#define GEN12_SQCM				_MMIO(0x8724)
+#define XEHP_SQCM				MCR_REG(0x8724)
 #define   EN_32B_ACCESS				REG_BIT(30)
 
 #define HSW_IDICR				_MMIO(0x9008)
@@ -516,6 +538,8 @@
 #define   GEN6_MBCTL_BOOT_FETCH_MECH		(1 << 0)
 
 /* Fuse readout registers for GT */
+#define XEHP_FUSE4				_MMIO(0x9114)
+#define   GT_L3_EXC_MASK			REG_GENMASK(6, 4)
 #define	GEN10_MIRROR_FUSE3			_MMIO(0x9118)
 #define   GEN10_L3BANK_PAIR_COUNT		4
 #define   GEN10_L3BANK_MASK			0x0F
@@ -644,6 +668,9 @@
 
 #define GEN7_MISCCPCTL				_MMIO(0x9424)
 #define   GEN7_DOP_CLOCK_GATE_ENABLE		(1 << 0)
+
+#define GEN8_MISCCPCTL				MCR_REG(0x9424)
+#define   GEN8_DOP_CLOCK_GATE_ENABLE		REG_BIT(0)
 #define   GEN12_DOP_CLOCK_GATE_RENDER_ENABLE	REG_BIT(1)
 #define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1 << 2)
 #define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1 << 4)
@@ -697,7 +724,8 @@
 #define   GAMTLBVEBOX0_CLKGATE_DIS		REG_BIT(16)
 #define   LTCDD_CLKGATE_DIS			REG_BIT(10)
 
-#define SLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x94d4)
+#define GEN11_SLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x94d4)
+#define XEHP_SLICE_UNIT_LEVEL_CLKGATE		MCR_REG(0x94d4)
 #define   SARBUNIT_CLKGATE_DIS			(1 << 5)
 #define   RCCUNIT_CLKGATE_DIS			(1 << 7)
 #define   MSCUNIT_CLKGATE_DIS			(1 << 10)
@@ -705,27 +733,27 @@
 #define   L3_CLKGATE_DIS			REG_BIT(16)
 #define   L3_CR2X_CLKGATE_DIS			REG_BIT(17)
 
-#define SCCGCTL94DC				_MMIO(0x94dc)
+#define SCCGCTL94DC				MCR_REG(0x94dc)
 #define   CG3DDISURB				REG_BIT(14)
 
 #define UNSLICE_UNIT_LEVEL_CLKGATE2		_MMIO(0x94e4)
 #define   VSUNIT_CLKGATE_DIS_TGL		REG_BIT(19)
 #define   PSDUNIT_CLKGATE_DIS			REG_BIT(5)
 
-#define SUBSLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x9524)
+#define GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE	MCR_REG(0x9524)
 #define   DSS_ROUTER_CLKGATE_DIS		REG_BIT(28)
 #define   GWUNIT_CLKGATE_DIS			REG_BIT(16)
 
-#define SUBSLICE_UNIT_LEVEL_CLKGATE2		_MMIO(0x9528)
+#define SUBSLICE_UNIT_LEVEL_CLKGATE2		MCR_REG(0x9528)
 #define   CPSSUNIT_CLKGATE_DIS			REG_BIT(9)
 
-#define SSMCGCTL9530				_MMIO(0x9530)
+#define SSMCGCTL9530				MCR_REG(0x9530)
 #define   RTFUNIT_CLKGATE_DIS			REG_BIT(18)
 
-#define GEN10_DFR_RATIO_EN_AND_CHICKEN		_MMIO(0x9550)
+#define GEN10_DFR_RATIO_EN_AND_CHICKEN		MCR_REG(0x9550)
 #define   DFR_DISABLE				(1 << 9)
 
-#define INF_UNIT_LEVEL_CLKGATE			_MMIO(0x9560)
+#define INF_UNIT_LEVEL_CLKGATE			MCR_REG(0x9560)
 #define   CGPSF_CLKGATE_DIS			(1 << 3)
 
 #define MICRO_BP0_0				_MMIO(0x9800)
@@ -898,6 +926,8 @@
 #define FORCEWAKE_MEDIA_VDBOX_GEN11(n)		_MMIO(0xa540 + (n) * 4)
 #define FORCEWAKE_MEDIA_VEBOX_GEN11(n)		_MMIO(0xa560 + (n) * 4)
 
+#define FORCEWAKE_REQ_GSC			_MMIO(0xa618)
+
 #define CHV_POWER_SS0_SIG1			_MMIO(0xa720)
 #define CHV_POWER_SS0_SIG2			_MMIO(0xa724)
 #define CHV_POWER_SS1_SIG1			_MMIO(0xa728)
@@ -935,7 +965,8 @@
 
 /* MOCS (Memory Object Control State) registers */
 #define GEN9_LNCFCMOCS(i)			_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
-#define GEN9_LNCFCMOCS_REG_COUNT		32
+#define XEHP_LNCFCMOCS(i)			MCR_REG(0xb020 + (i) * 4)
+#define LNCFCMOCS_REG_COUNT			32
 
 #define GEN7_L3CNTLREG3				_MMIO(0xb024)
 
@@ -951,15 +982,10 @@
 #define GEN7_L3LOG(slice, i)			_MMIO(0xb070 + (slice) * 0x200 + (i) * 4)
 #define   GEN7_L3LOG_SIZE			0x80
 
-#define GEN10_SCRATCH_LNCF2			_MMIO(0xb0a0)
-#define   PMFLUSHDONE_LNICRSDROP		(1 << 20)
-#define   PMFLUSH_GAPL3UNBLOCK			(1 << 21)
-#define   PMFLUSHDONE_LNEBLK			(1 << 22)
-
-#define XEHP_L3NODEARBCFG			_MMIO(0xb0b4)
+#define XEHP_L3NODEARBCFG			MCR_REG(0xb0b4)
 #define   XEHP_LNESPARE				REG_BIT(19)
 
-#define GEN8_L3SQCREG1				_MMIO(0xb100)
+#define GEN8_L3SQCREG1				MCR_REG(0xb100)
 /*
  * Note that on CHV the following has an off-by-one error wrt. to BSpec.
  * Using the formula in BSpec leads to a hang, while the formula here works
@@ -970,31 +996,28 @@
 #define   L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
 #define   L3_PRIO_CREDITS_MASK			((0x1f << 19) | (0x1f << 14))
 
-#define GEN10_L3_CHICKEN_MODE_REGISTER		_MMIO(0xb114)
-#define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
-
-#define GEN8_L3SQCREG4				_MMIO(0xb118)
+#define GEN8_L3SQCREG4				MCR_REG(0xb118)
 #define   GEN11_LQSC_CLEAN_EVICT_DISABLE	(1 << 6)
 #define   GEN8_LQSC_RO_PERF_DIS			(1 << 27)
 #define   GEN8_LQSC_FLUSH_COHERENT_LINES	(1 << 21)
 #define   GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE	REG_BIT(22)
 
-#define GEN9_SCRATCH1				_MMIO(0xb11c)
+#define GEN9_SCRATCH1				MCR_REG(0xb11c)
 #define   EVICTION_PERF_FIX_ENABLE		REG_BIT(8)
 
-#define BDW_SCRATCH1				_MMIO(0xb11c)
+#define BDW_SCRATCH1				MCR_REG(0xb11c)
 #define   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
 
-#define GEN11_SCRATCH2				_MMIO(0xb140)
+#define GEN11_SCRATCH2				MCR_REG(0xb140)
 #define   GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE	(1 << 19)
 
-#define GEN11_L3SQCREG5				_MMIO(0xb158)
+#define XEHP_L3SQCREG5				MCR_REG(0xb158)
 #define   L3_PWM_TIMER_INIT_VAL_MASK		REG_GENMASK(9, 0)
 
-#define MLTICTXCTL				_MMIO(0xb170)
+#define MLTICTXCTL				MCR_REG(0xb170)
 #define   TDONRENDER				REG_BIT(2)
 
-#define XEHP_L3SCQREG7				_MMIO(0xb188)
+#define XEHP_L3SCQREG7				MCR_REG(0xb188)
 #define   BLEND_FILL_CACHING_OPT_DIS		REG_BIT(3)
 
 #define XEHPC_L3SCRUB				_MMIO(0xb18c)
@@ -1002,7 +1025,7 @@
 #define   SCRUB_RATE_PER_BANK_MASK		REG_GENMASK(2, 0)
 #define   SCRUB_RATE_4B_PER_CLK			REG_FIELD_PREP(SCRUB_RATE_PER_BANK_MASK, 0x6)
 
-#define L3SQCREG1_CCS0				_MMIO(0xb200)
+#define L3SQCREG1_CCS0				MCR_REG(0xb200)
 #define   FLUSHALLNONCOH			REG_BIT(5)
 
 #define GEN11_GLBLINVL				_MMIO(0xb404)
@@ -1027,11 +1050,14 @@
 #define GEN9_BLT_MOCS(i)			_MMIO(__GEN9_BCS0_MOCS0 + (i) * 4)
 
 #define GEN12_FAULT_TLB_DATA0			_MMIO(0xceb8)
+#define XEHP_FAULT_TLB_DATA0			MCR_REG(0xceb8)
 #define GEN12_FAULT_TLB_DATA1			_MMIO(0xcebc)
+#define XEHP_FAULT_TLB_DATA1			MCR_REG(0xcebc)
 #define   FAULT_VA_HIGH_BITS			(0xf << 0)
 #define   FAULT_GTT_SEL				(1 << 4)
 
 #define GEN12_RING_FAULT_REG			_MMIO(0xcec4)
+#define XEHP_RING_FAULT_REG			MCR_REG(0xcec4)
 #define   GEN8_RING_FAULT_ENGINE_ID(x)		(((x) >> 12) & 0x7)
 #define   RING_FAULT_GTTSEL_MASK		(1 << 11)
 #define   RING_FAULT_SRCID(x)			(((x) >> 3) & 0xff)
@@ -1039,16 +1065,21 @@
 #define   RING_FAULT_VALID			(1 << 0)
 
 #define GEN12_GFX_TLB_INV_CR			_MMIO(0xced8)
+#define XEHP_GFX_TLB_INV_CR			MCR_REG(0xced8)
 #define GEN12_VD_TLB_INV_CR			_MMIO(0xcedc)
+#define XEHP_VD_TLB_INV_CR			MCR_REG(0xcedc)
 #define GEN12_VE_TLB_INV_CR			_MMIO(0xcee0)
+#define XEHP_VE_TLB_INV_CR			MCR_REG(0xcee0)
 #define GEN12_BLT_TLB_INV_CR			_MMIO(0xcee4)
+#define XEHP_BLT_TLB_INV_CR			MCR_REG(0xcee4)
 #define GEN12_COMPCTX_TLB_INV_CR		_MMIO(0xcf04)
+#define XEHP_COMPCTX_TLB_INV_CR			MCR_REG(0xcf04)
 
-#define GEN12_MERT_MOD_CTRL			_MMIO(0xcf28)
-#define RENDER_MOD_CTRL				_MMIO(0xcf2c)
-#define COMP_MOD_CTRL				_MMIO(0xcf30)
-#define VDBX_MOD_CTRL				_MMIO(0xcf34)
-#define VEBX_MOD_CTRL				_MMIO(0xcf38)
+#define XEHP_MERT_MOD_CTRL			MCR_REG(0xcf28)
+#define RENDER_MOD_CTRL				MCR_REG(0xcf2c)
+#define COMP_MOD_CTRL				MCR_REG(0xcf30)
+#define VDBX_MOD_CTRL				MCR_REG(0xcf34)
+#define VEBX_MOD_CTRL				MCR_REG(0xcf38)
 #define   FORCE_MISS_FTLB			REG_BIT(3)
 
 #define GEN12_GAMSTLB_CTRL			_MMIO(0xcf4c)
@@ -1063,48 +1094,52 @@
 #define GEN12_GAM_DONE				_MMIO(0xcf68)
 
 #define GEN7_HALF_SLICE_CHICKEN1		_MMIO(0xe100) /* IVB GT1 + VLV */
+#define GEN8_HALF_SLICE_CHICKEN1		MCR_REG(0xe100)
 #define   GEN7_MAX_PS_THREAD_DEP		(8 << 12)
 #define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1 << 10)
 #define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1 << 4)
 #define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1 << 3)
 
 #define GEN7_SAMPLER_INSTDONE			_MMIO(0xe160)
+#define GEN8_SAMPLER_INSTDONE			MCR_REG(0xe160)
 #define GEN7_ROW_INSTDONE			_MMIO(0xe164)
+#define GEN8_ROW_INSTDONE			MCR_REG(0xe164)
 
-#define HALF_SLICE_CHICKEN2			_MMIO(0xe180)
+#define HALF_SLICE_CHICKEN2			MCR_REG(0xe180)
 #define   GEN8_ST_PO_DISABLE			(1 << 13)
 
-#define HALF_SLICE_CHICKEN3			_MMIO(0xe184)
+#define HSW_HALF_SLICE_CHICKEN3			_MMIO(0xe184)
+#define GEN8_HALF_SLICE_CHICKEN3		MCR_REG(0xe184)
 #define   HSW_SAMPLE_C_PERFORMANCE		(1 << 9)
 #define   GEN8_CENTROID_PIXEL_OPT_DIS		(1 << 8)
 #define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS		(1 << 1)
 
-#define GEN9_HALF_SLICE_CHICKEN5		_MMIO(0xe188)
+#define GEN9_HALF_SLICE_CHICKEN5		MCR_REG(0xe188)
 #define   GEN9_DG_MIRROR_FIX_ENABLE		(1 << 5)
 #define   GEN9_CCS_TLB_PREFETCH_ENABLE		(1 << 3)
 
-#define GEN10_SAMPLER_MODE			_MMIO(0xe18c)
+#define GEN10_SAMPLER_MODE			MCR_REG(0xe18c)
 #define   ENABLE_SMALLPL			REG_BIT(15)
 #define   SC_DISABLE_POWER_OPTIMIZATION_EBB	REG_BIT(9)
 #define   GEN11_SAMPLER_ENABLE_HEADLESS_MSG	REG_BIT(5)
 
-#define GEN9_HALF_SLICE_CHICKEN7		_MMIO(0xe194)
+#define GEN9_HALF_SLICE_CHICKEN7		MCR_REG(0xe194)
 #define   DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA	REG_BIT(15)
 #define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	REG_BIT(8)
 #define   GEN9_ENABLE_YV12_BUGFIX		REG_BIT(4)
 #define   GEN9_ENABLE_GPGPU_PREEMPTION		REG_BIT(2)
 
-#define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
+#define GEN10_CACHE_MODE_SS			MCR_REG(0xe420)
 #define   ENABLE_EU_COUNT_FOR_TDL_FLUSH		REG_BIT(10)
 #define   DISABLE_ECC				REG_BIT(5)
 #define   FLOAT_BLEND_OPTIMIZATION_ENABLE	REG_BIT(4)
 #define   ENABLE_PREFETCH_INTO_IC		REG_BIT(3)
 
-#define EU_PERF_CNTL0				_MMIO(0xe458)
-#define EU_PERF_CNTL4				_MMIO(0xe45c)
+#define EU_PERF_CNTL0				PERF_REG(0xe458)
+#define EU_PERF_CNTL4				PERF_REG(0xe45c)
 
-#define GEN9_ROW_CHICKEN4			_MMIO(0xe48c)
+#define GEN9_ROW_CHICKEN4			MCR_REG(0xe48c)
 #define   GEN12_DISABLE_GRF_CLEAR		REG_BIT(13)
 #define   XEHP_DIS_BBL_SYSPIPE			REG_BIT(11)
 #define   GEN12_DISABLE_TDL_PUSH		REG_BIT(9)
@@ -1116,7 +1151,7 @@
 #define HSW_ROW_CHICKEN3			_MMIO(0xe49c)
 #define   HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE	(1 << 6)
 
-#define GEN8_ROW_CHICKEN			_MMIO(0xe4f0)
+#define GEN8_ROW_CHICKEN			MCR_REG(0xe4f0)
 #define   FLOW_CONTROL_ENABLE			REG_BIT(15)
 #define   UGM_BACKUP_MODE			REG_BIT(13)
 #define   MDQ_ARBITRATION_MODE			REG_BIT(12)
@@ -1127,42 +1162,43 @@
 #define   DISABLE_EARLY_EOT			REG_BIT(1)
 
 #define GEN7_ROW_CHICKEN2			_MMIO(0xe4f4)
+
+#define GEN8_ROW_CHICKEN2			MCR_REG(0xe4f4)
 #define   GEN12_DISABLE_READ_SUPPRESSION	REG_BIT(15)
 #define   GEN12_DISABLE_EARLY_READ		REG_BIT(14)
 #define   GEN12_ENABLE_LARGE_GRF_MODE		REG_BIT(12)
 #define   GEN12_PUSH_CONST_DEREF_HOLD_DIS	REG_BIT(8)
+#define   GEN12_DISABLE_DOP_GATING              REG_BIT(0)
 
-#define RT_CTRL					_MMIO(0xe530)
+#define RT_CTRL					MCR_REG(0xe530)
 #define   DIS_NULL_QUERY			REG_BIT(10)
 #define   STACKID_CTRL				REG_GENMASK(6, 5)
 #define   STACKID_CTRL_512			REG_FIELD_PREP(STACKID_CTRL, 0x2)
 
-#define EU_PERF_CNTL1				_MMIO(0xe558)
-#define EU_PERF_CNTL5				_MMIO(0xe55c)
+#define EU_PERF_CNTL1				PERF_REG(0xe558)
+#define EU_PERF_CNTL5				PERF_REG(0xe55c)
 
-#define GEN12_HDC_CHICKEN0			_MMIO(0xe5f0)
+#define XEHP_HDC_CHICKEN0			MCR_REG(0xe5f0)
 #define   LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK	REG_GENMASK(13, 11)
-#define ICL_HDC_MODE				_MMIO(0xe5f4)
+#define ICL_HDC_MODE				MCR_REG(0xe5f4)
 
-#define EU_PERF_CNTL2				_MMIO(0xe658)
-#define EU_PERF_CNTL6				_MMIO(0xe65c)
-#define EU_PERF_CNTL3				_MMIO(0xe758)
+#define EU_PERF_CNTL2				PERF_REG(0xe658)
+#define EU_PERF_CNTL6				PERF_REG(0xe65c)
+#define EU_PERF_CNTL3				PERF_REG(0xe758)
 
-#define LSC_CHICKEN_BIT_0			_MMIO(0xe7c8)
+#define LSC_CHICKEN_BIT_0			MCR_REG(0xe7c8)
 #define   DISABLE_D8_D16_COASLESCE		REG_BIT(30)
 #define   FORCE_1_SUB_MESSAGE_PER_FRAGMENT	REG_BIT(15)
-#define LSC_CHICKEN_BIT_0_UDW			_MMIO(0xe7c8 + 4)
+#define LSC_CHICKEN_BIT_0_UDW			MCR_REG(0xe7c8 + 4)
 #define   DIS_CHAIN_2XSIMD8			REG_BIT(55 - 32)
 #define   FORCE_SLM_FENCE_SCOPE_TO_TILE		REG_BIT(42 - 32)
 #define   FORCE_UGM_FENCE_SCOPE_TO_TILE		REG_BIT(41 - 32)
 #define   MAXREQS_PER_BANK			REG_GENMASK(39 - 32, 37 - 32)
 #define   DISABLE_128B_EVICTION_COMMAND_UDW	REG_BIT(36 - 32)
 
-#define SARB_CHICKEN1				_MMIO(0xe90c)
+#define SARB_CHICKEN1				MCR_REG(0xe90c)
 #define   COMP_CKN_IN				REG_GENMASK(30, 29)
 
-#define GEN7_HALF_SLICE_CHICKEN1_GT2		_MMIO(0xf100)
-
 #define GEN7_ROW_CHICKEN2_GT2			_MMIO(0xf4f4)
 #define   DOP_CLOCK_GATING_DISABLE		(1 << 0)
 #define   PUSH_CONSTANT_DEREF_DISABLE		(1 << 8)
@@ -1510,6 +1546,9 @@
 #define VLV_RENDER_C0_COUNT			_MMIO(0x138118)
 #define VLV_MEDIA_C0_COUNT			_MMIO(0x13811c)
 
+#define GEN12_RPSTAT1				_MMIO(0x1381b4)
+#define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
+
 #define GEN11_GT_INTR_DW(x)			_MMIO(0x190018 + ((x) * 4))
 #define   GEN11_CSME				(31)
 #define   GEN11_GUNIT				(28)
@@ -1580,6 +1619,11 @@
 
 #define GEN12_SFC_DONE(n)			_MMIO(0x1cc000 + (n) * 0x1000)
 
+#define GT0_PACKAGE_ENERGY_STATUS		_MMIO(0x250004)
+#define GT0_PACKAGE_RAPL_LIMIT			_MMIO(0x250008)
+#define GT0_PACKAGE_POWER_SKU_UNIT		_MMIO(0x250068)
+#define GT0_PLATFORM_ENERGY_STATUS		_MMIO(0x25006c)
+
 /*
  * Standalone Media's non-engine GT registers are located at their regular GT
  * offsets plus 0x380000.  This extra offset is stored inside the intel_uncore
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
index d651ccd0ab20..9486dd3bed99 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
@@ -22,11 +22,9 @@ bool is_object_gt(struct kobject *kobj)
 	return !strncmp(kobj->name, "gt", 2);
 }
 
-struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
+struct intel_gt *intel_gt_sysfs_get_drvdata(struct kobject *kobj,
 					    const char *name)
 {
-	struct kobject *kobj = &dev->kobj;
-
 	/*
 	 * We are interested at knowing from where the interface
 	 * has been called, whether it's called from gt/ or from
@@ -38,6 +36,7 @@ struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
 	 * "struct drm_i915_private *" type.
 	 */
 	if (!is_object_gt(kobj)) {
+		struct device *dev = kobj_to_dev(kobj);
 		struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
 
 		return to_gt(i915);
@@ -51,18 +50,18 @@ static struct kobject *gt_get_parent_obj(struct intel_gt *gt)
 	return &gt->i915->drm.primary->kdev->kobj;
 }
 
-static ssize_t id_show(struct device *dev,
-		       struct device_attribute *attr,
+static ssize_t id_show(struct kobject *kobj,
+		       struct kobj_attribute *attr,
 		       char *buf)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 
 	return sysfs_emit(buf, "%u\n", gt->info.id);
 }
-static DEVICE_ATTR_RO(id);
+static struct kobj_attribute attr_id = __ATTR_RO(id);
 
 static struct attribute *id_attrs[] = {
-	&dev_attr_id.attr,
+	&attr_id.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(id);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
index 6232923a420d..18bab835be02 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
@@ -18,11 +18,6 @@ bool is_object_gt(struct kobject *kobj);
 
 struct drm_i915_private *kobj_to_i915(struct kobject *kobj);
 
-struct kobject *
-intel_gt_create_kobj(struct intel_gt *gt,
-		     struct kobject *dir,
-		     const char *name);
-
 static inline struct intel_gt *kobj_to_gt(struct kobject *kobj)
 {
 	return container_of(kobj, struct intel_gt, sysfs_gt);
@@ -30,7 +25,7 @@ static inline struct intel_gt *kobj_to_gt(struct kobject *kobj)
 
 void intel_gt_sysfs_register(struct intel_gt *gt);
 void intel_gt_sysfs_unregister(struct intel_gt *gt);
-struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
+struct intel_gt *intel_gt_sysfs_get_drvdata(struct kobject *kobj,
 					    const char *name);
 
 #endif /* SYSFS_GT_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
index 180dd6f3ef57..2b5f05b31187 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
@@ -24,14 +24,15 @@ enum intel_gt_sysfs_op {
 };
 
 static int
-sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr,
+sysfs_gt_attribute_w_func(struct kobject *kobj, struct attribute *attr,
 			  int (func)(struct intel_gt *gt, u32 val), u32 val)
 {
 	struct intel_gt *gt;
 	int ret;
 
-	if (!is_object_gt(&dev->kobj)) {
+	if (!is_object_gt(kobj)) {
 		int i;
+		struct device *dev = kobj_to_dev(kobj);
 		struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
 
 		for_each_gt(gt, i915, i) {
@@ -40,7 +41,7 @@ sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr,
 				break;
 		}
 	} else {
-		gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+		gt = intel_gt_sysfs_get_drvdata(kobj, attr->name);
 		ret = func(gt, val);
 	}
 
@@ -48,7 +49,7 @@ sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr,
 }
 
 static u32
-sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr,
+sysfs_gt_attribute_r_func(struct kobject *kobj, struct attribute *attr,
 			  u32 (func)(struct intel_gt *gt),
 			  enum intel_gt_sysfs_op op)
 {
@@ -57,8 +58,9 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr,
 
 	ret = (op == INTEL_GT_SYSFS_MAX) ? 0 : (u32) -1;
 
-	if (!is_object_gt(&dev->kobj)) {
+	if (!is_object_gt(kobj)) {
 		int i;
+		struct device *dev = kobj_to_dev(kobj);
 		struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
 
 		for_each_gt(gt, i915, i) {
@@ -77,7 +79,7 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr,
 			}
 		}
 	} else {
-		gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+		gt = intel_gt_sysfs_get_drvdata(kobj, attr->name);
 		ret = func(gt);
 	}
 
@@ -92,6 +94,76 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr,
 #define sysfs_gt_attribute_r_max_func(d, a, f) \
 		sysfs_gt_attribute_r_func(d, a, f, INTEL_GT_SYSFS_MAX)
 
+#define INTEL_GT_SYSFS_SHOW(_name, _attr_type)							\
+	static ssize_t _name##_show_common(struct kobject *kobj,				\
+					   struct attribute *attr, char *buff)			\
+	{											\
+		u32 val = sysfs_gt_attribute_r_##_attr_type##_func(kobj, attr,			\
+								   __##_name##_show);		\
+												\
+		return sysfs_emit(buff, "%u\n", val);						\
+	}											\
+	static ssize_t _name##_show(struct kobject *kobj,					\
+				    struct kobj_attribute *attr, char *buff)			\
+	{											\
+		return _name ##_show_common(kobj, &attr->attr, buff);				\
+	}											\
+	static ssize_t _name##_dev_show(struct device *dev,					\
+					struct device_attribute *attr, char *buff)		\
+	{											\
+		return _name##_show_common(&dev->kobj, &attr->attr, buff);			\
+	}
+
+#define INTEL_GT_SYSFS_STORE(_name, _func)						\
+	static ssize_t _name##_store_common(struct kobject *kobj,			\
+					    struct attribute *attr,			\
+					    const char *buff, size_t count)		\
+	{										\
+		int ret;								\
+		u32 val;								\
+											\
+		ret = kstrtou32(buff, 0, &val);						\
+		if (ret)								\
+			return ret;							\
+											\
+		ret = sysfs_gt_attribute_w_func(kobj, attr, _func, val);		\
+											\
+		return ret ?: count;							\
+	}										\
+	static ssize_t _name##_store(struct kobject *kobj,				\
+				     struct kobj_attribute *attr, const char *buff,	\
+				     size_t count)					\
+	{										\
+		return _name##_store_common(kobj, &attr->attr, buff, count);		\
+	}										\
+	static ssize_t _name##_dev_store(struct device *dev,				\
+					 struct device_attribute *attr,			\
+					 const char *buff, size_t count)		\
+	{										\
+		return _name##_store_common(&dev->kobj, &attr->attr, buff, count);	\
+	}
+
+#define INTEL_GT_SYSFS_SHOW_MAX(_name) INTEL_GT_SYSFS_SHOW(_name, max)
+#define INTEL_GT_SYSFS_SHOW_MIN(_name) INTEL_GT_SYSFS_SHOW(_name, min)
+
+#define INTEL_GT_ATTR_RW(_name) \
+	static struct kobj_attribute attr_##_name = __ATTR_RW(_name)
+
+#define INTEL_GT_ATTR_RO(_name) \
+	static struct kobj_attribute attr_##_name = __ATTR_RO(_name)
+
+#define INTEL_GT_DUAL_ATTR_RW(_name) \
+	static struct device_attribute dev_attr_##_name = __ATTR(_name, 0644,		\
+								 _name##_dev_show,	\
+								 _name##_dev_store);	\
+	INTEL_GT_ATTR_RW(_name)
+
+#define INTEL_GT_DUAL_ATTR_RO(_name) \
+	static struct device_attribute dev_attr_##_name = __ATTR(_name, 0444,		\
+								 _name##_dev_show,	\
+								 NULL);			\
+	INTEL_GT_ATTR_RO(_name)
+
 #ifdef CONFIG_PM
 static u32 get_residency(struct intel_gt *gt, i915_reg_t reg)
 {
@@ -104,11 +176,8 @@ static u32 get_residency(struct intel_gt *gt, i915_reg_t reg)
 	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
 
-static ssize_t rc6_enable_show(struct device *dev,
-			       struct device_attribute *attr,
-			       char *buff)
+static u8 get_rc6_mask(struct intel_gt *gt)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
 	u8 mask = 0;
 
 	if (HAS_RC6(gt->i915))
@@ -118,37 +187,35 @@ static ssize_t rc6_enable_show(struct device *dev,
 	if (HAS_RC6pp(gt->i915))
 		mask |= BIT(2);
 
-	return sysfs_emit(buff, "%x\n", mask);
+	return mask;
 }
 
-static u32 __rc6_residency_ms_show(struct intel_gt *gt)
+static ssize_t rc6_enable_show(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       char *buff)
 {
-	return get_residency(gt, GEN6_GT_GFX_RC6);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
+
+	return sysfs_emit(buff, "%x\n", get_rc6_mask(gt));
 }
 
-static ssize_t rc6_residency_ms_show(struct device *dev,
-				     struct device_attribute *attr,
-				     char *buff)
+static ssize_t rc6_enable_dev_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buff)
 {
-	u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr,
-						      __rc6_residency_ms_show);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(&dev->kobj, attr->attr.name);
 
-	return sysfs_emit(buff, "%u\n", rc6_residency);
+	return sysfs_emit(buff, "%x\n", get_rc6_mask(gt));
 }
 
-static u32 __rc6p_residency_ms_show(struct intel_gt *gt)
+static u32 __rc6_residency_ms_show(struct intel_gt *gt)
 {
-	return get_residency(gt, GEN6_GT_GFX_RC6p);
+	return get_residency(gt, GEN6_GT_GFX_RC6);
 }
 
-static ssize_t rc6p_residency_ms_show(struct device *dev,
-				      struct device_attribute *attr,
-				      char *buff)
+static u32 __rc6p_residency_ms_show(struct intel_gt *gt)
 {
-	u32 rc6p_residency = sysfs_gt_attribute_r_min_func(dev, attr,
-						__rc6p_residency_ms_show);
-
-	return sysfs_emit(buff, "%u\n", rc6p_residency);
+	return get_residency(gt, GEN6_GT_GFX_RC6p);
 }
 
 static u32 __rc6pp_residency_ms_show(struct intel_gt *gt)
@@ -156,67 +223,69 @@ static u32 __rc6pp_residency_ms_show(struct intel_gt *gt)
 	return get_residency(gt, GEN6_GT_GFX_RC6pp);
 }
 
-static ssize_t rc6pp_residency_ms_show(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buff)
-{
-	u32 rc6pp_residency = sysfs_gt_attribute_r_min_func(dev, attr,
-						__rc6pp_residency_ms_show);
-
-	return sysfs_emit(buff, "%u\n", rc6pp_residency);
-}
-
 static u32 __media_rc6_residency_ms_show(struct intel_gt *gt)
 {
 	return get_residency(gt, VLV_GT_MEDIA_RC6);
 }
 
-static ssize_t media_rc6_residency_ms_show(struct device *dev,
-					   struct device_attribute *attr,
-					   char *buff)
-{
-	u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr,
-						__media_rc6_residency_ms_show);
+INTEL_GT_SYSFS_SHOW_MIN(rc6_residency_ms);
+INTEL_GT_SYSFS_SHOW_MIN(rc6p_residency_ms);
+INTEL_GT_SYSFS_SHOW_MIN(rc6pp_residency_ms);
+INTEL_GT_SYSFS_SHOW_MIN(media_rc6_residency_ms);
 
-	return sysfs_emit(buff, "%u\n", rc6_residency);
-}
-
-static DEVICE_ATTR_RO(rc6_enable);
-static DEVICE_ATTR_RO(rc6_residency_ms);
-static DEVICE_ATTR_RO(rc6p_residency_ms);
-static DEVICE_ATTR_RO(rc6pp_residency_ms);
-static DEVICE_ATTR_RO(media_rc6_residency_ms);
+INTEL_GT_DUAL_ATTR_RO(rc6_enable);
+INTEL_GT_DUAL_ATTR_RO(rc6_residency_ms);
+INTEL_GT_DUAL_ATTR_RO(rc6p_residency_ms);
+INTEL_GT_DUAL_ATTR_RO(rc6pp_residency_ms);
+INTEL_GT_DUAL_ATTR_RO(media_rc6_residency_ms);
 
 static struct attribute *rc6_attrs[] = {
+	&attr_rc6_enable.attr,
+	&attr_rc6_residency_ms.attr,
+	NULL
+};
+
+static struct attribute *rc6p_attrs[] = {
+	&attr_rc6p_residency_ms.attr,
+	&attr_rc6pp_residency_ms.attr,
+	NULL
+};
+
+static struct attribute *media_rc6_attrs[] = {
+	&attr_media_rc6_residency_ms.attr,
+	NULL
+};
+
+static struct attribute *rc6_dev_attrs[] = {
 	&dev_attr_rc6_enable.attr,
 	&dev_attr_rc6_residency_ms.attr,
 	NULL
 };
 
-static struct attribute *rc6p_attrs[] = {
+static struct attribute *rc6p_dev_attrs[] = {
 	&dev_attr_rc6p_residency_ms.attr,
 	&dev_attr_rc6pp_residency_ms.attr,
 	NULL
 };
 
-static struct attribute *media_rc6_attrs[] = {
+static struct attribute *media_rc6_dev_attrs[] = {
 	&dev_attr_media_rc6_residency_ms.attr,
 	NULL
 };
 
 static const struct attribute_group rc6_attr_group[] = {
 	{ .attrs = rc6_attrs, },
-	{ .name = power_group_name, .attrs = rc6_attrs, },
+	{ .name = power_group_name, .attrs = rc6_dev_attrs, },
 };
 
 static const struct attribute_group rc6p_attr_group[] = {
 	{ .attrs = rc6p_attrs, },
-	{ .name = power_group_name, .attrs = rc6p_attrs, },
+	{ .name = power_group_name, .attrs = rc6p_dev_attrs, },
 };
 
 static const struct attribute_group media_rc6_attr_group[] = {
 	{ .attrs = media_rc6_attrs, },
-	{ .name = power_group_name, .attrs = media_rc6_attrs, },
+	{ .name = power_group_name, .attrs = media_rc6_dev_attrs, },
 };
 
 static int __intel_gt_sysfs_create_group(struct kobject *kobj,
@@ -271,104 +340,34 @@ static u32 __act_freq_mhz_show(struct intel_gt *gt)
 	return intel_rps_read_actual_frequency(&gt->rps);
 }
 
-static ssize_t act_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 actual_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						    __act_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", actual_freq);
-}
-
 static u32 __cur_freq_mhz_show(struct intel_gt *gt)
 {
 	return intel_rps_get_requested_frequency(&gt->rps);
 }
 
-static ssize_t cur_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 cur_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						 __cur_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", cur_freq);
-}
-
 static u32 __boost_freq_mhz_show(struct intel_gt *gt)
 {
 	return intel_rps_get_boost_frequency(&gt->rps);
 }
 
-static ssize_t boost_freq_mhz_show(struct device *dev,
-				   struct device_attribute *attr,
-				   char *buff)
-{
-	u32 boost_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						   __boost_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", boost_freq);
-}
-
 static int __boost_freq_mhz_store(struct intel_gt *gt, u32 val)
 {
 	return intel_rps_set_boost_frequency(&gt->rps, val);
 }
 
-static ssize_t boost_freq_mhz_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buff, size_t count)
-{
-	ssize_t ret;
-	u32 val;
-
-	ret = kstrtou32(buff, 0, &val);
-	if (ret)
-		return ret;
-
-	return sysfs_gt_attribute_w_func(dev, attr,
-					 __boost_freq_mhz_store, val) ?: count;
-}
-
-static u32 __rp0_freq_mhz_show(struct intel_gt *gt)
+static u32 __RP0_freq_mhz_show(struct intel_gt *gt)
 {
 	return intel_rps_get_rp0_frequency(&gt->rps);
 }
 
-static ssize_t RP0_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 rp0_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						     __rp0_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", rp0_freq);
-}
-
-static u32 __rp1_freq_mhz_show(struct intel_gt *gt)
-{
-	return intel_rps_get_rp1_frequency(&gt->rps);
-}
-
-static ssize_t RP1_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 rp1_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						     __rp1_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", rp1_freq);
-}
-
-static u32 __rpn_freq_mhz_show(struct intel_gt *gt)
+static u32 __RPn_freq_mhz_show(struct intel_gt *gt)
 {
 	return intel_rps_get_rpn_frequency(&gt->rps);
 }
 
-static ssize_t RPn_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
+static u32 __RP1_freq_mhz_show(struct intel_gt *gt)
 {
-	u32 rpn_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						     __rpn_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", rpn_freq);
+	return intel_rps_get_rp1_frequency(&gt->rps);
 }
 
 static u32 __max_freq_mhz_show(struct intel_gt *gt)
@@ -376,71 +375,21 @@ static u32 __max_freq_mhz_show(struct intel_gt *gt)
 	return intel_rps_get_max_frequency(&gt->rps);
 }
 
-static ssize_t max_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 max_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						     __max_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", max_freq);
-}
-
 static int __set_max_freq(struct intel_gt *gt, u32 val)
 {
 	return intel_rps_set_max_frequency(&gt->rps, val);
 }
 
-static ssize_t max_freq_mhz_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buff, size_t count)
-{
-	int ret;
-	u32 val;
-
-	ret = kstrtou32(buff, 0, &val);
-	if (ret)
-		return ret;
-
-	ret = sysfs_gt_attribute_w_func(dev, attr, __set_max_freq, val);
-
-	return ret ?: count;
-}
-
 static u32 __min_freq_mhz_show(struct intel_gt *gt)
 {
 	return intel_rps_get_min_frequency(&gt->rps);
 }
 
-static ssize_t min_freq_mhz_show(struct device *dev,
-				 struct device_attribute *attr, char *buff)
-{
-	u32 min_freq = sysfs_gt_attribute_r_min_func(dev, attr,
-						     __min_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", min_freq);
-}
-
 static int __set_min_freq(struct intel_gt *gt, u32 val)
 {
 	return intel_rps_set_min_frequency(&gt->rps, val);
 }
 
-static ssize_t min_freq_mhz_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buff, size_t count)
-{
-	int ret;
-	u32 val;
-
-	ret = kstrtou32(buff, 0, &val);
-	if (ret)
-		return ret;
-
-	ret = sysfs_gt_attribute_w_func(dev, attr, __set_min_freq, val);
-
-	return ret ?: count;
-}
-
 static u32 __vlv_rpe_freq_mhz_show(struct intel_gt *gt)
 {
 	struct intel_rps *rps = &gt->rps;
@@ -448,23 +397,31 @@ static u32 __vlv_rpe_freq_mhz_show(struct intel_gt *gt)
 	return intel_gpu_freq(rps, rps->efficient_freq);
 }
 
-static ssize_t vlv_rpe_freq_mhz_show(struct device *dev,
-				     struct device_attribute *attr, char *buff)
-{
-	u32 rpe_freq = sysfs_gt_attribute_r_max_func(dev, attr,
-						 __vlv_rpe_freq_mhz_show);
-
-	return sysfs_emit(buff, "%u\n", rpe_freq);
-}
-
-#define INTEL_GT_RPS_SYSFS_ATTR(_name, _mode, _show, _store) \
-	static struct device_attribute dev_attr_gt_##_name = __ATTR(gt_##_name, _mode, _show, _store); \
-	static struct device_attribute dev_attr_rps_##_name = __ATTR(rps_##_name, _mode, _show, _store)
-
-#define INTEL_GT_RPS_SYSFS_ATTR_RO(_name)				\
-		INTEL_GT_RPS_SYSFS_ATTR(_name, 0444, _name##_show, NULL)
-#define INTEL_GT_RPS_SYSFS_ATTR_RW(_name)				\
-		INTEL_GT_RPS_SYSFS_ATTR(_name, 0644, _name##_show, _name##_store)
+INTEL_GT_SYSFS_SHOW_MAX(act_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(boost_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(cur_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(RP0_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(RP1_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(RPn_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(max_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MIN(min_freq_mhz);
+INTEL_GT_SYSFS_SHOW_MAX(vlv_rpe_freq_mhz);
+INTEL_GT_SYSFS_STORE(boost_freq_mhz, __boost_freq_mhz_store);
+INTEL_GT_SYSFS_STORE(max_freq_mhz, __set_max_freq);
+INTEL_GT_SYSFS_STORE(min_freq_mhz, __set_min_freq);
+
+#define INTEL_GT_RPS_SYSFS_ATTR(_name, _mode, _show, _store, _show_dev, _store_dev)		\
+	static struct device_attribute dev_attr_gt_##_name = __ATTR(gt_##_name, _mode,		\
+								    _show_dev, _store_dev);	\
+	static struct kobj_attribute attr_rps_##_name = __ATTR(rps_##_name, _mode,		\
+							       _show, _store)
+
+#define INTEL_GT_RPS_SYSFS_ATTR_RO(_name)						\
+		INTEL_GT_RPS_SYSFS_ATTR(_name, 0444, _name##_show, NULL,		\
+					_name##_dev_show, NULL)
+#define INTEL_GT_RPS_SYSFS_ATTR_RW(_name)						\
+		INTEL_GT_RPS_SYSFS_ATTR(_name, 0644, _name##_show, _name##_store,	\
+					_name##_dev_show, _name##_dev_store)
 
 /* The below macros generate static structures */
 INTEL_GT_RPS_SYSFS_ATTR_RO(act_freq_mhz);
@@ -475,32 +432,31 @@ INTEL_GT_RPS_SYSFS_ATTR_RO(RP1_freq_mhz);
 INTEL_GT_RPS_SYSFS_ATTR_RO(RPn_freq_mhz);
 INTEL_GT_RPS_SYSFS_ATTR_RW(max_freq_mhz);
 INTEL_GT_RPS_SYSFS_ATTR_RW(min_freq_mhz);
-
-static DEVICE_ATTR_RO(vlv_rpe_freq_mhz);
-
-#define GEN6_ATTR(s) { \
-		&dev_attr_##s##_act_freq_mhz.attr, \
-		&dev_attr_##s##_cur_freq_mhz.attr, \
-		&dev_attr_##s##_boost_freq_mhz.attr, \
-		&dev_attr_##s##_max_freq_mhz.attr, \
-		&dev_attr_##s##_min_freq_mhz.attr, \
-		&dev_attr_##s##_RP0_freq_mhz.attr, \
-		&dev_attr_##s##_RP1_freq_mhz.attr, \
-		&dev_attr_##s##_RPn_freq_mhz.attr, \
+INTEL_GT_RPS_SYSFS_ATTR_RO(vlv_rpe_freq_mhz);
+
+#define GEN6_ATTR(p, s) { \
+		&p##attr_##s##_act_freq_mhz.attr, \
+		&p##attr_##s##_cur_freq_mhz.attr, \
+		&p##attr_##s##_boost_freq_mhz.attr, \
+		&p##attr_##s##_max_freq_mhz.attr, \
+		&p##attr_##s##_min_freq_mhz.attr, \
+		&p##attr_##s##_RP0_freq_mhz.attr, \
+		&p##attr_##s##_RP1_freq_mhz.attr, \
+		&p##attr_##s##_RPn_freq_mhz.attr, \
 		NULL, \
 	}
 
-#define GEN6_RPS_ATTR GEN6_ATTR(rps)
-#define GEN6_GT_ATTR  GEN6_ATTR(gt)
+#define GEN6_RPS_ATTR GEN6_ATTR(, rps)
+#define GEN6_GT_ATTR  GEN6_ATTR(dev_, gt)
 
 static const struct attribute * const gen6_rps_attrs[] = GEN6_RPS_ATTR;
 static const struct attribute * const gen6_gt_attrs[]  = GEN6_GT_ATTR;
 
-static ssize_t punit_req_freq_mhz_show(struct device *dev,
-				       struct device_attribute *attr,
+static ssize_t punit_req_freq_mhz_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
 				       char *buff)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	u32 preq = intel_rps_read_punit_req_frequency(&gt->rps);
 
 	return sysfs_emit(buff, "%u\n", preq);
@@ -508,20 +464,20 @@ static ssize_t punit_req_freq_mhz_show(struct device *dev,
 
 struct intel_gt_bool_throttle_attr {
 	struct attribute attr;
-	ssize_t (*show)(struct device *dev, struct device_attribute *attr,
+	ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr,
 			char *buf);
-	i915_reg_t reg32;
+	i915_reg_t (*reg32)(struct intel_gt *gt);
 	u32 mask;
 };
 
-static ssize_t throttle_reason_bool_show(struct device *dev,
-					 struct device_attribute *attr,
+static ssize_t throttle_reason_bool_show(struct kobject *kobj,
+					 struct kobj_attribute *attr,
 					 char *buff)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	struct intel_gt_bool_throttle_attr *t_attr =
 				(struct intel_gt_bool_throttle_attr *) attr;
-	bool val = rps_read_mask_mmio(&gt->rps, t_attr->reg32, t_attr->mask);
+	bool val = rps_read_mask_mmio(&gt->rps, t_attr->reg32(gt), t_attr->mask);
 
 	return sysfs_emit(buff, "%u\n", val);
 }
@@ -530,11 +486,11 @@ static ssize_t throttle_reason_bool_show(struct device *dev,
 struct intel_gt_bool_throttle_attr attr_##sysfs_func__ = { \
 	.attr = { .name = __stringify(sysfs_func__), .mode = 0444 }, \
 	.show = throttle_reason_bool_show, \
-	.reg32 = GT0_PERF_LIMIT_REASONS, \
+	.reg32 = intel_gt_perf_limit_reasons_reg, \
 	.mask = mask__, \
 }
 
-static DEVICE_ATTR_RO(punit_req_freq_mhz);
+INTEL_GT_ATTR_RO(punit_req_freq_mhz);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_status, GT0_PERF_LIMIT_REASONS_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl1, POWER_LIMIT_1_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl2, POWER_LIMIT_2_MASK);
@@ -597,8 +553,8 @@ static const struct attribute *throttle_reason_attrs[] = {
 #define U8_8_VAL_MASK           0xffff
 #define U8_8_SCALE_TO_VALUE     "0.00390625"
 
-static ssize_t freq_factor_scale_show(struct device *dev,
-				      struct device_attribute *attr,
+static ssize_t freq_factor_scale_show(struct kobject *kobj,
+				      struct kobj_attribute *attr,
 				      char *buff)
 {
 	return sysfs_emit(buff, "%s\n", U8_8_SCALE_TO_VALUE);
@@ -610,11 +566,11 @@ static u32 media_ratio_mode_to_factor(u32 mode)
 	return !mode ? mode : 256 / mode;
 }
 
-static ssize_t media_freq_factor_show(struct device *dev,
-				      struct device_attribute *attr,
+static ssize_t media_freq_factor_show(struct kobject *kobj,
+				      struct kobj_attribute *attr,
 				      char *buff)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
 	intel_wakeref_t wakeref;
 	u32 mode;
@@ -641,11 +597,11 @@ static ssize_t media_freq_factor_show(struct device *dev,
 	return sysfs_emit(buff, "%u\n", media_ratio_mode_to_factor(mode));
 }
 
-static ssize_t media_freq_factor_store(struct device *dev,
-				       struct device_attribute *attr,
+static ssize_t media_freq_factor_store(struct kobject *kobj,
+				       struct kobj_attribute *attr,
 				       const char *buff, size_t count)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
 	u32 factor, mode;
 	int err;
@@ -670,11 +626,11 @@ static ssize_t media_freq_factor_store(struct device *dev,
 	return err ?: count;
 }
 
-static ssize_t media_RP0_freq_mhz_show(struct device *dev,
-				       struct device_attribute *attr,
+static ssize_t media_RP0_freq_mhz_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
 				       char *buff)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	u32 val;
 	int err;
 
@@ -691,11 +647,11 @@ static ssize_t media_RP0_freq_mhz_show(struct device *dev,
 	return sysfs_emit(buff, "%u\n", val);
 }
 
-static ssize_t media_RPn_freq_mhz_show(struct device *dev,
-				       struct device_attribute *attr,
+static ssize_t media_RPn_freq_mhz_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
 				       char *buff)
 {
-	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
 	u32 val;
 	int err;
 
@@ -712,17 +668,17 @@ static ssize_t media_RPn_freq_mhz_show(struct device *dev,
 	return sysfs_emit(buff, "%u\n", val);
 }
 
-static DEVICE_ATTR_RW(media_freq_factor);
-static struct device_attribute dev_attr_media_freq_factor_scale =
+INTEL_GT_ATTR_RW(media_freq_factor);
+static struct kobj_attribute attr_media_freq_factor_scale =
 	__ATTR(media_freq_factor.scale, 0444, freq_factor_scale_show, NULL);
-static DEVICE_ATTR_RO(media_RP0_freq_mhz);
-static DEVICE_ATTR_RO(media_RPn_freq_mhz);
+INTEL_GT_ATTR_RO(media_RP0_freq_mhz);
+INTEL_GT_ATTR_RO(media_RPn_freq_mhz);
 
 static const struct attribute *media_perf_power_attrs[] = {
-	&dev_attr_media_freq_factor.attr,
-	&dev_attr_media_freq_factor_scale.attr,
-	&dev_attr_media_RP0_freq_mhz.attr,
-	&dev_attr_media_RPn_freq_mhz.attr,
+	&attr_media_freq_factor.attr,
+	&attr_media_freq_factor_scale.attr,
+	&attr_media_RP0_freq_mhz.attr,
+	&attr_media_RPn_freq_mhz.attr,
 	NULL
 };
 
@@ -754,20 +710,29 @@ static const struct attribute * const rps_defaults_attrs[] = {
 	NULL
 };
 
-static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj,
-				const struct attribute * const *attrs)
+static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj)
 {
+	const struct attribute * const *attrs;
+	struct attribute *vlv_attr;
 	int ret;
 
 	if (GRAPHICS_VER(gt->i915) < 6)
 		return 0;
 
+	if (is_object_gt(kobj)) {
+		attrs = gen6_rps_attrs;
+		vlv_attr = &attr_rps_vlv_rpe_freq_mhz.attr;
+	} else {
+		attrs = gen6_gt_attrs;
+		vlv_attr = &dev_attr_gt_vlv_rpe_freq_mhz.attr;
+	}
+
 	ret = sysfs_create_files(kobj, attrs);
 	if (ret)
 		return ret;
 
 	if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915))
-		ret = sysfs_create_file(kobj, &dev_attr_vlv_rpe_freq_mhz.attr);
+		ret = sysfs_create_file(kobj, vlv_attr);
 
 	return ret;
 }
@@ -778,9 +743,7 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 
 	intel_sysfs_rc6_init(gt, kobj);
 
-	ret = is_object_gt(kobj) ?
-	      intel_sysfs_rps_init(gt, kobj, gen6_rps_attrs) :
-	      intel_sysfs_rps_init(gt, kobj, gen6_gt_attrs);
+	ret = intel_sysfs_rps_init(gt, kobj);
 	if (ret)
 		drm_warn(&gt->i915->drm,
 			 "failed to create gt%u RPS sysfs files (%pe)",
@@ -790,13 +753,13 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 	if (!is_object_gt(kobj))
 		return;
 
-	ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr);
+	ret = sysfs_create_file(kobj, &attr_punit_req_freq_mhz.attr);
 	if (ret)
 		drm_warn(&gt->i915->drm,
 			 "failed to create gt%u punit_req_freq_mhz sysfs (%pe)",
 			 gt->info.id, ERR_PTR(ret));
 
-	if (GRAPHICS_VER(gt->i915) >= 11) {
+	if (i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt))) {
 		ret = sysfs_create_files(kobj, throttle_reason_attrs);
 		if (ret)
 			drm_warn(&gt->i915->drm,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index f19c2de77ff6..a0cc73b401ef 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -20,6 +20,7 @@
 #include "intel_gsc.h"
 
 #include "i915_vma.h"
+#include "i915_perf_types.h"
 #include "intel_engine_types.h"
 #include "intel_gt_buffer_pool_types.h"
 #include "intel_hwconfig.h"
@@ -59,6 +60,9 @@ enum intel_steering_type {
 	L3BANK,
 	MSLICE,
 	LNCF,
+	GAM,
+	DSS,
+	OADDRM,
 
 	/*
 	 * On some platforms there are multiple types of MCR registers that
@@ -141,20 +145,6 @@ struct intel_gt {
 	struct intel_wakeref wakeref;
 	atomic_t user_wakeref;
 
-	/**
-	 *  Protects access to lmem usefault list.
-	 *  It is required, if we are outside of the runtime suspend path,
-	 *  access to @lmem_userfault_list requires always first grabbing the
-	 *  runtime pm, to ensure we can't race against runtime suspend.
-	 *  Once we have that we also need to grab @lmem_userfault_lock,
-	 *  at which point we have exclusive access.
-	 *  The runtime suspend path is special since it doesn't really hold any locks,
-	 *  but instead has exclusive access by virtue of all other accesses requiring
-	 *  holding the runtime pm wakeref.
-	 */
-	struct mutex lmem_userfault_lock;
-	struct list_head lmem_userfault_list;
-
 	struct list_head closed_vma;
 	spinlock_t closed_lock; /* guards the list of closed_vma */
 
@@ -170,9 +160,6 @@ struct intel_gt {
 	 */
 	intel_wakeref_t awake;
 
-	/* Manual runtime pm autosuspend delay for user GGTT/lmem mmaps */
-	struct intel_wakeref_auto userfault_wakeref;
-
 	u32 clock_frequency;
 	u32 clock_period_ns;
 
@@ -286,6 +273,8 @@ struct intel_gt {
 	/* sysfs defaults per gt */
 	struct gt_defaults defaults;
 	struct kobject *sysfs_defaults;
+
+	struct i915_perf_gt perf;
 };
 
 struct intel_gt_definition {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 2eaeba14319e..e82a9d763e57 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -15,6 +15,7 @@
 #include "i915_trace.h"
 #include "i915_utils.h"
 #include "intel_gt.h"
+#include "intel_gt_mcr.h"
 #include "intel_gt_regs.h"
 #include "intel_gtt.h"
 
@@ -269,11 +270,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 	memset64(vm->min_alignment, I915_GTT_MIN_ALIGNMENT,
 		 ARRAY_SIZE(vm->min_alignment));
 
-	if (HAS_64K_PAGES(vm->i915) && NEEDS_COMPACT_PT(vm->i915) &&
-	    subclass == VM_CLASS_PPGTT) {
-		vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_2M;
-		vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_2M;
-	} else if (HAS_64K_PAGES(vm->i915)) {
+	if (HAS_64K_PAGES(vm->i915)) {
 		vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_64K;
 		vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_64K;
 	}
@@ -343,7 +340,8 @@ int setup_scratch_page(struct i915_address_space *vm)
 	 */
 	size = I915_GTT_PAGE_SIZE_4K;
 	if (i915_vm_is_4lvl(vm) &&
-	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K))
+	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K) &&
+	    !HAS_64K_PAGES(vm->i915))
 		size = I915_GTT_PAGE_SIZE_64K;
 
 	do {
@@ -385,18 +383,6 @@ skip:
 		if (size == I915_GTT_PAGE_SIZE_4K)
 			return -ENOMEM;
 
-		/*
-		 * If we need 64K minimum GTT pages for device local-memory,
-		 * like on XEHPSDV, then we need to fail the allocation here,
-		 * otherwise we can't safely support the insertion of
-		 * local-memory pages for this vm, since the HW expects the
-		 * correct physical alignment and size when the page-table is
-		 * operating in 64K GTT mode, which includes any scratch PTEs,
-		 * since userspace can still touch them.
-		 */
-		if (HAS_64K_PAGES(vm->i915))
-			return -ENOMEM;
-
 		size = I915_GTT_PAGE_SIZE_4K;
 	} while (1);
 }
@@ -493,6 +479,18 @@ static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
 }
 
+static void xehp_setup_private_ppat(struct intel_gt *gt)
+{
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0), GEN8_PPAT_WB);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1), GEN8_PPAT_WC);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2), GEN8_PPAT_WT);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3), GEN8_PPAT_UC);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4), GEN8_PPAT_WB);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(5), GEN8_PPAT_WB);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(6), GEN8_PPAT_WB);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(7), GEN8_PPAT_WB);
+}
+
 static void icl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	intel_uncore_write(uncore,
@@ -585,13 +583,16 @@ static void chv_setup_private_ppat(struct intel_uncore *uncore)
 	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
 }
 
-void setup_private_pat(struct intel_uncore *uncore)
+void setup_private_pat(struct intel_gt *gt)
 {
-	struct drm_i915_private *i915 = uncore->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct drm_i915_private *i915 = gt->i915;
 
 	GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
 
-	if (GRAPHICS_VER(i915) >= 12)
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+		xehp_setup_private_ppat(gt);
+	else if (GRAPHICS_VER(i915) >= 12)
 		tgl_setup_private_ppat(uncore);
 	else if (GRAPHICS_VER(i915) >= 11)
 		icl_setup_private_ppat(uncore);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index c0ca53cba9f0..4d75ba4bb41d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -93,6 +93,7 @@ typedef u64 gen8_pte_t;
 #define GEN12_GGTT_PTE_LM	BIT_ULL(1)
 
 #define GEN12_PDE_64K BIT(6)
+#define GEN12_PTE_PS64 BIT(8)
 
 /*
  * Cacheability Control is a 4-bit value. The low three bits are stored in bits
@@ -667,7 +668,7 @@ void ppgtt_unbind_vma(struct i915_address_space *vm,
 
 void gtt_write_workarounds(struct intel_gt *gt);
 
-void setup_private_pat(struct intel_uncore *uncore);
+void setup_private_pat(struct intel_gt *gt);
 
 int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
 			   struct i915_vm_pt_stash *stash,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 3955292483a6..7771a19008c6 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -20,6 +20,30 @@
 #include "intel_ring.h"
 #include "shmem_utils.h"
 
+/*
+ * The per-platform tables are u8-encoded in @data. Decode @data and set the
+ * addresses' offset and commands in @regs. The following encoding is used
+ * for each byte. There are 2 steps: decoding commands and decoding addresses.
+ *
+ * Commands:
+ * [7]: create NOPs - number of NOPs are set in lower bits
+ * [6]: When creating MI_LOAD_REGISTER_IMM command, allow to set
+ *      MI_LRI_FORCE_POSTED
+ * [5:0]: Number of NOPs or registers to set values to in case of
+ *        MI_LOAD_REGISTER_IMM
+ *
+ * Addresses: these are decoded after a MI_LOAD_REGISTER_IMM command by "count"
+ * number of registers. They are set by using the REG/REG16 macros: the former
+ * is used for offsets smaller than 0x200 while the latter is for values bigger
+ * than that. Those macros already set all the bits documented below correctly:
+ *
+ * [7]: When a register offset needs more than 6 bits, use additional bytes, to
+ *      follow, for the lower bits
+ * [6:0]: Register offset, without considering the engine base.
+ *
+ * This function only tweaks the commands and register offsets. Values are not
+ * filled out.
+ */
 static void set_offsets(u32 *regs,
 			const u8 *data,
 			const struct intel_engine_cs *engine,
@@ -264,6 +288,39 @@ static const u8 dg2_xcs_offsets[] = {
 	END
 };
 
+static const u8 mtl_xcs_offsets[] = {
+	NOP(1),
+	LRI(13, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+	NOP(4),
+
+	NOP(1),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	END
+};
+
 static const u8 gen8_rcs_offsets[] = {
 	NOP(1),
 	LRI(14, POSTED),
@@ -606,6 +663,49 @@ static const u8 dg2_rcs_offsets[] = {
 	END
 };
 
+static const u8 mtl_rcs_offsets[] = {
+	NOP(1),
+	LRI(15, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+	REG(0x120),
+	REG(0x124),
+
+	NOP(1),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(2),
+	LRI(2, POSTED),
+	REG16(0x5a8),
+	REG16(0x5ac),
+
+	NOP(6),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END
+};
+
 #undef END
 #undef REG16
 #undef REG
@@ -624,7 +724,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		   !intel_engine_has_relative_mmio(engine));
 
 	if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) {
-		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
+			return mtl_rcs_offsets;
+		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
 			return dg2_rcs_offsets;
 		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
 			return xehp_rcs_offsets;
@@ -637,7 +739,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		else
 			return gen8_rcs_offsets;
 	} else {
-		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
+			return mtl_xcs_offsets;
+		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
 			return dg2_xcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_xcs_offsets;
@@ -745,19 +849,18 @@ static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
 static u32
 lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 {
-	switch (GRAPHICS_VER(engine->i915)) {
-	default:
-		MISSING_CASE(GRAPHICS_VER(engine->i915));
-		fallthrough;
-	case 12:
+	if (GRAPHICS_VER(engine->i915) >= 12)
 		return GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-	case 11:
+	else if (GRAPHICS_VER(engine->i915) >= 11)
 		return GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-	case 9:
+	else if (GRAPHICS_VER(engine->i915) >= 9)
 		return GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-	case 8:
+	else if (GRAPHICS_VER(engine->i915) >= 8)
 		return GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-	}
+
+	GEM_BUG_ON(GRAPHICS_VER(engine->i915) < 8);
+
+	return 0;
 }
 
 static void
@@ -1012,7 +1115,7 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		context_size += I915_GTT_PAGE_SIZE; /* for redzone */
 
-	if (GRAPHICS_VER(engine->i915) == 12) {
+	if (GRAPHICS_VER(engine->i915) >= 12) {
 		ce->wa_bb_page = context_size / PAGE_SIZE;
 		context_size += PAGE_SIZE;
 	}
@@ -1718,24 +1821,16 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine)
 	unsigned int i;
 	int err;
 
-	if (!(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
+	if (GRAPHICS_VER(engine->i915) >= 11 ||
+	    !(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
 		return;
 
-	switch (GRAPHICS_VER(engine->i915)) {
-	case 12:
-	case 11:
-		return;
-	case 9:
+	if (GRAPHICS_VER(engine->i915) == 9) {
 		wa_bb_fn[0] = gen9_init_indirectctx_bb;
 		wa_bb_fn[1] = NULL;
-		break;
-	case 8:
+	} else if (GRAPHICS_VER(engine->i915) == 8) {
 		wa_bb_fn[0] = gen8_init_indirectctx_bb;
 		wa_bb_fn[1] = NULL;
-		break;
-	default:
-		MISSING_CASE(GRAPHICS_VER(engine->i915));
-		return;
 	}
 
 	err = lrc_create_wa_ctx(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index a390f0813c8b..7111bae759f3 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -110,6 +110,8 @@ enum {
 #define XEHP_SW_CTX_ID_WIDTH			16
 #define XEHP_SW_COUNTER_SHIFT			58
 #define XEHP_SW_COUNTER_WIDTH			6
+#define GEN12_GUC_SW_CTX_ID_SHIFT		39
+#define GEN12_GUC_SW_CTX_ID_WIDTH		16
 
 static inline void lrc_runtime_start(struct intel_context *ce)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index aaaf1906026c..b405a04135ca 100644
--- a/drivers/gpu/drm/i915/gt/intel_migrate.c
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -10,6 +10,7 @@
 #include "intel_gtt.h"
 #include "intel_migrate.h"
 #include "intel_ring.h"
+#include "gem/i915_gem_lmem.h"
 
 struct insert_pte_data {
 	u64 offset;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 152244d7f62a..49fdd509527a 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -7,6 +7,7 @@
 
 #include "intel_engine.h"
 #include "intel_gt.h"
+#include "intel_gt_mcr.h"
 #include "intel_gt_regs.h"
 #include "intel_mocs.h"
 #include "intel_ring.h"
@@ -609,14 +610,17 @@ static u32 l3cc_combine(u16 low, u16 high)
 	     0; \
 	     i++)
 
-static void init_l3cc_table(struct intel_uncore *uncore,
+static void init_l3cc_table(struct intel_gt *gt,
 			    const struct drm_i915_mocs_table *table)
 {
 	unsigned int i;
 	u32 l3cc;
 
 	for_each_l3cc(l3cc, table, i)
-		intel_uncore_write_fw(uncore, GEN9_LNCFCMOCS(i), l3cc);
+		if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+			intel_gt_mcr_multicast_write_fw(gt, XEHP_LNCFCMOCS(i), l3cc);
+		else
+			intel_uncore_write_fw(gt->uncore, GEN9_LNCFCMOCS(i), l3cc);
 }
 
 void intel_mocs_init_engine(struct intel_engine_cs *engine)
@@ -636,7 +640,7 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
 		init_mocs_table(engine, &table);
 
 	if (flags & HAS_RENDER_L3CC && engine->class == RENDER_CLASS)
-		init_l3cc_table(engine->uncore, &table);
+		init_l3cc_table(engine->gt, &table);
 }
 
 static u32 global_mocs_offset(void)
@@ -672,7 +676,7 @@ void intel_mocs_init(struct intel_gt *gt)
 	 * memory transactions including guc transactions
 	 */
 	if (flags & HAS_RENDER_L3CC)
-		init_l3cc_table(gt->uncore, &table);
+		init_l3cc_table(gt, &table);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b36674356986..3159df6cdd49 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1278,7 +1278,7 @@ static void intel_gt_reset_global(struct intel_gt *gt,
 	kobject_uevent_env(kobj, KOBJ_CHANGE, reset_event);
 
 	/* Use a watchdog to ensure that our reset completes */
-	intel_wedge_on_timeout(&w, gt, 5 * HZ) {
+	intel_wedge_on_timeout(&w, gt, 60 * HZ) {
 		intel_display_prepare_reset(gt->i915);
 
 		intel_gt_reset(gt, engine_mask, reason);
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 6b86250c31ab..6c34a83c24b3 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -625,9 +625,7 @@ static void gen5_rps_disable(struct intel_rps *rps)
 	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
 
 	/* Ack interrupts, disable EFC interrupt */
-	intel_uncore_write(uncore, MEMINTREN,
-			   intel_uncore_read(uncore, MEMINTREN) &
-			   ~MEMINT_EVAL_CHG_EN);
+	intel_uncore_rmw(uncore, MEMINTREN, MEMINT_EVAL_CHG_EN, 0);
 	intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
 
 	/* Go back to the starting frequency */
@@ -1016,9 +1014,15 @@ void intel_rps_boost(struct i915_request *rq)
 		if (rps_uses_slpc(rps)) {
 			slpc = rps_to_slpc(rps);
 
+			if (slpc->min_freq_softlimit >= slpc->boost_freq)
+				return;
+
 			/* Return if old value is non zero */
-			if (!atomic_fetch_inc(&slpc->num_waiters))
+			if (!atomic_fetch_inc(&slpc->num_waiters)) {
+				GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
+					 rq->fence.context, rq->fence.seqno);
 				schedule_work(&slpc->boost_work);
+			}
 
 			return;
 		}
@@ -1085,15 +1089,25 @@ static u32 intel_rps_read_state_cap(struct intel_rps *rps)
 		return intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
 }
 
-/**
- * gen6_rps_get_freq_caps - Get freq caps exposed by HW
- * @rps: the intel_rps structure
- * @caps: returned freq caps
- *
- * Returned "caps" frequencies should be converted to MHz using
- * intel_gpu_freq()
- */
-void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps)
+static void
+mtl_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 rp_state_cap = rps_to_gt(rps)->type == GT_MEDIA ?
+				intel_uncore_read(uncore, MTL_MEDIAP_STATE_CAP) :
+				intel_uncore_read(uncore, MTL_RP_STATE_CAP);
+	u32 rpe = rps_to_gt(rps)->type == GT_MEDIA ?
+			intel_uncore_read(uncore, MTL_MPE_FREQUENCY) :
+			intel_uncore_read(uncore, MTL_GT_RPE_FREQUENCY);
+
+	/* MTL values are in units of 16.67 MHz */
+	caps->rp0_freq = REG_FIELD_GET(MTL_RP0_CAP_MASK, rp_state_cap);
+	caps->min_freq = REG_FIELD_GET(MTL_RPN_CAP_MASK, rp_state_cap);
+	caps->rp1_freq = REG_FIELD_GET(MTL_RPE_MASK, rpe);
+}
+
+static void
+__gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	u32 rp_state_cap;
@@ -1128,6 +1142,24 @@ void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *c
 	}
 }
 
+/**
+ * gen6_rps_get_freq_caps - Get freq caps exposed by HW
+ * @rps: the intel_rps structure
+ * @caps: returned freq caps
+ *
+ * Returned "caps" frequencies should be converted to MHz using
+ * intel_gpu_freq()
+ */
+void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (IS_METEORLAKE(i915))
+		return mtl_get_freq_caps(rps, caps);
+	else
+		return __gen6_rps_get_freq_caps(rps, caps);
+}
+
 static void gen6_rps_init(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
@@ -2191,6 +2223,213 @@ u32 intel_rps_get_rpn_frequency(struct intel_rps *rps)
 		return intel_gpu_freq(rps, rps->min_freq);
 }
 
+static void rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_rps_freq_caps caps;
+	u32 rp_state_limits;
+	u32 gt_perf_status;
+	u32 rpmodectl, rpinclimit, rpdeclimit;
+	u32 rpstat, cagf, reqf;
+	u32 rpcurupei, rpcurup, rpprevup;
+	u32 rpcurdownei, rpcurdown, rpprevdown;
+	u32 rpupei, rpupt, rpdownei, rpdownt;
+	u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
+
+	rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
+	gen6_rps_get_freq_caps(rps, &caps);
+	if (IS_GEN9_LP(i915))
+		gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
+	else
+		gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS);
+
+	/* RPSTAT1 is in the GT power well */
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+	reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ);
+	if (GRAPHICS_VER(i915) >= 9) {
+		reqf >>= 23;
+	} else {
+		reqf &= ~GEN6_TURBO_DISABLE;
+		if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+			reqf >>= 24;
+		else
+			reqf >>= 25;
+	}
+	reqf = intel_gpu_freq(rps, reqf);
+
+	rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
+	rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
+	rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
+
+	rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1);
+	rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
+	rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK;
+	rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK;
+	rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
+	rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
+	rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
+
+	rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI);
+	rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
+
+	rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI);
+	rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
+
+	cagf = intel_rps_read_actual_frequency(rps);
+
+	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+	if (GRAPHICS_VER(i915) >= 11) {
+		pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+		pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK);
+		/*
+		 * The equivalent to the PM ISR & IIR cannot be read
+		 * without affecting the current state of the system
+		 */
+		pm_isr = 0;
+		pm_iir = 0;
+	} else if (GRAPHICS_VER(i915) >= 8) {
+		pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2));
+		pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2));
+		pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2));
+		pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2));
+	} else {
+		pm_ier = intel_uncore_read(uncore, GEN6_PMIER);
+		pm_imr = intel_uncore_read(uncore, GEN6_PMIMR);
+		pm_isr = intel_uncore_read(uncore, GEN6_PMISR);
+		pm_iir = intel_uncore_read(uncore, GEN6_PMIIR);
+	}
+	pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK);
+
+	drm_printf(p, "Video Turbo Mode: %s\n",
+		   str_yes_no(rpmodectl & GEN6_RP_MEDIA_TURBO));
+	drm_printf(p, "HW control enabled: %s\n",
+		   str_yes_no(rpmodectl & GEN6_RP_ENABLE));
+	drm_printf(p, "SW control enabled: %s\n",
+		   str_yes_no((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE));
+
+	drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
+		   pm_ier, pm_imr, pm_mask);
+	if (GRAPHICS_VER(i915) <= 10)
+		drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n",
+			   pm_isr, pm_iir);
+	drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n",
+		   rps->pm_intrmsk_mbz);
+	drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
+	drm_printf(p, "Render p-state ratio: %d\n",
+		   (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8);
+	drm_printf(p, "Render p-state VID: %d\n",
+		   gt_perf_status & 0xff);
+	drm_printf(p, "Render p-state limit: %d\n",
+		   rp_state_limits & 0xff);
+	drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat);
+	drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl);
+	drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit);
+	drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
+	drm_printf(p, "RPNSWREQ: %dMHz\n", reqf);
+	drm_printf(p, "CAGF: %dMHz\n", cagf);
+	drm_printf(p, "RP CUR UP EI: %d (%lldns)\n",
+		   rpcurupei,
+		   intel_gt_pm_interval_to_ns(gt, rpcurupei));
+	drm_printf(p, "RP CUR UP: %d (%lldns)\n",
+		   rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup));
+	drm_printf(p, "RP PREV UP: %d (%lldns)\n",
+		   rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup));
+	drm_printf(p, "Up threshold: %d%%\n",
+		   rps->power.up_threshold);
+	drm_printf(p, "RP UP EI: %d (%lldns)\n",
+		   rpupei, intel_gt_pm_interval_to_ns(gt, rpupei));
+	drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n",
+		   rpupt, intel_gt_pm_interval_to_ns(gt, rpupt));
+
+	drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n",
+		   rpcurdownei,
+		   intel_gt_pm_interval_to_ns(gt, rpcurdownei));
+	drm_printf(p, "RP CUR DOWN: %d (%lldns)\n",
+		   rpcurdown,
+		   intel_gt_pm_interval_to_ns(gt, rpcurdown));
+	drm_printf(p, "RP PREV DOWN: %d (%lldns)\n",
+		   rpprevdown,
+		   intel_gt_pm_interval_to_ns(gt, rpprevdown));
+	drm_printf(p, "Down threshold: %d%%\n",
+		   rps->power.down_threshold);
+	drm_printf(p, "RP DOWN EI: %d (%lldns)\n",
+		   rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei));
+	drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n",
+		   rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt));
+
+	drm_printf(p, "Lowest (RPN) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.min_freq));
+	drm_printf(p, "Nominal (RP1) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.rp1_freq));
+	drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.rp0_freq));
+	drm_printf(p, "Max overclocked frequency: %dMHz\n",
+		   intel_gpu_freq(rps, rps->max_freq));
+
+	drm_printf(p, "Current freq: %d MHz\n",
+		   intel_gpu_freq(rps, rps->cur_freq));
+	drm_printf(p, "Actual freq: %d MHz\n", cagf);
+	drm_printf(p, "Idle freq: %d MHz\n",
+		   intel_gpu_freq(rps, rps->idle_freq));
+	drm_printf(p, "Min freq: %d MHz\n",
+		   intel_gpu_freq(rps, rps->min_freq));
+	drm_printf(p, "Boost freq: %d MHz\n",
+		   intel_gpu_freq(rps, rps->boost_freq));
+	drm_printf(p, "Max freq: %d MHz\n",
+		   intel_gpu_freq(rps, rps->max_freq));
+	drm_printf(p,
+		   "efficient (RPe) frequency: %d MHz\n",
+		   intel_gpu_freq(rps, rps->efficient_freq));
+}
+
+static void slpc_frequency_dump(struct intel_rps *rps, struct drm_printer *p)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_rps_freq_caps caps;
+	u32 pm_mask;
+
+	gen6_rps_get_freq_caps(rps, &caps);
+	pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK);
+
+	drm_printf(p, "PM MASK=0x%08x\n", pm_mask);
+	drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n",
+		   rps->pm_intrmsk_mbz);
+	drm_printf(p, "RPSTAT1: 0x%08x\n", intel_uncore_read(uncore, GEN6_RPSTAT1));
+	drm_printf(p, "RPNSWREQ: %dMHz\n", intel_rps_get_requested_frequency(rps));
+	drm_printf(p, "Lowest (RPN) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.min_freq));
+	drm_printf(p, "Nominal (RP1) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.rp1_freq));
+	drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n",
+		   intel_gpu_freq(rps, caps.rp0_freq));
+	drm_printf(p, "Current freq: %d MHz\n",
+		   intel_rps_get_requested_frequency(rps));
+	drm_printf(p, "Actual freq: %d MHz\n",
+		   intel_rps_read_actual_frequency(rps));
+	drm_printf(p, "Min freq: %d MHz\n",
+		   intel_rps_get_min_frequency(rps));
+	drm_printf(p, "Boost freq: %d MHz\n",
+		   intel_rps_get_boost_frequency(rps));
+	drm_printf(p, "Max freq: %d MHz\n",
+		   intel_rps_get_max_frequency(rps));
+	drm_printf(p,
+		   "efficient (RPe) frequency: %d MHz\n",
+		   intel_gpu_freq(rps, caps.rp1_freq));
+}
+
+void gen6_rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p)
+{
+	if (rps_uses_slpc(rps))
+		return slpc_frequency_dump(rps, p);
+	else
+		return rps_frequency_dump(rps, p);
+}
+
 static int set_max_freq(struct intel_rps *rps, u32 val)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 4509dfdc52e0..110300dfd438 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -10,6 +10,7 @@
 #include "i915_reg_defs.h"
 
 struct i915_request;
+struct drm_printer;
 
 void intel_rps_init_early(struct intel_rps *rps);
 void intel_rps_init(struct intel_rps *rps);
@@ -54,6 +55,8 @@ void intel_rps_lower_unslice(struct intel_rps *rps);
 u32 intel_rps_read_throttle_reason(struct intel_rps *rps);
 bool rps_read_mask_mmio(struct intel_rps *rps, i915_reg_t reg32, u32 mask);
 
+void gen6_rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p);
+
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
 void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 66f21c735d54..6c6198a257ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -677,8 +677,8 @@ u32 intel_sseu_make_rpcs(struct intel_gt *gt,
 	 * If i915/perf is active, we want a stable powergating configuration
 	 * on the system. Use the configuration pinned by i915/perf.
 	 */
-	if (i915->perf.exclusive_stream)
-		req_sseu = &i915->perf.sseu;
+	if (gt->perf.exclusive_stream)
+		req_sseu = &gt->perf.sseu;
 
 	slices = hweight8(req_sseu->slice_mask);
 	subslices = hweight8(req_sseu->subslice_mask);
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 6d2003d598e6..3cdf5c24dbc5 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -166,6 +166,21 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
 	_wa_add(wal, &wa);
 }
 
+static void wa_mcr_add(struct i915_wa_list *wal, i915_mcr_reg_t reg,
+		       u32 clear, u32 set, u32 read_mask, bool masked_reg)
+{
+	struct i915_wa wa = {
+		.mcr_reg = reg,
+		.clr  = clear,
+		.set  = set,
+		.read = read_mask,
+		.masked_reg = masked_reg,
+		.is_mcr = 1,
+	};
+
+	_wa_add(wal, &wa);
+}
+
 static void
 wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
 {
@@ -173,6 +188,12 @@ wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
 }
 
 static void
+wa_mcr_write_clr_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clear, u32 set)
+{
+	wa_mcr_add(wal, reg, clear, set, clear, false);
+}
+
+static void
 wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
 {
 	wa_write_clr_set(wal, reg, ~0, set);
@@ -185,11 +206,23 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
 }
 
 static void
+wa_mcr_write_or(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 set)
+{
+	wa_mcr_write_clr_set(wal, reg, set, set);
+}
+
+static void
 wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
 {
 	wa_write_clr_set(wal, reg, clr, 0);
 }
 
+static void
+wa_mcr_write_clr(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clr)
+{
+	wa_mcr_write_clr_set(wal, reg, clr, 0);
+}
+
 /*
  * WA operations on "masked register". A masked register has the upper 16 bits
  * documented as "masked" in b-spec. Its purpose is to allow writing to just a
@@ -208,18 +241,37 @@ wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 }
 
 static void
+wa_mcr_masked_en(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val)
+{
+	wa_mcr_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val, true);
+}
+
+static void
 wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
 	wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true);
 }
 
 static void
+wa_mcr_masked_dis(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val)
+{
+	wa_mcr_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true);
+}
+
+static void
 wa_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg,
 		    u32 mask, u32 val)
 {
 	wa_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true);
 }
 
+static void
+wa_mcr_masked_field_set(struct i915_wa_list *wal, i915_mcr_reg_t reg,
+			u32 mask, u32 val)
+{
+	wa_mcr_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true);
+}
+
 static void gen6_ctx_workarounds_init(struct intel_engine_cs *engine,
 				      struct i915_wa_list *wal)
 {
@@ -241,8 +293,8 @@ static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, RING_MI_MODE(RENDER_RING_BASE), ASYNC_FLIP_PERF_DISABLE);
 
 	/* WaDisablePartialInstShootdown:bdw,chv */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN,
-		     PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN,
+			 PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for a possible hang in the unlikely event a TLB
@@ -288,18 +340,18 @@ static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen8_ctx_workarounds_init(engine, wal);
 
 	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
 
 	/* WaDisableDopClockGating:bdw
 	 *
 	 * Also see the related UCGTCL1 write in bdw_init_clock_gating()
 	 * to disable EUTC clock gating.
 	 */
-	wa_masked_en(wal, GEN7_ROW_CHICKEN2,
-		     DOP_CLOCK_GATING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2,
+			 DOP_CLOCK_GATING_DISABLE);
 
-	wa_masked_en(wal, HALF_SLICE_CHICKEN3,
-		     GEN8_SAMPLER_POWER_BYPASS_DIS);
+	wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3,
+			 GEN8_SAMPLER_POWER_BYPASS_DIS);
 
 	wa_masked_en(wal, HDC_CHICKEN0,
 		     /* WaForceContextSaveRestoreNonCoherent:bdw */
@@ -314,7 +366,7 @@ static void chv_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen8_ctx_workarounds_init(engine, wal);
 
 	/* WaDisableThreadStallDopClockGating:chv */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
 
 	/* Improve HiZ throughput on CHV. */
 	wa_masked_en(wal, HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
@@ -333,21 +385,21 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine,
 		 */
 		wa_masked_en(wal, COMMON_SLICE_CHICKEN2,
 			     GEN9_PBE_COMPRESSED_HASH_SELECTION);
-		wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
-			     GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
+		wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
+				 GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
 	}
 
 	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
 	/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN,
-		     FLOW_CONTROL_ENABLE |
-		     PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN,
+			 FLOW_CONTROL_ENABLE |
+			 PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
 	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
 	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
-	wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
-		     GEN9_ENABLE_YV12_BUGFIX |
-		     GEN9_ENABLE_GPGPU_PREEMPTION);
+	wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
+			 GEN9_ENABLE_YV12_BUGFIX |
+			 GEN9_ENABLE_GPGPU_PREEMPTION);
 
 	/* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
 	/* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
@@ -356,8 +408,8 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine,
 		     GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
 
 	/* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
-	wa_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5,
-		      GEN9_CCS_TLB_PREFETCH_ENABLE);
+	wa_mcr_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5,
+			  GEN9_CCS_TLB_PREFETCH_ENABLE);
 
 	/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
 	wa_masked_en(wal, HDC_CHICKEN0,
@@ -386,11 +438,11 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine,
 	    IS_KABYLAKE(i915) ||
 	    IS_COFFEELAKE(i915) ||
 	    IS_COMETLAKE(i915))
-		wa_masked_en(wal, HALF_SLICE_CHICKEN3,
-			     GEN8_SAMPLER_POWER_BYPASS_DIS);
+		wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3,
+				 GEN8_SAMPLER_POWER_BYPASS_DIS);
 
 	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
-	wa_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
+	wa_mcr_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
 	/*
 	 * Supporting preemption with fine-granularity requires changes in the
@@ -469,8 +521,8 @@ static void bxt_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen9_ctx_workarounds_init(engine, wal);
 
 	/* WaDisableThreadStallDopClockGating:bxt */
-	wa_masked_en(wal, GEN8_ROW_CHICKEN,
-		     STALL_DOP_GATING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN,
+			 STALL_DOP_GATING_DISABLE);
 
 	/* WaToEnableHwFixForPushConstHWBug:bxt */
 	wa_masked_en(wal, COMMON_SLICE_CHICKEN2,
@@ -490,8 +542,8 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine,
 			     GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
 	/* WaDisableSbeCacheDispatchPortSharing:kbl */
-	wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1,
-		     GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1,
+			 GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 }
 
 static void glk_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -514,8 +566,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine,
 		     GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
 	/* WaDisableSbeCacheDispatchPortSharing:cfl */
-	wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1,
-		     GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+	wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1,
+			 GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 }
 
 static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -534,13 +586,13 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 * (the register is whitelisted in hardware now, so UMDs can opt in
 	 * for coherency if they have a good reason).
 	 */
-	wa_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
+	wa_mcr_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
 
 	/* WaEnableFloatBlendOptimization:icl */
-	wa_add(wal, GEN10_CACHE_MODE_SS, 0,
-	       _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE),
-	       0 /* write-only, so skip validation */,
-	       true);
+	wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0,
+		   _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE),
+		   0 /* write-only, so skip validation */,
+		   true);
 
 	/* WaDisableGPGPUMidThreadPreemption:icl */
 	wa_masked_field_set(wal, GEN8_CS_CHICKEN1,
@@ -548,8 +600,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 
 	/* allow headerless messages for preemptible GPGPU context */
-	wa_masked_en(wal, GEN10_SAMPLER_MODE,
-		     GEN11_SAMPLER_ENABLE_HEADLESS_MSG);
+	wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE,
+			 GEN11_SAMPLER_ENABLE_HEADLESS_MSG);
 
 	/* Wa_1604278689:icl,ehl */
 	wa_write(wal, IVB_FBC_RT_BASE, 0xFFFFFFFF & ~ILK_FBC_RT_VALID);
@@ -558,7 +610,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 			 0xFFFFFFFF);
 
 	/* Wa_1406306137:icl,ehl */
-	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
+	wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
 /*
@@ -569,13 +621,13 @@ static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 				   struct i915_wa_list *wal)
 {
 	wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
-	wa_write_clr_set(wal, GEN11_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
-			 REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
-	wa_add(wal,
-	       FF_MODE2,
-	       FF_MODE2_TDS_TIMER_MASK,
-	       FF_MODE2_TDS_TIMER_128,
-	       0, false);
+	wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
+			     REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
+	wa_mcr_add(wal,
+		   XEHP_FF_MODE2,
+		   FF_MODE2_TDS_TIMER_MASK,
+		   FF_MODE2_TDS_TIMER_128,
+		   0, false);
 }
 
 /*
@@ -599,7 +651,7 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 	 * verification is ignored.
 	 */
 	wa_add(wal,
-	       FF_MODE2,
+	       GEN12_FF_MODE2,
 	       FF_MODE2_TDS_TIMER_MASK,
 	       FF_MODE2_TDS_TIMER_128,
 	       0, false);
@@ -608,6 +660,8 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 				       struct i915_wa_list *wal)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	gen12_ctx_gt_tuning_init(engine, wal);
 
 	/*
@@ -637,10 +691,14 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
-	       FF_MODE2,
+	       GEN12_FF_MODE2,
 	       FF_MODE2_GS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224,
 	       0, false);
+
+	if (!IS_DG1(i915))
+		/* Wa_1806527549 */
+		wa_masked_en(wal, HIZ_CHICKEN, HZ_DEPTH_TEST_LE_GE_OPT_DISABLE);
 }
 
 static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -664,27 +722,27 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* Wa_16011186671:dg2_g11 */
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) {
-		wa_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH);
-		wa_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE);
+		wa_mcr_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH);
+		wa_mcr_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) {
 		/* Wa_14010469329:dg2_g10 */
-		wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3,
-			     XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE);
+		wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3,
+				 XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE);
 
 		/*
 		 * Wa_22010465075:dg2_g10
 		 * Wa_22010613112:dg2_g10
 		 * Wa_14010698770:dg2_g10
 		 */
-		wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3,
-			     GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
+		wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3,
+				 GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 	}
 
 	/* Wa_16013271637:dg2 */
-	wa_masked_en(wal, SLICE_COMMON_ECO_CHICKEN1,
-		     MSC_MSAA_REODER_BUF_BYPASS_DISABLE);
+	wa_mcr_masked_en(wal, XEHP_SLICE_COMMON_ECO_CHICKEN1,
+			 MSC_MSAA_REODER_BUF_BYPASS_DISABLE);
 
 	/* Wa_14014947963:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) ||
@@ -1076,18 +1134,23 @@ static void __set_mcr_steering(struct i915_wa_list *wal,
 	wa_write_clr_set(wal, steering_reg, mcr_mask, mcr);
 }
 
-static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
-			 unsigned int slice, unsigned int subslice)
+static void debug_dump_steering(struct intel_gt *gt)
 {
 	struct drm_printer p = drm_debug_printer("MCR Steering:");
 
+	if (drm_debug_enabled(DRM_UT_DRIVER))
+		intel_gt_mcr_report_steering(&p, gt, false);
+}
+
+static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
+			 unsigned int slice, unsigned int subslice)
+{
 	__set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice);
 
 	gt->default_steering.groupid = slice;
 	gt->default_steering.instanceid = subslice;
 
-	if (drm_debug_enabled(DRM_UT_DRIVER))
-		intel_gt_mcr_report_steering(&p, gt, false);
+	debug_dump_steering(gt);
 }
 
 static void
@@ -1181,6 +1244,9 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
 		gt->steering_table[MSLICE] = NULL;
 	}
 
+	if (IS_XEHPSDV(gt->i915) && slice_mask & BIT(0))
+		gt->steering_table[GAM] = NULL;
+
 	slice = __ffs(slice_mask);
 	subslice = intel_sseu_find_first_xehp_dss(sseu, GEN_DSS_PER_GSLICE, slice) %
 		GEN_DSS_PER_GSLICE;
@@ -1198,6 +1264,13 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
 	 */
 	__set_mcr_steering(wal, MCFG_MCR_SELECTOR, 0, 2);
 	__set_mcr_steering(wal, SF_MCR_SELECTOR, 0, 2);
+
+	/*
+	 * On DG2, GAM registers have a dedicated steering control register
+	 * and must always be programmed to a hardcoded groupid of "1."
+	 */
+	if (IS_DG2(gt->i915))
+		__set_mcr_steering(wal, GAM_MCR_SELECTOR, 1, 0);
 }
 
 static void
@@ -1254,22 +1327,22 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 		    PSDUNIT_CLKGATE_DIS);
 
 	/* Wa_1406680159:icl,ehl */
-	wa_write_or(wal,
-		    SUBSLICE_UNIT_LEVEL_CLKGATE,
-		    GWUNIT_CLKGATE_DIS);
+	wa_mcr_write_or(wal,
+			GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE,
+			GWUNIT_CLKGATE_DIS);
 
 	/* Wa_1607087056:icl,ehl,jsl */
 	if (IS_ICELAKE(i915) ||
 	    IS_JSL_EHL_GRAPHICS_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
-			    SLICE_UNIT_LEVEL_CLKGATE,
+			    GEN11_SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 
 	/*
 	 * This is not a documented workaround, but rather an optimization
 	 * to reduce sampler power.
 	 */
-	wa_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
+	wa_mcr_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
 }
 
 /*
@@ -1303,7 +1376,7 @@ gen12_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	wa_14011060649(gt, wal);
 
 	/* Wa_14011059788:tgl,rkl,adl-s,dg1,adl-p */
-	wa_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
+	wa_mcr_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE);
 }
 
 static void
@@ -1315,14 +1388,14 @@ tgl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 
 	/* Wa_1409420604:tgl */
 	if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0))
-		wa_write_or(wal,
-			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
-			    CPSSUNIT_CLKGATE_DIS);
+		wa_mcr_write_or(wal,
+				SUBSLICE_UNIT_LEVEL_CLKGATE2,
+				CPSSUNIT_CLKGATE_DIS);
 
 	/* Wa_1607087056:tgl also know as BUG:1409180338 */
 	if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
-			    SLICE_UNIT_LEVEL_CLKGATE,
+			    GEN11_SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 
 	/* Wa_1408615072:tgl[a0] */
@@ -1341,14 +1414,14 @@ dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	/* Wa_1607087056:dg1 */
 	if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
-			    SLICE_UNIT_LEVEL_CLKGATE,
+			    GEN11_SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 
 	/* Wa_1409420604:dg1 */
 	if (IS_DG1(i915))
-		wa_write_or(wal,
-			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
-			    CPSSUNIT_CLKGATE_DIS);
+		wa_mcr_write_or(wal,
+				SUBSLICE_UNIT_LEVEL_CLKGATE2,
+				CPSSUNIT_CLKGATE_DIS);
 
 	/* Wa_1408615072:dg1 */
 	/* Empirical testing shows this register is unaffected by engine reset. */
@@ -1365,7 +1438,7 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	xehp_init_mcr(gt, wal);
 
 	/* Wa_1409757795:xehpsdv */
-	wa_write_or(wal, SCCGCTL94DC, CG3DDISURB);
+	wa_mcr_write_or(wal, SCCGCTL94DC, CG3DDISURB);
 
 	/* Wa_16011155590:xehpsdv */
 	if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0))
@@ -1445,8 +1518,8 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 			    CG3DDISCFEG_CLKGATE_DIS);
 
 		/* Wa_14011006942:dg2 */
-		wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE,
-			    DSS_ROUTER_CLKGATE_DIS);
+		wa_mcr_write_or(wal, GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE,
+				DSS_ROUTER_CLKGATE_DIS);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) {
@@ -1457,7 +1530,7 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 		wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS);
 
 		/* Wa_14011371254:dg2_g10 */
-		wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS);
+		wa_mcr_write_or(wal, XEHP_SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS);
 
 		/* Wa_14011431319:dg2_g10 */
 		wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS |
@@ -1493,21 +1566,21 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 			    GAMEDIA_CLKGATE_DIS);
 
 		/* Wa_14011028019:dg2_g10 */
-		wa_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS);
+		wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS);
 	}
 
 	/* Wa_14014830051:dg2 */
-	wa_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN);
+	wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN);
 
 	/*
 	 * The following are not actually "workarounds" but rather
 	 * recommended tuning settings documented in the bspec's
 	 * performance guide section.
 	 */
-	wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS);
+	wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS);
 
 	/* Wa_14015795083 */
-	wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
+	wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
 }
 
 static void
@@ -1516,7 +1589,27 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	pvc_init_mcr(gt, wal);
 
 	/* Wa_14015795083 */
-	wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
+	wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
+}
+
+static void
+xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	/* FIXME: Actual workarounds will be added in future patch(es) */
+
+	/*
+	 * Unlike older platforms, we no longer setup implicit steering here;
+	 * all MCR accesses are explicitly steered.
+	 */
+	debug_dump_steering(gt);
+}
+
+static void
+xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	/* FIXME: Actual workarounds will be added in future patch(es) */
+
+	debug_dump_steering(gt);
 }
 
 static void
@@ -1524,7 +1617,18 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = gt->i915;
 
-	if (IS_PONTEVECCHIO(i915))
+	if (gt->type == GT_MEDIA) {
+		if (MEDIA_VER(i915) >= 13)
+			xelpmp_gt_workarounds_init(gt, wal);
+		else
+			MISSING_CASE(MEDIA_VER(i915));
+
+		return;
+	}
+
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		xelpg_gt_workarounds_init(gt, wal);
+	else if (IS_PONTEVECCHIO(i915))
 		pvc_gt_workarounds_init(gt, wal);
 	else if (IS_DG2(i915))
 		dg2_gt_workarounds_init(gt, wal);
@@ -1628,14 +1732,25 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal)
 		u32 val, old = 0;
 
 		/* open-coded rmw due to steering */
-		old = wa->clr ? intel_gt_mcr_read_any_fw(gt, wa->reg) : 0;
+		if (wa->clr)
+			old = wa->is_mcr ?
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
+				intel_uncore_read_fw(uncore, wa->reg);
 		val = (old & ~wa->clr) | wa->set;
-		if (val != old || !wa->clr)
-			intel_uncore_write_fw(uncore, wa->reg, val);
+		if (val != old || !wa->clr) {
+			if (wa->is_mcr)
+				intel_gt_mcr_multicast_write_fw(gt, wa->mcr_reg, val);
+			else
+				intel_uncore_write_fw(uncore, wa->reg, val);
+		}
+
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) {
+			u32 val = wa->is_mcr ?
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
+				intel_uncore_read_fw(uncore, wa->reg);
 
-		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-			wa_verify(wa, intel_gt_mcr_read_any_fw(gt, wa->reg),
-				  wal->name, "application");
+			wa_verify(wa, val, wal->name, "application");
+		}
 	}
 
 	intel_uncore_forcewake_put__locked(uncore, fw);
@@ -1664,8 +1779,9 @@ static bool wa_list_verify(struct intel_gt *gt,
 	intel_uncore_forcewake_get__locked(uncore, fw);
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
-		ok &= wa_verify(wa,
-				intel_gt_mcr_read_any_fw(gt, wa->reg),
+		ok &= wa_verify(wa, wa->is_mcr ?
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
+				intel_uncore_read_fw(uncore, wa->reg),
 				wal->name, from);
 
 	intel_uncore_forcewake_put__locked(uncore, fw);
@@ -1712,11 +1828,35 @@ whitelist_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags)
 }
 
 static void
+whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 flags)
+{
+	struct i915_wa wa = {
+		.mcr_reg = reg,
+		.is_mcr = 1,
+	};
+
+	if (GEM_DEBUG_WARN_ON(wal->count >= RING_MAX_NONPRIV_SLOTS))
+		return;
+
+	if (GEM_DEBUG_WARN_ON(!is_nonpriv_flags_valid(flags)))
+		return;
+
+	wa.mcr_reg.reg |= flags;
+	_wa_add(wal, &wa);
+}
+
+static void
 whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg)
 {
 	whitelist_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW);
 }
 
+static void
+whitelist_mcr_reg(struct i915_wa_list *wal, i915_mcr_reg_t reg)
+{
+	whitelist_mcr_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW);
+}
+
 static void gen9_whitelist_build(struct i915_wa_list *w)
 {
 	/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
@@ -1742,7 +1882,7 @@ static void skl_whitelist_build(struct intel_engine_cs *engine)
 	gen9_whitelist_build(w);
 
 	/* WaDisableLSQCROPERFforOCL:skl */
-	whitelist_reg(w, GEN8_L3SQCREG4);
+	whitelist_mcr_reg(w, GEN8_L3SQCREG4);
 }
 
 static void bxt_whitelist_build(struct intel_engine_cs *engine)
@@ -1763,7 +1903,7 @@ static void kbl_whitelist_build(struct intel_engine_cs *engine)
 	gen9_whitelist_build(w);
 
 	/* WaDisableLSQCROPERFforOCL:kbl */
-	whitelist_reg(w, GEN8_L3SQCREG4);
+	whitelist_mcr_reg(w, GEN8_L3SQCREG4);
 }
 
 static void glk_whitelist_build(struct intel_engine_cs *engine)
@@ -1828,10 +1968,10 @@ static void icl_whitelist_build(struct intel_engine_cs *engine)
 	switch (engine->class) {
 	case RENDER_CLASS:
 		/* WaAllowUMDToModifyHalfSliceChicken7:icl */
-		whitelist_reg(w, GEN9_HALF_SLICE_CHICKEN7);
+		whitelist_mcr_reg(w, GEN9_HALF_SLICE_CHICKEN7);
 
 		/* WaAllowUMDToModifySamplerMode:icl */
-		whitelist_reg(w, GEN10_SAMPLER_MODE);
+		whitelist_mcr_reg(w, GEN10_SAMPLER_MODE);
 
 		/* WaEnableStateCacheRedirectToCS:icl */
 		whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1);
@@ -2107,24 +2247,21 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14013392000:dg2_g11 */
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE);
-
-		/* Wa_16011620976:dg2_g11 */
-		wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8);
+		wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) ||
 	    IS_DG2_G11(i915) || IS_DG2_G12(i915)) {
 		/* Wa_1509727124:dg2 */
-		wa_masked_en(wal, GEN10_SAMPLER_MODE,
-			     SC_DISABLE_POWER_OPTIMIZATION_EBB);
+		wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE,
+				 SC_DISABLE_POWER_OPTIMIZATION_EBB);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) ||
 	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14012419201:dg2 */
-		wa_masked_en(wal, GEN9_ROW_CHICKEN4,
-			     GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX);
+		wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4,
+				 GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
@@ -2133,13 +2270,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_22012826095:dg2
 		 * Wa_22013059131:dg2
 		 */
-		wa_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW,
-				 MAXREQS_PER_BANK,
-				 REG_FIELD_PREP(MAXREQS_PER_BANK, 2));
+		wa_mcr_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW,
+				     MAXREQS_PER_BANK,
+				     REG_FIELD_PREP(MAXREQS_PER_BANK, 2));
 
 		/* Wa_22013059131:dg2 */
-		wa_write_or(wal, LSC_CHICKEN_BIT_0,
-			    FORCE_1_SUB_MESSAGE_PER_FRAGMENT);
+		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0,
+				FORCE_1_SUB_MESSAGE_PER_FRAGMENT);
 	}
 
 	/* Wa_1308578152:dg2_g10 when first gslice is fused off */
@@ -2152,19 +2289,19 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) ||
 	    IS_DG2_G11(i915) || IS_DG2_G12(i915)) {
 		/* Wa_22013037850:dg2 */
-		wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW,
-			    DISABLE_128B_EVICTION_COMMAND_UDW);
+		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW,
+				DISABLE_128B_EVICTION_COMMAND_UDW);
 
 		/* Wa_22012856258:dg2 */
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
-			     GEN12_DISABLE_READ_SUPPRESSION);
+		wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2,
+				 GEN12_DISABLE_READ_SUPPRESSION);
 
 		/*
 		 * Wa_22010960976:dg2
 		 * Wa_14013347512:dg2
 		 */
-		wa_masked_dis(wal, GEN12_HDC_CHICKEN0,
-			      LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK);
+		wa_mcr_masked_dis(wal, XEHP_HDC_CHICKEN0,
+				  LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) {
@@ -2172,8 +2309,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1608949956:dg2_g10
 		 * Wa_14010198302:dg2_g10
 		 */
-		wa_masked_en(wal, GEN8_ROW_CHICKEN,
-			     MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE);
+		wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN,
+				 MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE);
 
 		/*
 		 * Wa_14010918519:dg2_g10
@@ -2181,31 +2318,31 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping,
 		 * so ignoring verification.
 		 */
-		wa_add(wal, LSC_CHICKEN_BIT_0_UDW, 0,
-		       FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE,
-		       0, false);
+		wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0,
+			   FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE,
+			   0, false);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) {
 		/* Wa_22010430635:dg2 */
-		wa_masked_en(wal,
-			     GEN9_ROW_CHICKEN4,
-			     GEN12_DISABLE_GRF_CLEAR);
+		wa_mcr_masked_en(wal,
+				 GEN9_ROW_CHICKEN4,
+				 GEN12_DISABLE_GRF_CLEAR);
 
 		/* Wa_14010648519:dg2 */
-		wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
+		wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
 	}
 
 	/* Wa_14013202645:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
 	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0))
-		wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY);
+		wa_mcr_write_or(wal, RT_CTRL, DIS_NULL_QUERY);
 
 	/* Wa_22012532006:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) ||
 	    IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0))
-		wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
-			     DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA);
+		wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7,
+				 DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA);
 
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) {
 		/* Wa_14010680813:dg2_g10 */
@@ -2216,17 +2353,16 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) ||
 	    IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14012362059:dg2 */
-		wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) ||
 	    IS_DG2_G10(i915)) {
 		/* Wa_22014600077:dg2 */
-		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
-		       _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH),
-		       0 /* Wa_14012342262 :write-only reg, so skip
-			    verification */,
-		       true);
+		wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0,
+			   _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH),
+			   0 /* Wa_14012342262 write-only reg, so skip verification */,
+			   true);
 	}
 
 	if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
@@ -2253,7 +2389,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
+		wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
 
 		/*
 		 * Wa_1407928979:tgl A*
@@ -2282,22 +2418,22 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	    IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/* Wa_1409804808:tgl,rkl,dg1[a0],adl-s,adl-p */
-		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
-			     GEN12_PUSH_CONST_DEREF_HOLD_DIS);
+		wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2,
+				 GEN12_PUSH_CONST_DEREF_HOLD_DIS);
 
 		/*
 		 * Wa_1409085225:tgl
 		 * Wa_14010229206:tgl,rkl,dg1[a0],adl-s,adl-p
 		 */
-		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
+		wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 	}
 
 	if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
-	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_P(i915)) {
 		/*
 		 * Wa_1607030317:tgl
 		 * Wa_1607186500:tgl
-		 * Wa_1607297627:tgl,rkl,dg1[a0]
+		 * Wa_1607297627:tgl,rkl,dg1[a0],adlp
 		 *
 		 * On TGL and RKL there are multiple entries for this WA in the
 		 * BSpec; some indicate this is an A0-only WA, others indicate
@@ -2313,9 +2449,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) ||
 	    IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) {
 		/* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */
-		wa_masked_en(wal,
-			     GEN10_SAMPLER_MODE,
-			     ENABLE_SMALLPL);
+		wa_mcr_masked_en(wal,
+				 GEN10_SAMPLER_MODE,
+				 ENABLE_SMALLPL);
 	}
 
 	if (GRAPHICS_VER(i915) == 11) {
@@ -2349,9 +2485,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1405733216:icl
 		 * Formerly known as WaDisableCleanEvicts
 		 */
-		wa_write_or(wal,
-			    GEN8_L3SQCREG4,
-			    GEN11_LQSC_CLEAN_EVICT_DISABLE);
+		wa_mcr_write_or(wal,
+				GEN8_L3SQCREG4,
+				GEN11_LQSC_CLEAN_EVICT_DISABLE);
 
 		/* Wa_1606682166:icl */
 		wa_write_or(wal,
@@ -2359,10 +2495,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN7_DISABLE_SAMPLER_PREFETCH);
 
 		/* Wa_1409178092:icl */
-		wa_write_clr_set(wal,
-				 GEN11_SCRATCH2,
-				 GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE,
-				 0);
+		wa_mcr_write_clr_set(wal,
+				     GEN11_SCRATCH2,
+				     GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE,
+				     0);
 
 		/* WaEnable32PlaneMode:icl */
 		wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS,
@@ -2389,12 +2525,64 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
-	if (IS_GRAPHICS_VER(i915, 9, 12)) {
-		/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl,tgl */
+	/*
+	 * Intel platforms that support fine-grained preemption (i.e., gen9 and
+	 * beyond) allow the kernel-mode driver to choose between two different
+	 * options for controlling preemption granularity and behavior.
+	 *
+	 * Option 1 (hardware default):
+	 *   Preemption settings are controlled in a global manner via
+	 *   kernel-only register CS_DEBUG_MODE1 (0x20EC).  Any granularity
+	 *   and settings chosen by the kernel-mode driver will apply to all
+	 *   userspace clients.
+	 *
+	 * Option 2:
+	 *   Preemption settings are controlled on a per-context basis via
+	 *   register CS_CHICKEN1 (0x2580).  CS_CHICKEN1 is saved/restored on
+	 *   context switch and is writable by userspace (e.g., via
+	 *   MI_LOAD_REGISTER_IMMEDIATE instructions placed in a batch buffer)
+	 *   which allows different userspace drivers/clients to select
+	 *   different settings, or to change those settings on the fly in
+	 *   response to runtime needs.  This option was known by name
+	 *   "FtrPerCtxtPreemptionGranularityControl" at one time, although
+	 *   that name is somewhat misleading as other non-granularity
+	 *   preemption settings are also impacted by this decision.
+	 *
+	 * On Linux, our policy has always been to let userspace drivers
+	 * control preemption granularity/settings (Option 2).  This was
+	 * originally mandatory on gen9 to prevent ABI breakage (old gen9
+	 * userspace developed before object-level preemption was enabled would
+	 * not behave well if i915 were to go with Option 1 and enable that
+	 * preemption in a global manner).  On gen9 each context would have
+	 * object-level preemption disabled by default (see
+	 * WaDisable3DMidCmdPreemption in gen9_ctx_workarounds_init), but
+	 * userspace drivers could opt-in to object-level preemption as they
+	 * saw fit.  For post-gen9 platforms, we continue to utilize Option 2;
+	 * even though it is no longer necessary for ABI compatibility when
+	 * enabling a new platform, it does ensure that userspace will be able
+	 * to implement any workarounds that show up requiring temporary
+	 * adjustments to preemption behavior at runtime.
+	 *
+	 * Notes/Workarounds:
+	 *  - Wa_14015141709:  On DG2 and early steppings of MTL,
+	 *      CS_CHICKEN1[0] does not disable object-level preemption as
+	 *      it is supposed to (nor does CS_DEBUG_MODE1[0] if we had been
+	 *      using Option 1).  Effectively this means userspace is unable
+	 *      to disable object-level preemption on these platforms/steppings
+	 *      despite the setting here.
+	 *
+	 *  - Wa_16013994831:  May require that userspace program
+	 *      CS_CHICKEN1[10] when certain runtime conditions are true.
+	 *      Userspace requires Option 2 to be in effect for their update of
+	 *      CS_CHICKEN1[10] to be effective.
+	 *
+	 * Other workarounds may appear in the future that will also require
+	 * Option 2 behavior to allow proper userspace implementation.
+	 */
+	if (GRAPHICS_VER(i915) >= 9)
 		wa_masked_en(wal,
 			     GEN7_FF_SLICE_CS_CHICKEN1,
 			     GEN9_FFSC_PERCTX_PREEMPT_CTRL);
-	}
 
 	if (IS_SKYLAKE(i915) ||
 	    IS_KABYLAKE(i915) ||
@@ -2420,36 +2608,36 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE);
 
 		/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
-		wa_write_or(wal,
-			    BDW_SCRATCH1,
-			    GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
+		wa_mcr_write_or(wal,
+				BDW_SCRATCH1,
+				GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
 
 		/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
 		if (IS_GEN9_LP(i915))
-			wa_write_clr_set(wal,
-					 GEN8_L3SQCREG1,
-					 L3_PRIO_CREDITS_MASK,
-					 L3_GENERAL_PRIO_CREDITS(62) |
-					 L3_HIGH_PRIO_CREDITS(2));
+			wa_mcr_write_clr_set(wal,
+					     GEN8_L3SQCREG1,
+					     L3_PRIO_CREDITS_MASK,
+					     L3_GENERAL_PRIO_CREDITS(62) |
+					     L3_HIGH_PRIO_CREDITS(2));
 
 		/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
-		wa_write_or(wal,
-			    GEN8_L3SQCREG4,
-			    GEN8_LQSC_FLUSH_COHERENT_LINES);
+		wa_mcr_write_or(wal,
+				GEN8_L3SQCREG4,
+				GEN8_LQSC_FLUSH_COHERENT_LINES);
 
 		/* Disable atomics in L3 to prevent unrecoverable hangs */
 		wa_write_clr_set(wal, GEN9_SCRATCH_LNCF1,
 				 GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE, 0);
-		wa_write_clr_set(wal, GEN8_L3SQCREG4,
-				 GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0);
-		wa_write_clr_set(wal, GEN9_SCRATCH1,
-				 EVICTION_PERF_FIX_ENABLE, 0);
+		wa_mcr_write_clr_set(wal, GEN8_L3SQCREG4,
+				     GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0);
+		wa_mcr_write_clr_set(wal, GEN9_SCRATCH1,
+				     EVICTION_PERF_FIX_ENABLE, 0);
 	}
 
 	if (IS_HASWELL(i915)) {
 		/* WaSampleCChickenBitEnable:hsw */
 		wa_masked_en(wal,
-			     HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
+			     HSW_HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
 
 		wa_masked_dis(wal,
 			      CACHE_MODE_0_GEN7,
@@ -2657,7 +2845,7 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	if (IS_PVC_CT_STEP(engine->i915, STEP_A0, STEP_C0)) {
 		/* Wa_14014999345:pvc */
-		wa_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC);
+		wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC);
 	}
 }
 
@@ -2683,8 +2871,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915,
 	}
 
 	if (IS_DG2(i915)) {
-		wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
-		wa_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
+		wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
+		wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
 
 		/*
 		 * This is also listed as Wa_22012654132 for certain DG2
@@ -2695,10 +2883,10 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915,
 		 * back for verification on DG2 (due to Wa_14012342262), so
 		 * we need to explicitly skip the readback.
 		 */
-		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
-		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
-		       0 /* write-only, so skip validation */,
-		       true);
+		wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0,
+			   _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
+			   0 /* write-only, so skip validation */,
+			   true);
 	}
 
 	/*
@@ -2707,8 +2895,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915,
 	 * platforms.
 	 */
 	if (INTEL_INFO(i915)->tuning_thread_rr_after_dep)
-		wa_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE,
-				    THREAD_EX_ARB_MODE_RR_AFTER_DEP);
+		wa_mcr_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE,
+					THREAD_EX_ARB_MODE_RR_AFTER_DEP);
 }
 
 /*
@@ -2734,30 +2922,30 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 
 	if (IS_XEHPSDV(i915)) {
 		/* Wa_1409954639 */
-		wa_masked_en(wal,
-			     GEN8_ROW_CHICKEN,
-			     SYSTOLIC_DOP_CLOCK_GATING_DIS);
+		wa_mcr_masked_en(wal,
+				 GEN8_ROW_CHICKEN,
+				 SYSTOLIC_DOP_CLOCK_GATING_DIS);
 
 		/* Wa_1607196519 */
-		wa_masked_en(wal,
-			     GEN9_ROW_CHICKEN4,
-			     GEN12_DISABLE_GRF_CLEAR);
+		wa_mcr_masked_en(wal,
+				 GEN9_ROW_CHICKEN4,
+				 GEN12_DISABLE_GRF_CLEAR);
 
 		/* Wa_14010670810:xehpsdv */
-		wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
+		wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
 
 		/* Wa_14010449647:xehpsdv */
-		wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1,
-			     GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+		wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1,
+				 GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
 
 		/* Wa_18011725039:xehpsdv */
 		if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) {
-			wa_masked_dis(wal, MLTICTXCTL, TDONRENDER);
-			wa_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH);
+			wa_mcr_masked_dis(wal, MLTICTXCTL, TDONRENDER);
+			wa_mcr_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH);
 		}
 
 		/* Wa_14012362059:xehpsdv */
-		wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB);
 
 		/* Wa_14014368820:xehpsdv */
 		wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS |
@@ -2766,19 +2954,30 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 
 	if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) {
 		/* Wa_14015227452:dg2,pvc */
-		wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE);
+		wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE);
 
 		/* Wa_22014226127:dg2,pvc */
-		wa_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE);
+		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE);
 
 		/* Wa_16015675438:dg2,pvc */
 		wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE);
 
 		/* Wa_18018781329:dg2,pvc */
-		wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+		wa_mcr_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB);
+	}
+
+	if (IS_DG2(i915)) {
+		/*
+		 * Wa_16011620976:dg2_g11
+		 * Wa_22015475538:dg2
+		 */
+		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8);
+
+		/* Wa_18017747507:dg2 */
+		wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
index 8a4b6de4e754..7c8b01d00043 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
@@ -11,11 +11,16 @@
 #include "i915_reg_defs.h"
 
 struct i915_wa {
-	i915_reg_t	reg;
+	union {
+		i915_reg_t	reg;
+		i915_mcr_reg_t	mcr_reg;
+	};
 	u32		clr;
 	u32		set;
 	u32		read;
-	bool		masked_reg;
+
+	u32		masked_reg:1;
+	u32		is_mcr:1;
 };
 
 struct i915_wa_list {
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 1b75f478d1b8..881b64f3e7b9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -39,6 +39,16 @@ static int perf_end(struct intel_gt *gt)
 	return igt_flush_test(gt->i915);
 }
 
+static i915_reg_t timestamp_reg(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *i915 = engine->i915;
+
+	if (GRAPHICS_VER(i915) == 5 || IS_G4X(i915))
+		return RING_TIMESTAMP_UDW(engine->mmio_base);
+	else
+		return RING_TIMESTAMP(engine->mmio_base);
+}
+
 static int write_timestamp(struct i915_request *rq, int slot)
 {
 	struct intel_timeline *tl =
@@ -55,7 +65,7 @@ static int write_timestamp(struct i915_request *rq, int slot)
 	if (GRAPHICS_VER(rq->engine->i915) >= 8)
 		cmd++;
 	*cs++ = cmd;
-	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base));
+	*cs++ = i915_mmio_reg_offset(timestamp_reg(rq->engine));
 	*cs++ = tl->hwsp_offset + slot * sizeof(u32);
 	*cs++ = 0;
 
@@ -125,7 +135,7 @@ static int perf_mi_bb_start(void *arg)
 	enum intel_engine_id id;
 	int err = 0;
 
-	if (GRAPHICS_VER(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
 	perf_begin(gt);
@@ -135,6 +145,9 @@ static int perf_mi_bb_start(void *arg)
 		u32 cycles[COUNT];
 		int i;
 
+		if (GRAPHICS_VER(engine->i915) < 7 && engine->id != RCS0)
+			continue;
+
 		intel_engine_pm_get(engine);
 
 		batch = create_empty_batch(ce);
@@ -249,7 +262,7 @@ static int perf_mi_noop(void *arg)
 	enum intel_engine_id id;
 	int err = 0;
 
-	if (GRAPHICS_VER(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
 	perf_begin(gt);
@@ -259,6 +272,9 @@ static int perf_mi_noop(void *arg)
 		u32 cycles[COUNT];
 		int i;
 
+		if (GRAPHICS_VER(engine->i915) < 7 && engine->id != RCS0)
+			continue;
+
 		intel_engine_pm_get(engine);
 
 		base = create_empty_batch(ce);
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 1e08b2473b99..2c7c053a8808 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -85,8 +85,6 @@ static int wait_for_reset(struct intel_engine_cs *engine,
 			break;
 	} while (time_before(jiffies, timeout));
 
-	flush_scheduled_work();
-
 	if (rq->fence.error != -EIO) {
 		pr_err("%s: hanging request %llx:%lld not reset\n",
 		       engine->name,
@@ -3475,12 +3473,14 @@ static int random_priority(struct rnd_state *rnd)
 
 struct preempt_smoke {
 	struct intel_gt *gt;
+	struct kthread_work work;
 	struct i915_gem_context **contexts;
 	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object *batch;
 	unsigned int ncontext;
 	struct rnd_state prng;
 	unsigned long count;
+	int result;
 };
 
 static struct i915_gem_context *smoke_context(struct preempt_smoke *smoke)
@@ -3540,34 +3540,31 @@ unpin:
 	return err;
 }
 
-static int smoke_crescendo_thread(void *arg)
+static void smoke_crescendo_work(struct kthread_work *work)
 {
-	struct preempt_smoke *smoke = arg;
+	struct preempt_smoke *smoke = container_of(work, typeof(*smoke), work);
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 
 	count = 0;
 	do {
 		struct i915_gem_context *ctx = smoke_context(smoke);
-		int err;
 
-		err = smoke_submit(smoke,
-				   ctx, count % I915_PRIORITY_MAX,
-				   smoke->batch);
-		if (err)
-			return err;
+		smoke->result = smoke_submit(smoke, ctx,
+					     count % I915_PRIORITY_MAX,
+					     smoke->batch);
 
 		count++;
-	} while (count < smoke->ncontext && !__igt_timeout(end_time, NULL));
+	} while (!smoke->result && count < smoke->ncontext &&
+		 !__igt_timeout(end_time, NULL));
 
 	smoke->count = count;
-	return 0;
 }
 
 static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 #define BATCH BIT(0)
 {
-	struct task_struct *tsk[I915_NUM_ENGINES] = {};
+	struct kthread_worker *worker[I915_NUM_ENGINES] = {};
 	struct preempt_smoke *arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -3578,6 +3575,8 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	if (!arg)
 		return -ENOMEM;
 
+	memset(arg, 0, I915_NUM_ENGINES * sizeof(*arg));
+
 	for_each_engine(engine, smoke->gt, id) {
 		arg[id] = *smoke;
 		arg[id].engine = engine;
@@ -3585,31 +3584,28 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 			arg[id].batch = NULL;
 		arg[id].count = 0;
 
-		tsk[id] = kthread_run(smoke_crescendo_thread, arg,
-				      "igt/smoke:%d", id);
-		if (IS_ERR(tsk[id])) {
-			err = PTR_ERR(tsk[id]);
+		worker[id] = kthread_create_worker(0, "igt/smoke:%d", id);
+		if (IS_ERR(worker[id])) {
+			err = PTR_ERR(worker[id]);
 			break;
 		}
-		get_task_struct(tsk[id]);
-	}
 
-	yield(); /* start all threads before we kthread_stop() */
+		kthread_init_work(&arg[id].work, smoke_crescendo_work);
+		kthread_queue_work(worker[id], &arg[id].work);
+	}
 
 	count = 0;
 	for_each_engine(engine, smoke->gt, id) {
-		int status;
-
-		if (IS_ERR_OR_NULL(tsk[id]))
+		if (IS_ERR_OR_NULL(worker[id]))
 			continue;
 
-		status = kthread_stop(tsk[id]);
-		if (status && !err)
-			err = status;
+		kthread_flush_work(&arg[id].work);
+		if (arg[id].result && !err)
+			err = arg[id].result;
 
 		count += arg[id].count;
 
-		put_task_struct(tsk[id]);
+		kthread_destroy_worker(worker[id]);
 	}
 
 	pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index be94f863bdef..b46425aeb2f0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -36,6 +36,19 @@ static int cmp_u32(const void *A, const void *B)
 		return 0;
 }
 
+static u32 read_timestamp(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *i915 = engine->i915;
+
+	/* On i965 the first read tends to give a stale value */
+	ENGINE_READ_FW(engine, RING_TIMESTAMP);
+
+	if (GRAPHICS_VER(i915) == 5 || IS_G4X(i915))
+		return ENGINE_READ_FW(engine, RING_TIMESTAMP_UDW);
+	else
+		return ENGINE_READ_FW(engine, RING_TIMESTAMP);
+}
+
 static void measure_clocks(struct intel_engine_cs *engine,
 			   u32 *out_cycles, ktime_t *out_dt)
 {
@@ -45,13 +58,13 @@ static void measure_clocks(struct intel_engine_cs *engine,
 
 	for (i = 0; i < 5; i++) {
 		local_irq_disable();
-		cycles[i] = -ENGINE_READ_FW(engine, RING_TIMESTAMP);
+		cycles[i] = -read_timestamp(engine);
 		dt[i] = ktime_get();
 
 		udelay(1000);
 
 		dt[i] = ktime_sub(ktime_get(), dt[i]);
-		cycles[i] += ENGINE_READ_FW(engine, RING_TIMESTAMP);
+		cycles[i] += read_timestamp(engine);
 		local_irq_enable();
 	}
 
@@ -78,25 +91,6 @@ static int live_gt_clocks(void *arg)
 	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
-	if (GRAPHICS_VER(gt->i915) == 5)
-		/*
-		 * XXX CS_TIMESTAMP low dword is dysfunctional?
-		 *
-		 * Ville's experiments indicate the high dword still works,
-		 * but at a correspondingly reduced frequency.
-		 */
-		return 0;
-
-	if (GRAPHICS_VER(gt->i915) == 4)
-		/*
-		 * XXX CS_TIMESTAMP appears gibberish
-		 *
-		 * Ville's experiments indicate that it mostly appears 'stuck'
-		 * in that we see the register report the same cycle count
-		 * for a couple of reads.
-		 */
-		return 0;
-
 	intel_gt_pm_get(gt);
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 7f3bb1d34dfb..71263058a7b0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -866,10 +866,13 @@ static int igt_reset_active_engine(void *arg)
 }
 
 struct active_engine {
-	struct task_struct *task;
+	struct kthread_worker *worker;
+	struct kthread_work work;
 	struct intel_engine_cs *engine;
 	unsigned long resets;
 	unsigned int flags;
+	bool stop;
+	int result;
 };
 
 #define TEST_ACTIVE	BIT(0)
@@ -900,10 +903,10 @@ static int active_request_put(struct i915_request *rq)
 	return err;
 }
 
-static int active_engine(void *data)
+static void active_engine(struct kthread_work *work)
 {
 	I915_RND_STATE(prng);
-	struct active_engine *arg = data;
+	struct active_engine *arg = container_of(work, typeof(*arg), work);
 	struct intel_engine_cs *engine = arg->engine;
 	struct i915_request *rq[8] = {};
 	struct intel_context *ce[ARRAY_SIZE(rq)];
@@ -913,16 +916,17 @@ static int active_engine(void *data)
 	for (count = 0; count < ARRAY_SIZE(ce); count++) {
 		ce[count] = intel_context_create(engine);
 		if (IS_ERR(ce[count])) {
-			err = PTR_ERR(ce[count]);
-			pr_err("[%s] Create context #%ld failed: %d!\n", engine->name, count, err);
+			arg->result = PTR_ERR(ce[count]);
+			pr_err("[%s] Create context #%ld failed: %d!\n",
+			       engine->name, count, arg->result);
 			while (--count)
 				intel_context_put(ce[count]);
-			return err;
+			return;
 		}
 	}
 
 	count = 0;
-	while (!kthread_should_stop()) {
+	while (!READ_ONCE(arg->stop)) {
 		unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1);
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
@@ -967,7 +971,7 @@ static int active_engine(void *data)
 		intel_context_put(ce[count]);
 	}
 
-	return err;
+	arg->result = err;
 }
 
 static int __igt_reset_engines(struct intel_gt *gt,
@@ -1022,7 +1026,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		memset(threads, 0, sizeof(*threads) * I915_NUM_ENGINES);
 		for_each_engine(other, gt, tmp) {
-			struct task_struct *tsk;
+			struct kthread_worker *worker;
 
 			threads[tmp].resets =
 				i915_reset_engine_count(global, other);
@@ -1036,19 +1040,21 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			threads[tmp].engine = other;
 			threads[tmp].flags = flags;
 
-			tsk = kthread_run(active_engine, &threads[tmp],
-					  "igt/%s", other->name);
-			if (IS_ERR(tsk)) {
-				err = PTR_ERR(tsk);
-				pr_err("[%s] Thread spawn failed: %d!\n", engine->name, err);
+			worker = kthread_create_worker(0, "igt/%s",
+						       other->name);
+			if (IS_ERR(worker)) {
+				err = PTR_ERR(worker);
+				pr_err("[%s] Worker create failed: %d!\n",
+				       engine->name, err);
 				goto unwind;
 			}
 
-			threads[tmp].task = tsk;
-			get_task_struct(tsk);
-		}
+			threads[tmp].worker = worker;
 
-		yield(); /* start all threads before we begin */
+			kthread_init_work(&threads[tmp].work, active_engine);
+			kthread_queue_work(threads[tmp].worker,
+					   &threads[tmp].work);
+		}
 
 		st_engine_heartbeat_disable_no_pm(engine);
 		GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id,
@@ -1197,17 +1203,20 @@ unwind:
 		for_each_engine(other, gt, tmp) {
 			int ret;
 
-			if (!threads[tmp].task)
+			if (!threads[tmp].worker)
 				continue;
 
-			ret = kthread_stop(threads[tmp].task);
+			WRITE_ONCE(threads[tmp].stop, true);
+			kthread_flush_work(&threads[tmp].work);
+			ret = READ_ONCE(threads[tmp].result);
 			if (ret) {
 				pr_err("kthread for other engine %s failed, err=%d\n",
 				       other->name, ret);
 				if (!err)
 					err = ret;
 			}
-			put_task_struct(threads[tmp].task);
+
+			kthread_destroy_worker(threads[tmp].worker);
 
 			/* GuC based resets are not logged per engine */
 			if (!using_guc) {
diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c
index 2b0c87999949..0dc5309c90a4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_migrate.c
+++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c
@@ -6,6 +6,7 @@
 #include <linux/sort.h>
 
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_lmem.h"
 
 #include "selftests/i915_random.h"
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index cfb4708dd62e..99a372486fb7 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -1107,21 +1107,27 @@ static u64 __measure_power(int duration_ms)
 	return div64_u64(1000 * 1000 * dE, dt);
 }
 
-static u64 measure_power_at(struct intel_rps *rps, int *freq)
+static u64 measure_power(struct intel_rps *rps, int *freq)
 {
 	u64 x[5];
 	int i;
 
-	*freq = rps_set_check(rps, *freq);
 	for (i = 0; i < 5; i++)
 		x[i] = __measure_power(5);
-	*freq = (*freq + read_cagf(rps)) / 2;
+
+	*freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2;
 
 	/* A simple triangle filter for better result stability */
 	sort(x, 5, sizeof(*x), cmp_u64, NULL);
 	return div_u64(x[1] + 2 * x[2] + x[3], 4);
 }
 
+static u64 measure_power_at(struct intel_rps *rps, int *freq)
+{
+	*freq = rps_set_check(rps, *freq);
+	return measure_power(rps, freq);
+}
+
 int live_rps_power(void *arg)
 {
 	struct intel_gt *gt = arg;
diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c
index f8a1d27df272..82ec95a299f6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_slpc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c
@@ -11,7 +11,8 @@
 enum test_type {
 	VARY_MIN,
 	VARY_MAX,
-	MAX_GRANTED
+	MAX_GRANTED,
+	SLPC_POWER,
 };
 
 static int slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 freq)
@@ -41,6 +42,39 @@ static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq)
 	return ret;
 }
 
+static int slpc_set_freq(struct intel_gt *gt, u32 freq)
+{
+	int err;
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+
+	err = slpc_set_max_freq(slpc, freq);
+	if (err) {
+		pr_err("Unable to update max freq");
+		return err;
+	}
+
+	err = slpc_set_min_freq(slpc, freq);
+	if (err) {
+		pr_err("Unable to update min freq");
+		return err;
+	}
+
+	return err;
+}
+
+static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power)
+{
+	int err = 0;
+
+	err = slpc_set_freq(gt, *freq);
+	if (err)
+		return err;
+	*freq = intel_rps_read_actual_frequency(&gt->rps);
+	*power = measure_power(&gt->rps, freq);
+
+	return err;
+}
+
 static int vary_max_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 			 u32 *max_act_freq)
 {
@@ -113,6 +147,58 @@ static int vary_min_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 	return err;
 }
 
+static int slpc_power(struct intel_gt *gt, struct intel_engine_cs *engine)
+{
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+	struct {
+		u64 power;
+		int freq;
+	} min, max;
+	int err = 0;
+
+	/*
+	 * Our fundamental assumption is that running at lower frequency
+	 * actually saves power. Let's see if our RAPL measurement supports
+	 * that theory.
+	 */
+	if (!librapl_supported(gt->i915))
+		return 0;
+
+	min.freq = slpc->min_freq;
+	err = measure_power_at_freq(gt, &min.freq, &min.power);
+
+	if (err)
+		return err;
+
+	max.freq = slpc->rp0_freq;
+	err = measure_power_at_freq(gt, &max.freq, &max.power);
+
+	if (err)
+		return err;
+
+	pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n",
+		engine->name,
+		min.power, min.freq,
+		max.power, max.freq);
+
+	if (10 * min.freq >= 9 * max.freq) {
+		pr_notice("Could not control frequency, ran at [%uMHz, %uMhz]\n",
+			  min.freq, max.freq);
+	}
+
+	if (11 * min.power > 10 * max.power) {
+		pr_err("%s: did not conserve power when setting lower frequency!\n",
+		       engine->name);
+		err = -EINVAL;
+	}
+
+	/* Restore min/max frequencies */
+	slpc_set_max_freq(slpc, slpc->rp0_freq);
+	slpc_set_min_freq(slpc, slpc->min_freq);
+
+	return err;
+}
+
 static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, u32 *max_act_freq)
 {
 	struct intel_gt *gt = rps_to_gt(rps);
@@ -153,6 +239,11 @@ static int run_test(struct intel_gt *gt, int test_type)
 	if (!intel_uc_uses_guc_slpc(&gt->uc))
 		return 0;
 
+	if (slpc->min_freq == slpc->rp0_freq) {
+		pr_err("Min/Max are fused to the same value\n");
+		return -EINVAL;
+	}
+
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
@@ -167,17 +258,14 @@ static int run_test(struct intel_gt *gt, int test_type)
 	}
 
 	/*
-	 * FIXME: With efficient frequency enabled, GuC can request
-	 * frequencies higher than the SLPC max. While this is fixed
-	 * in GuC, we level set these tests with RPn as min.
+	 * Set min frequency to RPn so that we can test the whole
+	 * range of RPn-RP0. This also turns off efficient freq
+	 * usage and makes results more predictable.
 	 */
 	err = slpc_set_min_freq(slpc, slpc->min_freq);
-	if (err)
+	if (err) {
+		pr_err("Unable to update min freq!");
 		return err;
-
-	if (slpc->min_freq == slpc->rp0_freq) {
-		pr_err("Min/Max are fused to the same value\n");
-		return -EINVAL;
 	}
 
 	intel_gt_pm_wait_for_idle(gt);
@@ -233,17 +321,23 @@ static int run_test(struct intel_gt *gt, int test_type)
 
 			err = max_granted_freq(slpc, rps, &max_act_freq);
 			break;
+
+		case SLPC_POWER:
+			err = slpc_power(gt, engine);
+			break;
 		}
 
-		pr_info("Max actual frequency for %s was %d\n",
-			engine->name, max_act_freq);
+		if (test_type != SLPC_POWER) {
+			pr_info("Max actual frequency for %s was %d\n",
+				engine->name, max_act_freq);
 
-		/* Actual frequency should rise above min */
-		if (max_act_freq <= slpc_min_freq) {
-			pr_err("Actual freq did not rise above min\n");
-			pr_err("Perf Limit Reasons: 0x%x\n",
-			       intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS));
-			err = -EINVAL;
+			/* Actual frequency should rise above min */
+			if (max_act_freq <= slpc->min_freq) {
+				pr_err("Actual freq did not rise above min\n");
+				pr_err("Perf Limit Reasons: 0x%x\n",
+				       intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS));
+				err = -EINVAL;
+			}
 		}
 
 		igt_spinner_end(&spin);
@@ -270,26 +364,66 @@ static int run_test(struct intel_gt *gt, int test_type)
 static int live_slpc_vary_min(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, VARY_MIN);
+		if (ret)
+			return ret;
+	}
 
-	return run_test(gt, VARY_MIN);
+	return ret;
 }
 
 static int live_slpc_vary_max(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, VARY_MAX);
+		if (ret)
+			return ret;
+	}
 
-	return run_test(gt, VARY_MAX);
+	return ret;
 }
 
 /* check if pcode can grant RP0 */
 static int live_slpc_max_granted(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
 
-	return run_test(gt, MAX_GRANTED);
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, MAX_GRANTED);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int live_slpc_power(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, SLPC_POWER);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
 }
 
 int intel_slpc_live_selftests(struct drm_i915_private *i915)
@@ -298,10 +432,16 @@ int intel_slpc_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_slpc_vary_max),
 		SUBTEST(live_slpc_vary_min),
 		SUBTEST(live_slpc_max_granted),
+		SUBTEST(live_slpc_power),
 	};
 
-	if (intel_gt_is_wedged(to_gt(i915)))
-		return 0;
+	struct intel_gt *gt;
+	unsigned int i;
+
+	for_each_gt(gt, i915, i) {
+		if (intel_gt_is_wedged(gt))
+			return 0;
+	}
 
 	return i915_live_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 67a9aab801dd..21b1edc052f8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -991,7 +991,7 @@ static bool pardon_reg(struct drm_i915_private *i915, i915_reg_t reg)
 	/* Alas, we must pardon some whitelists. Mistakes already made */
 	static const struct regmask pardon[] = {
 		{ GEN9_CTX_PREEMPT_REG, 9 },
-		{ GEN8_L3SQCREG4, 9 },
+		{ _MMIO(0xb118), 9 }, /* GEN8_L3SQCREG4 */
 	};
 
 	return find_reg(i915, reg, pardon, ARRAY_SIZE(pardon));
diff --git a/drivers/gpu/drm/i915/gt/sysfs_engines.c b/drivers/gpu/drm/i915/gt/sysfs_engines.c
index 967031056202..f2d9858d827c 100644
--- a/drivers/gpu/drm/i915/gt/sysfs_engines.c
+++ b/drivers/gpu/drm/i915/gt/sysfs_engines.c
@@ -144,7 +144,7 @@ max_spin_store(struct kobject *kobj, struct kobj_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct intel_engine_cs *engine = kobj_to_engine(kobj);
-	unsigned long long duration;
+	unsigned long long duration, clamped;
 	int err;
 
 	/*
@@ -168,7 +168,8 @@ max_spin_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (err)
 		return err;
 
-	if (duration > jiffies_to_nsecs(2))
+	clamped = intel_clamp_max_busywait_duration_ns(engine, duration);
+	if (duration != clamped)
 		return -EINVAL;
 
 	WRITE_ONCE(engine->props.max_busywait_duration_ns, duration);
@@ -203,7 +204,7 @@ timeslice_store(struct kobject *kobj, struct kobj_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct intel_engine_cs *engine = kobj_to_engine(kobj);
-	unsigned long long duration;
+	unsigned long long duration, clamped;
 	int err;
 
 	/*
@@ -218,7 +219,8 @@ timeslice_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (err)
 		return err;
 
-	if (duration > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+	clamped = intel_clamp_timeslice_duration_ms(engine, duration);
+	if (duration != clamped)
 		return -EINVAL;
 
 	WRITE_ONCE(engine->props.timeslice_duration_ms, duration);
@@ -256,7 +258,7 @@ stop_store(struct kobject *kobj, struct kobj_attribute *attr,
 	   const char *buf, size_t count)
 {
 	struct intel_engine_cs *engine = kobj_to_engine(kobj);
-	unsigned long long duration;
+	unsigned long long duration, clamped;
 	int err;
 
 	/*
@@ -272,7 +274,8 @@ stop_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (err)
 		return err;
 
-	if (duration > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+	clamped = intel_clamp_stop_timeout_ms(engine, duration);
+	if (duration != clamped)
 		return -EINVAL;
 
 	WRITE_ONCE(engine->props.stop_timeout_ms, duration);
@@ -306,7 +309,7 @@ preempt_timeout_store(struct kobject *kobj, struct kobj_attribute *attr,
 		      const char *buf, size_t count)
 {
 	struct intel_engine_cs *engine = kobj_to_engine(kobj);
-	unsigned long long timeout;
+	unsigned long long timeout, clamped;
 	int err;
 
 	/*
@@ -322,7 +325,8 @@ preempt_timeout_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (err)
 		return err;
 
-	if (timeout > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+	clamped = intel_clamp_preempt_timeout_ms(engine, timeout);
+	if (timeout != clamped)
 		return -EINVAL;
 
 	WRITE_ONCE(engine->props.preempt_timeout_ms, timeout);
@@ -362,7 +366,7 @@ heartbeat_store(struct kobject *kobj, struct kobj_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct intel_engine_cs *engine = kobj_to_engine(kobj);
-	unsigned long long delay;
+	unsigned long long delay, clamped;
 	int err;
 
 	/*
@@ -379,7 +383,8 @@ heartbeat_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (err)
 		return err;
 
-	if (delay >= jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+	clamped = intel_clamp_heartbeat_interval_ms(engine, delay);
+	if (delay != clamped)
 		return -EINVAL;
 
 	err = intel_engine_set_heartbeat(engine, delay);
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
index 29ef8afc8c2e..f359bef046e0 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
@@ -117,6 +117,7 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_ENTER_S_STATE = 0x501,
 	INTEL_GUC_ACTION_EXIT_S_STATE = 0x502,
 	INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506,
+	INTEL_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509,
 	INTEL_GUC_ACTION_SCHED_CONTEXT = 0x1000,
 	INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001,
 	INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002,
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
index 4c840a2639dc..811add10c30d 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
@@ -128,6 +128,15 @@ enum slpc_media_ratio_mode {
 	SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO = 2,
 };
 
+enum slpc_gucrc_mode {
+	SLPC_GUCRC_MODE_HW = 0,
+	SLPC_GUCRC_MODE_GUCRC_NO_RC6 = 1,
+	SLPC_GUCRC_MODE_GUCRC_STATIC_TIMEOUT = 2,
+	SLPC_GUCRC_MODE_GUCRC_DYNAMIC_HYSTERESIS = 3,
+
+	SLPC_GUCRC_MODE_MAX,
+};
+
 enum slpc_event_id {
 	SLPC_EVENT_RESET = 0,
 	SLPC_EVENT_SHUTDOWN = 1,
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
index 4a59478c3b5c..58012edd4eb0 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
@@ -82,9 +82,16 @@
 #define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_LEN		1u
 
 /*
+ * Global scheduling policy update keys.
+ */
+enum {
+	GUC_SCHEDULING_POLICIES_KLV_ID_RENDER_COMPUTE_YIELD	= 0x1001,
+};
+
+/*
  * Per context scheduling policy update keys.
  */
-enum  {
+enum {
 	GUC_CONTEXT_POLICIES_KLV_ID_EXECUTION_QUANTUM			= 0x2001,
 	GUC_CONTEXT_POLICIES_KLV_ID_PREEMPTION_TIMEOUT			= 0x2002,
 	GUC_CONTEXT_POLICIES_KLV_ID_SCHEDULING_PRIORITY			= 0x2003,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index bac06e3d6f2c..27b09ba1d295 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -441,6 +441,7 @@ err_log:
 err_fw:
 	intel_uc_fw_fini(&guc->fw);
 out:
+	intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_INIT_FAIL);
 	i915_probe_error(gt->i915, "failed with %d\n", ret);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 804133df1ac9..357873ef692b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -113,6 +113,10 @@ struct intel_guc {
 		 */
 		struct list_head guc_id_list;
 		/**
+		 * @guc_ids_in_use: Number single-lrc guc_ids in use
+		 */
+		unsigned int guc_ids_in_use;
+		/**
 		 * @destroyed_contexts: list of contexts waiting to be destroyed
 		 * (deregistered with the GuC)
 		 */
@@ -132,6 +136,16 @@ struct intel_guc {
 		 * @reset_fail_mask: mask of engines that failed to reset
 		 */
 		intel_engine_mask_t reset_fail_mask;
+		/**
+		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
+		 * contexts
+		 */
+		unsigned int sched_disable_delay_ms;
+		/**
+		 * @sched_disable_gucid_threshold: threshold of min remaining available
+		 * guc_ids before we start bypassing the schedule disable delay
+		 */
+		unsigned int sched_disable_gucid_threshold;
 	} submission_state;
 
 	/**
@@ -466,4 +480,6 @@ void intel_guc_write_barrier(struct intel_guc *guc);
 
 void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
 
+int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index 74cbe8eaf531..a419d60166c8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -5,6 +5,7 @@
 
 #include <linux/bsearch.h>
 
+#include "gem/i915_gem_lmem.h"
 #include "gt/intel_engine_regs.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_mcr.h"
@@ -277,24 +278,16 @@ __mmio_reg_add(struct temp_regset *regset, struct guc_mmio_reg *reg)
 	return slot;
 }
 
-#define GUC_REGSET_STEERING(group, instance) ( \
-	FIELD_PREP(GUC_REGSET_STEERING_GROUP, (group)) | \
-	FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, (instance)) | \
-	GUC_REGSET_NEEDS_STEERING \
-)
-
 static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
 					  struct temp_regset *regset,
-					  i915_reg_t reg, u32 flags)
+					  u32 offset, u32 flags)
 {
 	u32 count = regset->storage_used - (regset->registers - regset->storage);
-	u32 offset = i915_mmio_reg_offset(reg);
 	struct guc_mmio_reg entry = {
 		.offset = offset,
 		.flags = flags,
 	};
 	struct guc_mmio_reg *slot;
-	u8 group, inst;
 
 	/*
 	 * The mmio list is built using separate lists within the driver.
@@ -306,17 +299,6 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
 		    sizeof(entry), guc_mmio_reg_cmp))
 		return 0;
 
-	/*
-	 * The GuC doesn't have a default steering, so we need to explicitly
-	 * steer all registers that need steering. However, we do not keep track
-	 * of all the steering ranges, only of those that have a chance of using
-	 * a non-default steering from the i915 pov. Instead of adding such
-	 * tracking, it is easier to just program the default steering for all
-	 * regs that don't need a non-default one.
-	 */
-	intel_gt_mcr_get_nonterminated_steering(gt, reg, &group, &inst);
-	entry.flags |= GUC_REGSET_STEERING(group, inst);
-
 	slot = __mmio_reg_add(regset, &entry);
 	if (IS_ERR(slot))
 		return PTR_ERR(slot);
@@ -335,6 +317,38 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
 #define GUC_MMIO_REG_ADD(gt, regset, reg, masked) \
 	guc_mmio_reg_add(gt, \
 			 regset, \
+			 i915_mmio_reg_offset(reg), \
+			 (masked) ? GUC_REGSET_MASKED : 0)
+
+#define GUC_REGSET_STEERING(group, instance) ( \
+	FIELD_PREP(GUC_REGSET_STEERING_GROUP, (group)) | \
+	FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, (instance)) | \
+	GUC_REGSET_NEEDS_STEERING \
+)
+
+static long __must_check guc_mcr_reg_add(struct intel_gt *gt,
+					 struct temp_regset *regset,
+					 i915_mcr_reg_t reg, u32 flags)
+{
+	u8 group, inst;
+
+	/*
+	 * The GuC doesn't have a default steering, so we need to explicitly
+	 * steer all registers that need steering. However, we do not keep track
+	 * of all the steering ranges, only of those that have a chance of using
+	 * a non-default steering from the i915 pov. Instead of adding such
+	 * tracking, it is easier to just program the default steering for all
+	 * regs that don't need a non-default one.
+	 */
+	intel_gt_mcr_get_nonterminated_steering(gt, reg, &group, &inst);
+	flags |= GUC_REGSET_STEERING(group, inst);
+
+	return guc_mmio_reg_add(gt, regset, i915_mmio_reg_offset(reg), flags);
+}
+
+#define GUC_MCR_REG_ADD(gt, regset, reg, masked) \
+	guc_mcr_reg_add(gt, \
+			 regset, \
 			 (reg), \
 			 (masked) ? GUC_REGSET_MASKED : 0)
 
@@ -372,8 +386,21 @@ static int guc_mmio_regset_init(struct temp_regset *regset,
 					false);
 
 	/* add in local MOCS registers */
-	for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++)
-		ret |= GUC_MMIO_REG_ADD(gt, regset, GEN9_LNCFCMOCS(i), false);
+	for (i = 0; i < LNCFCMOCS_REG_COUNT; i++)
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+			ret |= GUC_MCR_REG_ADD(gt, regset, XEHP_LNCFCMOCS(i), false);
+		else
+			ret |= GUC_MMIO_REG_ADD(gt, regset, GEN9_LNCFCMOCS(i), false);
+
+	if (GRAPHICS_VER(engine->i915) >= 12) {
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL0, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL1, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL2, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL3, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL4, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL5, false);
+		ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL6, false);
+	}
 
 	return ret ? -1 : 0;
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
index 8f1165146013..4e6dca707d94 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
@@ -169,6 +169,8 @@ static struct __guc_mmio_reg_descr_group default_lists[] = {
 	MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0),
 	MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
 	MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
+	MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS),
+	MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS),
 	MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
 	MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
 	MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
@@ -182,6 +184,8 @@ static const struct __guc_mmio_reg_descr_group xe_lpd_lists[] = {
 	MAKE_REGLIST(xe_lpd_global_regs, PF, GLOBAL, 0),
 	MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
 	MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
+	MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS),
+	MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS),
 	MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
 	MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
 	MAKE_REGLIST(xe_lpd_vec_class_regs, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
@@ -240,19 +244,19 @@ static void guc_capture_free_extlists(struct __guc_mmio_reg_descr_group *reglist
 
 struct __ext_steer_reg {
 	const char *name;
-	i915_reg_t reg;
+	i915_mcr_reg_t reg;
 };
 
 static const struct __ext_steer_reg xe_extregs[] = {
-	{"GEN7_SAMPLER_INSTDONE", GEN7_SAMPLER_INSTDONE},
-	{"GEN7_ROW_INSTDONE", GEN7_ROW_INSTDONE}
+	{"GEN8_SAMPLER_INSTDONE", GEN8_SAMPLER_INSTDONE},
+	{"GEN8_ROW_INSTDONE", GEN8_ROW_INSTDONE}
 };
 
 static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
 			   const struct __ext_steer_reg *extlist,
 			   int slice_id, int subslice_id)
 {
-	ext->reg = extlist->reg;
+	ext->reg = _MMIO(i915_mmio_reg_offset(extlist->reg));
 	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
 	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
 	ext->regname = extlist->name;
@@ -419,6 +423,44 @@ guc_capture_get_device_reglist(struct intel_guc *guc)
 	return default_lists;
 }
 
+static const char *
+__stringify_type(u32 type)
+{
+	switch (type) {
+	case GUC_CAPTURE_LIST_TYPE_GLOBAL:
+		return "Global";
+	case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
+		return "Class";
+	case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
+		return "Instance";
+	default:
+		break;
+	}
+
+	return "unknown";
+}
+
+static const char *
+__stringify_engclass(u32 class)
+{
+	switch (class) {
+	case GUC_RENDER_CLASS:
+		return "Render";
+	case GUC_VIDEO_CLASS:
+		return "Video";
+	case GUC_VIDEOENHANCE_CLASS:
+		return "VideoEnhance";
+	case GUC_BLITTER_CLASS:
+		return "Blitter";
+	case GUC_COMPUTE_CLASS:
+		return "Compute";
+	default:
+		break;
+	}
+
+	return "unknown";
+}
+
 static int
 guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
 		      struct guc_mmio_reg *ptr, u16 num_entries)
@@ -482,32 +524,55 @@ guc_cap_list_num_regs(struct intel_guc_state_capture *gc, u32 owner, u32 type, u
 	return num_regs;
 }
 
-int
-intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
-			      size_t *size)
+static int
+guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
+			size_t *size, bool is_purpose_est)
 {
 	struct intel_guc_state_capture *gc = guc->capture;
+	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 	struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid];
 	int num_regs;
 
-	if (!gc->reglists)
+	if (!gc->reglists) {
+		drm_warn(&i915->drm, "GuC-capture: No reglist on this device\n");
 		return -ENODEV;
+	}
 
 	if (cache->is_valid) {
 		*size = cache->size;
 		return cache->status;
 	}
 
+	if (!is_purpose_est && owner == GUC_CAPTURE_LIST_INDEX_PF &&
+	    !guc_capture_get_one_list(gc->reglists, owner, type, classid)) {
+		if (type == GUC_CAPTURE_LIST_TYPE_GLOBAL)
+			drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist Global!\n");
+		else
+			drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist %s(%u):%s(%u)!\n",
+				 __stringify_type(type), type,
+				 __stringify_engclass(classid), classid);
+		return -ENODATA;
+	}
+
 	num_regs = guc_cap_list_num_regs(gc, owner, type, classid);
+	/* intentional empty lists can exist depending on hw config */
 	if (!num_regs)
 		return -ENODATA;
 
-	*size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
-			   (num_regs * sizeof(struct guc_mmio_reg)));
+	if (size)
+		*size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
+				   (num_regs * sizeof(struct guc_mmio_reg)));
 
 	return 0;
 }
 
+int
+intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
+			      size_t *size)
+{
+	return guc_capture_getlistsize(guc, owner, type, classid, size, false);
+}
+
 static void guc_capture_create_prealloc_nodes(struct intel_guc *guc);
 
 int
@@ -606,7 +671,7 @@ guc_capture_output_min_size_est(struct intel_guc *guc)
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	int worst_min_size = 0, num_regs = 0;
+	int worst_min_size = 0;
 	size_t tmp = 0;
 
 	if (!guc->capture)
@@ -627,21 +692,19 @@ guc_capture_output_min_size_est(struct intel_guc *guc)
 		worst_min_size += sizeof(struct guc_state_capture_group_header_t) +
 					 (3 * sizeof(struct guc_state_capture_header_t));
 
-		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp))
-			num_regs += tmp;
+		if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp, true))
+			worst_min_size += tmp;
 
-		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
-						   engine->class, &tmp)) {
-			num_regs += tmp;
+		if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
+					     engine->class, &tmp, true)) {
+			worst_min_size += tmp;
 		}
-		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
-						   engine->class, &tmp)) {
-			num_regs += tmp;
+		if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
+					     engine->class, &tmp, true)) {
+			worst_min_size += tmp;
 		}
 	}
 
-	worst_min_size += (num_regs * sizeof(struct guc_mmio_reg));
-
 	return worst_min_size;
 }
 
@@ -658,15 +721,23 @@ static void check_guc_capture_size(struct intel_guc *guc)
 	int spare_size = min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER;
 	u32 buffer_size = intel_guc_log_section_size_capture(&guc->log);
 
+	/*
+	 * NOTE: min_size is much smaller than the capture region allocation (DG2: <80K vs 1MB)
+	 * Additionally, its based on space needed to fit all engines getting reset at once
+	 * within the same G2H handler task slot. This is very unlikely. However, if GuC really
+	 * does run out of space for whatever reason, we will see an separate warning message
+	 * when processing the G2H event capture-notification, search for:
+	 * INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE.
+	 */
 	if (min_size < 0)
 		drm_warn(&i915->drm, "Failed to calculate GuC error state capture buffer minimum size: %d!\n",
 			 min_size);
 	else if (min_size > buffer_size)
-		drm_warn(&i915->drm, "GuC error state capture buffer is too small: %d < %d\n",
+		drm_warn(&i915->drm, "GuC error state capture buffer maybe small: %d < %d\n",
 			 buffer_size, min_size);
 	else if (spare_size > buffer_size)
-		drm_notice(&i915->drm, "GuC error state capture buffer maybe too small: %d < %d (min = %d)\n",
-			   buffer_size, spare_size, min_size);
+		drm_dbg(&i915->drm, "GuC error state capture buffer lacks spare size: %d < %d (min = %d)\n",
+			buffer_size, spare_size, min_size);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
index 25f09a420561..7269eb0bbedf 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
@@ -71,12 +71,73 @@ static bool intel_eval_slpc_support(void *data)
 	return intel_guc_slpc_is_used(guc);
 }
 
+static int guc_sched_disable_delay_ms_get(void *data, u64 *val)
+{
+	struct intel_guc *guc = data;
+
+	if (!intel_guc_submission_is_used(guc))
+		return -ENODEV;
+
+	*val = (u64)guc->submission_state.sched_disable_delay_ms;
+
+	return 0;
+}
+
+static int guc_sched_disable_delay_ms_set(void *data, u64 val)
+{
+	struct intel_guc *guc = data;
+
+	if (!intel_guc_submission_is_used(guc))
+		return -ENODEV;
+
+	/* clamp to a practical limit, 1 minute is reasonable for a longest delay */
+	guc->submission_state.sched_disable_delay_ms = min_t(u64, val, 60000);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_delay_ms_fops,
+			guc_sched_disable_delay_ms_get,
+			guc_sched_disable_delay_ms_set, "%lld\n");
+
+static int guc_sched_disable_gucid_threshold_get(void *data, u64 *val)
+{
+	struct intel_guc *guc = data;
+
+	if (!intel_guc_submission_is_used(guc))
+		return -ENODEV;
+
+	*val = guc->submission_state.sched_disable_gucid_threshold;
+	return 0;
+}
+
+static int guc_sched_disable_gucid_threshold_set(void *data, u64 val)
+{
+	struct intel_guc *guc = data;
+
+	if (!intel_guc_submission_is_used(guc))
+		return -ENODEV;
+
+	if (val > intel_guc_sched_disable_gucid_threshold_max(guc))
+		guc->submission_state.sched_disable_gucid_threshold =
+			intel_guc_sched_disable_gucid_threshold_max(guc);
+	else
+		guc->submission_state.sched_disable_gucid_threshold = val;
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_gucid_threshold_fops,
+			guc_sched_disable_gucid_threshold_get,
+			guc_sched_disable_gucid_threshold_set, "%lld\n");
+
 void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
 {
 	static const struct intel_gt_debugfs_file files[] = {
 		{ "guc_info", &guc_info_fops, NULL },
 		{ "guc_registered_contexts", &guc_registered_contexts_fops, NULL },
 		{ "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support},
+		{ "guc_sched_disable_delay_ms", &guc_sched_disable_delay_ms_fops, NULL },
+		{ "guc_sched_disable_gucid_threshold", &guc_sched_disable_gucid_threshold_fops,
+		   NULL },
 	};
 
 	if (!intel_guc_is_supported(guc))
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index a0372735cddb..5b86b2e286e0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -10,12 +10,15 @@
  */
 
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 #include "intel_guc_fw.h"
 #include "i915_drv.h"
 
-static void guc_prepare_xfer(struct intel_uncore *uncore)
+static void guc_prepare_xfer(struct intel_gt *gt)
 {
+	struct intel_uncore *uncore = gt->uncore;
+
 	u32 shim_flags = GUC_ENABLE_READ_CACHE_LOGIC |
 			 GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA |
 			 GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA |
@@ -35,8 +38,9 @@ static void guc_prepare_xfer(struct intel_uncore *uncore)
 
 	if (GRAPHICS_VER(uncore->i915) == 9) {
 		/* DOP Clock Gating Enable for GuC clocks */
-		intel_uncore_rmw(uncore, GEN7_MISCCPCTL,
-				 0, GEN8_DOP_CLOCK_GATE_GUC_ENABLE);
+		intel_gt_mcr_multicast_write(gt, GEN8_MISCCPCTL,
+					     GEN8_DOP_CLOCK_GATE_GUC_ENABLE |
+					     intel_gt_mcr_read_any(gt, GEN8_MISCCPCTL));
 
 		/* allows for 5us (in 10ns units) before GT can go to RC6 */
 		intel_uncore_write(uncore, GUC_ARAT_C6DIS, 0x1FF);
@@ -168,7 +172,7 @@ int intel_guc_fw_upload(struct intel_guc *guc)
 	struct intel_uncore *uncore = gt->uncore;
 	int ret;
 
-	guc_prepare_xfer(uncore);
+	guc_prepare_xfer(gt);
 
 	/*
 	 * Note that GuC needs the CSS header plus uKernel code to be copied
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index 323b055e5db9..968ebd79dce7 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -290,6 +290,25 @@ struct guc_update_context_policy {
 	struct guc_klv_generic_dw_t klv[GUC_CONTEXT_POLICIES_KLV_NUM_IDS];
 } __packed;
 
+/* Format of the UPDATE_SCHEDULING_POLICIES H2G data packet */
+struct guc_update_scheduling_policy_header {
+	u32 action;
+} __packed;
+
+/*
+ * Can't dynmically allocate memory for the scheduling policy KLV because
+ * it will be sent from within the reset path. Need a fixed size lump on
+ * the stack instead :(.
+ *
+ * Currently, there is only one KLV defined, which has 1 word of KL + 2 words of V.
+ */
+#define MAX_SCHEDULING_POLICY_SIZE 3
+
+struct guc_update_scheduling_policy {
+	struct guc_update_scheduling_policy_header header;
+	u32 data[MAX_SCHEDULING_POLICY_SIZE];
+} __packed;
+
 #define GUC_POWER_UNSPECIFIED	0
 #define GUC_POWER_D0		1
 #define GUC_POWER_D1		2
@@ -298,6 +317,9 @@ struct guc_update_context_policy {
 
 /* Scheduling policy settings */
 
+#define GLOBAL_SCHEDULE_POLICY_RC_YIELD_DURATION	100	/* in ms */
+#define GLOBAL_SCHEDULE_POLICY_RC_YIELD_RATIO		50	/* in percent */
+
 #define GLOBAL_POLICY_MAX_NUM_WI 15
 
 /* Don't reset an engine upon preemption failure */
@@ -305,6 +327,27 @@ struct guc_update_context_policy {
 
 #define GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000
 
+/*
+ * GuC converts the timeout to clock ticks internally. Different platforms have
+ * different GuC clocks. Thus, the maximum value before overflow is platform
+ * dependent. Current worst case scenario is about 110s. So, the spec says to
+ * limit to 100s to be safe.
+ */
+#define GUC_POLICY_MAX_EXEC_QUANTUM_US		(100 * 1000 * 1000UL)
+#define GUC_POLICY_MAX_PREEMPT_TIMEOUT_US	(100 * 1000 * 1000UL)
+
+static inline u32 guc_policy_max_exec_quantum_ms(void)
+{
+	BUILD_BUG_ON(GUC_POLICY_MAX_EXEC_QUANTUM_US >= UINT_MAX);
+	return GUC_POLICY_MAX_EXEC_QUANTUM_US / 1000;
+}
+
+static inline u32 guc_policy_max_preempt_timeout_ms(void)
+{
+	BUILD_BUG_ON(GUC_POLICY_MAX_PREEMPT_TIMEOUT_US >= UINT_MAX);
+	return GUC_POLICY_MAX_PREEMPT_TIMEOUT_US / 1000;
+}
+
 struct guc_policies {
 	u32 submission_queue_depth[GUC_MAX_ENGINE_CLASSES];
 	/* In micro seconds. How much time to allow before DPC processing is
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 55d3ef93e86f..68331c538b0a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -16,15 +16,15 @@
 #if defined(CONFIG_DRM_I915_DEBUG_GUC)
 #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE	SZ_2M
 #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE	SZ_16M
-#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_4M
+#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_1M
 #elif defined(CONFIG_DRM_I915_DEBUG_GEM)
 #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE	SZ_1M
 #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE	SZ_2M
-#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_4M
+#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_1M
 #else
 #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE	SZ_8K
 #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE	SZ_64K
-#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_2M
+#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_1M
 #endif
 
 static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index fdd895f73f9f..63464933cbce 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -137,6 +137,17 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value)
 	return ret > 0 ? -EPROTO : ret;
 }
 
+static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1),
+		id,
+	};
+
+	return intel_guc_send(guc, request, ARRAY_SIZE(request));
+}
+
 static bool slpc_is_running(struct intel_guc_slpc *slpc)
 {
 	return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING;
@@ -190,6 +201,15 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value)
 	return ret;
 }
 
+static int slpc_unset_param(struct intel_guc_slpc *slpc, u8 id)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+
+	GEM_BUG_ON(id >= SLPC_MAX_PARAM);
+
+	return guc_action_slpc_unset_param(guc, id);
+}
+
 static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq)
 {
 	struct drm_i915_private *i915 = slpc_to_i915(slpc);
@@ -263,6 +283,7 @@ int intel_guc_slpc_init(struct intel_guc_slpc *slpc)
 
 	slpc->max_freq_softlimit = 0;
 	slpc->min_freq_softlimit = 0;
+	slpc->min_is_rpmax = false;
 
 	slpc->boost_freq = 0;
 	atomic_set(&slpc->num_waiters, 0);
@@ -588,6 +609,39 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc)
 	return 0;
 }
 
+static bool is_slpc_min_freq_rpmax(struct intel_guc_slpc *slpc)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	int slpc_min_freq;
+	int ret;
+
+	ret = intel_guc_slpc_get_min_freq(slpc, &slpc_min_freq);
+	if (ret) {
+		drm_err(&i915->drm,
+			"Failed to get min freq: (%d)\n",
+			ret);
+		return false;
+	}
+
+	if (slpc_min_freq == SLPC_MAX_FREQ_MHZ)
+		return true;
+	else
+		return false;
+}
+
+static void update_server_min_softlimit(struct intel_guc_slpc *slpc)
+{
+	/* For server parts, SLPC min will be at RPMax.
+	 * Use min softlimit to clamp it to RP0 instead.
+	 */
+	if (!slpc->min_freq_softlimit &&
+	    is_slpc_min_freq_rpmax(slpc)) {
+		slpc->min_is_rpmax = true;
+		slpc->min_freq_softlimit = slpc->rp0_freq;
+		(slpc_to_gt(slpc))->defaults.min_freq = slpc->min_freq_softlimit;
+	}
+}
+
 static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc)
 {
 	/* Force SLPC to used platform rp0 */
@@ -610,6 +664,52 @@ static void slpc_get_rp_values(struct intel_guc_slpc *slpc)
 		slpc->boost_freq = slpc->rp0_freq;
 }
 
+/**
+ * intel_guc_slpc_override_gucrc_mode() - override GUCRC mode
+ * @slpc: pointer to intel_guc_slpc.
+ * @mode: new value of the mode.
+ *
+ * This function will override the GUCRC mode.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode)
+{
+	int ret;
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+
+	if (mode >= SLPC_GUCRC_MODE_MAX)
+		return -EINVAL;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_set_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE, mode);
+		if (ret)
+			drm_err(&i915->drm,
+				"Override gucrc mode %d failed %d\n",
+				mode, ret);
+	}
+
+	return ret;
+}
+
+int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_unset_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE);
+		if (ret)
+			drm_err(&i915->drm,
+				"Unsetting gucrc mode failed %d\n",
+				ret);
+	}
+
+	return ret;
+}
+
 /*
  * intel_guc_slpc_enable() - Start SLPC
  * @slpc: pointer to intel_guc_slpc.
@@ -647,6 +747,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc)
 
 	slpc_get_rp_values(slpc);
 
+	/* Handle the case where min=max=RPmax */
+	update_server_min_softlimit(slpc);
+
 	/* Set SLPC max limit to RP0 */
 	ret = slpc_use_fused_rp0(slpc);
 	if (unlikely(ret)) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
index 82a98f78f96c..17ed515f6a85 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
@@ -9,6 +9,8 @@
 #include "intel_guc_submission.h"
 #include "intel_guc_slpc_types.h"
 
+#define SLPC_MAX_FREQ_MHZ 4250
+
 struct intel_gt;
 struct drm_printer;
 
@@ -42,5 +44,7 @@ int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val);
 void intel_guc_pm_intrmsk_enable(struct intel_gt *gt);
 void intel_guc_slpc_boost(struct intel_guc_slpc *slpc);
 void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
index 73d208123528..a6ef53b04e04 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
@@ -19,6 +19,9 @@ struct intel_guc_slpc {
 	bool supported;
 	bool selected;
 
+	/* Indicates this is a server part */
+	bool min_is_rpmax;
+
 	/* platform frequency limits */
 	u32 min_freq;
 	u32 rp0_freq;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 1db59eeb34db..4ccb29f9ac55 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -6,6 +6,7 @@
 #include <linux/circ_buf.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_lmem.h"
 #include "gt/gen8_engine_cs.h"
 #include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
@@ -65,7 +66,13 @@
  * corresponding G2H returns indicating the scheduling disable operation has
  * completed it is safe to unpin the context. While a disable is in flight it
  * isn't safe to resubmit the context so a fence is used to stall all future
- * requests of that context until the G2H is returned.
+ * requests of that context until the G2H is returned. Because this interaction
+ * with the GuC takes a non-zero amount of time we delay the disabling of
+ * scheduling after the pin count goes to zero by a configurable period of time
+ * (see SCHED_DISABLE_DELAY_MS). The thought is this gives the user a window of
+ * time to resubmit something on the context before doing this costly operation.
+ * This delay is only done if the context isn't closed and the guc_id usage is
+ * less than a threshold (see NUM_SCHED_DISABLE_GUC_IDS_THRESHOLD).
  *
  * Context deregistration:
  * Before a context can be destroyed or if we steal its guc_id we must
@@ -163,7 +170,8 @@ guc_create_parallel(struct intel_engine_cs **engines,
 #define SCHED_STATE_PENDING_ENABLE			BIT(5)
 #define SCHED_STATE_REGISTERED				BIT(6)
 #define SCHED_STATE_POLICY_REQUIRED			BIT(7)
-#define SCHED_STATE_BLOCKED_SHIFT			8
+#define SCHED_STATE_CLOSED				BIT(8)
+#define SCHED_STATE_BLOCKED_SHIFT			9
 #define SCHED_STATE_BLOCKED		BIT(SCHED_STATE_BLOCKED_SHIFT)
 #define SCHED_STATE_BLOCKED_MASK	(0xfff << SCHED_STATE_BLOCKED_SHIFT)
 
@@ -173,12 +181,20 @@ static inline void init_sched_state(struct intel_context *ce)
 	ce->guc_state.sched_state &= SCHED_STATE_BLOCKED_MASK;
 }
 
+/*
+ * Kernel contexts can have SCHED_STATE_REGISTERED after suspend.
+ * A context close can race with the submission path, so SCHED_STATE_CLOSED
+ * can be set immediately before we try to register.
+ */
+#define SCHED_STATE_VALID_INIT \
+	(SCHED_STATE_BLOCKED_MASK | \
+	 SCHED_STATE_CLOSED | \
+	 SCHED_STATE_REGISTERED)
+
 __maybe_unused
 static bool sched_state_is_init(struct intel_context *ce)
 {
-	/* Kernel contexts can have SCHED_STATE_REGISTERED after suspend. */
-	return !(ce->guc_state.sched_state &
-		 ~(SCHED_STATE_BLOCKED_MASK | SCHED_STATE_REGISTERED));
+	return !(ce->guc_state.sched_state & ~SCHED_STATE_VALID_INIT);
 }
 
 static inline bool
@@ -319,6 +335,17 @@ static inline void clr_context_policy_required(struct intel_context *ce)
 	ce->guc_state.sched_state &= ~SCHED_STATE_POLICY_REQUIRED;
 }
 
+static inline bool context_close_done(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_CLOSED;
+}
+
+static inline void set_context_close_done(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_CLOSED;
+}
+
 static inline u32 context_blocked(struct intel_context *ce)
 {
 	return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >>
@@ -343,25 +370,6 @@ static inline void decr_context_blocked(struct intel_context *ce)
 	ce->guc_state.sched_state -= SCHED_STATE_BLOCKED;
 }
 
-static inline bool context_has_committed_requests(struct intel_context *ce)
-{
-	return !!ce->guc_state.number_committed_requests;
-}
-
-static inline void incr_context_committed_requests(struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->guc_state.lock);
-	++ce->guc_state.number_committed_requests;
-	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
-}
-
-static inline void decr_context_committed_requests(struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->guc_state.lock);
-	--ce->guc_state.number_committed_requests;
-	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
-}
-
 static struct intel_context *
 request_to_scheduling_context(struct i915_request *rq)
 {
@@ -1067,6 +1075,12 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 
 		xa_unlock(&guc->context_lookup);
 
+		if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
+		    (cancel_delayed_work(&ce->guc_state.sched_disable_delay_work))) {
+			/* successful cancel so jump straight to close it */
+			intel_context_sched_disable_unpin(ce);
+		}
+
 		spin_lock(&ce->guc_state.lock);
 
 		/*
@@ -1994,6 +2008,9 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (!intel_context_is_parent(ce))
+		++guc->submission_state.guc_ids_in_use;
+
 	ce->guc_id.id = ret;
 	return 0;
 }
@@ -2003,14 +2020,16 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	GEM_BUG_ON(intel_context_is_child(ce));
 
 	if (!context_guc_id_invalid(ce)) {
-		if (intel_context_is_parent(ce))
+		if (intel_context_is_parent(ce)) {
 			bitmap_release_region(guc->submission_state.guc_ids_bitmap,
 					      ce->guc_id.id,
 					      order_base_2(ce->parallel.number_children
 							   + 1));
-		else
+		} else {
+			--guc->submission_state.guc_ids_in_use;
 			ida_simple_remove(&guc->submission_state.guc_ids,
 					  ce->guc_id.id);
+		}
 		clr_ctx_id_mapping(guc, ce->guc_id.id);
 		set_context_guc_id_invalid(ce);
 	}
@@ -2429,6 +2448,10 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop)
 	int ret;
 
 	/* NB: For both of these, zero means disabled. */
+	GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000,
+				  execution_quantum));
+	GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000,
+				  preemption_timeout));
 	execution_quantum = engine->props.timeslice_duration_ms * 1000;
 	preemption_timeout = engine->props.preempt_timeout_ms * 1000;
 
@@ -2462,6 +2485,10 @@ static void guc_context_policy_init_v69(struct intel_engine_cs *engine,
 		desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69;
 
 	/* NB: For both of these, zero means disabled. */
+	GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000,
+				  desc->execution_quantum));
+	GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000,
+				  desc->preemption_timeout));
 	desc->execution_quantum = engine->props.timeslice_duration_ms * 1000;
 	desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
 }
@@ -2998,41 +3025,104 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
 	}
 }
 
-static void guc_context_sched_disable(struct intel_context *ce)
+static void do_sched_disable(struct intel_guc *guc, struct intel_context *ce,
+			     unsigned long flags)
+	__releases(ce->guc_state.lock)
 {
-	struct intel_guc *guc = ce_to_guc(ce);
-	unsigned long flags;
 	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
 	intel_wakeref_t wakeref;
 	u16 guc_id;
 
+	lockdep_assert_held(&ce->guc_state.lock);
+	guc_id = prep_context_pending_disable(ce);
+
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		__guc_context_sched_disable(guc, ce, guc_id);
+}
+
+static bool bypass_sched_disable(struct intel_guc *guc,
+				 struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
 	GEM_BUG_ON(intel_context_is_child(ce));
 
+	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
+	    !ctx_id_mapped(guc, ce->guc_id.id)) {
+		clr_context_enabled(ce);
+		return true;
+	}
+
+	return !context_enabled(ce);
+}
+
+static void __delay_sched_disable(struct work_struct *wrk)
+{
+	struct intel_context *ce =
+		container_of(wrk, typeof(*ce), guc_state.sched_disable_delay_work.work);
+	struct intel_guc *guc = ce_to_guc(ce);
+	unsigned long flags;
+
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 
+	if (bypass_sched_disable(guc, ce)) {
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		intel_context_sched_disable_unpin(ce);
+	} else {
+		do_sched_disable(guc, ce, flags);
+	}
+}
+
+static bool guc_id_pressure(struct intel_guc *guc, struct intel_context *ce)
+{
 	/*
-	 * We have to check if the context has been disabled by another thread,
-	 * check if submssion has been disabled to seal a race with reset and
-	 * finally check if any more requests have been committed to the
-	 * context ensursing that a request doesn't slip through the
-	 * 'context_pending_disable' fence.
+	 * parent contexts are perma-pinned, if we are unpinning do schedule
+	 * disable immediately.
 	 */
-	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
-		     context_has_committed_requests(ce))) {
-		clr_context_enabled(ce);
+	if (intel_context_is_parent(ce))
+		return true;
+
+	/*
+	 * If we are beyond the threshold for avail guc_ids, do schedule disable immediately.
+	 */
+	return guc->submission_state.guc_ids_in_use >
+		guc->submission_state.sched_disable_gucid_threshold;
+}
+
+static void guc_context_sched_disable(struct intel_context *ce)
+{
+	struct intel_guc *guc = ce_to_guc(ce);
+	u64 delay = guc->submission_state.sched_disable_delay_ms;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+
+	if (bypass_sched_disable(guc, ce)) {
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		goto unpin;
+		intel_context_sched_disable_unpin(ce);
+	} else if (!intel_context_is_closed(ce) && !guc_id_pressure(guc, ce) &&
+		   delay) {
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		mod_delayed_work(system_unbound_wq,
+				 &ce->guc_state.sched_disable_delay_work,
+				 msecs_to_jiffies(delay));
+	} else {
+		do_sched_disable(guc, ce, flags);
 	}
-	guc_id = prep_context_pending_disable(ce);
+}
 
-	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+static void guc_context_close(struct intel_context *ce)
+{
+	unsigned long flags;
 
-	with_intel_runtime_pm(runtime_pm, wakeref)
-		__guc_context_sched_disable(guc, ce, guc_id);
+	if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
+	    cancel_delayed_work(&ce->guc_state.sched_disable_delay_work))
+		__delay_sched_disable(&ce->guc_state.sched_disable_delay_work.work);
 
-	return;
-unpin:
-	intel_context_sched_disable_unpin(ce);
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	set_context_close_done(ce);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 }
 
 static inline void guc_lrc_desc_unpin(struct intel_context *ce)
@@ -3071,7 +3161,6 @@ static void __guc_context_destroy(struct intel_context *ce)
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_HIGH] ||
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] ||
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_NORMAL]);
-	GEM_BUG_ON(ce->guc_state.number_committed_requests);
 
 	lrc_fini(ce);
 	intel_context_fini(ce);
@@ -3340,8 +3429,6 @@ static void remove_from_context(struct i915_request *rq)
 
 	guc_prio_fini(rq, ce);
 
-	decr_context_committed_requests(ce);
-
 	spin_unlock_irq(&ce->guc_state.lock);
 
 	atomic_dec(&ce->guc_id.ref);
@@ -3351,6 +3438,8 @@ static void remove_from_context(struct i915_request *rq)
 static const struct intel_context_ops guc_context_ops = {
 	.alloc = guc_context_alloc,
 
+	.close = guc_context_close,
+
 	.pre_pin = guc_context_pre_pin,
 	.pin = guc_context_pin,
 	.unpin = guc_context_unpin,
@@ -3433,6 +3522,10 @@ static void guc_context_init(struct intel_context *ce)
 	rcu_read_unlock();
 
 	ce->guc_state.prio = map_i915_prio_to_guc_prio(prio);
+
+	INIT_DELAYED_WORK(&ce->guc_state.sched_disable_delay_work,
+			  __delay_sched_disable);
+
 	set_bit(CONTEXT_GUC_INIT, &ce->flags);
 }
 
@@ -3471,6 +3564,26 @@ static int guc_request_alloc(struct i915_request *rq)
 		guc_context_init(ce);
 
 	/*
+	 * If the context gets closed while the execbuf is ongoing, the context
+	 * close code will race with the below code to cancel the delayed work.
+	 * If the context close wins the race and cancels the work, it will
+	 * immediately call the sched disable (see guc_context_close), so there
+	 * is a chance we can get past this check while the sched_disable code
+	 * is being executed. To make sure that code completes before we check
+	 * the status further down, we wait for the close process to complete.
+	 * Else, this code path could send a request down thinking that the
+	 * context is still in a schedule-enable mode while the GuC ends up
+	 * dropping the request completely because the disable did go from the
+	 * context_close path right to GuC just prior. In the event the CT is
+	 * full, we could potentially need to wait up to 1.5 seconds.
+	 */
+	if (cancel_delayed_work_sync(&ce->guc_state.sched_disable_delay_work))
+		intel_context_sched_disable_unpin(ce);
+	else if (intel_context_is_closed(ce))
+		if (wait_for(context_close_done(ce), 1500))
+			drm_warn(&guc_to_gt(guc)->i915->drm,
+				 "timed out waiting on context sched close before realloc\n");
+	/*
 	 * Call pin_guc_id here rather than in the pinning step as with
 	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
 	 * guc_id and creating horrible race conditions. This is especially bad
@@ -3524,7 +3637,6 @@ out:
 
 		list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences);
 	}
-	incr_context_committed_requests(ce);
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
 	return 0;
@@ -3600,6 +3712,8 @@ static int guc_virtual_context_alloc(struct intel_context *ce)
 static const struct intel_context_ops virtual_guc_context_ops = {
 	.alloc = guc_virtual_context_alloc,
 
+	.close = guc_context_close,
+
 	.pre_pin = guc_virtual_context_pre_pin,
 	.pin = guc_virtual_context_pin,
 	.unpin = guc_virtual_context_unpin,
@@ -3689,6 +3803,8 @@ static void guc_child_context_destroy(struct kref *kref)
 static const struct intel_context_ops virtual_parent_context_ops = {
 	.alloc = guc_virtual_context_alloc,
 
+	.close = guc_context_close,
+
 	.pre_pin = guc_context_pre_pin,
 	.pin = guc_parent_context_pin,
 	.unpin = guc_parent_context_unpin,
@@ -4093,7 +4209,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 
 	engine->emit_bb_start = gen8_emit_bb_start;
 	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
-		engine->emit_bb_start = gen125_emit_bb_start;
+		engine->emit_bb_start = xehp_emit_bb_start;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
@@ -4177,6 +4293,98 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
 	return 0;
 }
 
+struct scheduling_policy {
+	/* internal data */
+	u32 max_words, num_words;
+	u32 count;
+	/* API data */
+	struct guc_update_scheduling_policy h2g;
+};
+
+static u32 __guc_scheduling_policy_action_size(struct scheduling_policy *policy)
+{
+	u32 *start = (void *)&policy->h2g;
+	u32 *end = policy->h2g.data + policy->num_words;
+	size_t delta = end - start;
+
+	return delta;
+}
+
+static struct scheduling_policy *__guc_scheduling_policy_start_klv(struct scheduling_policy *policy)
+{
+	policy->h2g.header.action = INTEL_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV;
+	policy->max_words = ARRAY_SIZE(policy->h2g.data);
+	policy->num_words = 0;
+	policy->count = 0;
+
+	return policy;
+}
+
+static void __guc_scheduling_policy_add_klv(struct scheduling_policy *policy,
+					    u32 action, u32 *data, u32 len)
+{
+	u32 *klv_ptr = policy->h2g.data + policy->num_words;
+
+	GEM_BUG_ON((policy->num_words + 1 + len) > policy->max_words);
+	*(klv_ptr++) = FIELD_PREP(GUC_KLV_0_KEY, action) |
+		       FIELD_PREP(GUC_KLV_0_LEN, len);
+	memcpy(klv_ptr, data, sizeof(u32) * len);
+	policy->num_words += 1 + len;
+	policy->count++;
+}
+
+static int __guc_action_set_scheduling_policies(struct intel_guc *guc,
+						struct scheduling_policy *policy)
+{
+	int ret;
+
+	ret = intel_guc_send(guc, (u32 *)&policy->h2g,
+			     __guc_scheduling_policy_action_size(policy));
+	if (ret < 0)
+		return ret;
+
+	if (ret != policy->count) {
+		drm_warn(&guc_to_gt(guc)->i915->drm, "GuC global scheduler policy processed %d of %d KLVs!",
+			 ret, policy->count);
+		if (ret > policy->count)
+			return -EPROTO;
+	}
+
+	return 0;
+}
+
+static int guc_init_global_schedule_policy(struct intel_guc *guc)
+{
+	struct scheduling_policy policy;
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	if (GET_UC_VER(guc) < MAKE_UC_VER(70, 3, 0))
+		return 0;
+
+	__guc_scheduling_policy_start_klv(&policy);
+
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref) {
+		u32 yield[] = {
+			GLOBAL_SCHEDULE_POLICY_RC_YIELD_DURATION,
+			GLOBAL_SCHEDULE_POLICY_RC_YIELD_RATIO,
+		};
+
+		__guc_scheduling_policy_add_klv(&policy,
+						GUC_SCHEDULING_POLICIES_KLV_ID_RENDER_COMPUTE_YIELD,
+						yield, ARRAY_SIZE(yield));
+
+		ret = __guc_action_set_scheduling_policies(guc, &policy);
+		if (ret)
+			i915_probe_error(gt->i915,
+					 "Failed to configure global scheduling policies: %pe!\n",
+					 ERR_PTR(ret));
+	}
+
+	return ret;
+}
+
 void intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -4189,6 +4397,7 @@ void intel_guc_submission_enable(struct intel_guc *guc)
 
 	guc_init_lrc_mapping(guc);
 	guc_init_engine_stats(guc);
+	guc_init_global_schedule_policy(guc);
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
@@ -4219,6 +4428,26 @@ static bool __guc_submission_selected(struct intel_guc *guc)
 	return i915->params.enable_guc & ENABLE_GUC_SUBMISSION;
 }
 
+int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc)
+{
+	return guc->submission_state.num_guc_ids - NUMBER_MULTI_LRC_GUC_ID(guc);
+}
+
+/*
+ * This default value of 33 milisecs (+1 milisec round up) ensures 30fps or higher
+ * workloads are able to enjoy the latency reduction when delaying the schedule-disable
+ * operation. This matches the 30fps game-render + encode (real world) workload this
+ * knob was tested against.
+ */
+#define SCHED_DISABLE_DELAY_MS	34
+
+/*
+ * A threshold of 75% is a reasonable starting point considering that real world apps
+ * generally don't get anywhere near this.
+ */
+#define NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(__guc) \
+	(((intel_guc_sched_disable_gucid_threshold_max(guc)) * 3) / 4)
+
 void intel_guc_submission_init_early(struct intel_guc *guc)
 {
 	xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ);
@@ -4235,7 +4464,10 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
 	spin_lock_init(&guc->timestamp.lock);
 	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
 
+	guc->submission_state.sched_disable_delay_ms = SCHED_DISABLE_DELAY_MS;
 	guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID;
+	guc->submission_state.sched_disable_gucid_threshold =
+		NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(guc);
 	guc->submission_supported = __guc_submission_supported(guc);
 	guc->submission_selected = __guc_submission_selected(guc);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 3bb8838e325a..fbc8bae14f76 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -10,6 +10,9 @@
 #include "intel_huc.h"
 #include "i915_drv.h"
 
+#include <linux/device/bus.h>
+#include <linux/mei_aux.h>
+
 /**
  * DOC: HuC
  *
@@ -42,6 +45,172 @@
  * HuC-specific commands.
  */
 
+/*
+ * MEI-GSC load is an async process. The probing of the exposed aux device
+ * (see intel_gsc.c) usually happens a few seconds after i915 probe, depending
+ * on when the kernel schedules it. Unless something goes terribly wrong, we're
+ * guaranteed for this to happen during boot, so the big timeout is a safety net
+ * that we never expect to need.
+ * MEI-PXP + HuC load usually takes ~300ms, but if the GSC needs to be resumed
+ * and/or reset, this can take longer. Note that the kernel might schedule
+ * other work between the i915 init/resume and the MEI one, which can add to
+ * the delay.
+ */
+#define GSC_INIT_TIMEOUT_MS 10000
+#define PXP_INIT_TIMEOUT_MS 5000
+
+static int sw_fence_dummy_notify(struct i915_sw_fence *sf,
+				 enum i915_sw_fence_notify state)
+{
+	return NOTIFY_DONE;
+}
+
+static void __delayed_huc_load_complete(struct intel_huc *huc)
+{
+	if (!i915_sw_fence_done(&huc->delayed_load.fence))
+		i915_sw_fence_complete(&huc->delayed_load.fence);
+}
+
+static void delayed_huc_load_complete(struct intel_huc *huc)
+{
+	hrtimer_cancel(&huc->delayed_load.timer);
+	__delayed_huc_load_complete(huc);
+}
+
+static void __gsc_init_error(struct intel_huc *huc)
+{
+	huc->delayed_load.status = INTEL_HUC_DELAYED_LOAD_ERROR;
+	__delayed_huc_load_complete(huc);
+}
+
+static void gsc_init_error(struct intel_huc *huc)
+{
+	hrtimer_cancel(&huc->delayed_load.timer);
+	__gsc_init_error(huc);
+}
+
+static void gsc_init_done(struct intel_huc *huc)
+{
+	hrtimer_cancel(&huc->delayed_load.timer);
+
+	/* MEI-GSC init is done, now we wait for MEI-PXP to bind */
+	huc->delayed_load.status = INTEL_HUC_WAITING_ON_PXP;
+	if (!i915_sw_fence_done(&huc->delayed_load.fence))
+		hrtimer_start(&huc->delayed_load.timer,
+			      ms_to_ktime(PXP_INIT_TIMEOUT_MS),
+			      HRTIMER_MODE_REL);
+}
+
+static enum hrtimer_restart huc_delayed_load_timer_callback(struct hrtimer *hrtimer)
+{
+	struct intel_huc *huc = container_of(hrtimer, struct intel_huc, delayed_load.timer);
+
+	if (!intel_huc_is_authenticated(huc)) {
+		if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_GSC)
+			drm_notice(&huc_to_gt(huc)->i915->drm,
+				   "timed out waiting for MEI GSC init to load HuC\n");
+		else if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_PXP)
+			drm_notice(&huc_to_gt(huc)->i915->drm,
+				   "timed out waiting for MEI PXP init to load HuC\n");
+		else
+			MISSING_CASE(huc->delayed_load.status);
+
+		__gsc_init_error(huc);
+	}
+
+	return HRTIMER_NORESTART;
+}
+
+static void huc_delayed_load_start(struct intel_huc *huc)
+{
+	ktime_t delay;
+
+	GEM_BUG_ON(intel_huc_is_authenticated(huc));
+
+	/*
+	 * On resume we don't have to wait for MEI-GSC to be re-probed, but we
+	 * do need to wait for MEI-PXP to reset & re-bind
+	 */
+	switch (huc->delayed_load.status) {
+	case INTEL_HUC_WAITING_ON_GSC:
+		delay = ms_to_ktime(GSC_INIT_TIMEOUT_MS);
+		break;
+	case INTEL_HUC_WAITING_ON_PXP:
+		delay = ms_to_ktime(PXP_INIT_TIMEOUT_MS);
+		break;
+	default:
+		gsc_init_error(huc);
+		return;
+	}
+
+	/*
+	 * This fence is always complete unless we're waiting for the
+	 * GSC device to come up to load the HuC. We arm the fence here
+	 * and complete it when we confirm that the HuC is loaded from
+	 * the PXP bind callback.
+	 */
+	GEM_BUG_ON(!i915_sw_fence_done(&huc->delayed_load.fence));
+	i915_sw_fence_fini(&huc->delayed_load.fence);
+	i915_sw_fence_reinit(&huc->delayed_load.fence);
+	i915_sw_fence_await(&huc->delayed_load.fence);
+	i915_sw_fence_commit(&huc->delayed_load.fence);
+
+	hrtimer_start(&huc->delayed_load.timer, delay, HRTIMER_MODE_REL);
+}
+
+static int gsc_notifier(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct intel_huc *huc = container_of(nb, struct intel_huc, delayed_load.nb);
+	struct intel_gsc_intf *intf = &huc_to_gt(huc)->gsc.intf[0];
+
+	if (!intf->adev || &intf->adev->aux_dev.dev != dev)
+		return 0;
+
+	switch (action) {
+	case BUS_NOTIFY_BOUND_DRIVER: /* mei driver bound to aux device */
+		gsc_init_done(huc);
+		break;
+
+	case BUS_NOTIFY_DRIVER_NOT_BOUND: /* mei driver fails to be bound */
+	case BUS_NOTIFY_UNBIND_DRIVER: /* mei driver about to be unbound */
+		drm_info(&huc_to_gt(huc)->i915->drm,
+			 "mei driver not bound, disabling HuC load\n");
+		gsc_init_error(huc);
+		break;
+	}
+
+	return 0;
+}
+
+void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus)
+{
+	int ret;
+
+	if (!intel_huc_is_loaded_by_gsc(huc))
+		return;
+
+	huc->delayed_load.nb.notifier_call = gsc_notifier;
+	ret = bus_register_notifier(bus, &huc->delayed_load.nb);
+	if (ret) {
+		drm_err(&huc_to_gt(huc)->i915->drm,
+			"failed to register GSC notifier\n");
+		huc->delayed_load.nb.notifier_call = NULL;
+		gsc_init_error(huc);
+	}
+}
+
+void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus)
+{
+	if (!huc->delayed_load.nb.notifier_call)
+		return;
+
+	delayed_huc_load_complete(huc);
+
+	bus_unregister_notifier(bus, &huc->delayed_load.nb);
+	huc->delayed_load.nb.notifier_call = NULL;
+}
+
 void intel_huc_init_early(struct intel_huc *huc)
 {
 	struct drm_i915_private *i915 = huc_to_gt(huc)->i915;
@@ -57,6 +226,17 @@ void intel_huc_init_early(struct intel_huc *huc)
 		huc->status.mask = HUC_FW_VERIFIED;
 		huc->status.value = HUC_FW_VERIFIED;
 	}
+
+	/*
+	 * Initialize fence to be complete as this is expected to be complete
+	 * unless there is a delayed HuC reload in progress.
+	 */
+	i915_sw_fence_init(&huc->delayed_load.fence,
+			   sw_fence_dummy_notify);
+	i915_sw_fence_commit(&huc->delayed_load.fence);
+
+	hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	huc->delayed_load.timer.function = huc_delayed_load_timer_callback;
 }
 
 #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
@@ -113,6 +293,7 @@ int intel_huc_init(struct intel_huc *huc)
 	return 0;
 
 out:
+	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_INIT_FAIL);
 	drm_info(&i915->drm, "HuC init failed with %d\n", err);
 	return err;
 }
@@ -122,9 +303,50 @@ void intel_huc_fini(struct intel_huc *huc)
 	if (!intel_uc_fw_is_loadable(&huc->fw))
 		return;
 
+	delayed_huc_load_complete(huc);
+
+	i915_sw_fence_fini(&huc->delayed_load.fence);
 	intel_uc_fw_fini(&huc->fw);
 }
 
+void intel_huc_suspend(struct intel_huc *huc)
+{
+	if (!intel_uc_fw_is_loadable(&huc->fw))
+		return;
+
+	/*
+	 * in the unlikely case that we're suspending before the GSC has
+	 * completed its loading sequence, just stop waiting. We'll restart
+	 * on resume.
+	 */
+	delayed_huc_load_complete(huc);
+}
+
+int intel_huc_wait_for_auth_complete(struct intel_huc *huc)
+{
+	struct intel_gt *gt = huc_to_gt(huc);
+	int ret;
+
+	ret = __intel_wait_for_register(gt->uncore,
+					huc->status.reg,
+					huc->status.mask,
+					huc->status.value,
+					2, 50, NULL);
+
+	/* mark the load process as complete even if the wait failed */
+	delayed_huc_load_complete(huc);
+
+	if (ret) {
+		drm_err(&gt->i915->drm, "HuC: Firmware not verified %d\n", ret);
+		intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL);
+		return ret;
+	}
+
+	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING);
+	drm_info(&gt->i915->drm, "HuC authenticated\n");
+	return 0;
+}
+
 /**
  * intel_huc_auth() - Authenticate HuC uCode
  * @huc: intel_huc structure
@@ -161,27 +383,18 @@ int intel_huc_auth(struct intel_huc *huc)
 	}
 
 	/* Check authentication status, it should be done by now */
-	ret = __intel_wait_for_register(gt->uncore,
-					huc->status.reg,
-					huc->status.mask,
-					huc->status.value,
-					2, 50, NULL);
-	if (ret) {
-		DRM_ERROR("HuC: Firmware not verified %d\n", ret);
+	ret = intel_huc_wait_for_auth_complete(huc);
+	if (ret)
 		goto fail;
-	}
 
-	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING);
-	drm_info(&gt->i915->drm, "HuC authenticated\n");
 	return 0;
 
 fail:
 	i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret);
-	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL);
 	return ret;
 }
 
-static bool huc_is_authenticated(struct intel_huc *huc)
+bool intel_huc_is_authenticated(struct intel_huc *huc)
 {
 	struct intel_gt *gt = huc_to_gt(huc);
 	intel_wakeref_t wakeref;
@@ -200,13 +413,8 @@ static bool huc_is_authenticated(struct intel_huc *huc)
  * This function reads status register to verify if HuC
  * firmware was successfully loaded.
  *
- * Returns:
- *  * -ENODEV if HuC is not present on this platform,
- *  * -EOPNOTSUPP if HuC firmware is disabled,
- *  * -ENOPKG if HuC firmware was not installed,
- *  * -ENOEXEC if HuC firmware is invalid or mismatched,
- *  * 0 if HuC firmware is not running,
- *  * 1 if HuC firmware is authenticated and running.
+ * The return values match what is expected for the I915_PARAM_HUC_STATUS
+ * getparam.
  */
 int intel_huc_check_status(struct intel_huc *huc)
 {
@@ -219,11 +427,21 @@ int intel_huc_check_status(struct intel_huc *huc)
 		return -ENOPKG;
 	case INTEL_UC_FIRMWARE_ERROR:
 		return -ENOEXEC;
+	case INTEL_UC_FIRMWARE_INIT_FAIL:
+		return -ENOMEM;
+	case INTEL_UC_FIRMWARE_LOAD_FAIL:
+		return -EIO;
 	default:
 		break;
 	}
 
-	return huc_is_authenticated(huc);
+	return intel_huc_is_authenticated(huc);
+}
+
+static bool huc_has_delayed_load(struct intel_huc *huc)
+{
+	return intel_huc_is_loaded_by_gsc(huc) &&
+	       (huc->delayed_load.status != INTEL_HUC_DELAYED_LOAD_ERROR);
 }
 
 void intel_huc_update_auth_status(struct intel_huc *huc)
@@ -231,9 +449,11 @@ void intel_huc_update_auth_status(struct intel_huc *huc)
 	if (!intel_uc_fw_is_loadable(&huc->fw))
 		return;
 
-	if (huc_is_authenticated(huc))
+	if (intel_huc_is_authenticated(huc))
 		intel_uc_fw_change_status(&huc->fw,
 					  INTEL_UC_FIRMWARE_RUNNING);
+	else if (huc_has_delayed_load(huc))
+		huc_delayed_load_start(huc);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index d7e25b6e879e..52db03620c60 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -7,9 +7,21 @@
 #define _INTEL_HUC_H_
 
 #include "i915_reg_defs.h"
+#include "i915_sw_fence.h"
 #include "intel_uc_fw.h"
 #include "intel_huc_fw.h"
 
+#include <linux/notifier.h>
+#include <linux/hrtimer.h>
+
+struct bus_type;
+
+enum intel_huc_delayed_load_status {
+	INTEL_HUC_WAITING_ON_GSC = 0,
+	INTEL_HUC_WAITING_ON_PXP,
+	INTEL_HUC_DELAYED_LOAD_ERROR,
+};
+
 struct intel_huc {
 	/* Generic uC firmware management */
 	struct intel_uc_fw fw;
@@ -20,14 +32,27 @@ struct intel_huc {
 		u32 mask;
 		u32 value;
 	} status;
+
+	struct {
+		struct i915_sw_fence fence;
+		struct hrtimer timer;
+		struct notifier_block nb;
+		enum intel_huc_delayed_load_status status;
+	} delayed_load;
 };
 
 void intel_huc_init_early(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
+void intel_huc_suspend(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc);
+int intel_huc_wait_for_auth_complete(struct intel_huc *huc);
 int intel_huc_check_status(struct intel_huc *huc);
 void intel_huc_update_auth_status(struct intel_huc *huc);
+bool intel_huc_is_authenticated(struct intel_huc *huc);
+
+void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
+void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
 
 static inline int intel_huc_sanitize(struct intel_huc *huc)
 {
@@ -56,6 +81,12 @@ static inline bool intel_huc_is_loaded_by_gsc(const struct intel_huc *huc)
 	return huc->fw.loaded_via_gsc;
 }
 
+static inline bool intel_huc_wait_required(struct intel_huc *huc)
+{
+	return intel_huc_is_used(huc) && intel_huc_is_loaded_by_gsc(huc) &&
+	       !intel_huc_is_authenticated(huc);
+}
+
 void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
index 9d6ab1e01639..4f246416db17 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -3,9 +3,43 @@
  * Copyright © 2014-2019 Intel Corporation
  */
 
+#include "gt/intel_gsc.h"
 #include "gt/intel_gt.h"
+#include "intel_huc.h"
 #include "intel_huc_fw.h"
 #include "i915_drv.h"
+#include "pxp/intel_pxp_huc.h"
+
+int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc)
+{
+	int ret;
+
+	if (!intel_huc_is_loaded_by_gsc(huc))
+		return -ENODEV;
+
+	if (!intel_uc_fw_is_loadable(&huc->fw))
+		return -ENOEXEC;
+
+	/*
+	 * If we abort a suspend, HuC might still be loaded when the mei
+	 * component gets re-bound and this function called again. If so, just
+	 * mark the HuC as loaded.
+	 */
+	if (intel_huc_is_authenticated(huc)) {
+		intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING);
+		return 0;
+	}
+
+	GEM_WARN_ON(intel_uc_fw_is_loaded(&huc->fw));
+
+	ret = intel_pxp_huc_load_and_auth(&huc_to_gt(huc)->pxp);
+	if (ret)
+		return ret;
+
+	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_TRANSFERRED);
+
+	return intel_huc_wait_for_auth_complete(huc);
+}
 
 /**
  * intel_huc_fw_upload() - load HuC uCode to device via DMA transfer
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
index 12f264ee3e0b..db42e238b45f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
@@ -8,6 +8,7 @@
 
 struct intel_huc;
 
+int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc);
 int intel_huc_fw_upload(struct intel_huc *huc);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index b91ad4aede1f..de2843dc1307 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -93,7 +93,8 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 	fw_def(BROXTON,      0, guc_mmp(bxt,  70, 1, 1)) \
 	fw_def(SKYLAKE,      0, guc_mmp(skl,  70, 1, 1))
 
-#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_raw, huc_mmp) \
+#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_raw, huc_mmp, huc_gsc) \
+	fw_def(DG2,          0, huc_gsc(dg2)) \
 	fw_def(ALDERLAKE_P,  0, huc_raw(tgl)) \
 	fw_def(ALDERLAKE_P,  0, huc_mmp(tgl,  7, 9, 3)) \
 	fw_def(ALDERLAKE_S,  0, huc_raw(tgl)) \
@@ -141,6 +142,9 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 #define MAKE_HUC_FW_PATH_BLANK(prefix_) \
 	__MAKE_UC_FW_PATH_BLANK(prefix_, "_huc")
 
+#define MAKE_HUC_FW_PATH_GSC(prefix_) \
+	__MAKE_UC_FW_PATH_BLANK(prefix_, "_huc_gsc")
+
 #define MAKE_HUC_FW_PATH_MMP(prefix_, major_, minor_, patch_) \
 	__MAKE_UC_FW_PATH_MMP(prefix_, "_huc_", major_, minor_, patch_)
 
@@ -153,7 +157,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 	MODULE_FIRMWARE(uc_);
 
 INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH_MAJOR, MAKE_GUC_FW_PATH_MMP)
-INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH_BLANK, MAKE_HUC_FW_PATH_MMP)
+INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH_BLANK, MAKE_HUC_FW_PATH_MMP, MAKE_HUC_FW_PATH_GSC)
 
 /*
  * The next expansion of the table macros (in __uc_fw_auto_select below) provides
@@ -168,6 +172,7 @@ struct __packed uc_fw_blob {
 	u8 major;
 	u8 minor;
 	u8 patch;
+	bool loaded_via_gsc;
 };
 
 #define UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \
@@ -176,16 +181,16 @@ struct __packed uc_fw_blob {
 	.patch = patch_, \
 	.path = path_,
 
-#define UC_FW_BLOB_NEW(major_, minor_, patch_, path_) \
+#define UC_FW_BLOB_NEW(major_, minor_, patch_, gsc_, path_) \
 	{ UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \
-	  .legacy = false }
+	  .legacy = false, .loaded_via_gsc = gsc_ }
 
 #define UC_FW_BLOB_OLD(major_, minor_, patch_, path_) \
 	{ UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \
 	  .legacy = true }
 
 #define GUC_FW_BLOB(prefix_, major_, minor_) \
-	UC_FW_BLOB_NEW(major_, minor_, 0, \
+	UC_FW_BLOB_NEW(major_, minor_, 0, false, \
 		       MAKE_GUC_FW_PATH_MAJOR(prefix_, major_, minor_))
 
 #define GUC_FW_BLOB_MMP(prefix_, major_, minor_, patch_) \
@@ -193,12 +198,15 @@ struct __packed uc_fw_blob {
 		       MAKE_GUC_FW_PATH_MMP(prefix_, major_, minor_, patch_))
 
 #define HUC_FW_BLOB(prefix_) \
-	UC_FW_BLOB_NEW(0, 0, 0, MAKE_HUC_FW_PATH_BLANK(prefix_))
+	UC_FW_BLOB_NEW(0, 0, 0, false, MAKE_HUC_FW_PATH_BLANK(prefix_))
 
 #define HUC_FW_BLOB_MMP(prefix_, major_, minor_, patch_) \
 	UC_FW_BLOB_OLD(major_, minor_, patch_, \
 		       MAKE_HUC_FW_PATH_MMP(prefix_, major_, minor_, patch_))
 
+#define HUC_FW_BLOB_GSC(prefix_) \
+	UC_FW_BLOB_NEW(0, 0, 0, true, MAKE_HUC_FW_PATH_GSC(prefix_))
+
 struct __packed uc_fw_platform_requirement {
 	enum intel_platform p;
 	u8 rev; /* first platform rev using this FW */
@@ -224,7 +232,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
 		INTEL_GUC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB, GUC_FW_BLOB_MMP)
 	};
 	static const struct uc_fw_platform_requirement blobs_huc[] = {
-		INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB, HUC_FW_BLOB_MMP)
+		INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB, HUC_FW_BLOB_MMP, HUC_FW_BLOB_GSC)
 	};
 	static const struct fw_blobs_by_type blobs_all[INTEL_UC_FW_NUM_TYPES] = {
 		[INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) },
@@ -272,6 +280,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
 		uc_fw->file_wanted.path = blob->path;
 		uc_fw->file_wanted.major_ver = blob->major;
 		uc_fw->file_wanted.minor_ver = blob->minor;
+		uc_fw->loaded_via_gsc = blob->loaded_via_gsc;
 		found = true;
 		break;
 	}
@@ -904,7 +913,6 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw)
 out_unpin:
 	i915_gem_object_unpin_pages(uc_fw->obj);
 out:
-	intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_INIT_FAIL);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index eef3bba8a41b..357c5b65e097 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -354,9 +354,9 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
 	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
 
 	vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size =
-		pci_resource_len(pdev, GTTMMADR_BAR);
+		pci_resource_len(pdev, GEN4_GTTMMADR_BAR);
 	vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size =
-		pci_resource_len(pdev, GTT_APERTURE_BAR);
+		pci_resource_len(pdev, GEN4_GMADR_BAR);
 
 	memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4);
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index daac2050d77d..1cb388484bf0 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -734,7 +734,7 @@ static i915_reg_t force_nonpriv_white_list[] = {
 	_MMIO(0x770c),
 	_MMIO(0x83a8),
 	_MMIO(0xb110),
-	GEN8_L3SQCREG4,//_MMIO(0xb118)
+	_MMIO(0xb118),
 	_MMIO(0xe100),
 	_MMIO(0xe18c),
 	_MMIO(0xe48c),
@@ -2257,7 +2257,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(_MMIO(0x2438), D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(_MMIO(0x243c), D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(_MMIO(0x7018), D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(HSW_HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* display */
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 1c6e941c9666..200c1162daa3 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -106,15 +106,15 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, GEN8_CS_CHICKEN1, 0xffff, true}, /* 0x2580 */
 	{RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */
 	{RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */
-	{RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */
-	{RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */
+	{RCS0, _MMIO(0xb118), 0, false}, /* GEN8_L3SQCREG4 */
+	{RCS0, _MMIO(0xb11c), 0, false}, /* GEN9_SCRATCH1 */
 	{RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */
 	{RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */
-	{RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */
-	{RCS0, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */
-	{RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
-	{RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
-	{RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
+	{RCS0, _MMIO(0xe180), 0xffff, true}, /* HALF_SLICE_CHICKEN2 */
+	{RCS0, _MMIO(0xe184), 0xffff, true}, /* GEN8_HALF_SLICE_CHICKEN3 */
+	{RCS0, _MMIO(0xe188), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN5 */
+	{RCS0, _MMIO(0xe194), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN7 */
+	{RCS0, _MMIO(0xe4f0), 0xffff, true}, /* GEN8_ROW_CHICKEN */
 	{RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */
 	{RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */
 	{RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index c459eb362c47..c3d43f9b1e45 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -81,6 +81,7 @@
 #include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_getparam.h"
+#include "i915_hwmon.h"
 #include "i915_ioc32.h"
 #include "i915_ioctl.h"
 #include "i915_irq.h"
@@ -337,7 +338,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 	if (i915_inject_probe_failure(dev_priv))
 		return -ENODEV;
 
-	intel_device_info_subplatform_init(dev_priv);
+	intel_device_info_runtime_init_early(dev_priv);
+
 	intel_step_init(dev_priv);
 
 	intel_uncore_mmio_debug_init_early(dev_priv);
@@ -353,6 +355,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->display.wm.wm_mutex);
 	mutex_init(&dev_priv->display.pps.mutex);
 	mutex_init(&dev_priv->display.hdcp.comp_mutex);
+	spin_lock_init(&dev_priv->display.dkl.phy_lock);
 
 	i915_memcpy_init_early(dev_priv);
 	intel_runtime_pm_init_early(&dev_priv->runtime_pm);
@@ -738,7 +741,6 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv)
  */
 static void i915_driver_register(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_gt *gt;
 	unsigned int i;
 
@@ -748,7 +750,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	intel_vgpu_register(dev_priv);
 
 	/* Reveal our presence to userspace */
-	if (drm_dev_register(dev, 0)) {
+	if (drm_dev_register(&dev_priv->drm, 0)) {
 		drm_err(&dev_priv->drm,
 			"Failed to register driver for userspace access!\n");
 		return;
@@ -763,6 +765,8 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	for_each_gt(gt, dev_priv, i)
 		intel_gt_driver_register(gt);
 
+	i915_hwmon_register(dev_priv);
+
 	intel_display_driver_register(dev_priv);
 
 	intel_power_domains_enable(dev_priv);
@@ -795,6 +799,8 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 	for_each_gt(gt, dev_priv, i)
 		intel_gt_driver_unregister(gt);
 
+	i915_hwmon_unregister(dev_priv);
+
 	i915_perf_unregister(dev_priv);
 	i915_pmu_unregister(dev_priv);
 
@@ -893,10 +899,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (IS_ERR(i915))
 		return PTR_ERR(i915);
 
-	/* Disable nuclear pageflip by default on pre-ILK */
-	if (!i915->params.nuclear_pageflip && DISPLAY_VER(i915) < 5)
-		i915->drm.driver_features &= ~DRIVER_ATOMIC;
-
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto out_fini;
@@ -1092,32 +1094,30 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 
 static void intel_suspend_encoders(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *encoder;
 
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
-	drm_modeset_lock_all(dev);
-	for_each_intel_encoder(dev, encoder)
+	drm_modeset_lock_all(&dev_priv->drm);
+	for_each_intel_encoder(&dev_priv->drm, encoder)
 		if (encoder->suspend)
 			encoder->suspend(encoder);
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 }
 
 static void intel_shutdown_encoders(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *encoder;
 
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
-	drm_modeset_lock_all(dev);
-	for_each_intel_encoder(dev, encoder)
+	drm_modeset_lock_all(&dev_priv->drm);
+	for_each_intel_encoder(&dev_priv->drm, encoder)
 		if (encoder->shutdown)
 			encoder->shutdown(encoder);
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 }
 
 void i915_driver_shutdown(struct drm_i915_private *i915)
@@ -1661,7 +1661,8 @@ static int intel_runtime_suspend(struct device *kdev)
 
 		intel_runtime_pm_enable_interrupts(dev_priv);
 
-		intel_gt_runtime_resume(to_gt(dev_priv));
+		for_each_gt(gt, dev_priv, i)
+			intel_gt_runtime_resume(gt);
 
 		enable_rpm_wakeref_asserts(rpm);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bdc81db76dbd..05b3300cc4ed 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -40,7 +40,6 @@
 #include "display/intel_display_core.h"
 
 #include "gem/i915_gem_context_types.h"
-#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_shrinker.h"
 #include "gem/i915_gem_stolen.h"
 
@@ -75,9 +74,6 @@ struct intel_limit;
 struct intel_overlay_error_state;
 struct vlv_s0ix_state;
 
-/* Threshold == 5 for long IRQs, 50 for short */
-#define HPD_STORM_DEFAULT_THRESHOLD 50
-
 #define I915_GEM_GPU_DOMAINS \
 	(I915_GEM_DOMAIN_RENDER | \
 	 I915_GEM_DOMAIN_SAMPLER | \
@@ -353,6 +349,8 @@ struct drm_i915_private {
 
 	struct i915_perf perf;
 
+	struct i915_hwmon *hwmon;
+
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct intel_gt gt0;
 
@@ -871,6 +869,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_DOUBLE_BUFFERED_M_N(dev_priv)	(DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
 
 #define HAS_CDCLK_CRAWL(dev_priv)	 (INTEL_INFO(dev_priv)->display.has_cdclk_crawl)
+#define HAS_CDCLK_SQUASH(dev_priv)	 (INTEL_INFO(dev_priv)->display.has_cdclk_squash)
 #define HAS_DDI(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ddi)
 #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->display.has_fpga_dbg)
 #define HAS_PSR(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_psr)
@@ -900,19 +899,17 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm)
 #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc)
 
+#define HAS_OA_BPC_REPORTING(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_oa_bpc_reporting)
+#define HAS_OA_SLICE_CONTRIB_LIMITS(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_oa_slice_contrib_limits)
+
 /*
  * Set this flag, when platform requires 64K GTT page sizes or larger for
  * device local memory access.
  */
 #define HAS_64K_PAGES(dev_priv) (INTEL_INFO(dev_priv)->has_64k_pages)
 
-/*
- * Set this flag when platform doesn't allow both 64k pages and 4k pages in
- * the same PT. this flag means we need to support compact PT layout for the
- * ppGTT when using the 64K GTT pages.
- */
-#define NEEDS_COMPACT_PT(dev_priv) (INTEL_INFO(dev_priv)->needs_compact_pt)
-
 #define HAS_IPC(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ipc)
 
 #define HAS_REGION(i915, i) (RUNTIME_INFO(i915)->memory_regions & (i))
@@ -938,6 +935,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch)
 
+#define HAS_GMD_ID(i915)	(INTEL_INFO(i915)->has_gmd_id)
+
 #define HAS_LSPCON(dev_priv) (IS_DISPLAY_VER(dev_priv, 9, 10))
 
 #define HAS_L3_CCS_READ(i915) (INTEL_INFO(i915)->has_l3_ccs_read)
@@ -976,6 +975,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_ONE_EU_PER_FUSE_BIT(i915)	(INTEL_INFO(i915)->has_one_eu_per_fuse_bit)
 
+#define HAS_LMEMBAR_SMEM_STOLEN(i915) (!HAS_LMEM(i915) && \
+				       GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+
 /* intel_device_info.c */
 static inline struct intel_device_info *
 mkwrite_device_info(struct drm_i915_private *dev_priv)
@@ -983,16 +985,4 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
 	return (struct intel_device_info *)INTEL_INFO(dev_priv);
 }
 
-static inline enum i915_map_type
-i915_coherent_map_type(struct drm_i915_private *i915,
-		       struct drm_i915_gem_object *obj, bool always_coherent)
-{
-	if (i915_gem_object_is_lmem(obj))
-		return I915_MAP_WC;
-	if (HAS_LLC(i915) || always_coherent)
-		return I915_MAP_WB;
-	else
-		return I915_MAP_WC;
-}
-
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2bdddb61ebd7..299f94a9fb87 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -843,7 +843,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 		__i915_gem_object_release_mmap_gtt(obj);
 
 	list_for_each_entry_safe(obj, on,
-				 &to_gt(i915)->lmem_userfault_list, userfault_link)
+				 &i915->runtime_pm.lmem_userfault_list, userfault_link)
 		i915_gem_object_runtime_pm_release_mmap_offset(obj);
 
 	/*
@@ -1128,6 +1128,8 @@ void i915_gem_drain_workqueue(struct drm_i915_private *i915)
 
 int i915_gem_init(struct drm_i915_private *dev_priv)
 {
+	struct intel_gt *gt;
+	unsigned int i;
 	int ret;
 
 	/* We need to fallback to 4K pages if host doesn't support huge gtt. */
@@ -1158,9 +1160,11 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_init_clock_gating(dev_priv);
 
-	ret = intel_gt_init(to_gt(dev_priv));
-	if (ret)
-		goto err_unlock;
+	for_each_gt(gt, dev_priv, i) {
+		ret = intel_gt_init(gt);
+		if (ret)
+			goto err_unlock;
+	}
 
 	return 0;
 
@@ -1173,8 +1177,13 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 err_unlock:
 	i915_gem_drain_workqueue(dev_priv);
 
-	if (ret != -EIO)
-		intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc);
+	if (ret != -EIO) {
+		for_each_gt(gt, dev_priv, i) {
+			intel_gt_driver_remove(gt);
+			intel_gt_driver_release(gt);
+			intel_uc_cleanup_firmwares(&gt->uc);
+		}
+	}
 
 	if (ret == -EIO) {
 		/*
@@ -1182,10 +1191,12 @@ err_unlock:
 		 * as wedged. But we only want to do this when the GPU is angry,
 		 * for all other failure, such as an allocation failure, bail.
 		 */
-		if (!intel_gt_is_wedged(to_gt(dev_priv))) {
-			i915_probe_error(dev_priv,
-					 "Failed to initialize GPU, declaring it wedged!\n");
-			intel_gt_set_wedged(to_gt(dev_priv));
+		for_each_gt(gt, dev_priv, i) {
+			if (!intel_gt_is_wedged(gt)) {
+				i915_probe_error(dev_priv,
+						 "Failed to initialize GPU, declaring it wedged!\n");
+				intel_gt_set_wedged(gt);
+			}
 		}
 
 		/* Minimal basic recovery for KMS */
@@ -1213,23 +1224,27 @@ void i915_gem_driver_unregister(struct drm_i915_private *i915)
 
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 {
-	intel_wakeref_auto_fini(&to_gt(dev_priv)->userfault_wakeref);
+	struct intel_gt *gt;
+	unsigned int i;
 
 	i915_gem_suspend_late(dev_priv);
-	intel_gt_driver_remove(to_gt(dev_priv));
+	for_each_gt(gt, dev_priv, i)
+		intel_gt_driver_remove(gt);
 	dev_priv->uabi_engines = RB_ROOT;
 
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
-
-	i915_gem_drain_freed_objects(dev_priv);
 }
 
 void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 {
-	intel_gt_driver_release(to_gt(dev_priv));
+	struct intel_gt *gt;
+	unsigned int i;
 
-	intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc);
+	for_each_gt(gt, dev_priv, i) {
+		intel_gt_driver_release(gt);
+		intel_uc_cleanup_firmwares(&gt->uc);
+	}
 
 	/* Flush any outstanding work, including i915_gem_context.release_work. */
 	i915_gem_drain_workqueue(dev_priv);
@@ -1259,7 +1274,7 @@ void i915_gem_init_early(struct drm_i915_private *dev_priv)
 
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
 {
-	i915_gem_drain_freed_objects(dev_priv);
+	i915_gem_drain_workqueue(dev_priv);
 	GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list));
 	GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
 	drm_WARN_ON(&dev_priv->drm, dev_priv->mm.shrink_count);
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 342c8ca6414e..3047e80e1163 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -175,6 +175,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_PERF_REVISION:
 		value = i915_perf_ioctl_version();
 		break;
+	case I915_PARAM_OA_TIMESTAMP_FREQUENCY:
+		value = i915_perf_oa_timestamp_frequency(i915);
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9ea2fe34e7d3..f2d53edcd2ee 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1221,7 +1221,10 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
 	if (GRAPHICS_VER(i915) >= 6) {
 		ee->rc_psmi = ENGINE_READ(engine, RING_PSMI_CTL);
 
-		if (GRAPHICS_VER(i915) >= 12)
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+			ee->fault_reg = intel_gt_mcr_read_any(engine->gt,
+							      XEHP_RING_FAULT_REG);
+		else if (GRAPHICS_VER(i915) >= 12)
 			ee->fault_reg = intel_uncore_read(engine->uncore,
 							  GEN12_RING_FAULT_REG);
 		else if (GRAPHICS_VER(i915) >= 8)
@@ -1820,7 +1823,12 @@ static void gt_record_global_regs(struct intel_gt_coredump *gt)
 	if (GRAPHICS_VER(i915) == 7)
 		gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
 
-	if (GRAPHICS_VER(i915) >= 12) {
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+		gt->fault_data0 = intel_gt_mcr_read_any((struct intel_gt *)gt->_gt,
+							XEHP_FAULT_TLB_DATA0);
+		gt->fault_data1 = intel_gt_mcr_read_any((struct intel_gt *)gt->_gt,
+							XEHP_FAULT_TLB_DATA1);
+	} else if (GRAPHICS_VER(i915) >= 12) {
 		gt->fault_data0 = intel_uncore_read(uncore,
 						    GEN12_FAULT_TLB_DATA0);
 		gt->fault_data1 = intel_uncore_read(uncore,
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
new file mode 100644
index 000000000000..c588a17f97e9
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_hwmon.c
@@ -0,0 +1,732 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/types.h>
+
+#include "i915_drv.h"
+#include "i915_hwmon.h"
+#include "i915_reg.h"
+#include "intel_mchbar_regs.h"
+#include "intel_pcode.h"
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_regs.h"
+
+/*
+ * SF_* - scale factors for particular quantities according to hwmon spec.
+ * - voltage  - millivolts
+ * - power  - microwatts
+ * - curr   - milliamperes
+ * - energy - microjoules
+ * - time   - milliseconds
+ */
+#define SF_VOLTAGE	1000
+#define SF_POWER	1000000
+#define SF_CURR		1000
+#define SF_ENERGY	1000000
+#define SF_TIME		1000
+
+struct hwm_reg {
+	i915_reg_t gt_perf_status;
+	i915_reg_t pkg_power_sku_unit;
+	i915_reg_t pkg_power_sku;
+	i915_reg_t pkg_rapl_limit;
+	i915_reg_t energy_status_all;
+	i915_reg_t energy_status_tile;
+};
+
+struct hwm_energy_info {
+	u32 reg_val_prev;
+	long accum_energy;			/* Accumulated energy for energy1_input */
+};
+
+struct hwm_drvdata {
+	struct i915_hwmon *hwmon;
+	struct intel_uncore *uncore;
+	struct device *hwmon_dev;
+	struct hwm_energy_info ei;		/*  Energy info for energy1_input */
+	char name[12];
+	int gt_n;
+};
+
+struct i915_hwmon {
+	struct hwm_drvdata ddat;
+	struct hwm_drvdata ddat_gt[I915_MAX_GT];
+	struct mutex hwmon_lock;		/* counter overflow logic and rmw */
+	struct hwm_reg rg;
+	int scl_shift_power;
+	int scl_shift_energy;
+	int scl_shift_time;
+};
+
+static void
+hwm_locked_with_pm_intel_uncore_rmw(struct hwm_drvdata *ddat,
+				    i915_reg_t reg, u32 clear, u32 set)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	struct intel_uncore *uncore = ddat->uncore;
+	intel_wakeref_t wakeref;
+
+	mutex_lock(&hwmon->hwmon_lock);
+
+	with_intel_runtime_pm(uncore->rpm, wakeref)
+		intel_uncore_rmw(uncore, reg, clear, set);
+
+	mutex_unlock(&hwmon->hwmon_lock);
+}
+
+/*
+ * This function's return type of u64 allows for the case where the scaling
+ * of the field taken from the 32-bit register value might cause a result to
+ * exceed 32 bits.
+ */
+static u64
+hwm_field_read_and_scale(struct hwm_drvdata *ddat, i915_reg_t rgadr,
+			 u32 field_msk, int nshift, u32 scale_factor)
+{
+	struct intel_uncore *uncore = ddat->uncore;
+	intel_wakeref_t wakeref;
+	u32 reg_value;
+
+	with_intel_runtime_pm(uncore->rpm, wakeref)
+		reg_value = intel_uncore_read(uncore, rgadr);
+
+	reg_value = REG_FIELD_GET(field_msk, reg_value);
+
+	return mul_u64_u32_shr(reg_value, scale_factor, nshift);
+}
+
+static void
+hwm_field_scale_and_write(struct hwm_drvdata *ddat, i915_reg_t rgadr,
+			  int nshift, unsigned int scale_factor, long lval)
+{
+	u32 nval;
+
+	/* Computation in 64-bits to avoid overflow. Round to nearest. */
+	nval = DIV_ROUND_CLOSEST_ULL((u64)lval << nshift, scale_factor);
+
+	hwm_locked_with_pm_intel_uncore_rmw(ddat, rgadr,
+					    PKG_PWR_LIM_1,
+					    REG_FIELD_PREP(PKG_PWR_LIM_1, nval));
+}
+
+/*
+ * hwm_energy - Obtain energy value
+ *
+ * The underlying energy hardware register is 32-bits and is subject to
+ * overflow. How long before overflow? For example, with an example
+ * scaling bit shift of 14 bits (see register *PACKAGE_POWER_SKU_UNIT) and
+ * a power draw of 1000 watts, the 32-bit counter will overflow in
+ * approximately 4.36 minutes.
+ *
+ * Examples:
+ *    1 watt:  (2^32 >> 14) /    1 W / (60 * 60 * 24) secs/day -> 3 days
+ * 1000 watts: (2^32 >> 14) / 1000 W / 60             secs/min -> 4.36 minutes
+ *
+ * The function significantly increases overflow duration (from 4.36
+ * minutes) by accumulating the energy register into a 'long' as allowed by
+ * the hwmon API. Using x86_64 128 bit arithmetic (see mul_u64_u32_shr()),
+ * a 'long' of 63 bits, SF_ENERGY of 1e6 (~20 bits) and
+ * hwmon->scl_shift_energy of 14 bits we have 57 (63 - 20 + 14) bits before
+ * energy1_input overflows. This at 1000 W is an overflow duration of 278 years.
+ */
+static void
+hwm_energy(struct hwm_drvdata *ddat, long *energy)
+{
+	struct intel_uncore *uncore = ddat->uncore;
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	struct hwm_energy_info *ei = &ddat->ei;
+	intel_wakeref_t wakeref;
+	i915_reg_t rgaddr;
+	u32 reg_val;
+
+	if (ddat->gt_n >= 0)
+		rgaddr = hwmon->rg.energy_status_tile;
+	else
+		rgaddr = hwmon->rg.energy_status_all;
+
+	mutex_lock(&hwmon->hwmon_lock);
+
+	with_intel_runtime_pm(uncore->rpm, wakeref)
+		reg_val = intel_uncore_read(uncore, rgaddr);
+
+	if (reg_val >= ei->reg_val_prev)
+		ei->accum_energy += reg_val - ei->reg_val_prev;
+	else
+		ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val;
+	ei->reg_val_prev = reg_val;
+
+	*energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY,
+				  hwmon->scl_shift_energy);
+	mutex_unlock(&hwmon->hwmon_lock);
+}
+
+static ssize_t
+hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	intel_wakeref_t wakeref;
+	u32 r, x, y, x_w = 2; /* 2 bits */
+	u64 tau4, out;
+
+	with_intel_runtime_pm(ddat->uncore->rpm, wakeref)
+		r = intel_uncore_read(ddat->uncore, hwmon->rg.pkg_rapl_limit);
+
+	x = REG_FIELD_GET(PKG_PWR_LIM_1_TIME_X, r);
+	y = REG_FIELD_GET(PKG_PWR_LIM_1_TIME_Y, r);
+	/*
+	 * tau = 1.x * power(2,y), x = bits(23:22), y = bits(21:17)
+	 *     = (4 | x) << (y - 2)
+	 * where (y - 2) ensures a 1.x fixed point representation of 1.x
+	 * However because y can be < 2, we compute
+	 *     tau4 = (4 | x) << y
+	 * but add 2 when doing the final right shift to account for units
+	 */
+	tau4 = ((1 << x_w) | x) << y;
+	/* val in hwmon interface units (millisec) */
+	out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
+
+	return sysfs_emit(buf, "%llu\n", out);
+}
+
+static ssize_t
+hwm_power1_max_interval_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	u32 x, y, rxy, x_w = 2; /* 2 bits */
+	u64 tau4, r, max_win;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	/*
+	 * Max HW supported tau in '1.x * power(2,y)' format, x = 0, y = 0x12
+	 * The hwmon->scl_shift_time default of 0xa results in a max tau of 256 seconds
+	 */
+#define PKG_MAX_WIN_DEFAULT 0x12ull
+
+	/*
+	 * val must be < max in hwmon interface units. The steps below are
+	 * explained in i915_power1_max_interval_show()
+	 */
+	r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT);
+	x = REG_FIELD_GET(PKG_MAX_WIN_X, r);
+	y = REG_FIELD_GET(PKG_MAX_WIN_Y, r);
+	tau4 = ((1 << x_w) | x) << y;
+	max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
+
+	if (val > max_win)
+		return -EINVAL;
+
+	/* val in hw units */
+	val = DIV_ROUND_CLOSEST_ULL((u64)val << hwmon->scl_shift_time, SF_TIME);
+	/* Convert to 1.x * power(2,y) */
+	if (!val)
+		return -EINVAL;
+	y = ilog2(val);
+	/* x = (val - (1 << y)) >> (y - 2); */
+	x = (val - (1ul << y)) << x_w >> y;
+
+	rxy = REG_FIELD_PREP(PKG_PWR_LIM_1_TIME_X, x) | REG_FIELD_PREP(PKG_PWR_LIM_1_TIME_Y, y);
+
+	hwm_locked_with_pm_intel_uncore_rmw(ddat, hwmon->rg.pkg_rapl_limit,
+					    PKG_PWR_LIM_1_TIME, rxy);
+	return count;
+}
+
+static SENSOR_DEVICE_ATTR(power1_max_interval, 0664,
+			  hwm_power1_max_interval_show,
+			  hwm_power1_max_interval_store, 0);
+
+static struct attribute *hwm_attributes[] = {
+	&sensor_dev_attr_power1_max_interval.dev_attr.attr,
+	NULL
+};
+
+static umode_t hwm_attributes_visible(struct kobject *kobj,
+				      struct attribute *attr, int index)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+	struct i915_hwmon *hwmon = ddat->hwmon;
+
+	if (attr == &sensor_dev_attr_power1_max_interval.dev_attr.attr)
+		return i915_mmio_reg_valid(hwmon->rg.pkg_rapl_limit) ? attr->mode : 0;
+
+	return 0;
+}
+
+static const struct attribute_group hwm_attrgroup = {
+	.attrs = hwm_attributes,
+	.is_visible = hwm_attributes_visible,
+};
+
+static const struct attribute_group *hwm_groups[] = {
+	&hwm_attrgroup,
+	NULL
+};
+
+static const struct hwmon_channel_info *hwm_info[] = {
+	HWMON_CHANNEL_INFO(in, HWMON_I_INPUT),
+	HWMON_CHANNEL_INFO(power, HWMON_P_MAX | HWMON_P_RATED_MAX | HWMON_P_CRIT),
+	HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT),
+	HWMON_CHANNEL_INFO(curr, HWMON_C_CRIT),
+	NULL
+};
+
+static const struct hwmon_channel_info *hwm_gt_info[] = {
+	HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT),
+	NULL
+};
+
+/* I1 is exposed as power_crit or as curr_crit depending on bit 31 */
+static int hwm_pcode_read_i1(struct drm_i915_private *i915, u32 *uval)
+{
+	return snb_pcode_read_p(&i915->uncore, PCODE_POWER_SETUP,
+				POWER_SETUP_SUBCOMMAND_READ_I1, 0, uval);
+}
+
+static int hwm_pcode_write_i1(struct drm_i915_private *i915, u32 uval)
+{
+	return  snb_pcode_write_p(&i915->uncore, PCODE_POWER_SETUP,
+				  POWER_SETUP_SUBCOMMAND_WRITE_I1, 0, uval);
+}
+
+static umode_t
+hwm_in_is_visible(const struct hwm_drvdata *ddat, u32 attr)
+{
+	struct drm_i915_private *i915 = ddat->uncore->i915;
+
+	switch (attr) {
+	case hwmon_in_input:
+		return IS_DG1(i915) || IS_DG2(i915) ? 0444 : 0;
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_in_read(struct hwm_drvdata *ddat, u32 attr, long *val)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	intel_wakeref_t wakeref;
+	u32 reg_value;
+
+	switch (attr) {
+	case hwmon_in_input:
+		with_intel_runtime_pm(ddat->uncore->rpm, wakeref)
+			reg_value = intel_uncore_read(ddat->uncore, hwmon->rg.gt_perf_status);
+		/* HW register value in units of 2.5 millivolt */
+		*val = DIV_ROUND_CLOSEST(REG_FIELD_GET(GEN12_VOLTAGE_MASK, reg_value) * 25, 10);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t
+hwm_power_is_visible(const struct hwm_drvdata *ddat, u32 attr, int chan)
+{
+	struct drm_i915_private *i915 = ddat->uncore->i915;
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_power_max:
+		return i915_mmio_reg_valid(hwmon->rg.pkg_rapl_limit) ? 0664 : 0;
+	case hwmon_power_rated_max:
+		return i915_mmio_reg_valid(hwmon->rg.pkg_power_sku) ? 0444 : 0;
+	case hwmon_power_crit:
+		return (hwm_pcode_read_i1(i915, &uval) ||
+			!(uval & POWER_SETUP_I1_WATTS)) ? 0 : 0644;
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_power_read(struct hwm_drvdata *ddat, u32 attr, int chan, long *val)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	int ret;
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_power_max:
+		*val = hwm_field_read_and_scale(ddat,
+						hwmon->rg.pkg_rapl_limit,
+						PKG_PWR_LIM_1,
+						hwmon->scl_shift_power,
+						SF_POWER);
+		return 0;
+	case hwmon_power_rated_max:
+		*val = hwm_field_read_and_scale(ddat,
+						hwmon->rg.pkg_power_sku,
+						PKG_PKG_TDP,
+						hwmon->scl_shift_power,
+						SF_POWER);
+		return 0;
+	case hwmon_power_crit:
+		ret = hwm_pcode_read_i1(ddat->uncore->i915, &uval);
+		if (ret)
+			return ret;
+		if (!(uval & POWER_SETUP_I1_WATTS))
+			return -ENODEV;
+		*val = mul_u64_u32_shr(REG_FIELD_GET(POWER_SETUP_I1_DATA_MASK, uval),
+				       SF_POWER, POWER_SETUP_I1_SHIFT);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+hwm_power_write(struct hwm_drvdata *ddat, u32 attr, int chan, long val)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_power_max:
+		hwm_field_scale_and_write(ddat,
+					  hwmon->rg.pkg_rapl_limit,
+					  hwmon->scl_shift_power,
+					  SF_POWER, val);
+		return 0;
+	case hwmon_power_crit:
+		uval = DIV_ROUND_CLOSEST_ULL(val << POWER_SETUP_I1_SHIFT, SF_POWER);
+		return hwm_pcode_write_i1(ddat->uncore->i915, uval);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t
+hwm_energy_is_visible(const struct hwm_drvdata *ddat, u32 attr)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	i915_reg_t rgaddr;
+
+	switch (attr) {
+	case hwmon_energy_input:
+		if (ddat->gt_n >= 0)
+			rgaddr = hwmon->rg.energy_status_tile;
+		else
+			rgaddr = hwmon->rg.energy_status_all;
+		return i915_mmio_reg_valid(rgaddr) ? 0444 : 0;
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_energy_read(struct hwm_drvdata *ddat, u32 attr, long *val)
+{
+	switch (attr) {
+	case hwmon_energy_input:
+		hwm_energy(ddat, val);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t
+hwm_curr_is_visible(const struct hwm_drvdata *ddat, u32 attr)
+{
+	struct drm_i915_private *i915 = ddat->uncore->i915;
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_curr_crit:
+		return (hwm_pcode_read_i1(i915, &uval) ||
+			(uval & POWER_SETUP_I1_WATTS)) ? 0 : 0644;
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_curr_read(struct hwm_drvdata *ddat, u32 attr, long *val)
+{
+	int ret;
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_curr_crit:
+		ret = hwm_pcode_read_i1(ddat->uncore->i915, &uval);
+		if (ret)
+			return ret;
+		if (uval & POWER_SETUP_I1_WATTS)
+			return -ENODEV;
+		*val = mul_u64_u32_shr(REG_FIELD_GET(POWER_SETUP_I1_DATA_MASK, uval),
+				       SF_CURR, POWER_SETUP_I1_SHIFT);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+hwm_curr_write(struct hwm_drvdata *ddat, u32 attr, long val)
+{
+	u32 uval;
+
+	switch (attr) {
+	case hwmon_curr_crit:
+		uval = DIV_ROUND_CLOSEST_ULL(val << POWER_SETUP_I1_SHIFT, SF_CURR);
+		return hwm_pcode_write_i1(ddat->uncore->i915, uval);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t
+hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type,
+	       u32 attr, int channel)
+{
+	struct hwm_drvdata *ddat = (struct hwm_drvdata *)drvdata;
+
+	switch (type) {
+	case hwmon_in:
+		return hwm_in_is_visible(ddat, attr);
+	case hwmon_power:
+		return hwm_power_is_visible(ddat, attr, channel);
+	case hwmon_energy:
+		return hwm_energy_is_visible(ddat, attr);
+	case hwmon_curr:
+		return hwm_curr_is_visible(ddat, attr);
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+	 int channel, long *val)
+{
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_in:
+		return hwm_in_read(ddat, attr, val);
+	case hwmon_power:
+		return hwm_power_read(ddat, attr, channel, val);
+	case hwmon_energy:
+		return hwm_energy_read(ddat, attr, val);
+	case hwmon_curr:
+		return hwm_curr_read(ddat, attr, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+hwm_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+	  int channel, long val)
+{
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_power:
+		return hwm_power_write(ddat, attr, channel, val);
+	case hwmon_curr:
+		return hwm_curr_write(ddat, attr, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops hwm_ops = {
+	.is_visible = hwm_is_visible,
+	.read = hwm_read,
+	.write = hwm_write,
+};
+
+static const struct hwmon_chip_info hwm_chip_info = {
+	.ops = &hwm_ops,
+	.info = hwm_info,
+};
+
+static umode_t
+hwm_gt_is_visible(const void *drvdata, enum hwmon_sensor_types type,
+		  u32 attr, int channel)
+{
+	struct hwm_drvdata *ddat = (struct hwm_drvdata *)drvdata;
+
+	switch (type) {
+	case hwmon_energy:
+		return hwm_energy_is_visible(ddat, attr);
+	default:
+		return 0;
+	}
+}
+
+static int
+hwm_gt_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+	    int channel, long *val)
+{
+	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_energy:
+		return hwm_energy_read(ddat, attr, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops hwm_gt_ops = {
+	.is_visible = hwm_gt_is_visible,
+	.read = hwm_gt_read,
+};
+
+static const struct hwmon_chip_info hwm_gt_chip_info = {
+	.ops = &hwm_gt_ops,
+	.info = hwm_gt_info,
+};
+
+static void
+hwm_get_preregistration_info(struct drm_i915_private *i915)
+{
+	struct i915_hwmon *hwmon = i915->hwmon;
+	struct intel_uncore *uncore = &i915->uncore;
+	struct hwm_drvdata *ddat = &hwmon->ddat;
+	intel_wakeref_t wakeref;
+	u32 val_sku_unit = 0;
+	struct intel_gt *gt;
+	long energy;
+	int i;
+
+	/* Available for all Gen12+/dGfx */
+	hwmon->rg.gt_perf_status = GEN12_RPSTAT1;
+
+	if (IS_DG1(i915) || IS_DG2(i915)) {
+		hwmon->rg.pkg_power_sku_unit = PCU_PACKAGE_POWER_SKU_UNIT;
+		hwmon->rg.pkg_power_sku = PCU_PACKAGE_POWER_SKU;
+		hwmon->rg.pkg_rapl_limit = PCU_PACKAGE_RAPL_LIMIT;
+		hwmon->rg.energy_status_all = PCU_PACKAGE_ENERGY_STATUS;
+		hwmon->rg.energy_status_tile = INVALID_MMIO_REG;
+	} else if (IS_XEHPSDV(i915)) {
+		hwmon->rg.pkg_power_sku_unit = GT0_PACKAGE_POWER_SKU_UNIT;
+		hwmon->rg.pkg_power_sku = INVALID_MMIO_REG;
+		hwmon->rg.pkg_rapl_limit = GT0_PACKAGE_RAPL_LIMIT;
+		hwmon->rg.energy_status_all = GT0_PLATFORM_ENERGY_STATUS;
+		hwmon->rg.energy_status_tile = GT0_PACKAGE_ENERGY_STATUS;
+	} else {
+		hwmon->rg.pkg_power_sku_unit = INVALID_MMIO_REG;
+		hwmon->rg.pkg_power_sku = INVALID_MMIO_REG;
+		hwmon->rg.pkg_rapl_limit = INVALID_MMIO_REG;
+		hwmon->rg.energy_status_all = INVALID_MMIO_REG;
+		hwmon->rg.energy_status_tile = INVALID_MMIO_REG;
+	}
+
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		/*
+		 * The contents of register hwmon->rg.pkg_power_sku_unit do not change,
+		 * so read it once and store the shift values.
+		 */
+		if (i915_mmio_reg_valid(hwmon->rg.pkg_power_sku_unit))
+			val_sku_unit = intel_uncore_read(uncore,
+							 hwmon->rg.pkg_power_sku_unit);
+	}
+
+	hwmon->scl_shift_power = REG_FIELD_GET(PKG_PWR_UNIT, val_sku_unit);
+	hwmon->scl_shift_energy = REG_FIELD_GET(PKG_ENERGY_UNIT, val_sku_unit);
+	hwmon->scl_shift_time = REG_FIELD_GET(PKG_TIME_UNIT, val_sku_unit);
+
+	/*
+	 * Initialize 'struct hwm_energy_info', i.e. set fields to the
+	 * first value of the energy register read
+	 */
+	if (i915_mmio_reg_valid(hwmon->rg.energy_status_all))
+		hwm_energy(ddat, &energy);
+	if (i915_mmio_reg_valid(hwmon->rg.energy_status_tile)) {
+		for_each_gt(gt, i915, i)
+			hwm_energy(&hwmon->ddat_gt[i], &energy);
+	}
+}
+
+void i915_hwmon_register(struct drm_i915_private *i915)
+{
+	struct device *dev = i915->drm.dev;
+	struct i915_hwmon *hwmon;
+	struct device *hwmon_dev;
+	struct hwm_drvdata *ddat;
+	struct hwm_drvdata *ddat_gt;
+	struct intel_gt *gt;
+	int i;
+
+	/* hwmon is available only for dGfx */
+	if (!IS_DGFX(i915))
+		return;
+
+	hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return;
+
+	i915->hwmon = hwmon;
+	mutex_init(&hwmon->hwmon_lock);
+	ddat = &hwmon->ddat;
+
+	ddat->hwmon = hwmon;
+	ddat->uncore = &i915->uncore;
+	snprintf(ddat->name, sizeof(ddat->name), "i915");
+	ddat->gt_n = -1;
+
+	for_each_gt(gt, i915, i) {
+		ddat_gt = hwmon->ddat_gt + i;
+
+		ddat_gt->hwmon = hwmon;
+		ddat_gt->uncore = gt->uncore;
+		snprintf(ddat_gt->name, sizeof(ddat_gt->name), "i915_gt%u", i);
+		ddat_gt->gt_n = i;
+	}
+
+	hwm_get_preregistration_info(i915);
+
+	/*  hwmon_dev points to device hwmon<i> */
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat->name,
+							 ddat,
+							 &hwm_chip_info,
+							 hwm_groups);
+	if (IS_ERR(hwmon_dev)) {
+		i915->hwmon = NULL;
+		return;
+	}
+
+	ddat->hwmon_dev = hwmon_dev;
+
+	for_each_gt(gt, i915, i) {
+		ddat_gt = hwmon->ddat_gt + i;
+		/*
+		 * Create per-gt directories only if a per-gt attribute is
+		 * visible. Currently this is only energy
+		 */
+		if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0))
+			continue;
+
+		hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name,
+								 ddat_gt,
+								 &hwm_gt_chip_info,
+								 NULL);
+		if (!IS_ERR(hwmon_dev))
+			ddat_gt->hwmon_dev = hwmon_dev;
+	}
+}
+
+void i915_hwmon_unregister(struct drm_i915_private *i915)
+{
+	fetch_and_zero(&i915->hwmon);
+}
diff --git a/drivers/gpu/drm/i915/i915_hwmon.h b/drivers/gpu/drm/i915/i915_hwmon.h
new file mode 100644
index 000000000000..7ca9cf2c34c9
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_hwmon.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: MIT */
+
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __I915_HWMON_H__
+#define __I915_HWMON_H__
+
+struct drm_i915_private;
+
+#if IS_REACHABLE(CONFIG_HWMON)
+void i915_hwmon_register(struct drm_i915_private *i915);
+void i915_hwmon_unregister(struct drm_i915_private *i915);
+#else
+static inline void i915_hwmon_register(struct drm_i915_private *i915) { };
+static inline void i915_hwmon_unregister(struct drm_i915_private *i915) { };
+#endif
+
+#endif /* __I915_HWMON_H__ */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 86a42d9e8041..d68859866bf2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -325,15 +325,10 @@ i915_hotplug_interrupt_update_locked(struct drm_i915_private *dev_priv,
 				     u32 mask,
 				     u32 bits)
 {
-	u32 val;
-
 	lockdep_assert_held(&dev_priv->irq_lock);
 	drm_WARN_ON(&dev_priv->drm, bits & ~mask);
 
-	val = intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_EN);
-	val &= ~mask;
-	val |= bits;
-	intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_EN, val);
+	intel_uncore_rmw(&dev_priv->uncore, PORT_HOTPLUG_EN, mask, bits);
 }
 
 /**
@@ -1057,8 +1052,8 @@ static void ivb_parity_work(struct work_struct *work)
 	if (drm_WARN_ON(&dev_priv->drm, !dev_priv->l3_parity.which_slice))
 		goto out;
 
-	misccpctl = intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL);
-	intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+	misccpctl = intel_uncore_rmw(&dev_priv->uncore, GEN7_MISCCPCTL,
+				     GEN7_DOP_CLOCK_GATE_ENABLE, 0);
 	intel_uncore_posting_read(&dev_priv->uncore, GEN7_MISCCPCTL);
 
 	while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) {
@@ -1689,8 +1684,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		 * bits this time around.
 		 */
 		intel_uncore_write(&dev_priv->uncore, VLV_MASTER_IER, 0);
-		ier = intel_uncore_read(&dev_priv->uncore, VLV_IER);
-		intel_uncore_write(&dev_priv->uncore, VLV_IER, 0);
+		ier = intel_uncore_rmw(&dev_priv->uncore, VLV_IER, ~0, 0);
 
 		if (gt_iir)
 			intel_uncore_write(&dev_priv->uncore, GTIIR, gt_iir);
@@ -1775,8 +1769,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		 * bits this time around.
 		 */
 		intel_uncore_write(&dev_priv->uncore, GEN8_MASTER_IRQ, 0);
-		ier = intel_uncore_read(&dev_priv->uncore, VLV_IER);
-		intel_uncore_write(&dev_priv->uncore, VLV_IER, 0);
+		ier = intel_uncore_rmw(&dev_priv->uncore, VLV_IER, ~0, 0);
 
 		gen8_gt_irq_handler(to_gt(dev_priv), master_ctl);
 
@@ -1981,8 +1974,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	if (ddi_hotplug_trigger) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_DDI);
-		intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_DDI, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   ddi_hotplug_trigger, dig_hotplug_reg,
@@ -1993,8 +1985,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	if (tc_hotplug_trigger) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_TC);
-		intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_TC, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_TC, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   tc_hotplug_trigger, dig_hotplug_reg,
@@ -2019,8 +2010,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	if (hotplug_trigger) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG);
-		intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   hotplug_trigger, dig_hotplug_reg,
@@ -2031,8 +2021,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	if (hotplug2_trigger) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG2);
-		intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG2, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG2, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   hotplug2_trigger, dig_hotplug_reg,
@@ -2052,8 +2041,7 @@ static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv,
 {
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
-	dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL);
-	intel_uncore_write(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg);
+	dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, 0, 0);
 
 	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 			   hotplug_trigger, dig_hotplug_reg,
@@ -2232,8 +2220,7 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
 {
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
-	dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG);
-	intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, dig_hotplug_reg);
+	dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, 0, 0);
 
 	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 			   hotplug_trigger, dig_hotplug_reg,
@@ -2252,8 +2239,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 	if (trigger_tc) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL);
-		intel_uncore_write(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   trigger_tc, dig_hotplug_reg,
@@ -2264,8 +2250,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 	if (trigger_tbt) {
 		u32 dig_hotplug_reg;
 
-		dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL);
-		intel_uncore_write(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, dig_hotplug_reg);
+		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, 0, 0);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   trigger_tbt, dig_hotplug_reg,
@@ -2355,8 +2340,7 @@ gen8_de_misc_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 			else
 				iir_reg = EDP_PSR_IIR;
 
-			psr_iir = intel_uncore_read(&dev_priv->uncore, iir_reg);
-			intel_uncore_write(&dev_priv->uncore, iir_reg, psr_iir);
+			psr_iir = intel_uncore_rmw(&dev_priv->uncore, iir_reg, 0, 0);
 
 			if (psr_iir)
 				found = true;
@@ -2426,8 +2410,7 @@ static void gen11_dsi_te_interrupt_handler(struct drm_i915_private *dev_priv,
 
 	/* clear TE in dsi IIR */
 	port = (te_trigger & DSI1_TE) ? PORT_B : PORT_A;
-	tmp = intel_uncore_read(&dev_priv->uncore, DSI_INTR_IDENT_REG(port));
-	intel_uncore_write(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), tmp);
+	tmp = intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), 0, 0);
 }
 
 static u32 gen8_de_pipe_flip_done_mask(struct drm_i915_private *i915)
@@ -2884,7 +2867,6 @@ static bool gen11_dsi_configure_te(struct intel_crtc *intel_crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	enum port port;
-	u32 tmp;
 
 	if (!(intel_crtc->mode_flags &
 	    (I915_MODE_FLAG_DSI_USE_TE1 | I915_MODE_FLAG_DSI_USE_TE0)))
@@ -2896,16 +2878,10 @@ static bool gen11_dsi_configure_te(struct intel_crtc *intel_crtc,
 	else
 		port = PORT_A;
 
-	tmp =  intel_uncore_read(&dev_priv->uncore, DSI_INTR_MASK_REG(port));
-	if (enable)
-		tmp &= ~DSI_TE_EVENT;
-	else
-		tmp |= DSI_TE_EVENT;
-
-	intel_uncore_write(&dev_priv->uncore, DSI_INTR_MASK_REG(port), tmp);
+	intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_MASK_REG(port), DSI_TE_EVENT,
+			 enable ? 0 : DSI_TE_EVENT);
 
-	tmp = intel_uncore_read(&dev_priv->uncore, DSI_INTR_IDENT_REG(port));
-	intel_uncore_write(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), tmp);
+	intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), 0, 0);
 
 	return true;
 }
@@ -3020,7 +2996,7 @@ static void vlv_display_irq_reset(struct drm_i915_private *dev_priv)
 		intel_uncore_write(uncore, DPINVGTT, DPINVGTT_STATUS_MASK_VLV);
 
 	i915_hotplug_interrupt_update_locked(dev_priv, 0xffffffff, 0);
-	intel_uncore_write(uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT));
+	intel_uncore_rmw(uncore, PORT_HOTPLUG_STAT, 0, 0);
 
 	i9xx_pipestat_irq_reset(dev_priv);
 
@@ -3118,7 +3094,7 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
-	gen8_master_intr_disable(dev_priv->uncore.regs);
+	gen8_master_intr_disable(uncore->regs);
 
 	gen8_gt_irq_reset(to_gt(dev_priv));
 	gen8_display_irq_reset(dev_priv);
@@ -3250,7 +3226,7 @@ static void cherryview_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
-	intel_uncore_write(&dev_priv->uncore, GEN8_MASTER_IRQ, 0);
+	intel_uncore_write(uncore, GEN8_MASTER_IRQ, 0);
 	intel_uncore_posting_read(&dev_priv->uncore, GEN8_MASTER_IRQ);
 
 	gen8_gt_irq_reset(to_gt(dev_priv));
@@ -3290,23 +3266,20 @@ static u32 ibx_hotplug_enables(struct drm_i915_private *i915,
 
 static void ibx_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
 	/*
 	 * Enable digital hotplug on the PCH, and configure the DP short pulse
 	 * duration to 2ms (which is the minimum in the Display Port spec).
 	 * The pulse duration bits are reserved on LPT+.
 	 */
-	hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG);
-	hotplug &= ~(PORTA_HOTPLUG_ENABLE |
-		     PORTB_HOTPLUG_ENABLE |
-		     PORTC_HOTPLUG_ENABLE |
-		     PORTD_HOTPLUG_ENABLE |
-		     PORTB_PULSE_DURATION_MASK |
-		     PORTC_PULSE_DURATION_MASK |
-		     PORTD_PULSE_DURATION_MASK);
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, ibx_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG,
+			 PORTA_HOTPLUG_ENABLE |
+			 PORTB_HOTPLUG_ENABLE |
+			 PORTC_HOTPLUG_ENABLE |
+			 PORTD_HOTPLUG_ENABLE |
+			 PORTB_PULSE_DURATION_MASK |
+			 PORTC_PULSE_DURATION_MASK |
+			 PORTD_PULSE_DURATION_MASK,
+			 intel_hpd_hotplug_enables(dev_priv, ibx_hotplug_enables));
 }
 
 static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -3353,30 +3326,24 @@ static u32 icp_tc_hotplug_enables(struct drm_i915_private *i915,
 
 static void icp_ddi_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
-	hotplug = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_DDI);
-	hotplug &= ~(SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_A) |
-		     SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_B) |
-		     SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_C) |
-		     SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_D));
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, icp_ddi_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_DDI, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI,
+			 SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_A) |
+			 SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_B) |
+			 SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_C) |
+			 SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_D),
+			 intel_hpd_hotplug_enables(dev_priv, icp_ddi_hotplug_enables));
 }
 
 static void icp_tc_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
-	hotplug = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_TC);
-	hotplug &= ~(ICP_TC_HPD_ENABLE(HPD_PORT_TC1) |
-		     ICP_TC_HPD_ENABLE(HPD_PORT_TC2) |
-		     ICP_TC_HPD_ENABLE(HPD_PORT_TC3) |
-		     ICP_TC_HPD_ENABLE(HPD_PORT_TC4) |
-		     ICP_TC_HPD_ENABLE(HPD_PORT_TC5) |
-		     ICP_TC_HPD_ENABLE(HPD_PORT_TC6));
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, icp_tc_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_TC, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_TC,
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC1) |
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC2) |
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC3) |
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC4) |
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC5) |
+			 ICP_TC_HPD_ENABLE(HPD_PORT_TC6),
+			 intel_hpd_hotplug_enables(dev_priv, icp_tc_hotplug_enables));
 }
 
 static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -3411,62 +3378,54 @@ static u32 gen11_hotplug_enables(struct drm_i915_private *i915,
 	}
 }
 
-static void dg1_hpd_irq_setup(struct drm_i915_private *dev_priv)
+static void dg1_hpd_invert(struct drm_i915_private *i915)
 {
-	u32 val;
-
-	val = intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN1);
-	val |= (INVERT_DDIA_HPD |
-		INVERT_DDIB_HPD |
-		INVERT_DDIC_HPD |
-		INVERT_DDID_HPD);
-	intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN1, val);
+	u32 val = (INVERT_DDIA_HPD |
+		   INVERT_DDIB_HPD |
+		   INVERT_DDIC_HPD |
+		   INVERT_DDID_HPD);
+	intel_uncore_rmw(&i915->uncore, SOUTH_CHICKEN1, 0, val);
+}
 
+static void dg1_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	dg1_hpd_invert(dev_priv);
 	icp_hpd_irq_setup(dev_priv);
 }
 
 static void gen11_tc_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
-	hotplug = intel_uncore_read(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL);
-	hotplug &= ~(GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6));
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL,
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6),
+			 intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables));
 }
 
 static void gen11_tbt_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
-	hotplug = intel_uncore_read(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL);
-	hotplug &= ~(GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) |
-		     GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6));
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL,
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) |
+			 GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6),
+			 intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables));
 }
 
 static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
-	u32 val;
 
 	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.hpd);
 	hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.hpd);
 
-	val = intel_uncore_read(&dev_priv->uncore, GEN11_DE_HPD_IMR);
-	val &= ~hotplug_irqs;
-	val |= ~enabled_irqs & hotplug_irqs;
-	intel_uncore_write(&dev_priv->uncore, GEN11_DE_HPD_IMR, val);
+	intel_uncore_rmw(&dev_priv->uncore, GEN11_DE_HPD_IMR, hotplug_irqs,
+			 ~enabled_irqs & hotplug_irqs);
 	intel_uncore_posting_read(&dev_priv->uncore, GEN11_DE_HPD_IMR);
 
 	gen11_tc_hpd_detection_setup(dev_priv);
@@ -3506,29 +3465,22 @@ static u32 spt_hotplug2_enables(struct drm_i915_private *i915,
 
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 val, hotplug;
-
 	/* Display WA #1179 WaHardHangonHotPlug: cnp */
 	if (HAS_PCH_CNP(dev_priv)) {
-		val = intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN1);
-		val &= ~CHASSIS_CLK_REQ_DURATION_MASK;
-		val |= CHASSIS_CLK_REQ_DURATION(0xf);
-		intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN1, val);
+		intel_uncore_rmw(&dev_priv->uncore, SOUTH_CHICKEN1, CHASSIS_CLK_REQ_DURATION_MASK,
+				 CHASSIS_CLK_REQ_DURATION(0xf));
 	}
 
 	/* Enable digital hotplug on the PCH */
-	hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG);
-	hotplug &= ~(PORTA_HOTPLUG_ENABLE |
-		     PORTB_HOTPLUG_ENABLE |
-		     PORTC_HOTPLUG_ENABLE |
-		     PORTD_HOTPLUG_ENABLE);
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, spt_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG,
+			 PORTA_HOTPLUG_ENABLE |
+			 PORTB_HOTPLUG_ENABLE |
+			 PORTC_HOTPLUG_ENABLE |
+			 PORTD_HOTPLUG_ENABLE,
+			 intel_hpd_hotplug_enables(dev_priv, spt_hotplug_enables));
 
-	hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG2);
-	hotplug &= ~PORTE_HOTPLUG_ENABLE;
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, spt_hotplug2_enables);
-	intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG2, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG2, PORTE_HOTPLUG_ENABLE,
+			 intel_hpd_hotplug_enables(dev_priv, spt_hotplug2_enables));
 }
 
 static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -3560,18 +3512,14 @@ static u32 ilk_hotplug_enables(struct drm_i915_private *i915,
 
 static void ilk_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
 	/*
 	 * Enable digital hotplug on the CPU, and configure the DP short pulse
 	 * duration to 2ms (which is the minimum in the Display Port spec)
 	 * The pulse duration bits are reserved on HSW+.
 	 */
-	hotplug = intel_uncore_read(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL);
-	hotplug &= ~(DIGITAL_PORTA_HOTPLUG_ENABLE |
-		     DIGITAL_PORTA_PULSE_DURATION_MASK);
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, ilk_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL,
+			 DIGITAL_PORTA_HOTPLUG_ENABLE | DIGITAL_PORTA_PULSE_DURATION_MASK,
+			 intel_hpd_hotplug_enables(dev_priv, ilk_hotplug_enables));
 }
 
 static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -3619,17 +3567,12 @@ static u32 bxt_hotplug_enables(struct drm_i915_private *i915,
 
 static void bxt_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug;
-
-	hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG);
-	hotplug &= ~(PORTA_HOTPLUG_ENABLE |
-		     PORTB_HOTPLUG_ENABLE |
-		     PORTC_HOTPLUG_ENABLE |
-		     BXT_DDIA_HPD_INVERT |
-		     BXT_DDIB_HPD_INVERT |
-		     BXT_DDIC_HPD_INVERT);
-	hotplug |= intel_hpd_hotplug_enables(dev_priv, bxt_hotplug_enables);
-	intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug);
+	intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG,
+			 PORTA_HOTPLUG_ENABLE |
+			 PORTB_HOTPLUG_ENABLE |
+			 PORTC_HOTPLUG_ENABLE |
+			 BXT_DDI_HPD_INVERT_MASK,
+			 intel_hpd_hotplug_enables(dev_priv, bxt_hotplug_enables));
 }
 
 static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -4009,9 +3952,7 @@ static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv,
 {
 	u32 emr;
 
-	*eir = intel_uncore_read(&dev_priv->uncore, EIR);
-
-	intel_uncore_write(&dev_priv->uncore, EIR, *eir);
+	*eir = intel_uncore_rmw(&dev_priv->uncore, EIR, 0, 0);
 
 	*eir_stuck = intel_uncore_read(&dev_priv->uncore, EIR);
 	if (*eir_stuck == 0)
@@ -4027,8 +3968,7 @@ static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv,
 	 * (or by a GPU reset) so we mask any bit that
 	 * remains set.
 	 */
-	emr = intel_uncore_read(&dev_priv->uncore, EMR);
-	intel_uncore_write(&dev_priv->uncore, EMR, 0xffffffff);
+	emr = intel_uncore_rmw(&dev_priv->uncore, EMR, ~0, 0xffffffff);
 	intel_uncore_write(&dev_priv->uncore, EMR, emr | *eir_stuck);
 }
 
@@ -4095,7 +4035,7 @@ static void i915_irq_reset(struct drm_i915_private *dev_priv)
 
 	if (I915_HAS_HOTPLUG(dev_priv)) {
 		i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
-		intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT));
+		intel_uncore_rmw(&dev_priv->uncore, PORT_HOTPLUG_STAT, 0, 0);
 	}
 
 	i9xx_pipestat_irq_reset(dev_priv);
@@ -4109,8 +4049,8 @@ static void i915_irq_postinstall(struct drm_i915_private *dev_priv)
 	struct intel_uncore *uncore = &dev_priv->uncore;
 	u32 enable_mask;
 
-	intel_uncore_write(&dev_priv->uncore, EMR, ~(I915_ERROR_PAGE_TABLE |
-			  I915_ERROR_MEMORY_REFRESH));
+	intel_uncore_write(uncore, EMR, ~(I915_ERROR_PAGE_TABLE |
+					  I915_ERROR_MEMORY_REFRESH));
 
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask =
@@ -4205,7 +4145,7 @@ static void i965_irq_reset(struct drm_i915_private *dev_priv)
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
 	i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
-	intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT));
+	intel_uncore_rmw(uncore, PORT_HOTPLUG_STAT, 0, 0);
 
 	i9xx_pipestat_irq_reset(dev_priv);
 
@@ -4232,7 +4172,7 @@ static void i965_irq_postinstall(struct drm_i915_private *dev_priv)
 		error_mask = ~(I915_ERROR_PAGE_TABLE |
 			       I915_ERROR_MEMORY_REFRESH);
 	}
-	intel_uncore_write(&dev_priv->uncore, EMR, error_mask);
+	intel_uncore_write(uncore, EMR, error_mask);
 
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask =
@@ -4383,7 +4323,6 @@ void intel_hpd_irq_setup(struct drm_i915_private *i915)
  */
 void intel_irq_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	int i;
 
 	INIT_WORK(&dev_priv->l3_parity.error_work, ivb_parity_work);
@@ -4399,9 +4338,9 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 
 	intel_hpd_init_pins(dev_priv);
 
-	intel_hpd_init_work(dev_priv);
+	intel_hpd_init_early(dev_priv);
 
-	dev->vblank_disable_immediate = true;
+	dev_priv->drm.vblank_disable_immediate = true;
 
 	/* Most platforms treat the display irq block as an always-on
 	 * power domain. vlv/chv can disable it at runtime and need
@@ -4413,15 +4352,6 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		dev_priv->display_irqs_enabled = false;
 
-	dev_priv->display.hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD;
-	/* If we have MST support, we want to avoid doing short HPD IRQ storm
-	 * detection, as short HPD storms will occur as a natural part of
-	 * sideband messaging with MST.
-	 * On older platforms however, IRQ storms can occur with both long and
-	 * short pulses, as seen on some G4x systems.
-	 */
-	dev_priv->display.hotplug.hpd_short_storm_enabled = !HAS_DP_MST(dev_priv);
-
 	if (HAS_GMCH(dev_priv)) {
 		if (I915_HAS_HOTPLUG(dev_priv))
 			dev_priv->display.funcs.hotplug = &i915_hpd_funcs;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index cd4487a1d3be..211913be40ce 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1023,6 +1023,8 @@ static const struct intel_device_info adl_p_info = {
 	.has_logical_ring_contexts = 1, \
 	.has_logical_ring_elsq = 1, \
 	.has_mslice_steering = 1, \
+	.has_oa_bpc_reporting = 1, \
+	.has_oa_slice_contrib_limits = 1, \
 	.has_rc6 = 1, \
 	.has_reset_engine = 1, \
 	.has_rps = 1, \
@@ -1042,7 +1044,6 @@ static const struct intel_device_info xehpsdv_info = {
 	PLATFORM(INTEL_XEHPSDV),
 	NO_DISPLAY,
 	.has_64k_pages = 1,
-	.needs_compact_pt = 1,
 	.has_media_ratio_mode = 1,
 	.__runtime.platform_engine_mask =
 		BIT(RCS0) | BIT(BCS0) |
@@ -1064,8 +1065,8 @@ static const struct intel_device_info xehpsdv_info = {
 	.has_64k_pages = 1, \
 	.has_guc_deprivilege = 1, \
 	.has_heci_pxp = 1, \
-	.needs_compact_pt = 1, \
 	.has_media_ratio_mode = 1, \
+	.display.has_cdclk_squash = 1, \
 	.__runtime.platform_engine_mask = \
 		BIT(RCS0) | BIT(BCS0) | \
 		BIT(VECS0) | BIT(VECS1) | \
@@ -1144,6 +1145,8 @@ static const struct intel_device_info mtl_info = {
 	.display.has_modular_fia = 1,
 	.extra_gt_list = xelpmp_extra_gt,
 	.has_flat_ccs = 0,
+	.has_gmd_id = 1,
+	.has_mslice_steering = 0,
 	.has_snoop = 1,
 	.__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
 	.__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0),
@@ -1296,9 +1299,7 @@ bool i915_pci_resource_valid(struct pci_dev *pdev, int bar)
 
 static bool intel_mmio_bar_valid(struct pci_dev *pdev, struct intel_device_info *intel_info)
 {
-	int gttmmaddr_bar = intel_info->__runtime.graphics.ip.ver == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR;
-
-	return i915_pci_resource_valid(pdev, gttmmaddr_bar);
+	return i915_pci_resource_valid(pdev, intel_mmio_bar(intel_info->__runtime.graphics.ip.ver));
 }
 
 static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0defbb43ceea..0dd597a7a11f 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -204,10 +204,12 @@
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_clock_utils.h"
+#include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_lrc.h"
 #include "gt/intel_lrc_reg.h"
 #include "gt/intel_ring.h"
+#include "gt/uc/intel_guc_slpc.h"
 
 #include "i915_drv.h"
 #include "i915_file_private.h"
@@ -286,6 +288,7 @@ static u32 i915_perf_stream_paranoid = true;
 #define OAREPORT_REASON_CTX_SWITCH     (1<<3)
 #define OAREPORT_REASON_CLK_RATIO      (1<<5)
 
+#define HAS_MI_SET_PREDICATE(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 
 /* For sysctl proc_dointvec_minmax of i915_oa_max_sample_rate
  *
@@ -320,6 +323,8 @@ static const struct i915_oa_format oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A12]		    = { 0, 64 },
 	[I915_OA_FORMAT_A12_B8_C8]	    = { 2, 128 },
 	[I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 },
+	[I915_OAR_FORMAT_A32u40_A4u32_B8_C8]    = { 5, 256 },
+	[I915_OA_FORMAT_A24u40_A14u32_B8_C8]    = { 5, 256 },
 };
 
 #define SAMPLE_OA_REPORT      (1<<0)
@@ -462,7 +467,7 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
 static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 {
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	unsigned long flags;
 	bool pollin;
 	u32 hw_tail;
@@ -599,7 +604,7 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 			    size_t *offset,
 			    const u8 *report)
 {
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	struct drm_i915_perf_record_header header;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
@@ -649,14 +654,13 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t *offset)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	u32 mask = (OA_BUFFER_SIZE - 1);
 	size_t start_offset = *offset;
 	unsigned long flags;
 	u32 head, tail;
-	u32 taken;
 	int ret = 0;
 
 	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
@@ -692,7 +696,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 
 
 	for (/* none */;
-	     (taken = OA_TAKEN(tail, head));
+	     OA_TAKEN(tail, head);
 	     head = (head + report_size) & mask) {
 		u8 *report = oa_buf_base + head;
 		u32 *report32 = (void *)report;
@@ -774,7 +778,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * switches since it's not-uncommon for periodic samples to
 		 * identify a switch before any 'context switch' report.
 		 */
-		if (!stream->perf->exclusive_stream->ctx ||
+		if (!stream->ctx ||
 		    stream->specific_ctx_id == ctx_id ||
 		    stream->oa_buffer.last_ctx_id == stream->specific_ctx_id ||
 		    reason & OAREPORT_REASON_CTX_SWITCH) {
@@ -783,7 +787,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			 * While filtering for a single context we avoid
 			 * leaking the IDs of other contexts.
 			 */
-			if (stream->perf->exclusive_stream->ctx &&
+			if (stream->ctx &&
 			    stream->specific_ctx_id != ctx_id) {
 				report32[2] = INVALID_CTX_ID;
 			}
@@ -943,14 +947,13 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t *offset)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	u32 mask = (OA_BUFFER_SIZE - 1);
 	size_t start_offset = *offset;
 	unsigned long flags;
 	u32 head, tail;
-	u32 taken;
 	int ret = 0;
 
 	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
@@ -984,7 +987,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 
 
 	for (/* none */;
-	     (taken = OA_TAKEN(tail, head));
+	     OA_TAKEN(tail, head);
 	     head = (head + report_size) & mask) {
 		u8 *report = oa_buf_base + head;
 		u32 *report32 = (void *)report;
@@ -1233,6 +1236,196 @@ retry:
 	return stream->pinned_ctx;
 }
 
+static int
+__store_reg_to_mem(struct i915_request *rq, i915_reg_t reg, u32 ggtt_offset)
+{
+	u32 *cs, cmd;
+
+	cmd = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	if (GRAPHICS_VER(rq->engine->i915) >= 8)
+		cmd++;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(reg);
+	*cs++ = ggtt_offset;
+	*cs++ = 0;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int
+__read_reg(struct intel_context *ce, i915_reg_t reg, u32 ggtt_offset)
+{
+	struct i915_request *rq;
+	int err;
+
+	rq = i915_request_create(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+
+	err = __store_reg_to_mem(rq, reg, ggtt_offset);
+
+	i915_request_add(rq);
+	if (!err && i915_request_wait(rq, 0, HZ / 2) < 0)
+		err = -ETIME;
+
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int
+gen12_guc_sw_ctx_id(struct intel_context *ce, u32 *ctx_id)
+{
+	struct i915_vma *scratch;
+	u32 *val;
+	int err;
+
+	scratch = __vm_create_scratch_for_read_pinned(&ce->engine->gt->ggtt->vm, 4);
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
+
+	err = i915_vma_sync(scratch);
+	if (err)
+		goto err_scratch;
+
+	err = __read_reg(ce, RING_EXECLIST_STATUS_HI(ce->engine->mmio_base),
+			 i915_ggtt_offset(scratch));
+	if (err)
+		goto err_scratch;
+
+	val = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB);
+	if (IS_ERR(val)) {
+		err = PTR_ERR(val);
+		goto err_scratch;
+	}
+
+	*ctx_id = *val;
+	i915_gem_object_unpin_map(scratch->obj);
+
+err_scratch:
+	i915_vma_unpin_and_release(&scratch, 0);
+	return err;
+}
+
+/*
+ * For execlist mode of submission, pick an unused context id
+ * 0 - (NUM_CONTEXT_TAG -1) are used by other contexts
+ * XXX_MAX_CONTEXT_HW_ID is used by idle context
+ *
+ * For GuC mode of submission read context id from the upper dword of the
+ * EXECLIST_STATUS register. Note that we read this value only once and expect
+ * that the value stays fixed for the entire OA use case. There are cases where
+ * GuC KMD implementation may deregister a context to reuse it's context id, but
+ * we prevent that from happening to the OA context by pinning it.
+ */
+static int gen12_get_render_context_id(struct i915_perf_stream *stream)
+{
+	u32 ctx_id, mask;
+	int ret;
+
+	if (intel_engine_uses_guc(stream->engine)) {
+		ret = gen12_guc_sw_ctx_id(stream->pinned_ctx, &ctx_id);
+		if (ret)
+			return ret;
+
+		mask = ((1U << GEN12_GUC_SW_CTX_ID_WIDTH) - 1) <<
+			(GEN12_GUC_SW_CTX_ID_SHIFT - 32);
+	} else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 50)) {
+		ctx_id = (XEHP_MAX_CONTEXT_HW_ID - 1) <<
+			(XEHP_SW_CTX_ID_SHIFT - 32);
+
+		mask = ((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
+			(XEHP_SW_CTX_ID_SHIFT - 32);
+	} else {
+		ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) <<
+			 (GEN11_SW_CTX_ID_SHIFT - 32);
+
+		mask = ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) <<
+			(GEN11_SW_CTX_ID_SHIFT - 32);
+	}
+	stream->specific_ctx_id = ctx_id & mask;
+	stream->specific_ctx_id_mask = mask;
+
+	return 0;
+}
+
+static bool oa_find_reg_in_lri(u32 *state, u32 reg, u32 *offset, u32 end)
+{
+	u32 idx = *offset;
+	u32 len = min(MI_LRI_LEN(state[idx]) + idx, end);
+	bool found = false;
+
+	idx++;
+	for (; idx < len; idx += 2) {
+		if (state[idx] == reg) {
+			found = true;
+			break;
+		}
+	}
+
+	*offset = idx;
+	return found;
+}
+
+static u32 oa_context_image_offset(struct intel_context *ce, u32 reg)
+{
+	u32 offset, len = (ce->engine->context_size - PAGE_SIZE) / 4;
+	u32 *state = ce->lrc_reg_state;
+
+	for (offset = 0; offset < len; ) {
+		if (IS_MI_LRI_CMD(state[offset])) {
+			/*
+			 * We expect reg-value pairs in MI_LRI command, so
+			 * MI_LRI_LEN() should be even, if not, issue a warning.
+			 */
+			drm_WARN_ON(&ce->engine->i915->drm,
+				    MI_LRI_LEN(state[offset]) & 0x1);
+
+			if (oa_find_reg_in_lri(state, reg, &offset, len))
+				break;
+		} else {
+			offset++;
+		}
+	}
+
+	return offset < len ? offset : U32_MAX;
+}
+
+static int set_oa_ctx_ctrl_offset(struct intel_context *ce)
+{
+	i915_reg_t reg = GEN12_OACTXCONTROL(ce->engine->mmio_base);
+	struct i915_perf *perf = &ce->engine->i915->perf;
+	u32 offset = perf->ctx_oactxctrl_offset;
+
+	/* Do this only once. Failure is stored as offset of U32_MAX */
+	if (offset)
+		goto exit;
+
+	offset = oa_context_image_offset(ce, i915_mmio_reg_offset(reg));
+	perf->ctx_oactxctrl_offset = offset;
+
+	drm_dbg(&ce->engine->i915->drm,
+		"%s oa ctx control at 0x%08x dword offset\n",
+		ce->engine->name, offset);
+
+exit:
+	return offset && offset != U32_MAX ? 0 : -ENODEV;
+}
+
+static bool engine_supports_mi_query(struct intel_engine_cs *engine)
+{
+	return engine->class == RENDER_CLASS;
+}
+
 /**
  * oa_get_render_ctx_id - determine and hold ctx hw id
  * @stream: An i915-perf stream opened for OA metrics
@@ -1246,11 +1439,27 @@ retry:
 static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct intel_context *ce;
+	int ret = 0;
 
 	ce = oa_pin_context(stream);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
+	if (engine_supports_mi_query(stream->engine)) {
+		/*
+		 * We are enabling perf query here. If we don't find the context
+		 * offset here, just return an error.
+		 */
+		ret = set_oa_ctx_ctrl_offset(ce);
+		if (ret) {
+			intel_context_unpin(ce);
+			drm_err(&stream->perf->i915->drm,
+				"Enabling perf query failed for %s\n",
+				stream->engine->name);
+			return ret;
+		}
+	}
+
 	switch (GRAPHICS_VER(ce->engine->i915)) {
 	case 7: {
 		/*
@@ -1292,24 +1501,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 
 	case 11:
 	case 12:
-		if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 50)) {
-			stream->specific_ctx_id_mask =
-				((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
-				(XEHP_SW_CTX_ID_SHIFT - 32);
-			stream->specific_ctx_id =
-				(XEHP_MAX_CONTEXT_HW_ID - 1) <<
-				(XEHP_SW_CTX_ID_SHIFT - 32);
-		} else {
-			stream->specific_ctx_id_mask =
-				((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-			/*
-			 * Pick an unused context id
-			 * 0 - BITS_PER_LONG are used by other contexts
-			 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
-			 */
-			stream->specific_ctx_id =
-				(GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		}
+		ret = gen12_get_render_context_id(stream);
 		break;
 
 	default:
@@ -1323,7 +1515,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		stream->specific_ctx_id,
 		stream->specific_ctx_id_mask);
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -1375,8 +1567,9 @@ free_noa_wait(struct i915_perf_stream *stream)
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	if (WARN_ON(stream != perf->exclusive_stream))
+	if (WARN_ON(stream != gt->perf.exclusive_stream))
 		return;
 
 	/*
@@ -1385,11 +1578,20 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	 *
 	 * See i915_oa_init_reg_state() and lrc_configure_all_contexts()
 	 */
-	WRITE_ONCE(perf->exclusive_stream, NULL);
+	WRITE_ONCE(gt->perf.exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(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)))
+		drm_WARN_ON(&gt->i915->drm,
+			    intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc));
+
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
 
@@ -1563,6 +1765,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
+	struct intel_gt *gt = stream->engine->gt;
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	int ret;
@@ -1582,11 +1785,22 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 	i915_gem_object_set_cache_coherency(bo, I915_CACHE_LLC);
 
 	/* PreHSW required 512K alignment, HSW requires 16M */
-	vma = i915_gem_object_ggtt_pin(bo, NULL, 0, SZ_16M, 0);
+	vma = i915_vma_instance(bo, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unref;
 	}
+
+	/*
+	 * PreHSW required 512K alignment.
+	 * HSW and onwards, align to requested size of OA buffer.
+	 */
+	ret = i915_vma_pin(vma, 0, SZ_16M, PIN_GLOBAL | PIN_HIGH);
+	if (ret) {
+		drm_err(&gt->i915->drm, "Failed to pin OA buffer %d\n", ret);
+		goto err_unref;
+	}
+
 	stream->oa_buffer.vma = vma;
 
 	stream->oa_buffer.vaddr =
@@ -1636,6 +1850,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
 static int alloc_noa_wait(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
+	struct intel_gt *gt = stream->engine->gt;
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	const u64 delay_ticks = 0xffffffffffffffff -
@@ -1654,6 +1869,9 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 		DELTA_TARGET,
 		N_CS_GPR
 	};
+	i915_reg_t mi_predicate_result = HAS_MI_SET_PREDICATE(i915) ?
+					  MI_PREDICATE_RESULT_2_ENGINE(base) :
+					  MI_PREDICATE_RESULT_1(RENDER_RING_BASE);
 
 	bo = i915_gem_object_create_internal(i915, 4096);
 	if (IS_ERR(bo)) {
@@ -1673,12 +1891,16 @@ retry:
 	 * multiple OA config BOs will have a jump to this address and it
 	 * needs to be fixed during the lifetime of the i915/perf stream.
 	 */
-	vma = i915_gem_object_ggtt_pin_ww(bo, &ww, NULL, 0, 0, PIN_HIGH);
+	vma = i915_vma_instance(bo, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out_ww;
 	}
 
+	ret = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	if (ret)
+		goto out_ww;
+
 	batch = cs = i915_gem_object_pin_map(bo, I915_MAP_WB);
 	if (IS_ERR(batch)) {
 		ret = PTR_ERR(batch);
@@ -1691,7 +1913,7 @@ retry:
 			stream, cs, true /* save */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, true /* save */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
+		stream, cs, true /* save */, mi_predicate_result,
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* First timestamp snapshot location. */
@@ -1745,7 +1967,10 @@ retry:
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
+	*cs++ = i915_mmio_reg_offset(mi_predicate_result);
+
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE | 1;
 
 	/* Restart from the beginning if we had timestamps roll over. */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1755,6 +1980,9 @@ retry:
 	*cs++ = i915_ggtt_offset(vma) + (ts0 - batch) * 4;
 	*cs++ = 0;
 
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE;
+
 	/*
 	 * Now add the diff between to previous timestamps and add it to :
 	 *      (((1 * << 64) - 1) - delay_ns)
@@ -1782,7 +2010,10 @@ retry:
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
+	*cs++ = i915_mmio_reg_offset(mi_predicate_result);
+
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE | 1;
 
 	/* Predicate the jump.  */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1792,13 +2023,16 @@ retry:
 	*cs++ = i915_ggtt_offset(vma) + (jump - batch) * 4;
 	*cs++ = 0;
 
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE;
+
 	/* Restore registers. */
 	for (i = 0; i < N_CS_GPR; i++)
 		cs = save_restore_register(
 			stream, cs, false /* restore */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, false /* restore */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
+		stream, cs, false /* restore */, mi_predicate_result,
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* And return to the ring. */
@@ -2283,11 +2517,12 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream,
 {
 	int err;
 	struct intel_context *ce = stream->pinned_ctx;
-	u32 format = stream->oa_buffer.format;
+	u32 format = stream->oa_buffer.format->format;
+	u32 offset = stream->perf->ctx_oactxctrl_offset;
 	struct flex regs_context[] = {
 		{
 			GEN8_OACTXCONTROL,
-			stream->perf->ctx_oactxctrl_offset + 1,
+			offset + 1,
 			active ? GEN8_OA_COUNTER_RESUME : 0,
 		},
 	};
@@ -2312,12 +2547,13 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream,
 		},
 	};
 
-	/* Modify the context image of pinned context with regs_context*/
+	/* Modify the context image of pinned context with regs_context */
 	err = intel_context_lock_pinned(ce);
 	if (err)
 		return err;
 
-	err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context));
+	err = gen8_modify_context(ce, regs_context,
+				  ARRAY_SIZE(regs_context));
 	intel_context_unlock_pinned(ce);
 	if (err)
 		return err;
@@ -2359,10 +2595,11 @@ oa_configure_all_contexts(struct i915_perf_stream *stream,
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_engine_cs *engine;
+	struct intel_gt *gt = stream->engine->gt;
 	struct i915_gem_context *ctx, *cn;
 	int err;
 
-	lockdep_assert_held(&stream->perf->lock);
+	lockdep_assert_held(&gt->perf.lock);
 
 	/*
 	 * The OA register config is setup through the context image. This image
@@ -2442,6 +2679,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream,
 			   const struct i915_oa_config *oa_config,
 			   struct i915_active *active)
 {
+	u32 ctx_oactxctrl = stream->perf->ctx_oactxctrl_offset;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
 	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
 #define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
@@ -2452,7 +2690,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream,
 		},
 		{
 			GEN8_OACTXCONTROL,
-			stream->perf->ctx_oactxctrl_offset + 1,
+			ctx_oactxctrl + 1,
 		},
 		{ EU_PERF_CNTL0, ctx_flexeuN(0) },
 		{ EU_PERF_CNTL1, ctx_flexeuN(1) },
@@ -2540,12 +2778,26 @@ static int
 gen12_enable_metric_set(struct i915_perf_stream *stream,
 			struct i915_active *active)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
+	u32 sqcnt1;
 	int ret;
 
+	/*
+	 * Wa_1508761755:xehpsdv, dg2
+	 * EU NOA signals behave incorrectly if EU clock gating is enabled.
+	 * Disable thread stall DOP gating and EU DOP gating.
+	 */
+	if (IS_XEHPSDV(i915) || IS_DG2(i915)) {
+		intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN,
+					     _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+		intel_uncore_write(uncore, GEN7_ROW_CHICKEN2,
+				   _MASKED_BIT_ENABLE(GEN12_DISABLE_DOP_GATING));
+	}
+
 	intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG,
 			   /* Disable clk ratio reports, like previous Gens. */
 			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
@@ -2563,6 +2815,16 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 			    : 0);
 
 	/*
+	 * Initialize Super Queue Internal Cnt Register
+	 * Set PMON Enable in order to collect valid metrics.
+	 * Enable byets per clock reporting in OA for XEHPSDV onward.
+	 */
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1);
+
+	/*
 	 * Update all contexts prior writing the mux configurations as we need
 	 * to make sure all slices/subslices are ON before writing to NOA
 	 * registers.
@@ -2611,6 +2873,19 @@ static void gen11_disable_metric_set(struct i915_perf_stream *stream)
 static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
+	struct drm_i915_private *i915 = stream->perf->i915;
+	u32 sqcnt1;
+
+	/*
+	 * Wa_1508761755:xehpsdv, dg2
+	 * Enable thread stall DOP gating and EU DOP gating.
+	 */
+	if (IS_XEHPSDV(i915) || IS_DG2(i915)) {
+		intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN,
+					     _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE));
+		intel_uncore_write(uncore, GEN7_ROW_CHICKEN2,
+				   _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING));
+	}
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen12_configure_all_contexts(stream, NULL, NULL);
@@ -2621,6 +2896,12 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
+
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	/* Reset PMON Enable to save power. */
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, sqcnt1, 0);
 }
 
 static void gen7_oa_enable(struct i915_perf_stream *stream)
@@ -2630,7 +2911,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 	u32 ctx_id = stream->specific_ctx_id;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * Reset buf pointers so we don't forward reports from before now.
@@ -2656,7 +2937,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 static void gen8_oa_enable(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * Reset buf pointers so we don't forward reports from before now.
@@ -2682,7 +2963,7 @@ static void gen8_oa_enable(struct i915_perf_stream *stream)
 static void gen12_oa_enable(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * If we don't want OA reports from the OA buffer, then we don't even
@@ -2838,6 +3119,30 @@ get_sseu_config(struct intel_sseu *out_sseu,
 	return i915_gem_user_to_context_sseu(engine->gt, drm_sseu, out_sseu);
 }
 
+/*
+ * OA timestamp frequency = CS timestamp frequency in most platforms. On some
+ * platforms OA unit ignores the CTC_SHIFT and the 2 timestamps differ. In such
+ * cases, return the adjusted CS timestamp frequency to the user.
+ */
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
+{
+	/* Wa_18013179988:dg2 */
+	if (IS_DG2(i915)) {
+		intel_wakeref_t wakeref;
+		u32 reg, shift;
+
+		with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref)
+			reg = intel_uncore_read(to_gt(i915)->uncore, RPM_CONFIG0);
+
+		shift = REG_FIELD_GET(GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK,
+				      reg);
+
+		return to_gt(i915)->clock_frequency << (3 - shift);
+	}
+
+	return to_gt(i915)->clock_frequency;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2862,7 +3167,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
-	int format_size;
+	struct intel_gt *gt;
 	int ret;
 
 	if (!props->engine) {
@@ -2870,6 +3175,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			"OA engine not specified\n");
 		return -EINVAL;
 	}
+	gt = props->engine->gt;
 
 	/*
 	 * If the sysfs metrics/ directory wasn't registered for some
@@ -2900,7 +3206,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 * counter reports and marshal to the appropriate client
 	 * we currently only allow exclusive access
 	 */
-	if (perf->exclusive_stream) {
+	if (gt->perf.exclusive_stream) {
 		drm_dbg(&stream->perf->i915->drm,
 			"OA unit already in use\n");
 		return -EBUSY;
@@ -2917,20 +3223,15 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	stream->sample_size = sizeof(struct drm_i915_perf_record_header);
 
-	format_size = perf->oa_formats[props->oa_format].size;
+	stream->oa_buffer.format = &perf->oa_formats[props->oa_format];
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format->size == 0))
+		return -EINVAL;
 
 	stream->sample_flags = props->sample_flags;
-	stream->sample_size += format_size;
-
-	stream->oa_buffer.format_size = format_size;
-	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format_size == 0))
-		return -EINVAL;
+	stream->sample_size += stream->oa_buffer.format->size;
 
 	stream->hold_preemption = props->hold_preemption;
 
-	stream->oa_buffer.format =
-		perf->oa_formats[props->oa_format].format;
-
 	stream->periodic = props->oa_periodic;
 	if (stream->periodic)
 		stream->period_exponent = props->oa_period_exponent;
@@ -2974,14 +3275,31 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	intel_engine_pm_get(stream->engine);
 	intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL);
 
+	/*
+	 * Wa_16011777198:dg2: GuC resets render as part of the Wa. This causes
+	 * OA to lose the configuration state. Prevent this by overriding GUCRC
+	 * mode.
+	 */
+	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))) {
+		ret = intel_guc_slpc_override_gucrc_mode(&gt->uc.guc.slpc,
+							 SLPC_GUCRC_MODE_GUCRC_NO_RC6);
+		if (ret) {
+			drm_dbg(&stream->perf->i915->drm,
+				"Unable to override gucrc mode\n");
+			goto err_config;
+		}
+	}
+
 	ret = alloc_oa_buffer(stream);
 	if (ret)
 		goto err_oa_buf_alloc;
 
 	stream->ops = &i915_oa_stream_ops;
 
-	perf->sseu = props->sseu;
-	WRITE_ONCE(perf->exclusive_stream, stream);
+	stream->engine->gt->perf.sseu = props->sseu;
+	WRITE_ONCE(gt->perf.exclusive_stream, stream);
 
 	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
@@ -2999,11 +3317,12 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->poll_check_timer.function = oa_poll_check_timer_cb;
 	init_waitqueue_head(&stream->poll_wq);
 	spin_lock_init(&stream->oa_buffer.ptr_lock);
+	mutex_init(&stream->lock);
 
 	return 0;
 
 err_enable:
-	WRITE_ONCE(perf->exclusive_stream, NULL);
+	WRITE_ONCE(gt->perf.exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -3033,7 +3352,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 		return;
 
 	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
-	stream = READ_ONCE(engine->i915->perf.exclusive_stream);
+	stream = READ_ONCE(engine->gt->perf.exclusive_stream);
 	if (stream && GRAPHICS_VER(stream->perf->i915) < 12)
 		gen8_update_reg_state_unlocked(ce, stream);
 }
@@ -3062,7 +3381,6 @@ static ssize_t i915_perf_read(struct file *file,
 			      loff_t *ppos)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
 	size_t offset = 0;
 	int ret;
 
@@ -3086,14 +3404,14 @@ static ssize_t i915_perf_read(struct file *file,
 			if (ret)
 				return ret;
 
-			mutex_lock(&perf->lock);
+			mutex_lock(&stream->lock);
 			ret = stream->ops->read(stream, buf, count, &offset);
-			mutex_unlock(&perf->lock);
+			mutex_unlock(&stream->lock);
 		} while (!offset && !ret);
 	} else {
-		mutex_lock(&perf->lock);
+		mutex_lock(&stream->lock);
 		ret = stream->ops->read(stream, buf, count, &offset);
-		mutex_unlock(&perf->lock);
+		mutex_unlock(&stream->lock);
 	}
 
 	/* We allow the poll checking to sometimes report false positive EPOLLIN
@@ -3140,9 +3458,6 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that
  * will be woken for new stream data.
  *
- * Note: The &perf->lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: any poll events that are ready without sleeping
  */
 static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
@@ -3181,12 +3496,11 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
 static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
 	__poll_t ret;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&stream->lock);
 	ret = i915_perf_poll_locked(stream, file, wait);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&stream->lock);
 
 	return ret;
 }
@@ -3285,9 +3599,6 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
  * @cmd: the ioctl request
  * @arg: the ioctl data
  *
- * Note: The &perf->lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: zero on success or a negative error code. Returns -EINVAL for
  * an unknown ioctl request.
  */
@@ -3325,12 +3636,11 @@ static long i915_perf_ioctl(struct file *file,
 			    unsigned long arg)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
 	long ret;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&stream->lock);
 	ret = i915_perf_ioctl_locked(stream, cmd, arg);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&stream->lock);
 
 	return ret;
 }
@@ -3342,7 +3652,7 @@ static long i915_perf_ioctl(struct file *file,
  * Frees all resources associated with the given i915 perf @stream, disabling
  * any associated data capture in the process.
  *
- * Note: The &perf->lock mutex has been taken to serialize
+ * Note: The &gt->perf.lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  */
 static void i915_perf_destroy_locked(struct i915_perf_stream *stream)
@@ -3374,10 +3684,16 @@ static int i915_perf_release(struct inode *inode, struct file *file)
 {
 	struct i915_perf_stream *stream = file->private_data;
 	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	mutex_lock(&perf->lock);
+	/*
+	 * Within this call, we know that the fd is being closed and we have no
+	 * other user of stream->lock. Use the perf lock to destroy the stream
+	 * here.
+	 */
+	mutex_lock(&gt->perf.lock);
 	i915_perf_destroy_locked(stream);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	/* Release the reference the perf stream kept on the driver. */
 	drm_dev_put(&perf->i915->drm);
@@ -3410,7 +3726,7 @@ static const struct file_operations fops = {
  * See i915_perf_ioctl_open() for interface details.
  *
  * Implements further stream config validation and stream initialization on
- * behalf of i915_perf_open_ioctl() with the &perf->lock mutex
+ * behalf of i915_perf_open_ioctl() with the &gt->perf.lock mutex
  * taken to serialize with any non-file-operation driver hooks.
  *
  * Note: at this point the @props have only been validated in isolation and
@@ -3565,8 +3881,10 @@ err:
 
 static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
 {
-	return intel_gt_clock_interval_to_ns(to_gt(perf->i915),
-					     2ULL << exponent);
+	u64 nom = (2ULL << exponent) * NSEC_PER_SEC;
+	u32 den = i915_perf_oa_timestamp_frequency(perf->i915);
+
+	return div_u64(nom + den - 1, den);
 }
 
 static __always_inline bool
@@ -3794,7 +4112,7 @@ static int read_properties_unlocked(struct i915_perf *perf,
  * mutex to avoid an awkward lockdep with mmap_lock.
  *
  * Most of the implementation details are handled by
- * i915_perf_open_ioctl_locked() after taking the &perf->lock
+ * i915_perf_open_ioctl_locked() after taking the &gt->perf.lock
  * mutex for serializing with any non-file-operation driver hooks.
  *
  * Return: A newly opened i915 Perf stream file descriptor or negative
@@ -3805,6 +4123,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 {
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_open_param *param = data;
+	struct intel_gt *gt;
 	struct perf_open_properties props;
 	u32 known_open_flags;
 	int ret;
@@ -3831,9 +4150,11 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		return ret;
 
-	mutex_lock(&perf->lock);
+	gt = props.engine->gt;
+
+	mutex_lock(&gt->perf.lock);
 	ret = i915_perf_open_ioctl_locked(perf, param, &props, file);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	return ret;
 }
@@ -3849,6 +4170,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 void i915_perf_register(struct drm_i915_private *i915)
 {
 	struct i915_perf *perf = &i915->perf;
+	struct intel_gt *gt = to_gt(i915);
 
 	if (!perf->i915)
 		return;
@@ -3857,13 +4179,13 @@ void i915_perf_register(struct drm_i915_private *i915)
 	 * i915_perf_open_ioctl(); considering that we register after
 	 * being exposed to userspace.
 	 */
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 
 	perf->metrics_kobj =
 		kobject_create_and_add("metrics",
 				       &i915->drm.primary->kdev->kobj);
 
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 }
 
 /**
@@ -3939,6 +4261,11 @@ static const struct i915_range gen12_oa_b_counters[] = {
 	{}
 };
 
+static const struct i915_range xehp_oa_b_counters[] = {
+	{ .start = 0xdc48, .end = 0xdc48 },	/* OAA_ENABLE_REG */
+	{ .start = 0xdd00, .end = 0xdd48 },	/* OAG_LCE0_0 - OAA_LENABLE_REG */
+};
+
 static const struct i915_range gen7_oa_mux_regs[] = {
 	{ .start = 0x91b8, .end = 0x91cc },	/* OA_PERFCNT[1-2], OA_PERFMATRIX */
 	{ .start = 0x9800, .end = 0x9888 },	/* MICRO_BP0_0 - NOA_WRITE */
@@ -4013,6 +4340,12 @@ static bool gen12_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 	return reg_in_range_table(addr, gen12_oa_b_counters);
 }
 
+static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
+{
+	return reg_in_range_table(addr, xehp_oa_b_counters) ||
+		reg_in_range_table(addr, gen12_oa_b_counters);
+}
+
 static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return reg_in_range_table(addr, gen12_oa_mux_regs);
@@ -4411,11 +4744,47 @@ static void oa_init_supported_formats(struct i915_perf *perf)
 		oa_format_add(perf, I915_OA_FORMAT_C4_B8);
 		break;
 
+	case INTEL_DG2:
+		oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8);
+		oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8);
+		break;
+
 	default:
 		MISSING_CASE(platform);
 	}
 }
 
+static void i915_perf_init_info(struct drm_i915_private *i915)
+{
+	struct i915_perf *perf = &i915->perf;
+
+	switch (GRAPHICS_VER(i915)) {
+	case 8:
+		perf->ctx_oactxctrl_offset = 0x120;
+		perf->ctx_flexeu0_offset = 0x2ce;
+		perf->gen8_valid_ctx_bit = BIT(25);
+		break;
+	case 9:
+		perf->ctx_oactxctrl_offset = 0x128;
+		perf->ctx_flexeu0_offset = 0x3de;
+		perf->gen8_valid_ctx_bit = BIT(16);
+		break;
+	case 11:
+		perf->ctx_oactxctrl_offset = 0x124;
+		perf->ctx_flexeu0_offset = 0x78e;
+		perf->gen8_valid_ctx_bit = BIT(16);
+		break;
+	case 12:
+		/*
+		 * Calculate offset at runtime in oa_pin_context for gen12 and
+		 * cache the value in perf->ctx_oactxctrl_offset.
+		 */
+		break;
+	default:
+		MISSING_CASE(GRAPHICS_VER(i915));
+	}
+}
+
 /**
  * i915_perf_init - initialize i915-perf state on module bind
  * @i915: i915 device instance
@@ -4429,12 +4798,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 {
 	struct i915_perf *perf = &i915->perf;
 
-	/* XXX const struct i915_perf_ops! */
-
-	/* i915_perf is not enabled for DG2 yet */
-	if (IS_DG2(i915))
-		return;
-
 	perf->oa_formats = oa_formats;
 	if (IS_HASWELL(i915)) {
 		perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr;
@@ -4454,6 +4817,7 @@ void i915_perf_init(struct drm_i915_private *i915)
 		 * execlist mode by default.
 		 */
 		perf->ops.read = gen8_oa_read;
+		i915_perf_init_info(i915);
 
 		if (IS_GRAPHICS_VER(i915, 8, 9)) {
 			perf->ops.is_valid_b_counter_reg =
@@ -4473,18 +4837,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen8_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
-
-			if (GRAPHICS_VER(i915) == 8) {
-				perf->ctx_oactxctrl_offset = 0x120;
-				perf->ctx_flexeu0_offset = 0x2ce;
-
-				perf->gen8_valid_ctx_bit = BIT(25);
-			} else {
-				perf->ctx_oactxctrl_offset = 0x128;
-				perf->ctx_flexeu0_offset = 0x3de;
-
-				perf->gen8_valid_ctx_bit = BIT(16);
-			}
 		} else if (GRAPHICS_VER(i915) == 11) {
 			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
@@ -4498,13 +4850,10 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen11_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
-
-			perf->ctx_oactxctrl_offset = 0x124;
-			perf->ctx_flexeu0_offset = 0x78e;
-
-			perf->gen8_valid_ctx_bit = BIT(16);
 		} else if (GRAPHICS_VER(i915) == 12) {
 			perf->ops.is_valid_b_counter_reg =
+				HAS_OA_SLICE_CONTRIB_LIMITS(i915) ?
+				xehp_is_valid_b_counter_addr :
 				gen12_is_valid_b_counter_addr;
 			perf->ops.is_valid_mux_reg =
 				gen12_is_valid_mux_addr;
@@ -4516,14 +4865,15 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen12_enable_metric_set;
 			perf->ops.disable_metric_set = gen12_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen12_oa_hw_tail_read;
-
-			perf->ctx_flexeu0_offset = 0;
-			perf->ctx_oactxctrl_offset = 0x144;
 		}
 	}
 
 	if (perf->ops.enable_metric_set) {
-		mutex_init(&perf->lock);
+		struct intel_gt *gt;
+		int i;
+
+		for_each_gt(gt, i915, i)
+			mutex_init(&gt->perf.lock);
 
 		/* Choose a representative limit */
 		oa_sample_rate_hard_limit = to_gt(i915)->clock_frequency / 2;
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 1d1329e5af3a..f96e09a4af04 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -57,4 +57,6 @@ static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
 	kref_put(&oa_config->ref, i915_oa_config_release);
 }
 
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915);
+
 #endif /* __I915_PERF_H__ */
diff --git a/drivers/gpu/drm/i915/i915_perf_oa_regs.h b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
index f31c9f13a9fc..381d94101610 100644
--- a/drivers/gpu/drm/i915/i915_perf_oa_regs.h
+++ b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
@@ -97,7 +97,7 @@
 #define  GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1
 #define  GEN12_OAR_OACONTROL_COUNTER_ENABLE       (1 << 0)
 
-#define GEN12_OACTXCONTROL _MMIO(0x2360)
+#define GEN12_OACTXCONTROL(base) _MMIO((base) + 0x360)
 #define GEN12_OAR_OASTATUS _MMIO(0x2968)
 
 /* Gen12 OAG unit */
@@ -134,4 +134,8 @@
 #define GDT_CHICKEN_BITS    _MMIO(0x9840)
 #define   GT_NOA_ENABLE	    0x00000080
 
+#define GEN12_SQCNT1				_MMIO(0x8718)
+#define   GEN12_SQCNT1_PMON_ENABLE		REG_BIT(30)
+#define   GEN12_SQCNT1_OABPC			REG_BIT(29)
+
 #endif /* __INTEL_PERF_OA_REGS__ */
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 05cb9a335a97..e0c96b44eda8 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -146,6 +146,11 @@ struct i915_perf_stream {
 	 */
 	struct intel_engine_cs *engine;
 
+	/*
+	 * Lock associated with operations on stream
+	 */
+	struct mutex lock;
+
 	/**
 	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
 	 * properties given when opening a stream, representing the contents
@@ -245,11 +250,10 @@ struct i915_perf_stream {
 	 * @oa_buffer: State of the OA buffer.
 	 */
 	struct {
+		const struct i915_oa_format *format;
 		struct i915_vma *vma;
 		u8 *vaddr;
 		u32 last_ctx_id;
-		int format;
-		int format_size;
 		int size_exponent;
 
 		/**
@@ -380,6 +384,26 @@ struct i915_oa_ops {
 	u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream);
 };
 
+struct i915_perf_gt {
+	/*
+	 * Lock associated with anything below within this structure.
+	 */
+	struct mutex lock;
+
+	/**
+	 * @sseu: sseu configuration selected to run while perf is active,
+	 * applies to all contexts.
+	 */
+	struct intel_sseu sseu;
+
+	/*
+	 * @exclusive_stream: The stream currently using the OA unit. This is
+	 * sometimes accessed outside a syscall associated to its file
+	 * descriptor.
+	 */
+	struct i915_perf_stream *exclusive_stream;
+};
+
 struct i915_perf {
 	struct drm_i915_private *i915;
 
@@ -397,25 +421,6 @@ struct i915_perf {
 	 */
 	struct idr metrics_idr;
 
-	/*
-	 * Lock associated with anything below within this structure
-	 * except exclusive_stream.
-	 */
-	struct mutex lock;
-
-	/*
-	 * The stream currently using the OA unit. If accessed
-	 * outside a syscall associated to its file
-	 * descriptor.
-	 */
-	struct i915_perf_stream *exclusive_stream;
-
-	/**
-	 * @sseu: sseu configuration selected to run while perf is active,
-	 * applies to all contexts.
-	 */
-	struct intel_sseu sseu;
-
 	/**
 	 * For rate limiting any notifications of spurious
 	 * invalid OA reports
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0b287a59dc2f..1c0da50c0dc7 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1796,6 +1796,15 @@
 #define XEHPSDV_RP_STATE_CAP	_MMIO(0x250014)
 #define PVC_RP_STATE_CAP	_MMIO(0x281014)
 
+#define MTL_RP_STATE_CAP	_MMIO(0x138000)
+#define MTL_MEDIAP_STATE_CAP	_MMIO(0x138020)
+#define   MTL_RP0_CAP_MASK	REG_GENMASK(8, 0)
+#define   MTL_RPN_CAP_MASK	REG_GENMASK(24, 16)
+
+#define MTL_GT_RPE_FREQUENCY	_MMIO(0x13800c)
+#define MTL_MPE_FREQUENCY	_MMIO(0x13802c)
+#define   MTL_RPE_MASK		REG_GENMASK(8, 0)
+
 #define GT0_PERF_LIMIT_REASONS		_MMIO(0x1381a8)
 #define   GT0_PERF_LIMIT_REASONS_MASK	0xde3
 #define   PROCHOT_MASK			REG_BIT(0)
@@ -1806,6 +1815,8 @@
 #define   POWER_LIMIT_4_MASK		REG_BIT(8)
 #define   POWER_LIMIT_1_MASK		REG_BIT(10)
 #define   POWER_LIMIT_2_MASK		REG_BIT(11)
+#define   GT0_PERF_LIMIT_REASONS_LOG_MASK REG_GENMASK(31, 16)
+#define MTL_MEDIA_PERF_LIMIT_REASONS	_MMIO(0x138030)
 
 #define CHV_CLK_CTL1			_MMIO(0x101100)
 #define VLV_CLK_CTL2			_MMIO(0x101104)
@@ -5847,6 +5858,11 @@
 #define ICL_DSSM_CDCLK_PLL_REFCLK_19_2MHz	(1 << 29)
 #define ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz	(2 << 29)
 
+#define GMD_ID_DISPLAY				_MMIO(0x510a0)
+#define   GMD_ID_ARCH_MASK			REG_GENMASK(31, 22)
+#define   GMD_ID_RELEASE_MASK			REG_GENMASK(21, 14)
+#define   GMD_ID_STEP				REG_GENMASK(5, 0)
+
 /*GEN11 chicken */
 #define _PIPEA_CHICKEN				0x70038
 #define _PIPEB_CHICKEN				0x71038
@@ -6647,6 +6663,12 @@
 #define   DG1_PCODE_STATUS			0x7E
 #define     DG1_UNCORE_GET_INIT_STATUS		0x0
 #define     DG1_UNCORE_INIT_STATUS_COMPLETE	0x1
+#define   PCODE_POWER_SETUP			0x7C
+#define     POWER_SETUP_SUBCOMMAND_READ_I1	0x4
+#define     POWER_SETUP_SUBCOMMAND_WRITE_I1	0x5
+#define	    POWER_SETUP_I1_WATTS		REG_BIT(31)
+#define	    POWER_SETUP_I1_SHIFT		6	/* 10.6 fixed point format */
+#define	    POWER_SETUP_I1_DATA_MASK		REG_GENMASK(15, 0)
 #define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US	0x23
 #define   XEHP_PCODE_FREQUENCY_CONFIG		0x6e	/* xehpsdv, pvc */
 /* XEHP_PCODE_FREQUENCY_CONFIG sub-commands (param1) */
@@ -7413,182 +7435,6 @@ enum skl_power_gate {
 						   _ADLS_DPLL4_CFGCR1, \
 						   _ADLS_DPLL3_CFGCR1)
 
-#define _DKL_PHY1_BASE			0x168000
-#define _DKL_PHY2_BASE			0x169000
-#define _DKL_PHY3_BASE			0x16A000
-#define _DKL_PHY4_BASE			0x16B000
-#define _DKL_PHY5_BASE			0x16C000
-#define _DKL_PHY6_BASE			0x16D000
-
-/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */
-#define _DKL_PCS_DW5			0x14
-#define DKL_PCS_DW5(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-						    _DKL_PCS_DW5)
-#define   DKL_PCS_DW5_CORE_SOFTRESET	REG_BIT(11)
-
-#define _DKL_PLL_DIV0			0x200
-#define   DKL_PLL_DIV0_AFC_STARTUP_MASK	REG_GENMASK(27, 25)
-#define   DKL_PLL_DIV0_AFC_STARTUP(val)	REG_FIELD_PREP(DKL_PLL_DIV0_AFC_STARTUP_MASK, (val))
-#define   DKL_PLL_DIV0_INTEG_COEFF(x)	((x) << 16)
-#define   DKL_PLL_DIV0_INTEG_COEFF_MASK	(0x1F << 16)
-#define   DKL_PLL_DIV0_PROP_COEFF(x)	((x) << 12)
-#define   DKL_PLL_DIV0_PROP_COEFF_MASK	(0xF << 12)
-#define   DKL_PLL_DIV0_FBPREDIV_SHIFT   (8)
-#define   DKL_PLL_DIV0_FBPREDIV(x)	((x) << DKL_PLL_DIV0_FBPREDIV_SHIFT)
-#define   DKL_PLL_DIV0_FBPREDIV_MASK	(0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT)
-#define   DKL_PLL_DIV0_FBDIV_INT(x)	((x) << 0)
-#define   DKL_PLL_DIV0_FBDIV_INT_MASK	(0xFF << 0)
-#define   DKL_PLL_DIV0_MASK		(DKL_PLL_DIV0_INTEG_COEFF_MASK | \
-					 DKL_PLL_DIV0_PROP_COEFF_MASK | \
-					 DKL_PLL_DIV0_FBPREDIV_MASK | \
-					 DKL_PLL_DIV0_FBDIV_INT_MASK)
-#define DKL_PLL_DIV0(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-						    _DKL_PLL_DIV0)
-
-#define _DKL_PLL_DIV1				0x204
-#define   DKL_PLL_DIV1_IREF_TRIM(x)		((x) << 16)
-#define   DKL_PLL_DIV1_IREF_TRIM_MASK		(0x1F << 16)
-#define   DKL_PLL_DIV1_TDC_TARGET_CNT(x)	((x) << 0)
-#define   DKL_PLL_DIV1_TDC_TARGET_CNT_MASK	(0xFF << 0)
-#define DKL_PLL_DIV1(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-						    _DKL_PLL_DIV1)
-
-#define _DKL_PLL_SSC				0x210
-#define   DKL_PLL_SSC_IREF_NDIV_RATIO(x)	((x) << 29)
-#define   DKL_PLL_SSC_IREF_NDIV_RATIO_MASK	(0x7 << 29)
-#define   DKL_PLL_SSC_STEP_LEN(x)		((x) << 16)
-#define   DKL_PLL_SSC_STEP_LEN_MASK		(0xFF << 16)
-#define   DKL_PLL_SSC_STEP_NUM(x)		((x) << 11)
-#define   DKL_PLL_SSC_STEP_NUM_MASK		(0x7 << 11)
-#define   DKL_PLL_SSC_EN			(1 << 9)
-#define DKL_PLL_SSC(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-						    _DKL_PLL_SSC)
-
-#define _DKL_PLL_BIAS			0x214
-#define   DKL_PLL_BIAS_FRAC_EN_H	(1 << 30)
-#define   DKL_PLL_BIAS_FBDIV_SHIFT	(8)
-#define   DKL_PLL_BIAS_FBDIV_FRAC(x)	((x) << DKL_PLL_BIAS_FBDIV_SHIFT)
-#define   DKL_PLL_BIAS_FBDIV_FRAC_MASK	(0x3FFFFF << DKL_PLL_BIAS_FBDIV_SHIFT)
-#define DKL_PLL_BIAS(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-						    _DKL_PLL_BIAS)
-
-#define _DKL_PLL_TDC_COLDST_BIAS		0x218
-#define   DKL_PLL_TDC_SSC_STEP_SIZE(x)		((x) << 8)
-#define   DKL_PLL_TDC_SSC_STEP_SIZE_MASK	(0xFF << 8)
-#define   DKL_PLL_TDC_FEED_FWD_GAIN(x)		((x) << 0)
-#define   DKL_PLL_TDC_FEED_FWD_GAIN_MASK	(0xFF << 0)
-#define DKL_PLL_TDC_COLDST_BIAS(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_PLL_TDC_COLDST_BIAS)
-
-#define _DKL_REFCLKIN_CTL		0x12C
-/* Bits are the same as MG_REFCLKIN_CTL */
-#define DKL_REFCLKIN_CTL(tc_port)	_MMIO(_PORT(tc_port, \
-						    _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-					      _DKL_REFCLKIN_CTL)
-
-#define _DKL_CLKTOP2_HSCLKCTL		0xD4
-/* Bits are the same as MG_CLKTOP2_HSCLKCTL */
-#define DKL_CLKTOP2_HSCLKCTL(tc_port)	_MMIO(_PORT(tc_port, \
-						    _DKL_PHY1_BASE, \
-						    _DKL_PHY2_BASE) + \
-					      _DKL_CLKTOP2_HSCLKCTL)
-
-#define _DKL_CLKTOP2_CORECLKCTL1		0xD8
-/* Bits are the same as MG_CLKTOP2_CORECLKCTL1 */
-#define DKL_CLKTOP2_CORECLKCTL1(tc_port)	_MMIO(_PORT(tc_port, \
-							    _DKL_PHY1_BASE, \
-							    _DKL_PHY2_BASE) + \
-						      _DKL_CLKTOP2_CORECLKCTL1)
-
-#define _DKL_TX_DPCNTL0				0x2C0
-#define  DKL_TX_PRESHOOT_COEFF(x)			((x) << 13)
-#define  DKL_TX_PRESHOOT_COEFF_MASK			(0x1f << 13)
-#define  DKL_TX_DE_EMPHASIS_COEFF(x)		((x) << 8)
-#define  DKL_TX_DE_EMPAHSIS_COEFF_MASK		(0x1f << 8)
-#define  DKL_TX_VSWING_CONTROL(x)			((x) << 0)
-#define  DKL_TX_VSWING_CONTROL_MASK			(0x7 << 0)
-#define DKL_TX_DPCNTL0(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_DPCNTL0)
-
-#define _DKL_TX_DPCNTL1				0x2C4
-/* Bits are the same as DKL_TX_DPCNTRL0 */
-#define DKL_TX_DPCNTL1(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_DPCNTL1)
-
-#define _DKL_TX_DPCNTL2					0x2C8
-#define  DKL_TX_DP20BITMODE				REG_BIT(2)
-#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK	REG_GENMASK(4, 3)
-#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(val)	REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK, (val))
-#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK	REG_GENMASK(6, 5)
-#define  DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(val)	REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, (val))
-#define DKL_TX_DPCNTL2(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_DPCNTL2)
-
-#define _DKL_TX_FW_CALIB				0x2F8
-#define  DKL_TX_CFG_DISABLE_WAIT_INIT			(1 << 7)
-#define DKL_TX_FW_CALIB(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_FW_CALIB)
-
-#define _DKL_TX_PMD_LANE_SUS				0xD00
-#define DKL_TX_PMD_LANE_SUS(tc_port) _MMIO(_PORT(tc_port, \
-							  _DKL_PHY1_BASE, \
-							  _DKL_PHY2_BASE) + \
-							  _DKL_TX_PMD_LANE_SUS)
-
-#define _DKL_TX_DW17					0xDC4
-#define DKL_TX_DW17(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_DW17)
-
-#define _DKL_TX_DW18					0xDC8
-#define DKL_TX_DW18(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_TX_DW18)
-
-#define _DKL_DP_MODE					0xA0
-#define DKL_DP_MODE(tc_port) _MMIO(_PORT(tc_port, \
-						     _DKL_PHY1_BASE, \
-						     _DKL_PHY2_BASE) + \
-						     _DKL_DP_MODE)
-
-#define _DKL_CMN_UC_DW27			0x36C
-#define  DKL_CMN_UC_DW27_UC_HEALTH		(0x1 << 15)
-#define DKL_CMN_UC_DW_27(tc_port)		_MMIO(_PORT(tc_port, \
-							    _DKL_PHY1_BASE, \
-							    _DKL_PHY2_BASE) + \
-							    _DKL_CMN_UC_DW27)
-
-/*
- * Each Dekel PHY is addressed through a 4KB aperture. Each PHY has more than
- * 4KB of register space, so a separate index is programmed in HIP_INDEX_REG0
- * or HIP_INDEX_REG1, based on the port number, to set the upper 2 address
- * bits that point the 4KB window into the full PHY register space.
- */
-#define _HIP_INDEX_REG0			0x1010A0
-#define _HIP_INDEX_REG1			0x1010A4
-#define HIP_INDEX_REG(tc_port)		_MMIO((tc_port) < 4 ? _HIP_INDEX_REG0 \
-					      : _HIP_INDEX_REG1)
-#define _HIP_INDEX_SHIFT(tc_port)	(8 * ((tc_port) % 4))
-#define HIP_INDEX_VAL(tc_port, val)	((val) << _HIP_INDEX_SHIFT(tc_port))
-
 /* BXT display engine PLL */
 #define BXT_DE_PLL_CTL			_MMIO(0x6d000)
 #define   BXT_DE_PLL_RATIO(x)		(x)	/* {60,65,100} * 19.2MHz */
@@ -7959,8 +7805,13 @@ enum skl_power_gate {
 							   _ICL_PIPE_DSS_CTL2_PB, \
 							   _ICL_PIPE_DSS_CTL2_PC)
 
+#define GGC				_MMIO(0x108040)
+#define   GMS_MASK			REG_GENMASK(15, 8)
+#define   GGMS_MASK			REG_GENMASK(7, 6)
+
 #define GEN12_GSMBASE			_MMIO(0x108100)
 #define GEN12_DSMBASE			_MMIO(0x1080C0)
+#define   GEN12_BDSM_MASK		REG_GENMASK64(63, 20)
 
 #define XEHP_CLOCK_GATE_DIS		_MMIO(0x101014)
 #define   SGSI_SIDECLK_DIS		REG_BIT(17)
@@ -8341,6 +8192,11 @@ enum skl_power_gate {
 #define GEN12_CULLBIT2			_MMIO(0x7030)
 #define GEN12_STATE_ACK_DEBUG		_MMIO(0x20BC)
 
+#define _MTL_CLKGATE_DIS_TRANS_A			0x604E8
+#define _MTL_CLKGATE_DIS_TRANS_B			0x614E8
+#define MTL_CLKGATE_DIS_TRANS(trans)			_MMIO_TRANS2(trans, _MTL_CLKGATE_DIS_TRANS_A)
+#define  MTL_CLKGATE_DIS_TRANS_DMASC_GATING_DIS		REG_BIT(7)
+
 #define MTL_LATENCY_LP0_LP1		_MMIO(0x45780)
 #define MTL_LATENCY_LP2_LP3		_MMIO(0x45784)
 #define MTL_LATENCY_LP4_LP5		_MMIO(0x45788)
@@ -8364,4 +8220,6 @@ enum skl_power_gate {
 #define   MTL_TRAS_MASK			REG_GENMASK(16, 8)
 #define   MTL_TRDPRE_MASK		REG_GENMASK(7, 0)
 
+#define MTL_MEDIA_GSI_BASE		0x380000
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_reg_defs.h b/drivers/gpu/drm/i915/i915_reg_defs.h
index 8f486f77609f..f1859046a9c4 100644
--- a/drivers/gpu/drm/i915/i915_reg_defs.h
+++ b/drivers/gpu/drm/i915/i915_reg_defs.h
@@ -104,22 +104,21 @@ typedef struct {
 
 #define _MMIO(r) ((const i915_reg_t){ .reg = (r) })
 
-#define INVALID_MMIO_REG _MMIO(0)
-
-static __always_inline u32 i915_mmio_reg_offset(i915_reg_t reg)
-{
-	return reg.reg;
-}
+typedef struct {
+	u32 reg;
+} i915_mcr_reg_t;
 
-static inline bool i915_mmio_reg_equal(i915_reg_t a, i915_reg_t b)
-{
-	return i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b);
-}
+#define INVALID_MMIO_REG _MMIO(0)
 
-static inline bool i915_mmio_reg_valid(i915_reg_t reg)
-{
-	return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG);
-}
+/*
+ * These macros can be used on either i915_reg_t or i915_mcr_reg_t since they're
+ * simply operations on the register's offset and don't care about the MCR vs
+ * non-MCR nature of the register.
+ */
+#define i915_mmio_reg_offset(r) \
+	_Generic((r), i915_reg_t: (r).reg, i915_mcr_reg_t: (r).reg)
+#define i915_mmio_reg_equal(a, b) (i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b))
+#define i915_mmio_reg_valid(r) (!i915_mmio_reg_equal(r, INVALID_MMIO_REG))
 
 #define VLV_DISPLAY_BASE		0x180000
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 62fad16a55e8..f949a9495758 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1621,6 +1621,20 @@ i915_request_await_object(struct i915_request *to,
 	return ret;
 }
 
+static void i915_request_await_huc(struct i915_request *rq)
+{
+	struct intel_huc *huc = &rq->context->engine->gt->uc.huc;
+
+	/* don't stall kernel submissions! */
+	if (!rcu_access_pointer(rq->context->gem_context))
+		return;
+
+	if (intel_huc_wait_required(huc))
+		i915_sw_fence_await_sw_fence(&rq->submit,
+					     &huc->delayed_load.fence,
+					     &rq->hucq);
+}
+
 static struct i915_request *
 __i915_request_ensure_parallel_ordering(struct i915_request *rq,
 					struct intel_timeline *timeline)
@@ -1703,6 +1717,16 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	struct i915_request *prev;
 
 	/*
+	 * Media workloads may require HuC, so stall them until HuC loading is
+	 * complete. Note that HuC not being loaded when a user submission
+	 * arrives can only happen when HuC is loaded via GSC and in that case
+	 * we still expect the window between us starting to accept submissions
+	 * and HuC loading completion to be small (a few hundred ms).
+	 */
+	if (rq->engine->class == VIDEO_DECODE_CLASS)
+		i915_request_await_huc(rq);
+
+	/*
 	 * Dependency tracking and request ordering along the timeline
 	 * is special cased so that we can eliminate redundant ordering
 	 * operations while building the request (we know that the timeline
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 47041ec68df8..f5e1bb5e857a 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -348,6 +348,11 @@ struct i915_request {
 #define	GUC_PRIO_FINI	0xfe
 	u8 guc_prio;
 
+	/**
+	 * @hucq: wait queue entry used to wait on the HuC load to complete
+	 */
+	wait_queue_entry_t hucq;
+
 	I915_SELFTEST_DECLARE(struct {
 		struct list_head link;
 		unsigned long delay;
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 9ddb3e743a3e..b0a1db44f895 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -9,7 +9,8 @@
 
 #include <linux/pfn.h>
 #include <linux/scatterlist.h>
-#include <linux/swiotlb.h>
+#include <linux/dma-mapping.h>
+#include <xen/xen.h>
 
 #include "i915_gem.h"
 
@@ -127,19 +128,26 @@ static inline unsigned int i915_sg_dma_sizes(struct scatterlist *sg)
 	return page_sizes;
 }
 
-static inline unsigned int i915_sg_segment_size(void)
+static inline unsigned int i915_sg_segment_size(struct device *dev)
 {
-	unsigned int size = swiotlb_max_segment();
-
-	if (size == 0)
-		size = UINT_MAX;
-
-	size = rounddown(size, PAGE_SIZE);
-	/* swiotlb_max_segment_size can return 1 byte when it means one page. */
-	if (size < PAGE_SIZE)
-		size = PAGE_SIZE;
-
-	return size;
+	size_t max = min_t(size_t, UINT_MAX, dma_max_mapping_size(dev));
+
+	/*
+	 * For Xen PV guests pages aren't contiguous in DMA (machine) address
+	 * space.  The DMA API takes care of that both in dma_alloc_* (by
+	 * calling into the hypervisor to make the pages contiguous) and in
+	 * dma_map_* (by bounce buffering).  But i915 abuses ignores the
+	 * coherency aspects of the DMA API and thus can't cope with bounce
+	 * buffering actually happening, so add a hack here to force small
+	 * allocations and mappings when running in PV mode on Xen.
+	 *
+	 * Note this will still break if bounce buffering is required for other
+	 * reasons, like confidential computing hypervisors or PCIe root ports
+	 * with addressing limitations.
+	 */
+	if (xen_pv_domain())
+		max = PAGE_SIZE;
+	return round_down(max, PAGE_SIZE);
 }
 
 bool i915_sg_trim(struct sg_table *orig_st);
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index f54de0499be7..bdf3e22c0a34 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -92,12 +92,14 @@ int __i915_subtests(const char *caller,
 			T, ARRAY_SIZE(T), data)
 #define i915_live_subtests(T, data) ({ \
 	typecheck(struct drm_i915_private *, data); \
+	(data)->gt[0]->uc.guc.submission_state.sched_disable_delay_ms = 0; \
 	__i915_subtests(__func__, \
 			__i915_live_setup, __i915_live_teardown, \
 			T, ARRAY_SIZE(T), data); \
 })
 #define intel_gt_live_subtests(T, data) ({ \
 	typecheck(struct intel_gt *, data); \
+	(data)->uc.guc.submission_state.sched_disable_delay_ms = 0; \
 	__i915_subtests(__func__, \
 			__intel_gt_live_setup, __intel_gt_live_teardown, \
 			T, ARRAY_SIZE(T), data); \
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6fc0d1b89690..cc2a8821d22a 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -571,7 +571,6 @@ int __i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 
 int i915_sw_fence_await_reservation(struct i915_sw_fence *fence,
 				    struct dma_resv *resv,
-				    const struct dma_fence_ops *exclude,
 				    bool write,
 				    unsigned long timeout,
 				    gfp_t gfp)
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h
index 619fc5a22f0c..f752bfc7c6e1 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.h
+++ b/drivers/gpu/drm/i915/i915_sw_fence.h
@@ -91,7 +91,6 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 
 int i915_sw_fence_await_reservation(struct i915_sw_fence *fence,
 				    struct dma_resv *resv,
-				    const struct dma_fence_ops *exclude,
 				    bool write,
 				    unsigned long timeout,
 				    gfp_t gfp);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 37b5c9e9d260..c70a02517e02 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -671,21 +671,6 @@ TRACE_EVENT_CONDITION(i915_reg_rw,
 		(u32)(__entry->val >> 32))
 );
 
-TRACE_EVENT(intel_gpu_freq_change,
-	    TP_PROTO(u32 freq),
-	    TP_ARGS(freq),
-
-	    TP_STRUCT__entry(
-			     __field(u32, freq)
-			     ),
-
-	    TP_fast_assign(
-			   __entry->freq = freq;
-			   ),
-
-	    TP_printk("new_freq=%u", __entry->freq)
-);
-
 /**
  * DOC: i915_ppgtt_create and i915_ppgtt_release tracepoints
  *
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index f17c09ead7d7..c39488eb9eeb 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -776,12 +776,6 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
 
 	alignment = max(alignment, i915_vm_obj_min_alignment(vma->vm, vma->obj));
-	/*
-	 * for compact-pt we round up the reservation to prevent
-	 * any smaller pages being used within the same PDE
-	 */
-	if (NEEDS_COMPACT_PT(vma->vm->i915))
-		size = round_up(size, alignment);
 
 	/* If binding the object/GGTT view requires more space than the entire
 	 * aperture has, reject it early before evicting everything in a vain
@@ -820,7 +814,8 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 		 * forseeable future. See also i915_ggtt_offset().
 		 */
 		if (upper_32_bits(end - 1) &&
-		    vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+		    vma->page_sizes.sg > I915_GTT_PAGE_SIZE &&
+		    !HAS_64K_PAGES(vma->vm->i915)) {
 			/*
 			 * We can't mix 64K and 4K PTEs in the same page-table
 			 * (2M block), and so to avoid the ugliness and
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 20575eb77ea7..1dc1fb29a776 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -29,6 +29,7 @@
 
 #include "display/intel_cdclk.h"
 #include "display/intel_de.h"
+#include "gt/intel_gt_regs.h"
 #include "intel_device_info.h"
 #include "i915_drv.h"
 #include "i915_utils.h"
@@ -231,7 +232,7 @@ static bool find_devid(u16 id, const u16 *p, unsigned int num)
 	return false;
 }
 
-void intel_device_info_subplatform_init(struct drm_i915_private *i915)
+static void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 {
 	const struct intel_device_info *info = INTEL_INFO(i915);
 	const struct intel_runtime_info *rinfo = RUNTIME_INFO(i915);
@@ -288,6 +289,78 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 	RUNTIME_INFO(i915)->platform_mask[pi] |= mask;
 }
 
+static void ip_ver_read(struct drm_i915_private *i915, u32 offset, struct intel_ip_version *ip)
+{
+	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+	void __iomem *addr;
+	u32 val;
+	u8 expected_ver = ip->ver;
+	u8 expected_rel = ip->rel;
+
+	addr = pci_iomap_range(pdev, 0, offset, sizeof(u32));
+	if (drm_WARN_ON(&i915->drm, !addr))
+		return;
+
+	val = ioread32(addr);
+	pci_iounmap(pdev, addr);
+
+	ip->ver = REG_FIELD_GET(GMD_ID_ARCH_MASK, val);
+	ip->rel = REG_FIELD_GET(GMD_ID_RELEASE_MASK, val);
+	ip->step = REG_FIELD_GET(GMD_ID_STEP, val);
+
+	/* Sanity check against expected versions from device info */
+	if (IP_VER(ip->ver, ip->rel) < IP_VER(expected_ver, expected_rel))
+		drm_dbg(&i915->drm,
+			"Hardware reports GMD IP version %u.%u (REG[0x%x] = 0x%08x) but minimum expected is %u.%u\n",
+			ip->ver, ip->rel, offset, val, expected_ver, expected_rel);
+}
+
+/*
+ * Setup the graphics version for the current device.  This must be done before
+ * any code that performs checks on GRAPHICS_VER or DISPLAY_VER, so this
+ * function should be called very early in the driver initialization sequence.
+ *
+ * Regular MMIO access is not yet setup at the point this function is called so
+ * we peek at the appropriate MMIO offset directly.  The GMD_ID register is
+ * part of an 'always on' power well by design, so we don't need to worry about
+ * forcewake while reading it.
+ */
+static void intel_ipver_early_init(struct drm_i915_private *i915)
+{
+	struct intel_runtime_info *runtime = RUNTIME_INFO(i915);
+
+	if (!HAS_GMD_ID(i915)) {
+		drm_WARN_ON(&i915->drm, RUNTIME_INFO(i915)->graphics.ip.ver > 12);
+		/*
+		 * On older platforms, graphics and media share the same ip
+		 * version and release.
+		 */
+		RUNTIME_INFO(i915)->media.ip =
+			RUNTIME_INFO(i915)->graphics.ip;
+		return;
+	}
+
+	ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_GRAPHICS),
+		    &runtime->graphics.ip);
+	ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_DISPLAY),
+		    &runtime->display.ip);
+	ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_MEDIA),
+		    &runtime->media.ip);
+}
+
+/**
+ * intel_device_info_runtime_init_early - initialize early runtime info
+ * @i915: the i915 device
+ *
+ * Determine early intel_device_info fields at runtime. This function needs
+ * to be called before the MMIO has been setup.
+ */
+void intel_device_info_runtime_init_early(struct drm_i915_private *i915)
+{
+	intel_ipver_early_init(i915);
+	intel_device_info_subplatform_init(i915);
+}
+
 /**
  * intel_device_info_runtime_init - initialize runtime info
  * @dev_priv: the i915 device
@@ -442,6 +515,11 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 		runtime->has_dmc = false;
 		runtime->has_dsc = false;
 	}
+
+	/* Disable nuclear pageflip by default on pre-g4x */
+	if (!dev_priv->params.nuclear_pageflip &&
+	    DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
+		dev_priv->drm.driver_features &= ~DRIVER_ATOMIC;
 }
 
 void intel_driver_caps_print(const struct intel_driver_caps *caps,
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index d638235e1d26..d588e5fd2eea 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -146,13 +146,13 @@ enum intel_ppgtt_type {
 	/* Keep has_* in alphabetical order */ \
 	func(has_64bit_reloc); \
 	func(has_64k_pages); \
-	func(needs_compact_pt); \
 	func(gpu_reset_clobbers_display); \
 	func(has_reset_engine); \
 	func(has_3d_pipeline); \
 	func(has_4tile); \
 	func(has_flat_ccs); \
 	func(has_global_mocs); \
+	func(has_gmd_id); \
 	func(has_gt_uc); \
 	func(has_heci_pxp); \
 	func(has_heci_gscfi); \
@@ -164,6 +164,8 @@ enum intel_ppgtt_type {
 	func(has_logical_ring_elsq); \
 	func(has_media_ratio_mode); \
 	func(has_mslice_steering); \
+	func(has_oa_bpc_reporting); \
+	func(has_oa_slice_contrib_limits); \
 	func(has_one_eu_per_fuse_bit); \
 	func(has_pxp); \
 	func(has_rc6); \
@@ -180,6 +182,7 @@ enum intel_ppgtt_type {
 	/* Keep in alphabetical order */ \
 	func(cursor_needs_physical); \
 	func(has_cdclk_crawl); \
+	func(has_cdclk_squash); \
 	func(has_ddi); \
 	func(has_dp_mst); \
 	func(has_dsb); \
@@ -195,20 +198,25 @@ enum intel_ppgtt_type {
 	func(overlay_needs_physical); \
 	func(supports_tv);
 
-struct ip_version {
+struct intel_ip_version {
 	u8 ver;
 	u8 rel;
+	u8 step;
 };
 
 struct intel_runtime_info {
+	/*
+	 * Single "graphics" IP version that represents
+	 * render, compute and copy behavior.
+	 */
 	struct {
-		struct ip_version ip;
+		struct intel_ip_version ip;
 	} graphics;
 	struct {
-		struct ip_version ip;
+		struct intel_ip_version ip;
 	} media;
 	struct {
-		struct ip_version ip;
+		struct intel_ip_version ip;
 	} display;
 
 	/*
@@ -308,7 +316,7 @@ struct intel_driver_caps {
 
 const char *intel_platform_name(enum intel_platform platform);
 
-void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv);
+void intel_device_info_runtime_init_early(struct drm_i915_private *dev_priv);
 void intel_device_info_runtime_init(struct drm_i915_private *dev_priv);
 
 void intel_device_info_print(const struct intel_device_info *info,
diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
index 8279dc580a3e..638b77d64bf4 100644
--- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
+++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
@@ -102,7 +102,7 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(_MMIO(0x2438));
 	MMIO_D(_MMIO(0x243c));
 	MMIO_D(_MMIO(0x7018));
-	MMIO_D(HALF_SLICE_CHICKEN3);
+	MMIO_D(HSW_HALF_SLICE_CHICKEN3);
 	MMIO_D(GEN7_HALF_SLICE_CHICKEN1);
 	/* display */
 	MMIO_F(_MMIO(0x60220), 0x20);
diff --git a/drivers/gpu/drm/i915/intel_mchbar_regs.h b/drivers/gpu/drm/i915/intel_mchbar_regs.h
index ffc702b79579..f93e9af43ac3 100644
--- a/drivers/gpu/drm/i915/intel_mchbar_regs.h
+++ b/drivers/gpu/drm/i915/intel_mchbar_regs.h
@@ -189,6 +189,21 @@
 #define  DG1_QCLK_RATIO_MASK			REG_GENMASK(9, 2)
 #define  DG1_QCLK_REFERENCE			REG_BIT(10)
 
+/*
+ * *_PACKAGE_POWER_SKU - SKU power and timing parameters.
+ */
+#define PCU_PACKAGE_POWER_SKU			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5930)
+#define   PKG_PKG_TDP				GENMASK_ULL(14, 0)
+#define   PKG_MAX_WIN				GENMASK_ULL(54, 48)
+#define     PKG_MAX_WIN_X			GENMASK_ULL(54, 53)
+#define     PKG_MAX_WIN_Y			GENMASK_ULL(52, 48)
+
+#define PCU_PACKAGE_POWER_SKU_UNIT		_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5938)
+#define   PKG_PWR_UNIT				REG_GENMASK(3, 0)
+#define   PKG_ENERGY_UNIT			REG_GENMASK(12, 8)
+#define   PKG_TIME_UNIT				REG_GENMASK(19, 16)
+#define PCU_PACKAGE_ENERGY_STATUS              _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x593c)
+
 #define GEN6_GT_PERF_STATUS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5948)
 #define GEN6_RP_STATE_LIMITS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
 #define GEN6_RP_STATE_CAP			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
@@ -198,6 +213,12 @@
 
 #define GEN10_FREQ_INFO_REC			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5ef0)
 #define   RPE_MASK				REG_GENMASK(15, 8)
+#define PCU_PACKAGE_RAPL_LIMIT			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x59a0)
+#define   PKG_PWR_LIM_1				REG_GENMASK(14, 0)
+#define   PKG_PWR_LIM_1_EN			REG_BIT(15)
+#define   PKG_PWR_LIM_1_TIME			REG_GENMASK(23, 17)
+#define   PKG_PWR_LIM_1_TIME_X			REG_GENMASK(23, 22)
+#define   PKG_PWR_LIM_1_TIME_Y			REG_GENMASK(21, 17)
 
 /* snb MCH registers for priority tuning */
 #define MCH_SSKPD				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5d10)
diff --git a/drivers/gpu/drm/i915/intel_pci_config.h b/drivers/gpu/drm/i915/intel_pci_config.h
index 4977a524ce6f..23b8e519f333 100644
--- a/drivers/gpu/drm/i915/intel_pci_config.h
+++ b/drivers/gpu/drm/i915/intel_pci_config.h
@@ -7,11 +7,29 @@
 #define __INTEL_PCI_CONFIG_H__
 
 /* PCI BARs */
-#define GTTMMADR_BAR				0
-#define GEN2_GTTMMADR_BAR			1
-#define GFXMEM_BAR				2
-#define GTT_APERTURE_BAR			GFXMEM_BAR
-#define GEN12_LMEM_BAR				GFXMEM_BAR
+#define GEN2_GMADR_BAR				0
+#define GEN2_MMADR_BAR				1 /* MMIO+GTT, despite the name */
+#define GEN2_IO_BAR				2 /* 85x/865 */
+
+#define GEN3_MMADR_BAR				0 /* MMIO only */
+#define GEN3_IO_BAR				1
+#define GEN3_GMADR_BAR				2
+#define GEN3_GTTADR_BAR				3 /* GTT only */
+
+#define GEN4_GTTMMADR_BAR			0 /* MMIO+GTT */
+#define GEN4_GMADR_BAR				2
+#define GEN4_IO_BAR				4
+
+#define GEN12_LMEM_BAR				2
+
+static inline int intel_mmio_bar(int graphics_ver)
+{
+	switch (graphics_ver) {
+	case 2: return GEN2_MMADR_BAR;
+	case 3: return GEN3_MMADR_BAR;
+	default: return GEN4_GTTMMADR_BAR;
+	}
+}
 
 /* BSM in include/drm/i915_drm.h */
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 8f86f56e7ca4..ee34e2785636 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -30,6 +30,8 @@
 #include "display/skl_watermark.h"
 
 #include "gt/intel_engine_regs.h"
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 
 #include "i915_drv.h"
@@ -58,25 +60,20 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 		 * Must match Sampler, Pixel Back End, and Media. See
 		 * WaCompressedResourceSamplerPbeMediaNewHashMode.
 		 */
-		intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
-			   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) |
-			   SKL_DE_COMPRESSED_HASH_MODE);
+		intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, SKL_DE_COMPRESSED_HASH_MODE);
 	}
 
 	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
-	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
-		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
+	intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, SKL_EDP_PSR_FIX_RDWRAP);
 
 	/* WaEnableChickenDCPR:skl,bxt,kbl,glk,cfl */
-	intel_uncore_write(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1,
-		   intel_uncore_read(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
+	intel_uncore_rmw(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1, 0, MASK_WAKEMEM);
 
 	/*
 	 * WaFbcWakeMemOn:skl,bxt,kbl,glk,cfl
 	 * Display WA #0859: skl,bxt,kbl,glk,cfl
 	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_MEMORY_WAKE);
+	intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_MEMORY_WAKE);
 }
 
 static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -84,15 +81,13 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WaDisableSDEUnitClockGating:bxt */
-	intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
-		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/*
 	 * FIXME:
 	 * GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only.
 	 */
-	intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
-		   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);
+	intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);
 
 	/*
 	 * Wa: Backlight PWM may stop in the asserted state, causing backlight
@@ -113,16 +108,13 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 	 * WaFbcTurnOffFbcWatermark:bxt
 	 * Display WA #0562: bxt
 	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_WM_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS);
 
 	/*
 	 * WaFbcHighMemBwCorruptionAvoidance:bxt
 	 * Display WA #0883: bxt
 	 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
-			   intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) |
-			   DPFC_DISABLE_DUMMY0);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), 0, DPFC_DISABLE_DUMMY0);
 }
 
 static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -895,19 +887,14 @@ static void pnv_update_wm(struct drm_i915_private *dev_priv)
 		wm = intel_calculate_wm(pixel_rate, &pnv_cursor_wm,
 					pnv_display_wm.fifo_size,
 					4, latency->cursor_sr);
-		reg = intel_uncore_read(&dev_priv->uncore, DSPFW3);
-		reg &= ~DSPFW_CURSOR_SR_MASK;
-		reg |= FW_WM(wm, CURSOR_SR);
-		intel_uncore_write(&dev_priv->uncore, DSPFW3, reg);
+		intel_uncore_rmw(&dev_priv->uncore, DSPFW3, DSPFW_CURSOR_SR_MASK,
+				 FW_WM(wm, CURSOR_SR));
 
 		/* Display HPLL off SR */
 		wm = intel_calculate_wm(pixel_rate, &pnv_display_hplloff_wm,
 					pnv_display_hplloff_wm.fifo_size,
 					cpp, latency->display_hpll_disable);
-		reg = intel_uncore_read(&dev_priv->uncore, DSPFW3);
-		reg &= ~DSPFW_HPLL_SR_MASK;
-		reg |= FW_WM(wm, HPLL_SR);
-		intel_uncore_write(&dev_priv->uncore, DSPFW3, reg);
+		intel_uncore_rmw(&dev_priv->uncore, DSPFW3, DSPFW_HPLL_SR_MASK, FW_WM(wm, HPLL_SR));
 
 		/* cursor HPLL off SR */
 		wm = intel_calculate_wm(pixel_rate, &pnv_cursor_hplloff_wm,
@@ -1337,34 +1324,14 @@ static bool g4x_compute_fbc_en(const struct g4x_wm_state *wm_state,
 	return true;
 }
 
-static int g4x_compute_pipe_wm(struct intel_atomic_state *state,
-			       struct intel_crtc *crtc)
+static int _g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc_state *crtc_state =
-		intel_atomic_get_new_crtc_state(state, crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
 	const struct g4x_pipe_wm *raw;
-	const struct intel_plane_state *old_plane_state;
-	const struct intel_plane_state *new_plane_state;
-	struct intel_plane *plane;
 	enum plane_id plane_id;
-	int i, level;
-	unsigned int dirty = 0;
-
-	for_each_oldnew_intel_plane_in_state(state, plane,
-					     old_plane_state,
-					     new_plane_state, i) {
-		if (new_plane_state->hw.crtc != &crtc->base &&
-		    old_plane_state->hw.crtc != &crtc->base)
-			continue;
-
-		if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
-			dirty |= BIT(plane->id);
-	}
-
-	if (!dirty)
-		return 0;
+	int level;
 
 	level = G4X_WM_LEVEL_NORMAL;
 	if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
@@ -1417,6 +1384,34 @@ static int g4x_compute_pipe_wm(struct intel_atomic_state *state,
 	return 0;
 }
 
+static int g4x_compute_pipe_wm(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_plane_state *old_plane_state;
+	const struct intel_plane_state *new_plane_state;
+	struct intel_plane *plane;
+	unsigned int dirty = 0;
+	int i;
+
+	for_each_oldnew_intel_plane_in_state(state, plane,
+					     old_plane_state,
+					     new_plane_state, i) {
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
+			continue;
+
+		if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
+			dirty |= BIT(plane->id);
+	}
+
+	if (!dirty)
+		return 0;
+
+	return _g4x_compute_pipe_wm(crtc_state);
+}
+
 static int g4x_compute_intermediate_wm(struct intel_atomic_state *state,
 				       struct intel_crtc *crtc)
 {
@@ -1857,64 +1852,17 @@ static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 		vlv_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level);
 }
 
-static int vlv_compute_pipe_wm(struct intel_atomic_state *state,
-			       struct intel_crtc *crtc)
+static int _vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_crtc_state *crtc_state =
-		intel_atomic_get_new_crtc_state(state, crtc);
 	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
 	int num_active_planes = hweight8(active_planes);
-	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
-	const struct intel_plane_state *old_plane_state;
-	const struct intel_plane_state *new_plane_state;
-	struct intel_plane *plane;
 	enum plane_id plane_id;
-	int level, ret, i;
-	unsigned int dirty = 0;
-
-	for_each_oldnew_intel_plane_in_state(state, plane,
-					     old_plane_state,
-					     new_plane_state, i) {
-		if (new_plane_state->hw.crtc != &crtc->base &&
-		    old_plane_state->hw.crtc != &crtc->base)
-			continue;
-
-		if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
-			dirty |= BIT(plane->id);
-	}
-
-	/*
-	 * DSPARB registers may have been reset due to the
-	 * power well being turned off. Make sure we restore
-	 * them to a consistent state even if no primary/sprite
-	 * planes are initially active.
-	 */
-	if (needs_modeset)
-		crtc_state->fifo_changed = true;
-
-	if (!dirty)
-		return 0;
-
-	/* cursor changes don't warrant a FIFO recompute */
-	if (dirty & ~BIT(PLANE_CURSOR)) {
-		const struct intel_crtc_state *old_crtc_state =
-			intel_atomic_get_old_crtc_state(state, crtc);
-		const struct vlv_fifo_state *old_fifo_state =
-			&old_crtc_state->wm.vlv.fifo_state;
-
-		ret = vlv_compute_fifo(crtc_state);
-		if (ret)
-			return ret;
-
-		if (needs_modeset ||
-		    memcmp(old_fifo_state, fifo_state,
-			   sizeof(*fifo_state)) != 0)
-			crtc_state->fifo_changed = true;
-	}
+	int level;
 
 	/* initially allow all levels */
 	wm_state->num_levels = intel_wm_num_levels(dev_priv);
@@ -1961,6 +1909,67 @@ static int vlv_compute_pipe_wm(struct intel_atomic_state *state,
 	return 0;
 }
 
+static int vlv_compute_pipe_wm(struct intel_atomic_state *state,
+			       struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
+	const struct intel_plane_state *old_plane_state;
+	const struct intel_plane_state *new_plane_state;
+	struct intel_plane *plane;
+	unsigned int dirty = 0;
+	int i;
+
+	for_each_oldnew_intel_plane_in_state(state, plane,
+					     old_plane_state,
+					     new_plane_state, i) {
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
+			continue;
+
+		if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
+			dirty |= BIT(plane->id);
+	}
+
+	/*
+	 * DSPARB registers may have been reset due to the
+	 * power well being turned off. Make sure we restore
+	 * them to a consistent state even if no primary/sprite
+	 * planes are initially active. We also force a FIFO
+	 * recomputation so that we are sure to sanitize the
+	 * FIFO setting we took over from the BIOS even if there
+	 * are no active planes on the crtc.
+	 */
+	if (needs_modeset)
+		dirty = ~0;
+
+	if (!dirty)
+		return 0;
+
+	/* cursor changes don't warrant a FIFO recompute */
+	if (dirty & ~BIT(PLANE_CURSOR)) {
+		const struct intel_crtc_state *old_crtc_state =
+			intel_atomic_get_old_crtc_state(state, crtc);
+		const struct vlv_fifo_state *old_fifo_state =
+			&old_crtc_state->wm.vlv.fifo_state;
+		const struct vlv_fifo_state *new_fifo_state =
+			&crtc_state->wm.vlv.fifo_state;
+		int ret;
+
+		ret = vlv_compute_fifo(crtc_state);
+		if (ret)
+			return ret;
+
+		if (needs_modeset ||
+		    memcmp(old_fifo_state, new_fifo_state,
+			   sizeof(*new_fifo_state)) != 0)
+			crtc_state->fifo_changed = true;
+	}
+
+	return _vlv_compute_pipe_wm(crtc_state);
+}
+
 #define VLV_FIFO(plane, value) \
 	(((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV)
 
@@ -3458,7 +3467,6 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 {
 	struct ilk_wm_values *previous = &dev_priv->display.wm.hw;
 	unsigned int dirty;
-	u32 val;
 
 	dirty = ilk_compute_wm_dirty(dev_priv, previous, results);
 	if (!dirty)
@@ -3474,32 +3482,20 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 		intel_uncore_write(&dev_priv->uncore, WM0_PIPE_ILK(PIPE_C), results->wm_pipe[2]);
 
 	if (dirty & WM_DIRTY_DDB) {
-		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-			val = intel_uncore_read(&dev_priv->uncore, WM_MISC);
-			if (results->partitioning == INTEL_DDB_PART_1_2)
-				val &= ~WM_MISC_DATA_PARTITION_5_6;
-			else
-				val |= WM_MISC_DATA_PARTITION_5_6;
-			intel_uncore_write(&dev_priv->uncore, WM_MISC, val);
-		} else {
-			val = intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL2);
-			if (results->partitioning == INTEL_DDB_PART_1_2)
-				val &= ~DISP_DATA_PARTITION_5_6;
-			else
-				val |= DISP_DATA_PARTITION_5_6;
-			intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL2, val);
-		}
-	}
-
-	if (dirty & WM_DIRTY_FBC) {
-		val = intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL);
-		if (results->enable_fbc_wm)
-			val &= ~DISP_FBC_WM_DIS;
+		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+			intel_uncore_rmw(&dev_priv->uncore, WM_MISC, WM_MISC_DATA_PARTITION_5_6,
+					 results->partitioning == INTEL_DDB_PART_1_2 ? 0 :
+					 WM_MISC_DATA_PARTITION_5_6);
 		else
-			val |= DISP_FBC_WM_DIS;
-		intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, val);
+			intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL2, DISP_DATA_PARTITION_5_6,
+					 results->partitioning == INTEL_DDB_PART_1_2 ? 0 :
+					 DISP_DATA_PARTITION_5_6);
 	}
 
+	if (dirty & WM_DIRTY_FBC)
+		intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, DISP_FBC_WM_DIS,
+				 results->enable_fbc_wm ? 0 : DISP_FBC_WM_DIS);
+
 	if (dirty & WM_DIRTY_LP(1) &&
 	    previous->wm_lp_spr[0] != results->wm_lp_spr[0])
 		intel_uncore_write(&dev_priv->uncore, WM1S_LP_ILK, results->wm_lp_spr[0]);
@@ -3824,6 +3820,8 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv)
 					     plane_id, USHRT_MAX);
 		g4x_raw_fbc_wm_set(crtc_state, level, USHRT_MAX);
 
+		g4x_invalidate_wms(crtc, active, level);
+
 		crtc_state->wm.g4x.optimal = *active;
 		crtc_state->wm.g4x.intermediate = *active;
 
@@ -3860,37 +3858,30 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
 			to_intel_crtc_state(crtc->base.state);
 		struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
-		struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
 		enum plane_id plane_id = plane->id;
-		int level;
+		int level, num_levels = intel_wm_num_levels(dev_priv);
 
 		if (plane_state->uapi.visible)
 			continue;
 
-		for (level = 0; level < 3; level++) {
+		for (level = 0; level < num_levels; level++) {
 			struct g4x_pipe_wm *raw =
 				&crtc_state->wm.g4x.raw[level];
 
 			raw->plane[plane_id] = 0;
-			wm_state->wm.plane[plane_id] = 0;
-		}
 
-		if (plane_id == PLANE_PRIMARY) {
-			for (level = 0; level < 3; level++) {
-				struct g4x_pipe_wm *raw =
-					&crtc_state->wm.g4x.raw[level];
+			if (plane_id == PLANE_PRIMARY)
 				raw->fbc = 0;
-			}
-
-			wm_state->sr.fbc = 0;
-			wm_state->hpll.fbc = 0;
-			wm_state->fbc_en = false;
 		}
 	}
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
+		int ret;
+
+		ret = _g4x_compute_pipe_wm(crtc_state);
+		drm_WARN_ON(&dev_priv->drm, ret);
 
 		crtc_state->wm.g4x.intermediate =
 			crtc_state->wm.g4x.optimal;
@@ -4016,30 +4007,27 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
 			to_intel_crtc_state(crtc->base.state);
 		struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
-		struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
-		const struct vlv_fifo_state *fifo_state =
-			&crtc_state->wm.vlv.fifo_state;
 		enum plane_id plane_id = plane->id;
-		int level;
+		int level, num_levels = intel_wm_num_levels(dev_priv);
 
 		if (plane_state->uapi.visible)
 			continue;
 
-		for (level = 0; level < wm_state->num_levels; level++) {
+		for (level = 0; level < num_levels; level++) {
 			struct g4x_pipe_wm *raw =
 				&crtc_state->wm.vlv.raw[level];
 
 			raw->plane[plane_id] = 0;
-
-			wm_state->wm[level].plane[plane_id] =
-				vlv_invert_wm_value(raw->plane[plane_id],
-						    fifo_state->plane[plane_id]);
 		}
 	}
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
+		int ret;
+
+		ret = _vlv_compute_pipe_wm(crtc_state);
+		drm_WARN_ON(&dev_priv->drm, ret);
 
 		crtc_state->wm.vlv.intermediate =
 			crtc_state->wm.vlv.optimal;
@@ -4057,9 +4045,9 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
  */
 static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv)
 {
-	intel_uncore_write(&dev_priv->uncore, WM3_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM3_LP_ILK) & ~WM_LP_ENABLE);
-	intel_uncore_write(&dev_priv->uncore, WM2_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM2_LP_ILK) & ~WM_LP_ENABLE);
-	intel_uncore_write(&dev_priv->uncore, WM1_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM1_LP_ILK) & ~WM_LP_ENABLE);
+	intel_uncore_rmw(&dev_priv->uncore, WM3_LP_ILK, WM_LP_ENABLE, 0);
+	intel_uncore_rmw(&dev_priv->uncore, WM2_LP_ILK, WM_LP_ENABLE, 0);
+	intel_uncore_rmw(&dev_priv->uncore, WM1_LP_ILK, WM_LP_ENABLE, 0);
 
 	/*
 	 * Don't touch WM_LP_SPRITE_ENABLE here.
@@ -4113,11 +4101,9 @@ static void g4x_disable_trickle_feed(struct drm_i915_private *dev_priv)
 	enum pipe pipe;
 
 	for_each_pipe(dev_priv, pipe) {
-		intel_uncore_write(&dev_priv->uncore, DSPCNTR(pipe),
-			   intel_uncore_read(&dev_priv->uncore, DSPCNTR(pipe)) |
-			   DISP_TRICKLE_FEED_DISABLE);
+		intel_uncore_rmw(&dev_priv->uncore, DSPCNTR(pipe), 0, DISP_TRICKLE_FEED_DISABLE);
 
-		intel_uncore_write(&dev_priv->uncore, DSPSURF(pipe), intel_uncore_read(&dev_priv->uncore, DSPSURF(pipe)));
+		intel_uncore_rmw(&dev_priv->uncore, DSPSURF(pipe), 0, 0);
 		intel_uncore_posting_read(&dev_priv->uncore, DSPSURF(pipe));
 	}
 }
@@ -4164,19 +4150,13 @@ static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_IRONLAKE_M(dev_priv)) {
 		/* WaFbcAsynchFlipDisableFbcQueue:ilk */
-		intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1,
-			   intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1) |
-			   ILK_FBCQ_DIS);
-		intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2,
-			   intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) |
-			   ILK_DPARB_GATE);
+		intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, 0, ILK_FBCQ_DIS);
+		intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_DPARB_GATE);
 	}
 
 	intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, dspclk_gate);
 
-	intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2,
-		   intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) |
-		   ILK_ELPIN_409_SELECT);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_ELPIN_409_SELECT);
 
 	g4x_disable_trickle_feed(dev_priv);
 
@@ -4196,8 +4176,7 @@ static void cpt_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE |
 		   PCH_DPLUNIT_CLOCK_GATE_DISABLE |
 		   PCH_CPUNIT_CLOCK_GATE_DISABLE);
-	intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN2, intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN2) |
-		   DPLS_EDP_PPS_FIX_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, SOUTH_CHICKEN2, 0, DPLS_EDP_PPS_FIX_DIS);
 	/* The below fixes the weird display corruption, a few pixels shifted
 	 * downward, on (only) LVDS of some HP laptops with IVY.
 	 */
@@ -4235,9 +4214,7 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, dspclk_gate);
 
-	intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2,
-		   intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) |
-		   ILK_ELPIN_409_SELECT);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_ELPIN_409_SELECT);
 
 	intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1,
 		   intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) |
@@ -4297,14 +4274,12 @@ static void lpt_init_clock_gating(struct drm_i915_private *dev_priv)
 	 * disabled when not needed anymore in order to save power.
 	 */
 	if (HAS_PCH_LPT_LP(dev_priv))
-		intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D,
-			   intel_uncore_read(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D) |
-			   PCH_LP_PARTITION_LEVEL_DISABLE);
+		intel_uncore_rmw(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D,
+				 0, PCH_LP_PARTITION_LEVEL_DISABLE);
 
 	/* WADPOClockGatingDisable:hsw */
-	intel_uncore_write(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A),
-		   intel_uncore_read(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A)) |
-		   TRANS_CHICKEN1_DP0UNIT_GC_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A),
+			 0, TRANS_CHICKEN1_DP0UNIT_GC_DISABLE);
 }
 
 static void lpt_suspend_hw(struct drm_i915_private *dev_priv)
@@ -4325,22 +4300,22 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
 	u32 val;
 
 	/* WaTempDisableDOPClkGating:bdw */
-	misccpctl = intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL);
-	intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+	misccpctl = intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL,
+					       GEN8_DOP_CLOCK_GATE_ENABLE, 0);
 
-	val = intel_uncore_read(&dev_priv->uncore, GEN8_L3SQCREG1);
+	val = intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1);
 	val &= ~L3_PRIO_CREDITS_MASK;
 	val |= L3_GENERAL_PRIO_CREDITS(general_prio_credits);
 	val |= L3_HIGH_PRIO_CREDITS(high_prio_credits);
-	intel_uncore_write(&dev_priv->uncore, GEN8_L3SQCREG1, val);
+	intel_gt_mcr_multicast_write(to_gt(dev_priv), GEN8_L3SQCREG1, val);
 
 	/*
 	 * Wait at least 100 clocks before re-enabling clock gating.
 	 * See the definition of L3SQCREG1 in BSpec.
 	 */
-	intel_uncore_posting_read(&dev_priv->uncore, GEN8_L3SQCREG1);
+	intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1);
 	udelay(1);
-	intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl);
+	intel_gt_mcr_multicast_write(to_gt(dev_priv), GEN8_MISCCPCTL, misccpctl);
 }
 
 static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4363,8 +4338,7 @@ static void gen12lp_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	/* Wa_1409825376:tgl (pre-prod)*/
 	if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0))
-		intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) |
-			   TGL_VRH_GATING_DIS);
+		intel_uncore_rmw(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, 0, TGL_VRH_GATING_DIS);
 
 	/* Wa_14013723622:tgl,rkl,dg1,adl-s */
 	if (DISPLAY_VER(dev_priv) == 12)
@@ -4389,8 +4363,7 @@ static void dg1_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	/* Wa_1409836686:dg1[a0] */
 	if (IS_DG1_GRAPHICS_STEP(dev_priv, STEP_A0, STEP_B0))
-		intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) |
-			   DPT_GATING_DIS);
+		intel_uncore_rmw(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, 0, DPT_GATING_DIS);
 }
 
 static void xehpsdv_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4432,8 +4405,7 @@ static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
 		return;
 
 	/* Display WA #1181 WaSouthDisplayDisablePWMCGEGating: cnp */
-	intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, intel_uncore_read(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D) |
-		   CNP_PWM_CGE_GATING_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, 0, CNP_PWM_CGE_GATING_DISABLE);
 }
 
 static void cfl_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4442,23 +4414,20 @@ static void cfl_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WAC6entrylatency:cfl */
-	intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) |
-		   FBC_LLC_FULLY_OPEN);
+	intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN);
 
 	/*
 	 * WaFbcTurnOffFbcWatermark:cfl
 	 * Display WA #0562: cfl
 	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_WM_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS);
 
 	/*
 	 * WaFbcNukeOnHostModify:cfl
 	 * Display WA #0873: cfl
 	 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
-			   intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) |
-			   DPFC_NUKE_ON_ANY_MODIFICATION);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
+			 0, DPFC_NUKE_ON_ANY_MODIFICATION);
 }
 
 static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4466,33 +4435,30 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WAC6entrylatency:kbl */
-	intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) |
-		   FBC_LLC_FULLY_OPEN);
+	intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN);
 
 	/* WaDisableSDEUnitClockGating:kbl */
 	if (IS_KBL_GRAPHICS_STEP(dev_priv, 0, STEP_C0))
-		intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
-			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+		intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6,
+				 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableGamClockGating:kbl */
 	if (IS_KBL_GRAPHICS_STEP(dev_priv, 0, STEP_C0))
-		intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) |
-			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
+		intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1,
+				 0, GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
 
 	/*
 	 * WaFbcTurnOffFbcWatermark:kbl
 	 * Display WA #0562: kbl
 	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_WM_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS);
 
 	/*
 	 * WaFbcNukeOnHostModify:kbl
 	 * Display WA #0873: kbl
 	 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
-			   intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) |
-			   DPFC_NUKE_ON_ANY_MODIFICATION);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
+			 0, DPFC_NUKE_ON_ANY_MODIFICATION);
 }
 
 static void skl_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4500,35 +4466,30 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WaDisableDopClockGating:skl */
-	intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL) &
-		   ~GEN7_DOP_CLOCK_GATE_ENABLE);
+	intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL,
+				   GEN8_DOP_CLOCK_GATE_ENABLE, 0);
 
 	/* WAC6entrylatency:skl */
-	intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) |
-		   FBC_LLC_FULLY_OPEN);
+	intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN);
 
 	/*
 	 * WaFbcTurnOffFbcWatermark:skl
 	 * Display WA #0562: skl
 	 */
-	intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) |
-		   DISP_FBC_WM_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS);
 
 	/*
 	 * WaFbcNukeOnHostModify:skl
 	 * Display WA #0873: skl
 	 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
-			   intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) |
-			   DPFC_NUKE_ON_ANY_MODIFICATION);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
+			 0, DPFC_NUKE_ON_ANY_MODIFICATION);
 
 	/*
 	 * WaFbcHighMemBwCorruptionAvoidance:skl
 	 * Display WA #0883: skl
 	 */
-	intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A),
-			   intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) |
-			   DPFC_DISABLE_DUMMY0);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), 0, DPFC_DISABLE_DUMMY0);
 }
 
 static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -4536,43 +4497,37 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 	enum pipe pipe;
 
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
-	intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
-		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
-		   HSW_FBCQ_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), 0, HSW_FBCQ_DIS);
 
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
-	intel_uncore_write(&dev_priv->uncore, GAM_ECOCHK, intel_uncore_read(&dev_priv->uncore, GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
+	intel_uncore_rmw(&dev_priv->uncore, GAM_ECOCHK, 0, HSW_ECOCHK_ARB_PRIO_SOL);
 
 	/* WaPsrDPAMaskVBlankInSRD:bdw */
-	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
-		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
+	intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, DPA_MASK_VBLANK_SRD);
 
 	for_each_pipe(dev_priv, pipe) {
 		/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
-		intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
-			   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) |
-			   BDW_DPRS_MASK_VBLANK_SRD);
+		intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+				 0, BDW_DPRS_MASK_VBLANK_SRD);
 	}
 
 	/* WaVSRefCountFullforceMissDisable:bdw */
 	/* WaDSRefCountFullforceMissDisable:bdw */
-	intel_uncore_write(&dev_priv->uncore, GEN7_FF_THREAD_MODE,
-		   intel_uncore_read(&dev_priv->uncore, GEN7_FF_THREAD_MODE) &
-		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_FF_THREAD_MODE,
+			 GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME, 0);
 
 	intel_uncore_write(&dev_priv->uncore, RING_PSMI_CTL(RENDER_RING_BASE),
 		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
 
 	/* WaDisableSDEUnitClockGating:bdw */
-	intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
-		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaProgramL3SqcReg1Default:bdw */
 	gen8_set_l3sqc_credits(dev_priv, 30, 2);
 
 	/* WaKVMNotificationOnConfigChange:bdw */
-	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR2_1, intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR2_1)
-		   | KVM_CONFIG_CHANGE_NOTIFICATION_SELECT);
+	intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR2_1,
+			 0, KVM_CONFIG_CHANGE_NOTIFICATION_SELECT);
 
 	lpt_init_clock_gating(dev_priv);
 
@@ -4581,38 +4536,30 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 	 * Also see the CHICKEN2 write in bdw_init_workarounds() to disable DOP
 	 * clock gating.
 	 */
-	intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1,
-		   intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) | GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1, 0, GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
 }
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
-	intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
-		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
-		   HSW_FBCQ_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), 0, HSW_FBCQ_DIS);
 
 	/* This is required by WaCatErrorRejectionIssue:hsw */
-	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
-		   intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
-		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+			 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
-	intel_uncore_write(&dev_priv->uncore, GAM_ECOCHK, intel_uncore_read(&dev_priv->uncore, GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
+	intel_uncore_rmw(&dev_priv->uncore, GAM_ECOCHK, 0, HSW_ECOCHK_ARB_PRIO_SOL);
 
 	lpt_init_clock_gating(dev_priv);
 }
 
 static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	u32 snpcr;
-
 	intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaFbcAsynchFlipDisableFbcQueue:ivb */
-	intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1,
-		   intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1) |
-		   ILK_FBCQ_DIS);
+	intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, 0, ILK_FBCQ_DIS);
 
 	/* WaDisableBackToBackFlipFix:ivb */
 	intel_uncore_write(&dev_priv->uncore, IVB_CHICKEN3,
@@ -4638,16 +4585,13 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 		   GEN6_RCZUNIT_CLOCK_GATE_DISABLE);
 
 	/* This is required by WaCatErrorRejectionIssue:ivb */
-	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
-			intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
-			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+			 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
 	g4x_disable_trickle_feed(dev_priv);
 
-	snpcr = intel_uncore_read(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR);
-	snpcr &= ~GEN6_MBC_SNPCR_MASK;
-	snpcr |= GEN6_MBC_SNPCR_MED;
-	intel_uncore_write(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR, snpcr);
+	intel_uncore_rmw(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR, GEN6_MBC_SNPCR_MASK,
+			 GEN6_MBC_SNPCR_MED);
 
 	if (!HAS_PCH_NOP(dev_priv))
 		cpt_init_clock_gating(dev_priv);
@@ -4667,9 +4611,8 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
 	/* This is required by WaCatErrorRejectionIssue:vlv */
-	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
-		   intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
-		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+			 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
 	/*
 	 * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
@@ -4681,8 +4624,7 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaDisableL3Bank2xClockGate:vlv
 	 * Disabling L3 clock gating- MMIO 940c[25] = 1
 	 * Set bit 25, to disable L3_BANK_2x_CLK_GATING */
-	intel_uncore_write(&dev_priv->uncore, GEN7_UCGCTL4,
-		   intel_uncore_read(&dev_priv->uncore, GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_UCGCTL4, 0, GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
 
 	/*
 	 * WaDisableVLVClockGating_VBIIssue:vlv
@@ -4696,21 +4638,18 @@ static void chv_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
-	intel_uncore_write(&dev_priv->uncore, GEN7_FF_THREAD_MODE,
-		   intel_uncore_read(&dev_priv->uncore, GEN7_FF_THREAD_MODE) &
-		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
+	intel_uncore_rmw(&dev_priv->uncore, GEN7_FF_THREAD_MODE,
+			 GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME, 0);
 
 	/* WaDisableSemaphoreAndSyncFlipWait:chv */
 	intel_uncore_write(&dev_priv->uncore, RING_PSMI_CTL(RENDER_RING_BASE),
 		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
 
 	/* WaDisableCSUnitClockGating:chv */
-	intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) |
-		   GEN6_CSUNIT_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1, 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableSDEUnitClockGating:chv */
-	intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
-		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+	intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/*
 	 * WaProgramL3SqcReg1Default:chv
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 6ed5786bcd29..129746713d07 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -591,8 +591,15 @@ void intel_runtime_pm_enable(struct intel_runtime_pm *rpm)
 		pm_runtime_use_autosuspend(kdev);
 	}
 
-	/* Enable by default */
-	pm_runtime_allow(kdev);
+	/*
+	 *  FIXME: Temp hammer to keep autosupend disable on lmem supported platforms.
+	 *  As per PCIe specs 5.3.1.4.1, all iomem read write request over a PCIe
+	 *  function will be unsupported in case PCIe endpoint function is in D3.
+	 *  Let's keep i915 autosuspend control 'on' till we fix all known issue
+	 *  with lmem access in D3.
+	 */
+	if (!IS_DGFX(i915))
+		pm_runtime_allow(kdev);
 
 	/*
 	 * The core calls the driver load handler with an RPM reference held.
@@ -626,6 +633,8 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm)
 						     runtime_pm);
 	int count = atomic_read(&rpm->wakeref_count);
 
+	intel_wakeref_auto_fini(&rpm->userfault_wakeref);
+
 	drm_WARN(&i915->drm, count,
 		 "i915 raw-wakerefs=%d wakelocks=%d on cleanup\n",
 		 intel_rpm_raw_wakeref_count(count),
@@ -645,4 +654,7 @@ void intel_runtime_pm_init_early(struct intel_runtime_pm *rpm)
 	rpm->available = HAS_RUNTIME_PM(i915);
 
 	init_intel_runtime_pm_wakeref(rpm);
+	INIT_LIST_HEAD(&rpm->lmem_userfault_list);
+	spin_lock_init(&rpm->lmem_userfault_lock);
+	intel_wakeref_auto_init(&rpm->userfault_wakeref, rpm);
 }
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h
index d9160e3ff4af..98b8b28baaa1 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.h
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.h
@@ -53,6 +53,28 @@ struct intel_runtime_pm {
 	bool irqs_enabled;
 	bool no_wakeref_tracking;
 
+	/*
+	 *  Protects access to lmem usefault list.
+	 *  It is required, if we are outside of the runtime suspend path,
+	 *  access to @lmem_userfault_list requires always first grabbing the
+	 *  runtime pm, to ensure we can't race against runtime suspend.
+	 *  Once we have that we also need to grab @lmem_userfault_lock,
+	 *  at which point we have exclusive access.
+	 *  The runtime suspend path is special since it doesn't really hold any locks,
+	 *  but instead has exclusive access by virtue of all other accesses requiring
+	 *  holding the runtime pm wakeref.
+	 */
+	spinlock_t lmem_userfault_lock;
+
+	/*
+	 *  Keep list of userfaulted gem obj, which require to release their
+	 *  mmap mappings at runtime suspend path.
+	 */
+	struct list_head lmem_userfault_list;
+
+	/* Manual runtime pm autosuspend delay for user GGTT/lmem mmaps */
+	struct intel_wakeref_auto userfault_wakeref;
+
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 	/*
 	 * To aide detection of wakeref leaks and general misuse, we
diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c
index 42b3133d8387..75d7a86c60c0 100644
--- a/drivers/gpu/drm/i915/intel_step.c
+++ b/drivers/gpu/drm/i915/intel_step.c
@@ -135,6 +135,19 @@ static const struct intel_step_info adlp_n_revids[] = {
 	[0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_D0 },
 };
 
+static u8 gmd_to_intel_step(struct drm_i915_private *i915,
+			    struct intel_ip_version *gmd)
+{
+	u8 step = gmd->step + STEP_A0;
+
+	if (step >= STEP_FUTURE) {
+		drm_dbg(&i915->drm, "Using future steppings\n");
+		return STEP_FUTURE;
+	}
+
+	return step;
+}
+
 static void pvc_step_init(struct drm_i915_private *i915, int pci_revid);
 
 void intel_step_init(struct drm_i915_private *i915)
@@ -144,6 +157,18 @@ void intel_step_init(struct drm_i915_private *i915)
 	int revid = INTEL_REVID(i915);
 	struct intel_step_info step = {};
 
+	if (HAS_GMD_ID(i915)) {
+		step.graphics_step = gmd_to_intel_step(i915,
+						       &RUNTIME_INFO(i915)->graphics.ip);
+		step.media_step = gmd_to_intel_step(i915,
+						    &RUNTIME_INFO(i915)->media.ip);
+		step.display_step = gmd_to_intel_step(i915,
+						      &RUNTIME_INFO(i915)->display.ip);
+		RUNTIME_INFO(i915)->step = step;
+
+		return;
+	}
+
 	if (IS_PONTEVECCHIO(i915)) {
 		pvc_step_init(i915, revid);
 		return;
diff --git a/drivers/gpu/drm/i915/intel_step.h b/drivers/gpu/drm/i915/intel_step.h
index a6b12bfa9744..96dfca4cba73 100644
--- a/drivers/gpu/drm/i915/intel_step.h
+++ b/drivers/gpu/drm/i915/intel_step.h
@@ -11,6 +11,10 @@
 struct drm_i915_private;
 
 struct intel_step_info {
+	/*
+	 * It is expected to have 4 number steps per letter. Deviation from
+	 * the expectation breaks gmd_to_intel_step().
+	 */
 	u8 graphics_step;	/* Represents the compute tile on Xe_HPC */
 	u8 display_step;
 	u8 media_step;
@@ -23,21 +27,43 @@ struct intel_step_info {
 	func(A0)			\
 	func(A1)			\
 	func(A2)			\
+	func(A3)			\
 	func(B0)			\
 	func(B1)			\
 	func(B2)			\
 	func(B3)			\
 	func(C0)			\
 	func(C1)			\
+	func(C2)			\
+	func(C3)			\
 	func(D0)			\
 	func(D1)			\
+	func(D2)			\
+	func(D3)			\
 	func(E0)			\
+	func(E1)			\
+	func(E2)			\
+	func(E3)			\
 	func(F0)			\
+	func(F1)			\
+	func(F2)			\
+	func(F3)			\
 	func(G0)			\
+	func(G1)			\
+	func(G2)			\
+	func(G3)			\
 	func(H0)			\
+	func(H1)			\
+	func(H2)			\
+	func(H3)			\
 	func(I0)			\
 	func(I1)			\
-	func(J0)
+	func(I2)			\
+	func(I3)			\
+	func(J0)			\
+	func(J1)			\
+	func(J2)			\
+	func(J3)
 
 /*
  * Symbolic steppings that do not match the hardware. These are valid both as gt
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 5cd423c7b646..2a3e2869fe71 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -104,6 +104,7 @@ static const char * const forcewake_domain_names[] = {
 	"vebox1",
 	"vebox2",
 	"vebox3",
+	"gsc",
 };
 
 const char *
@@ -888,10 +889,13 @@ void assert_forcewakes_active(struct intel_uncore *uncore,
 	spin_unlock_irq(&uncore->lock);
 }
 
-/* We give fast paths for the really cool registers */
+/*
+ * We give fast paths for the really cool registers.  The second range includes
+ * media domains (and the GSC starting from Xe_LPM+)
+ */
 #define NEEDS_FORCE_WAKE(reg) ({ \
 	u32 __reg = (reg); \
-	__reg < 0x40000 || __reg >= GEN11_BSD_RING_BASE; \
+	__reg < 0x40000 || __reg >= 0x116000; \
 })
 
 static int fw_range_cmp(u32 offset, const struct intel_forcewake_range *entry)
@@ -1131,6 +1135,45 @@ static const struct i915_range pvc_shadowed_regs[] = {
 	{ .start = 0x1F8510, .end = 0x1F8550 },
 };
 
+static const struct i915_range mtl_shadowed_regs[] = {
+	{ .start =   0x2030, .end =   0x2030 },
+	{ .start =   0x2510, .end =   0x2550 },
+	{ .start =   0xA008, .end =   0xA00C },
+	{ .start =   0xA188, .end =   0xA188 },
+	{ .start =   0xA278, .end =   0xA278 },
+	{ .start =   0xA540, .end =   0xA56C },
+	{ .start =   0xC050, .end =   0xC050 },
+	{ .start =   0xC340, .end =   0xC340 },
+	{ .start =   0xC4C8, .end =   0xC4C8 },
+	{ .start =   0xC4E0, .end =   0xC4E0 },
+	{ .start =   0xC600, .end =   0xC600 },
+	{ .start =   0xC658, .end =   0xC658 },
+	{ .start =   0xCFD4, .end =   0xCFDC },
+	{ .start =  0x22030, .end =  0x22030 },
+	{ .start =  0x22510, .end =  0x22550 },
+};
+
+static const struct i915_range xelpmp_shadowed_regs[] = {
+	{ .start = 0x1C0030, .end = 0x1C0030 },
+	{ .start = 0x1C0510, .end = 0x1C0550 },
+	{ .start = 0x1C8030, .end = 0x1C8030 },
+	{ .start = 0x1C8510, .end = 0x1C8550 },
+	{ .start = 0x1D0030, .end = 0x1D0030 },
+	{ .start = 0x1D0510, .end = 0x1D0550 },
+	{ .start = 0x38A008, .end = 0x38A00C },
+	{ .start = 0x38A188, .end = 0x38A188 },
+	{ .start = 0x38A278, .end = 0x38A278 },
+	{ .start = 0x38A540, .end = 0x38A56C },
+	{ .start = 0x38A618, .end = 0x38A618 },
+	{ .start = 0x38C050, .end = 0x38C050 },
+	{ .start = 0x38C340, .end = 0x38C340 },
+	{ .start = 0x38C4C8, .end = 0x38C4C8 },
+	{ .start = 0x38C4E0, .end = 0x38C4E4 },
+	{ .start = 0x38C600, .end = 0x38C600 },
+	{ .start = 0x38C658, .end = 0x38C658 },
+	{ .start = 0x38CFD4, .end = 0x38CFDC },
+};
+
 static int mmio_range_cmp(u32 key, const struct i915_range *range)
 {
 	if (key < range->start)
@@ -1639,25 +1682,27 @@ static const struct intel_forcewake_range __pvc_fw_ranges[] = {
 	GEN_FW_RANGE(0x12000, 0x12fff, 0), /*
 		0x12000 - 0x127ff: always on
 		0x12800 - 0x12fff: reserved */
-	GEN_FW_RANGE(0x13000, 0x23fff, FORCEWAKE_GT), /*
+	GEN_FW_RANGE(0x13000, 0x19fff, FORCEWAKE_GT), /*
 		0x13000 - 0x135ff: gt
 		0x13600 - 0x147ff: reserved
 		0x14800 - 0x153ff: gt
-		0x15400 - 0x19fff: reserved
-		0x1a000 - 0x1ffff: gt
-		0x20000 - 0x21fff: reserved
-		0x22000 - 0x23fff: gt */
+		0x15400 - 0x19fff: reserved */
+	GEN_FW_RANGE(0x1a000, 0x21fff, FORCEWAKE_RENDER), /*
+		0x1a000 - 0x1ffff: render
+		0x20000 - 0x21fff: reserved */
+	GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_GT),
 	GEN_FW_RANGE(0x24000, 0x2417f, 0), /*
 		24000 - 0x2407f: always on
 		24080 - 0x2417f: reserved */
-	GEN_FW_RANGE(0x24180, 0x3ffff, FORCEWAKE_GT), /*
+	GEN_FW_RANGE(0x24180, 0x25fff, FORCEWAKE_GT), /*
 		0x24180 - 0x241ff: gt
 		0x24200 - 0x251ff: reserved
 		0x25200 - 0x252ff: gt
-		0x25300 - 0x25fff: reserved
-		0x26000 - 0x27fff: gt
-		0x28000 - 0x2ffff: reserved
-		0x30000 - 0x3ffff: gt */
+		0x25300 - 0x25fff: reserved */
+	GEN_FW_RANGE(0x26000, 0x2ffff, FORCEWAKE_RENDER), /*
+		0x26000 - 0x27fff: render
+		0x28000 - 0x2ffff: reserved */
+	GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_GT),
 	GEN_FW_RANGE(0x40000, 0x1bffff, 0),
 	GEN_FW_RANGE(0x1c0000, 0x1c3fff, FORCEWAKE_MEDIA_VDBOX0), /*
 		0x1c0000 - 0x1c2bff: VD0
@@ -1679,6 +1724,162 @@ static const struct intel_forcewake_range __pvc_fw_ranges[] = {
 	GEN_FW_RANGE(0x3e0000, 0x3effff, FORCEWAKE_GT),
 };
 
+static const struct intel_forcewake_range __mtl_fw_ranges[] = {
+	GEN_FW_RANGE(0x0, 0xaff, 0),
+	GEN_FW_RANGE(0xb00, 0xbff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0xc00, 0xfff, 0),
+	GEN_FW_RANGE(0x1000, 0x1fff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x2700, 0x2fff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x3000, 0x3fff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x4000, 0x51ff, FORCEWAKE_GT), /*
+		0x4000 - 0x48ff: render
+		0x4900 - 0x51ff: reserved */
+	GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER), /*
+		0x5200 - 0x53ff: render
+		0x5400 - 0x54ff: reserved
+		0x5500 - 0x7fff: render */
+	GEN_FW_RANGE(0x8000, 0x813f, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x8140, 0x817f, FORCEWAKE_RENDER), /*
+		0x8140 - 0x815f: render
+		0x8160 - 0x817f: reserved */
+	GEN_FW_RANGE(0x8180, 0x81ff, 0),
+	GEN_FW_RANGE(0x8200, 0x94cf, FORCEWAKE_GT), /*
+		0x8200 - 0x87ff: gt
+		0x8800 - 0x8dff: reserved
+		0x8e00 - 0x8f7f: gt
+		0x8f80 - 0x8fff: reserved
+		0x9000 - 0x947f: gt
+		0x9480 - 0x94cf: reserved */
+	GEN_FW_RANGE(0x94d0, 0x955f, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x9560, 0x967f, 0), /*
+		0x9560 - 0x95ff: always on
+		0x9600 - 0x967f: reserved */
+	GEN_FW_RANGE(0x9680, 0x97ff, FORCEWAKE_RENDER), /*
+		0x9680 - 0x96ff: render
+		0x9700 - 0x97ff: reserved */
+	GEN_FW_RANGE(0x9800, 0xcfff, FORCEWAKE_GT), /*
+		0x9800 - 0xb4ff: gt
+		0xb500 - 0xbfff: reserved
+		0xc000 - 0xcfff: gt */
+	GEN_FW_RANGE(0xd000, 0xd7ff, 0), /*
+		0xd000 - 0xd3ff: always on
+		0xd400 - 0xd7ff: reserved */
+	GEN_FW_RANGE(0xd800, 0xd87f, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0xd880, 0xdbff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0xdc00, 0xdcff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0xdd00, 0xde7f, FORCEWAKE_GT), /*
+		0xdd00 - 0xddff: gt
+		0xde00 - 0xde7f: reserved */
+	GEN_FW_RANGE(0xde80, 0xe8ff, FORCEWAKE_RENDER), /*
+		0xde80 - 0xdfff: render
+		0xe000 - 0xe0ff: reserved
+		0xe100 - 0xe8ff: render */
+	GEN_FW_RANGE(0xe900, 0xe9ff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0xea00, 0x147ff, 0), /*
+		 0xea00 - 0x11fff: reserved
+		0x12000 - 0x127ff: always on
+		0x12800 - 0x147ff: reserved */
+	GEN_FW_RANGE(0x14800, 0x19fff, FORCEWAKE_GT), /*
+		0x14800 - 0x153ff: gt
+		0x15400 - 0x19fff: reserved */
+	GEN_FW_RANGE(0x1a000, 0x21fff, FORCEWAKE_RENDER), /*
+		0x1a000 - 0x1bfff: render
+		0x1c000 - 0x21fff: reserved */
+	GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x24000, 0x2ffff, 0), /*
+		0x24000 - 0x2407f: always on
+		0x24080 - 0x2ffff: reserved */
+	GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_GT)
+};
+
+/*
+ * Note that the register ranges here are the final offsets after
+ * translation of the GSI block to the 0x380000 offset.
+ *
+ * NOTE:  There are a couple MCR ranges near the bottom of this table
+ * that need to power up either VD0 or VD2 depending on which replicated
+ * instance of the register we're trying to access.  Our forcewake logic
+ * at the moment doesn't have a good way to take steering into consideration,
+ * and the driver doesn't even access any registers in those ranges today,
+ * so for now we just mark those ranges as FORCEWAKE_ALL.  That will ensure
+ * proper operation if we do start using the ranges in the future, and we
+ * can determine at that time whether it's worth adding extra complexity to
+ * the forcewake handling to take steering into consideration.
+ */
+static const struct intel_forcewake_range __xelpmp_fw_ranges[] = {
+	GEN_FW_RANGE(0x0, 0x115fff, 0), /* render GT range */
+	GEN_FW_RANGE(0x116000, 0x11ffff, FORCEWAKE_GSC), /*
+		0x116000 - 0x117fff: gsc
+		0x118000 - 0x119fff: reserved
+		0x11a000 - 0x11efff: gsc
+		0x11f000 - 0x11ffff: reserved */
+	GEN_FW_RANGE(0x120000, 0x1bffff, 0), /* non-GT range */
+	GEN_FW_RANGE(0x1c0000, 0x1c7fff, FORCEWAKE_MEDIA_VDBOX0), /*
+		0x1c0000 - 0x1c3dff: VD0
+		0x1c3e00 - 0x1c3eff: reserved
+		0x1c3f00 - 0x1c3fff: VD0
+		0x1c4000 - 0x1c7fff: reserved */
+	GEN_FW_RANGE(0x1c8000, 0x1cbfff, FORCEWAKE_MEDIA_VEBOX0), /*
+		0x1c8000 - 0x1ca0ff: VE0
+		0x1ca100 - 0x1cbfff: reserved */
+	GEN_FW_RANGE(0x1cc000, 0x1cffff, FORCEWAKE_MEDIA_VDBOX0), /*
+		0x1cc000 - 0x1cdfff: VD0
+		0x1ce000 - 0x1cffff: reserved */
+	GEN_FW_RANGE(0x1d0000, 0x1d7fff, FORCEWAKE_MEDIA_VDBOX2), /*
+		0x1d0000 - 0x1d3dff: VD2
+		0x1d3e00 - 0x1d3eff: reserved
+		0x1d4000 - 0x1d7fff: VD2 */
+	GEN_FW_RANGE(0x1d8000, 0x1da0ff, FORCEWAKE_MEDIA_VEBOX1),
+	GEN_FW_RANGE(0x1da100, 0x380aff, 0), /*
+		0x1da100 - 0x23ffff: reserved
+		0x240000 - 0x37ffff: non-GT range
+		0x380000 - 0x380aff: reserved */
+	GEN_FW_RANGE(0x380b00, 0x380bff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x380c00, 0x380fff, 0),
+	GEN_FW_RANGE(0x381000, 0x38817f, FORCEWAKE_GT), /*
+		0x381000 - 0x381fff: gt
+		0x382000 - 0x383fff: reserved
+		0x384000 - 0x384aff: gt
+		0x384b00 - 0x3851ff: reserved
+		0x385200 - 0x3871ff: gt
+		0x387200 - 0x387fff: reserved
+		0x388000 - 0x38813f: gt
+		0x388140 - 0x38817f: reserved */
+	GEN_FW_RANGE(0x388180, 0x3882ff, 0), /*
+		0x388180 - 0x3881ff: always on
+		0x388200 - 0x3882ff: reserved */
+	GEN_FW_RANGE(0x388300, 0x38955f, FORCEWAKE_GT), /*
+		0x388300 - 0x38887f: gt
+		0x388880 - 0x388fff: reserved
+		0x389000 - 0x38947f: gt
+		0x389480 - 0x38955f: reserved */
+	GEN_FW_RANGE(0x389560, 0x389fff, 0), /*
+		0x389560 - 0x3895ff: always on
+		0x389600 - 0x389fff: reserved */
+	GEN_FW_RANGE(0x38a000, 0x38cfff, FORCEWAKE_GT), /*
+		0x38a000 - 0x38afff: gt
+		0x38b000 - 0x38bfff: reserved
+		0x38c000 - 0x38cfff: gt */
+	GEN_FW_RANGE(0x38d000, 0x38d11f, 0),
+	GEN_FW_RANGE(0x38d120, 0x391fff, FORCEWAKE_GT), /*
+		0x38d120 - 0x38dfff: gt
+		0x38e000 - 0x38efff: reserved
+		0x38f000 - 0x38ffff: gt
+		0x389000 - 0x391fff: reserved */
+	GEN_FW_RANGE(0x392000, 0x392fff, 0), /*
+		0x392000 - 0x3927ff: always on
+		0x392800 - 0x292fff: reserved */
+	GEN_FW_RANGE(0x393000, 0x3931ff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x393200, 0x39323f, FORCEWAKE_ALL), /* instance-based, see note above */
+	GEN_FW_RANGE(0x393240, 0x3933ff, FORCEWAKE_GT),
+	GEN_FW_RANGE(0x393400, 0x3934ff, FORCEWAKE_ALL), /* instance-based, see note above */
+	GEN_FW_RANGE(0x393500, 0x393c7f, 0), /*
+		0x393500 - 0x393bff: reserved
+		0x393c00 - 0x393c7f: always on */
+	GEN_FW_RANGE(0x393c80, 0x393dff, FORCEWAKE_GT),
+};
+
 static void
 ilk_dummy_write(struct intel_uncore *uncore)
 {
@@ -2021,6 +2222,7 @@ static int __fw_domain_init(struct intel_uncore *uncore,
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX1 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX1));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX2 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX2));
 	BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX3 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX3));
+	BUILD_BUG_ON(FORCEWAKE_GSC != (1 << FW_DOMAIN_ID_GSC));
 
 	d->mask = BIT(domain_id);
 
@@ -2085,17 +2287,26 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore)
 	(ret ?: (ret = __fw_domain_init((uncore__), (id__), (set__), (ack__))))
 
 	if (GRAPHICS_VER(i915) >= 11) {
-		/* we'll prune the domains of missing engines later */
-		intel_engine_mask_t emask = RUNTIME_INFO(i915)->platform_engine_mask;
+		intel_engine_mask_t emask;
 		int i;
 
+		/* we'll prune the domains of missing engines later */
+		emask = uncore->gt->info.engine_mask;
+
 		uncore->fw_get_funcs = &uncore_get_fallback;
-		fw_domain_init(uncore, FW_DOMAIN_ID_RENDER,
-			       FORCEWAKE_RENDER_GEN9,
-			       FORCEWAKE_ACK_RENDER_GEN9);
-		fw_domain_init(uncore, FW_DOMAIN_ID_GT,
-			       FORCEWAKE_GT_GEN9,
-			       FORCEWAKE_ACK_GT_GEN9);
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+			fw_domain_init(uncore, FW_DOMAIN_ID_GT,
+				       FORCEWAKE_GT_GEN9,
+				       FORCEWAKE_ACK_GT_MTL);
+		else
+			fw_domain_init(uncore, FW_DOMAIN_ID_GT,
+				       FORCEWAKE_GT_GEN9,
+				       FORCEWAKE_ACK_GT_GEN9);
+
+		if (RCS_MASK(uncore->gt) || CCS_MASK(uncore->gt))
+			fw_domain_init(uncore, FW_DOMAIN_ID_RENDER,
+				       FORCEWAKE_RENDER_GEN9,
+				       FORCEWAKE_ACK_RENDER_GEN9);
 
 		for (i = 0; i < I915_MAX_VCS; i++) {
 			if (!__HAS_ENGINE(emask, _VCS(i)))
@@ -2113,6 +2324,10 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore)
 				       FORCEWAKE_MEDIA_VEBOX_GEN11(i),
 				       FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(i));
 		}
+
+		if (uncore->gt->type == GT_MEDIA)
+			fw_domain_init(uncore, FW_DOMAIN_ID_GSC,
+				       FORCEWAKE_REQ_GSC, FORCEWAKE_ACK_GSC);
 	} else if (IS_GRAPHICS_VER(i915, 9, 10)) {
 		uncore->fw_get_funcs = &uncore_get_fallback;
 		fw_domain_init(uncore, FW_DOMAIN_ID_RENDER,
@@ -2300,6 +2515,22 @@ static void uncore_raw_init(struct intel_uncore *uncore)
 	}
 }
 
+static int uncore_media_forcewake_init(struct intel_uncore *uncore)
+{
+	struct drm_i915_private *i915 = uncore->i915;
+
+	if (MEDIA_VER(i915) >= 13) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __xelpmp_fw_ranges);
+		ASSIGN_SHADOW_TABLE(uncore, xelpmp_shadowed_regs);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
+	} else {
+		MISSING_CASE(MEDIA_VER(i915));
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int uncore_forcewake_init(struct intel_uncore *uncore)
 {
 	struct drm_i915_private *i915 = uncore->i915;
@@ -2314,7 +2545,14 @@ static int uncore_forcewake_init(struct intel_uncore *uncore)
 
 	ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
 
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60)) {
+	if (uncore->gt->type == GT_MEDIA)
+		return uncore_media_forcewake_init(uncore);
+
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __mtl_fw_ranges);
+		ASSIGN_SHADOW_TABLE(uncore, mtl_shadowed_regs);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
+	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60)) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __pvc_fw_ranges);
 		ASSIGN_SHADOW_TABLE(uncore, pvc_shadowed_regs);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 5022bac80b67..5449146a0624 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -62,6 +62,7 @@ enum forcewake_domain_id {
 	FW_DOMAIN_ID_MEDIA_VEBOX1,
 	FW_DOMAIN_ID_MEDIA_VEBOX2,
 	FW_DOMAIN_ID_MEDIA_VEBOX3,
+	FW_DOMAIN_ID_GSC,
 
 	FW_DOMAIN_ID_COUNT
 };
@@ -82,6 +83,7 @@ enum forcewake_domains {
 	FORCEWAKE_MEDIA_VEBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX1),
 	FORCEWAKE_MEDIA_VEBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX2),
 	FORCEWAKE_MEDIA_VEBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX3),
+	FORCEWAKE_GSC		= BIT(FW_DOMAIN_ID_GSC),
 
 	FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1,
 };
@@ -431,15 +433,15 @@ intel_uncore_read64_2x32(struct intel_uncore *uncore,
 #define intel_uncore_write64_fw(...) __raw_uncore_write64(__VA_ARGS__)
 #define intel_uncore_posting_read_fw(...) ((void)intel_uncore_read_fw(__VA_ARGS__))
 
-static inline void intel_uncore_rmw(struct intel_uncore *uncore,
-				    i915_reg_t reg, u32 clear, u32 set)
+static inline u32 intel_uncore_rmw(struct intel_uncore *uncore,
+				   i915_reg_t reg, u32 clear, u32 set)
 {
 	u32 old, val;
 
 	old = intel_uncore_read(uncore, reg);
 	val = (old & ~clear) | set;
-	if (val != old)
-		intel_uncore_write(uncore, reg, val);
+	intel_uncore_write(uncore, reg, val);
+	return old;
 }
 
 static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c
index 69cdaaddc4a9..5efe61f67546 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c
@@ -103,19 +103,15 @@ static int create_vcs_context(struct intel_pxp *pxp)
 
 static void destroy_vcs_context(struct intel_pxp *pxp)
 {
-	intel_engine_destroy_pinned_context(fetch_and_zero(&pxp->ce));
+	if (pxp->ce)
+		intel_engine_destroy_pinned_context(fetch_and_zero(&pxp->ce));
 }
 
-void intel_pxp_init(struct intel_pxp *pxp)
+static void pxp_init_full(struct intel_pxp *pxp)
 {
 	struct intel_gt *gt = pxp_to_gt(pxp);
 	int ret;
 
-	if (!HAS_PXP(gt->i915))
-		return;
-
-	mutex_init(&pxp->tee_mutex);
-
 	/*
 	 * we'll use the completion to check if there is a termination pending,
 	 * so we start it as completed and we reinit it when a termination
@@ -124,8 +120,7 @@ void intel_pxp_init(struct intel_pxp *pxp)
 	init_completion(&pxp->termination);
 	complete_all(&pxp->termination);
 
-	mutex_init(&pxp->arb_mutex);
-	INIT_WORK(&pxp->session_work, intel_pxp_session_work);
+	intel_pxp_session_management_init(pxp);
 
 	ret = create_vcs_context(pxp);
 	if (ret)
@@ -143,11 +138,26 @@ out_context:
 	destroy_vcs_context(pxp);
 }
 
-void intel_pxp_fini(struct intel_pxp *pxp)
+void intel_pxp_init(struct intel_pxp *pxp)
 {
-	if (!intel_pxp_is_enabled(pxp))
+	struct intel_gt *gt = pxp_to_gt(pxp);
+
+	/* we rely on the mei PXP module */
+	if (!IS_ENABLED(CONFIG_INTEL_MEI_PXP))
 		return;
 
+	/*
+	 * If HuC is loaded by GSC but PXP is disabled, we can skip the init of
+	 * the full PXP session/object management and just init the tee channel.
+	 */
+	if (HAS_PXP(gt->i915))
+		pxp_init_full(pxp);
+	else if (intel_huc_is_loaded_by_gsc(&gt->uc.huc) && intel_uc_uses_huc(&gt->uc))
+		intel_pxp_tee_component_init(pxp);
+}
+
+void intel_pxp_fini(struct intel_pxp *pxp)
+{
 	pxp->arb_is_valid = false;
 
 	intel_pxp_tee_component_fini(pxp);
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h
index 73847e535cab..2da309088c6d 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h
@@ -12,7 +12,6 @@
 struct intel_pxp;
 struct drm_i915_gem_object;
 
-#ifdef CONFIG_DRM_I915_PXP
 struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp);
 bool intel_pxp_is_enabled(const struct intel_pxp *pxp);
 bool intel_pxp_is_active(const struct intel_pxp *pxp);
@@ -32,36 +31,5 @@ int intel_pxp_key_check(struct intel_pxp *pxp,
 			bool assign);
 
 void intel_pxp_invalidate(struct intel_pxp *pxp);
-#else
-static inline void intel_pxp_init(struct intel_pxp *pxp)
-{
-}
-
-static inline void intel_pxp_fini(struct intel_pxp *pxp)
-{
-}
-
-static inline int intel_pxp_start(struct intel_pxp *pxp)
-{
-	return -ENODEV;
-}
-
-static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp)
-{
-	return false;
-}
-
-static inline bool intel_pxp_is_active(const struct intel_pxp *pxp)
-{
-	return false;
-}
-
-static inline int intel_pxp_key_check(struct intel_pxp *pxp,
-				      struct drm_i915_gem_object *obj,
-				      bool assign)
-{
-	return -ENODEV;
-}
-#endif
 
 #endif /* __INTEL_PXP_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c
new file mode 100644
index 000000000000..7ec36d94e758
--- /dev/null
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright(c) 2021-2022, Intel Corporation. All rights reserved.
+ */
+
+#include "drm/i915_drm.h"
+#include "i915_drv.h"
+
+#include "gem/i915_gem_region.h"
+#include "gt/intel_gt.h"
+
+#include "intel_pxp.h"
+#include "intel_pxp_huc.h"
+#include "intel_pxp_tee.h"
+#include "intel_pxp_types.h"
+#include "intel_pxp_tee_interface.h"
+
+int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp)
+{
+	struct intel_gt *gt = pxp_to_gt(pxp);
+	struct intel_huc *huc = &gt->uc.huc;
+	struct pxp_tee_start_huc_auth_in huc_in = {0};
+	struct pxp_tee_start_huc_auth_out huc_out = {0};
+	dma_addr_t huc_phys_addr;
+	u8 client_id = 0;
+	u8 fence_id = 0;
+	int err;
+
+	if (!pxp->pxp_component)
+		return -ENODEV;
+
+	huc_phys_addr = i915_gem_object_get_dma_address(huc->fw.obj, 0);
+
+	/* write the PXP message into the lmem (the sg list) */
+	huc_in.header.api_version = PXP_TEE_43_APIVER;
+	huc_in.header.command_id  = PXP_TEE_43_START_HUC_AUTH;
+	huc_in.header.status      = 0;
+	huc_in.header.buffer_len  = sizeof(huc_in.huc_base_address);
+	huc_in.huc_base_address   = huc_phys_addr;
+
+	err = intel_pxp_tee_stream_message(pxp, client_id, fence_id,
+					   &huc_in, sizeof(huc_in),
+					   &huc_out, sizeof(huc_out));
+	if (err < 0) {
+		drm_err(&gt->i915->drm,
+			"Failed to send HuC load and auth command to GSC [%d]!\n",
+			err);
+		return err;
+	}
+
+	/*
+	 * HuC does sometimes survive suspend/resume (it depends on how "deep"
+	 * a sleep state the device reaches) so we can end up here on resume
+	 * with HuC already loaded, in which case the GSC will return
+	 * PXP_STATUS_OP_NOT_PERMITTED. We can therefore consider the GuC
+	 * correctly transferred in this scenario; if the same error is ever
+	 * returned with HuC not loaded we'll still catch it when we check the
+	 * authentication bit later.
+	 */
+	if (huc_out.header.status != PXP_STATUS_SUCCESS &&
+	    huc_out.header.status != PXP_STATUS_OP_NOT_PERMITTED) {
+		drm_err(&gt->i915->drm,
+			"HuC load failed with GSC error = 0x%x\n",
+			huc_out.header.status);
+		return -EPROTO;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h
new file mode 100644
index 000000000000..e40847a91c39
--- /dev/null
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright(c) 2021-2022, Intel Corporation. All rights reserved.
+ */
+
+#ifndef __INTEL_PXP_HUC_H__
+#define __INTEL_PXP_HUC_H__
+
+struct intel_pxp;
+
+int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp);
+
+#endif /* __INTEL_PXP_HUC_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h
index 8b5793654844..8c292dc86f68 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h
@@ -27,6 +27,14 @@ void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir);
 static inline void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir)
 {
 }
+
+static inline void intel_pxp_irq_enable(struct intel_pxp *pxp)
+{
+}
+
+static inline void intel_pxp_irq_disable(struct intel_pxp *pxp)
+{
+}
 #endif
 
 #endif /* __INTEL_PXP_IRQ_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
index 1bb5b5249157..85572360c71a 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
@@ -77,6 +77,7 @@ static int pxp_create_arb_session(struct intel_pxp *pxp)
 		drm_err(&gt->i915->drm, "arb session failed to go in play\n");
 		return ret;
 	}
+	drm_dbg(&gt->i915->drm, "PXP ARB session is alive\n");
 
 	if (!++pxp->key_instance)
 		++pxp->key_instance;
@@ -137,7 +138,7 @@ static void pxp_terminate_complete(struct intel_pxp *pxp)
 	complete_all(&pxp->termination);
 }
 
-void intel_pxp_session_work(struct work_struct *work)
+static void pxp_session_work(struct work_struct *work)
 {
 	struct intel_pxp *pxp = container_of(work, typeof(*pxp), session_work);
 	struct intel_gt *gt = pxp_to_gt(pxp);
@@ -172,3 +173,9 @@ void intel_pxp_session_work(struct work_struct *work)
 
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 }
+
+void intel_pxp_session_management_init(struct intel_pxp *pxp)
+{
+	mutex_init(&pxp->arb_mutex);
+	INIT_WORK(&pxp->session_work, pxp_session_work);
+}
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h
index ba4c9d2b94b7..903ac52cffa1 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h
@@ -8,8 +8,13 @@
 
 #include <linux/types.h>
 
-struct work_struct;
-
-void intel_pxp_session_work(struct work_struct *work);
+struct intel_pxp;
 
+#ifdef CONFIG_DRM_I915_PXP
+void intel_pxp_session_management_init(struct intel_pxp *pxp);
+#else
+static inline void intel_pxp_session_management_init(struct intel_pxp *pxp)
+{
+}
+#endif
 #endif /* __INTEL_PXP_SESSION_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
index 4b6f5655fab5..052fd2f9a583 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
@@ -8,11 +8,14 @@
 #include <drm/i915_pxp_tee_interface.h>
 #include <drm/i915_component.h>
 
+#include "gem/i915_gem_lmem.h"
+
 #include "i915_drv.h"
 #include "intel_pxp.h"
 #include "intel_pxp_session.h"
 #include "intel_pxp_tee.h"
 #include "intel_pxp_tee_interface.h"
+#include "intel_pxp_huc.h"
 
 static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev)
 {
@@ -69,6 +72,47 @@ unlock:
 	return ret;
 }
 
+int intel_pxp_tee_stream_message(struct intel_pxp *pxp,
+				 u8 client_id, u32 fence_id,
+				 void *msg_in, size_t msg_in_len,
+				 void *msg_out, size_t msg_out_len)
+{
+	/* TODO: for bigger objects we need to use a sg of 4k pages */
+	const size_t max_msg_size = PAGE_SIZE;
+	struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915;
+	struct i915_pxp_component *pxp_component = pxp->pxp_component;
+	unsigned int offset = 0;
+	struct scatterlist *sg;
+	int ret;
+
+	if (msg_in_len > max_msg_size || msg_out_len > max_msg_size)
+		return -ENOSPC;
+
+	mutex_lock(&pxp->tee_mutex);
+
+	if (unlikely(!pxp_component || !pxp_component->ops->gsc_command)) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
+	GEM_BUG_ON(!pxp->stream_cmd.obj);
+
+	sg = i915_gem_object_get_sg_dma(pxp->stream_cmd.obj, 0, &offset);
+
+	memcpy(pxp->stream_cmd.vaddr, msg_in, msg_in_len);
+
+	ret = pxp_component->ops->gsc_command(pxp_component->tee_dev, client_id,
+					      fence_id, sg, msg_in_len, sg);
+	if (ret < 0)
+		drm_err(&i915->drm, "Failed to send PXP TEE gsc command\n");
+	else
+		memcpy(msg_out, pxp->stream_cmd.vaddr, msg_out_len);
+
+unlock:
+	mutex_unlock(&pxp->tee_mutex);
+	return ret;
+}
+
 /**
  * i915_pxp_tee_component_bind - bind function to pass the function pointers to pxp_tee
  * @i915_kdev: pointer to i915 kernel device
@@ -84,24 +128,36 @@ static int i915_pxp_tee_component_bind(struct device *i915_kdev,
 {
 	struct drm_i915_private *i915 = kdev_to_i915(i915_kdev);
 	struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev);
+	struct intel_uc *uc = &pxp_to_gt(pxp)->uc;
 	intel_wakeref_t wakeref;
+	int ret = 0;
 
 	mutex_lock(&pxp->tee_mutex);
 	pxp->pxp_component = data;
 	pxp->pxp_component->tee_dev = tee_kdev;
 	mutex_unlock(&pxp->tee_mutex);
 
+	if (intel_uc_uses_huc(uc) && intel_huc_is_loaded_by_gsc(&uc->huc)) {
+		with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+			/* load huc via pxp */
+			ret = intel_huc_fw_load_and_auth_via_gsc(&uc->huc);
+			if (ret < 0)
+				drm_err(&i915->drm, "failed to load huc via gsc %d\n", ret);
+		}
+	}
+
 	/* if we are suspended, the HW will be re-initialized on resume */
 	wakeref = intel_runtime_pm_get_if_in_use(&i915->runtime_pm);
 	if (!wakeref)
 		return 0;
 
 	/* the component is required to fully start the PXP HW */
-	intel_pxp_init_hw(pxp);
+	if (intel_pxp_is_enabled(pxp))
+		intel_pxp_init_hw(pxp);
 
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
-	return 0;
+	return ret;
 }
 
 static void i915_pxp_tee_component_unbind(struct device *i915_kdev,
@@ -111,8 +167,9 @@ static void i915_pxp_tee_component_unbind(struct device *i915_kdev,
 	struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev);
 	intel_wakeref_t wakeref;
 
-	with_intel_runtime_pm_if_in_use(&i915->runtime_pm, wakeref)
-		intel_pxp_fini_hw(pxp);
+	if (intel_pxp_is_enabled(pxp))
+		with_intel_runtime_pm_if_in_use(&i915->runtime_pm, wakeref)
+			intel_pxp_fini_hw(pxp);
 
 	mutex_lock(&pxp->tee_mutex);
 	pxp->pxp_component = NULL;
@@ -124,22 +181,92 @@ static const struct component_ops i915_pxp_tee_component_ops = {
 	.unbind = i915_pxp_tee_component_unbind,
 };
 
+static int alloc_streaming_command(struct intel_pxp *pxp)
+{
+	struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915;
+	struct drm_i915_gem_object *obj = NULL;
+	void *cmd;
+	int err;
+
+	pxp->stream_cmd.obj = NULL;
+	pxp->stream_cmd.vaddr = NULL;
+
+	if (!IS_DGFX(i915))
+		return 0;
+
+	/* allocate lmem object of one page for PXP command memory and store it */
+	obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, I915_BO_ALLOC_CONTIGUOUS);
+	if (IS_ERR(obj)) {
+		drm_err(&i915->drm, "Failed to allocate pxp streaming command!\n");
+		return PTR_ERR(obj);
+	}
+
+	err = i915_gem_object_pin_pages_unlocked(obj);
+	if (err) {
+		drm_err(&i915->drm, "Failed to pin gsc message page!\n");
+		goto out_put;
+	}
+
+	/* map the lmem into the virtual memory pointer */
+	cmd = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(i915, obj, true));
+	if (IS_ERR(cmd)) {
+		drm_err(&i915->drm, "Failed to map gsc message page!\n");
+		err = PTR_ERR(cmd);
+		goto out_unpin;
+	}
+
+	memset(cmd, 0, obj->base.size);
+
+	pxp->stream_cmd.obj = obj;
+	pxp->stream_cmd.vaddr = cmd;
+
+	return 0;
+
+out_unpin:
+	i915_gem_object_unpin_pages(obj);
+out_put:
+	i915_gem_object_put(obj);
+	return err;
+}
+
+static void free_streaming_command(struct intel_pxp *pxp)
+{
+	struct drm_i915_gem_object *obj = fetch_and_zero(&pxp->stream_cmd.obj);
+
+	if (!obj)
+		return;
+
+	i915_gem_object_unpin_map(obj);
+	i915_gem_object_unpin_pages(obj);
+	i915_gem_object_put(obj);
+}
+
 int intel_pxp_tee_component_init(struct intel_pxp *pxp)
 {
 	int ret;
 	struct intel_gt *gt = pxp_to_gt(pxp);
 	struct drm_i915_private *i915 = gt->i915;
 
+	mutex_init(&pxp->tee_mutex);
+
+	ret = alloc_streaming_command(pxp);
+	if (ret)
+		return ret;
+
 	ret = component_add_typed(i915->drm.dev, &i915_pxp_tee_component_ops,
 				  I915_COMPONENT_PXP);
 	if (ret < 0) {
 		drm_err(&i915->drm, "Failed to add PXP component (%d)\n", ret);
-		return ret;
+		goto out_free;
 	}
 
 	pxp->pxp_component_added = true;
 
 	return 0;
+
+out_free:
+	free_streaming_command(pxp);
+	return ret;
 }
 
 void intel_pxp_tee_component_fini(struct intel_pxp *pxp)
@@ -151,6 +278,8 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp)
 
 	component_del(i915->drm.dev, &i915_pxp_tee_component_ops);
 	pxp->pxp_component_added = false;
+
+	free_streaming_command(pxp);
 }
 
 int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp,
@@ -174,6 +303,9 @@ int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp,
 
 	if (ret)
 		drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret);
+	else if (msg_out.header.status != 0x0)
+		drm_warn(&i915->drm, "PXP firmware failed arb session init request ret=[0x%08x]\n",
+			 msg_out.header.status);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h
index c136053ce340..aeb3dfe7ce96 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h
@@ -14,4 +14,9 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp);
 int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp,
 					 int arb_session_id);
 
+int intel_pxp_tee_stream_message(struct intel_pxp *pxp,
+				 u8 client_id, u32 fence_id,
+				 void *msg_in, size_t msg_in_len,
+				 void *msg_out, size_t msg_out_len);
+
 #endif /* __INTEL_PXP_TEE_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h
index 36e9b0868f5c..7edc1760f142 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: MIT */
 /*
- * Copyright(c) 2020, Intel Corporation. All rights reserved.
+ * Copyright(c) 2020-2022, Intel Corporation. All rights reserved.
  */
 
 #ifndef __INTEL_PXP_TEE_INTERFACE_H__
@@ -9,8 +9,20 @@
 #include <linux/types.h>
 
 #define PXP_TEE_APIVER 0x40002
+#define PXP_TEE_43_APIVER 0x00040003
 #define PXP_TEE_ARB_CMDID 0x1e
 #define PXP_TEE_ARB_PROTECTION_MODE 0x2
+#define PXP_TEE_43_START_HUC_AUTH   0x0000003A
+
+/*
+ * there are a lot of status codes for PXP, but we only define the ones we
+ * actually can handle in the driver. other failure codes will be printed to
+ * error msg for debug.
+ */
+enum pxp_status {
+	PXP_STATUS_SUCCESS = 0x0,
+	PXP_STATUS_OP_NOT_PERMITTED = 0x4013
+};
 
 /* PXP TEE message header */
 struct pxp_tee_cmd_header {
@@ -33,4 +45,13 @@ struct pxp_tee_create_arb_out {
 	struct pxp_tee_cmd_header header;
 } __packed;
 
+struct pxp_tee_start_huc_auth_in {
+	struct pxp_tee_cmd_header header;
+	__le64                    huc_base_address;
+};
+
+struct pxp_tee_start_huc_auth_out {
+	struct pxp_tee_cmd_header header;
+};
+
 #endif /* __INTEL_PXP_TEE_INTERFACE_H__ */
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
index 7ce5f37ee12e..f74b1e11a505 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
@@ -53,6 +53,12 @@ struct intel_pxp {
 	/** @tee_mutex: protects the tee channel binding and messaging. */
 	struct mutex tee_mutex;
 
+	/** @stream_cmd: LMEM obj used to send stream PXP commands to the GSC */
+	struct {
+		struct drm_i915_gem_object *obj; /* contains PXP command memory */
+		void *vaddr; /* virtual memory for PXP command */
+	} stream_cmd;
+
 	/**
 	 * @hw_state_invalidated: if the HW perceives an attack on the integrity
 	 * of the encryption it will invalidate the keys and expect SW to
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index e050a2de5fd1..27c733b00976 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -27,6 +27,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_context.h"
@@ -1113,15 +1114,8 @@ static int misaligned_case(struct i915_address_space *vm, struct intel_memory_re
 	expected_node_size = expected_vma_size;
 
 	if (HAS_64K_PAGES(vm->i915) && i915_gem_object_is_lmem(obj)) {
-		/*
-		 * The compact-pt should expand lmem node to 2MB for the ppGTT,
-		 * for all other cases we should only expect 64K.
-		 */
 		expected_vma_size = round_up(size, I915_GTT_PAGE_SIZE_64K);
-		if (NEEDS_COMPACT_PT(vm->i915) && !i915_is_ggtt(vm))
-			expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_2M);
-		else
-			expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_64K);
+		expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_64K);
 	}
 
 	if (vma->size != expected_vma_size || vma->node.size != expected_node_size) {
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index 429c6d73b159..24dde5531423 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -102,6 +102,12 @@ test_stream(struct i915_perf *perf)
 		I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8,
 	};
 	struct i915_perf_stream *stream;
+	struct intel_gt *gt;
+
+	if (!props.engine)
+		return NULL;
+
+	gt = props.engine->gt;
 
 	if (!oa_config)
 		return NULL;
@@ -116,12 +122,12 @@ test_stream(struct i915_perf *perf)
 
 	stream->perf = perf;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	if (i915_oa_stream_init(stream, &param, &props)) {
 		kfree(stream);
 		stream =  NULL;
 	}
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	i915_oa_config_put(oa_config);
 
@@ -130,11 +136,11 @@ test_stream(struct i915_perf *perf)
 
 static void stream_destroy(struct i915_perf_stream *stream)
 {
-	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	i915_perf_destroy_locked(stream);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 }
 
 static int live_sanitycheck(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 818a4909c1f3..a46350c37e9d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -299,9 +299,18 @@ __live_request_alloc(struct intel_context *ce)
 	return intel_context_create_request(ce);
 }
 
-static int __igt_breadcrumbs_smoketest(void *arg)
+struct smoke_thread {
+	struct kthread_worker *worker;
+	struct kthread_work work;
+	struct smoketest *t;
+	bool stop;
+	int result;
+};
+
+static void __igt_breadcrumbs_smoketest(struct kthread_work *work)
 {
-	struct smoketest *t = arg;
+	struct smoke_thread *thread = container_of(work, typeof(*thread), work);
+	struct smoketest *t = thread->t;
 	const unsigned int max_batch = min(t->ncontexts, t->max_batch) - 1;
 	const unsigned int total = 4 * t->ncontexts + 1;
 	unsigned int num_waits = 0, num_fences = 0;
@@ -320,8 +329,10 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 	 */
 
 	requests = kcalloc(total, sizeof(*requests), GFP_KERNEL);
-	if (!requests)
-		return -ENOMEM;
+	if (!requests) {
+		thread->result = -ENOMEM;
+		return;
+	}
 
 	order = i915_random_order(total, &prng);
 	if (!order) {
@@ -329,7 +340,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 		goto out_requests;
 	}
 
-	while (!kthread_should_stop()) {
+	while (!READ_ONCE(thread->stop)) {
 		struct i915_sw_fence *submit, *wait;
 		unsigned int n, count;
 
@@ -437,7 +448,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 	kfree(order);
 out_requests:
 	kfree(requests);
-	return err;
+	thread->result = err;
 }
 
 static int mock_breadcrumbs_smoketest(void *arg)
@@ -450,7 +461,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 		.request_alloc = __mock_request_alloc
 	};
 	unsigned int ncpus = num_online_cpus();
-	struct task_struct **threads;
+	struct smoke_thread *threads;
 	unsigned int n;
 	int ret = 0;
 
@@ -479,28 +490,37 @@ static int mock_breadcrumbs_smoketest(void *arg)
 	}
 
 	for (n = 0; n < ncpus; n++) {
-		threads[n] = kthread_run(__igt_breadcrumbs_smoketest,
-					 &t, "igt/%d", n);
-		if (IS_ERR(threads[n])) {
-			ret = PTR_ERR(threads[n]);
+		struct kthread_worker *worker;
+
+		worker = kthread_create_worker(0, "igt/%d", n);
+		if (IS_ERR(worker)) {
+			ret = PTR_ERR(worker);
 			ncpus = n;
 			break;
 		}
 
-		get_task_struct(threads[n]);
+		threads[n].worker = worker;
+		threads[n].t = &t;
+		threads[n].stop = false;
+		threads[n].result = 0;
+
+		kthread_init_work(&threads[n].work,
+				  __igt_breadcrumbs_smoketest);
+		kthread_queue_work(worker, &threads[n].work);
 	}
 
-	yield(); /* start all threads before we begin */
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
 	for (n = 0; n < ncpus; n++) {
 		int err;
 
-		err = kthread_stop(threads[n]);
+		WRITE_ONCE(threads[n].stop, true);
+		kthread_flush_work(&threads[n].work);
+		err = READ_ONCE(threads[n].result);
 		if (err < 0 && !ret)
 			ret = err;
 
-		put_task_struct(threads[n]);
+		kthread_destroy_worker(threads[n].worker);
 	}
 	pr_info("Completed %lu waits for %lu fence across %d cpus\n",
 		atomic_long_read(&t.num_waits),
@@ -1419,9 +1439,18 @@ out_free:
 	return err;
 }
 
-static int __live_parallel_engine1(void *arg)
+struct parallel_thread {
+	struct kthread_worker *worker;
+	struct kthread_work work;
+	struct intel_engine_cs *engine;
+	int result;
+};
+
+static void __live_parallel_engine1(struct kthread_work *work)
 {
-	struct intel_engine_cs *engine = arg;
+	struct parallel_thread *thread =
+		container_of(work, typeof(*thread), work);
+	struct intel_engine_cs *engine = thread->engine;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 	int err = 0;
@@ -1452,12 +1481,14 @@ static int __live_parallel_engine1(void *arg)
 	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu request + sync\n", engine->name, count);
-	return err;
+	thread->result = err;
 }
 
-static int __live_parallel_engineN(void *arg)
+static void __live_parallel_engineN(struct kthread_work *work)
 {
-	struct intel_engine_cs *engine = arg;
+	struct parallel_thread *thread =
+		container_of(work, typeof(*thread), work);
+	struct intel_engine_cs *engine = thread->engine;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 	int err = 0;
@@ -1479,7 +1510,7 @@ static int __live_parallel_engineN(void *arg)
 	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu requests\n", engine->name, count);
-	return err;
+	thread->result = err;
 }
 
 static bool wake_all(struct drm_i915_private *i915)
@@ -1505,9 +1536,11 @@ static int wait_for_all(struct drm_i915_private *i915)
 	return -ETIME;
 }
 
-static int __live_parallel_spin(void *arg)
+static void __live_parallel_spin(struct kthread_work *work)
 {
-	struct intel_engine_cs *engine = arg;
+	struct parallel_thread *thread =
+		container_of(work, typeof(*thread), work);
+	struct intel_engine_cs *engine = thread->engine;
 	struct igt_spinner spin;
 	struct i915_request *rq;
 	int err = 0;
@@ -1520,7 +1553,8 @@ static int __live_parallel_spin(void *arg)
 
 	if (igt_spinner_init(&spin, engine->gt)) {
 		wake_all(engine->i915);
-		return -ENOMEM;
+		thread->result = -ENOMEM;
+		return;
 	}
 
 	intel_engine_pm_get(engine);
@@ -1553,22 +1587,22 @@ static int __live_parallel_spin(void *arg)
 
 out_spin:
 	igt_spinner_fini(&spin);
-	return err;
+	thread->result = err;
 }
 
 static int live_parallel_engines(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	static int (* const func[])(void *arg) = {
+	static void (* const func[])(struct kthread_work *) = {
 		__live_parallel_engine1,
 		__live_parallel_engineN,
 		__live_parallel_spin,
 		NULL,
 	};
 	const unsigned int nengines = num_uabi_engines(i915);
+	struct parallel_thread *threads;
 	struct intel_engine_cs *engine;
-	int (* const *fn)(void *arg);
-	struct task_struct **tsk;
+	void (* const *fn)(struct kthread_work *);
 	int err = 0;
 
 	/*
@@ -1576,8 +1610,8 @@ static int live_parallel_engines(void *arg)
 	 * tests that we load up the system maximally.
 	 */
 
-	tsk = kcalloc(nengines, sizeof(*tsk), GFP_KERNEL);
-	if (!tsk)
+	threads = kcalloc(nengines, sizeof(*threads), GFP_KERNEL);
+	if (!threads)
 		return -ENOMEM;
 
 	for (fn = func; !err && *fn; fn++) {
@@ -1594,37 +1628,44 @@ static int live_parallel_engines(void *arg)
 
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
-			tsk[idx] = kthread_run(*fn, engine,
-					       "igt/parallel:%s",
-					       engine->name);
-			if (IS_ERR(tsk[idx])) {
-				err = PTR_ERR(tsk[idx]);
+			struct kthread_worker *worker;
+
+			worker = kthread_create_worker(0, "igt/parallel:%s",
+						       engine->name);
+			if (IS_ERR(worker)) {
+				err = PTR_ERR(worker);
 				break;
 			}
-			get_task_struct(tsk[idx++]);
-		}
 
-		yield(); /* start all threads before we kthread_stop() */
+			threads[idx].worker = worker;
+			threads[idx].result = 0;
+			threads[idx].engine = engine;
+
+			kthread_init_work(&threads[idx].work, *fn);
+			kthread_queue_work(worker, &threads[idx].work);
+			idx++;
+		}
 
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
 			int status;
 
-			if (IS_ERR(tsk[idx]))
+			if (!threads[idx].worker)
 				break;
 
-			status = kthread_stop(tsk[idx]);
+			kthread_flush_work(&threads[idx].work);
+			status = READ_ONCE(threads[idx].result);
 			if (status && !err)
 				err = status;
 
-			put_task_struct(tsk[idx++]);
+			kthread_destroy_worker(threads[idx++].worker);
 		}
 
 		if (igt_live_test_end(&t))
 			err = -EIO;
 	}
 
-	kfree(tsk);
+	kfree(threads);
 	return err;
 }
 
@@ -1672,7 +1713,7 @@ static int live_breadcrumbs_smoketest(void *arg)
 	const unsigned int ncpus = num_online_cpus();
 	unsigned long num_waits, num_fences;
 	struct intel_engine_cs *engine;
-	struct task_struct **threads;
+	struct smoke_thread *threads;
 	struct igt_live_test live;
 	intel_wakeref_t wakeref;
 	struct smoketest *smoke;
@@ -1746,23 +1787,26 @@ static int live_breadcrumbs_smoketest(void *arg)
 			 smoke[idx].max_batch, engine->name);
 
 		for (n = 0; n < ncpus; n++) {
-			struct task_struct *tsk;
+			unsigned int i = idx * ncpus + n;
+			struct kthread_worker *worker;
 
-			tsk = kthread_run(__igt_breadcrumbs_smoketest,
-					  &smoke[idx], "igt/%d.%d", idx, n);
-			if (IS_ERR(tsk)) {
-				ret = PTR_ERR(tsk);
+			worker = kthread_create_worker(0, "igt/%d.%d", idx, n);
+			if (IS_ERR(worker)) {
+				ret = PTR_ERR(worker);
 				goto out_flush;
 			}
 
-			get_task_struct(tsk);
-			threads[idx * ncpus + n] = tsk;
+			threads[i].worker = worker;
+			threads[i].t = &smoke[idx];
+
+			kthread_init_work(&threads[i].work,
+					  __igt_breadcrumbs_smoketest);
+			kthread_queue_work(worker, &threads[i].work);
 		}
 
 		idx++;
 	}
 
-	yield(); /* start all threads before we begin */
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
 out_flush:
@@ -1771,17 +1815,19 @@ out_flush:
 	num_fences = 0;
 	for_each_uabi_engine(engine, i915) {
 		for (n = 0; n < ncpus; n++) {
-			struct task_struct *tsk = threads[idx * ncpus + n];
+			unsigned int i = idx * ncpus + n;
 			int err;
 
-			if (!tsk)
+			if (!threads[i].worker)
 				continue;
 
-			err = kthread_stop(tsk);
+			WRITE_ONCE(threads[i].stop, true);
+			kthread_flush_work(&threads[i].work);
+			err = READ_ONCE(threads[i].result);
 			if (err < 0 && !ret)
 				ret = err;
 
-			put_task_struct(tsk);
+			kthread_destroy_worker(threads[i].worker);
 		}
 
 		num_waits += atomic_long_read(&smoke[idx].num_waits);
@@ -2891,9 +2937,18 @@ out:
 	return err;
 }
 
-static int p_sync0(void *arg)
+struct p_thread {
+	struct perf_stats p;
+	struct kthread_worker *worker;
+	struct kthread_work work;
+	struct intel_engine_cs *engine;
+	int result;
+};
+
+static void p_sync0(struct kthread_work *work)
 {
-	struct perf_stats *p = arg;
+	struct p_thread *thread = container_of(work, typeof(*thread), work);
+	struct perf_stats *p = &thread->p;
 	struct intel_engine_cs *engine = p->engine;
 	struct intel_context *ce;
 	IGT_TIMEOUT(end_time);
@@ -2902,13 +2957,16 @@ static int p_sync0(void *arg)
 	int err = 0;
 
 	ce = intel_context_create(engine);
-	if (IS_ERR(ce))
-		return PTR_ERR(ce);
+	if (IS_ERR(ce)) {
+		thread->result = PTR_ERR(ce);
+		return;
+	}
 
 	err = intel_context_pin(ce);
 	if (err) {
 		intel_context_put(ce);
-		return err;
+		thread->result = err;
+		return;
 	}
 
 	if (intel_engine_supports_stats(engine)) {
@@ -2958,12 +3016,13 @@ static int p_sync0(void *arg)
 
 	intel_context_unpin(ce);
 	intel_context_put(ce);
-	return err;
+	thread->result = err;
 }
 
-static int p_sync1(void *arg)
+static void p_sync1(struct kthread_work *work)
 {
-	struct perf_stats *p = arg;
+	struct p_thread *thread = container_of(work, typeof(*thread), work);
+	struct perf_stats *p = &thread->p;
 	struct intel_engine_cs *engine = p->engine;
 	struct i915_request *prev = NULL;
 	struct intel_context *ce;
@@ -2973,13 +3032,16 @@ static int p_sync1(void *arg)
 	int err = 0;
 
 	ce = intel_context_create(engine);
-	if (IS_ERR(ce))
-		return PTR_ERR(ce);
+	if (IS_ERR(ce)) {
+		thread->result = PTR_ERR(ce);
+		return;
+	}
 
 	err = intel_context_pin(ce);
 	if (err) {
 		intel_context_put(ce);
-		return err;
+		thread->result = err;
+		return;
 	}
 
 	if (intel_engine_supports_stats(engine)) {
@@ -3031,12 +3093,13 @@ static int p_sync1(void *arg)
 
 	intel_context_unpin(ce);
 	intel_context_put(ce);
-	return err;
+	thread->result = err;
 }
 
-static int p_many(void *arg)
+static void p_many(struct kthread_work *work)
 {
-	struct perf_stats *p = arg;
+	struct p_thread *thread = container_of(work, typeof(*thread), work);
+	struct perf_stats *p = &thread->p;
 	struct intel_engine_cs *engine = p->engine;
 	struct intel_context *ce;
 	IGT_TIMEOUT(end_time);
@@ -3045,13 +3108,16 @@ static int p_many(void *arg)
 	bool busy;
 
 	ce = intel_context_create(engine);
-	if (IS_ERR(ce))
-		return PTR_ERR(ce);
+	if (IS_ERR(ce)) {
+		thread->result = PTR_ERR(ce);
+		return;
+	}
 
 	err = intel_context_pin(ce);
 	if (err) {
 		intel_context_put(ce);
-		return err;
+		thread->result = err;
+		return;
 	}
 
 	if (intel_engine_supports_stats(engine)) {
@@ -3092,26 +3158,23 @@ static int p_many(void *arg)
 
 	intel_context_unpin(ce);
 	intel_context_put(ce);
-	return err;
+	thread->result = err;
 }
 
 static int perf_parallel_engines(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	static int (* const func[])(void *arg) = {
+	static void (* const func[])(struct kthread_work *) = {
 		p_sync0,
 		p_sync1,
 		p_many,
 		NULL,
 	};
 	const unsigned int nengines = num_uabi_engines(i915);
+	void (* const *fn)(struct kthread_work *);
 	struct intel_engine_cs *engine;
-	int (* const *fn)(void *arg);
 	struct pm_qos_request qos;
-	struct {
-		struct perf_stats p;
-		struct task_struct *tsk;
-	} *engines;
+	struct p_thread *engines;
 	int err = 0;
 
 	engines = kcalloc(nengines, sizeof(*engines), GFP_KERNEL);
@@ -3134,36 +3197,45 @@ static int perf_parallel_engines(void *arg)
 
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
+			struct kthread_worker *worker;
+
 			intel_engine_pm_get(engine);
 
 			memset(&engines[idx].p, 0, sizeof(engines[idx].p));
-			engines[idx].p.engine = engine;
 
-			engines[idx].tsk = kthread_run(*fn, &engines[idx].p,
-						       "igt:%s", engine->name);
-			if (IS_ERR(engines[idx].tsk)) {
-				err = PTR_ERR(engines[idx].tsk);
+			worker = kthread_create_worker(0, "igt:%s",
+						       engine->name);
+			if (IS_ERR(worker)) {
+				err = PTR_ERR(worker);
 				intel_engine_pm_put(engine);
 				break;
 			}
-			get_task_struct(engines[idx++].tsk);
-		}
+			engines[idx].worker = worker;
+			engines[idx].result = 0;
+			engines[idx].p.engine = engine;
+			engines[idx].engine = engine;
 
-		yield(); /* start all threads before we kthread_stop() */
+			kthread_init_work(&engines[idx].work, *fn);
+			kthread_queue_work(worker, &engines[idx].work);
+			idx++;
+		}
 
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
 			int status;
 
-			if (IS_ERR(engines[idx].tsk))
+			if (!engines[idx].worker)
 				break;
 
-			status = kthread_stop(engines[idx].tsk);
+			kthread_flush_work(&engines[idx].work);
+			status = READ_ONCE(engines[idx].result);
 			if (status && !err)
 				err = status;
 
 			intel_engine_pm_put(engine);
-			put_task_struct(engines[idx++].tsk);
+
+			kthread_destroy_worker(engines[idx].worker);
+			idx++;
 		}
 
 		if (igt_live_test_end(&t))
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index fda9bb79c049..e4281508d580 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -70,6 +70,8 @@ static int intel_shadow_table_check(void)
 		{ gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) },
 		{ dg2_shadowed_regs, ARRAY_SIZE(dg2_shadowed_regs) },
 		{ pvc_shadowed_regs, ARRAY_SIZE(pvc_shadowed_regs) },
+		{ mtl_shadowed_regs, ARRAY_SIZE(mtl_shadowed_regs) },
+		{ xelpmp_shadowed_regs, ARRAY_SIZE(xelpmp_shadowed_regs) },
 	};
 	const struct i915_range *range;
 	unsigned int i, j;
@@ -117,6 +119,8 @@ int intel_uncore_mock_selftests(void)
 		{ __gen12_fw_ranges, ARRAY_SIZE(__gen12_fw_ranges), true },
 		{ __xehp_fw_ranges, ARRAY_SIZE(__xehp_fw_ranges), true },
 		{ __pvc_fw_ranges, ARRAY_SIZE(__pvc_fw_ranges), true },
+		{ __mtl_fw_ranges, ARRAY_SIZE(__mtl_fw_ranges), true },
+		{ __xelpmp_fw_ranges, ARRAY_SIZE(__xelpmp_fw_ranges), true },
 	};
 	int err, i;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index fff11c90f1fa..f6a7c0bd2955 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -67,7 +67,6 @@ static void mock_device_release(struct drm_device *dev)
 	intel_gt_driver_remove(to_gt(i915));
 
 	i915_gem_drain_workqueue(i915);
-	i915_gem_drain_freed_objects(i915);
 
 	mock_fini_ggtt(to_gt(i915)->ggtt);
 	destroy_workqueue(i915->wq);
diff --git a/drivers/gpu/drm/i915/vlv_suspend.c b/drivers/gpu/drm/i915/vlv_suspend.c
index 664fde244f59..02e63ed77f60 100644
--- a/drivers/gpu/drm/i915/vlv_suspend.c
+++ b/drivers/gpu/drm/i915/vlv_suspend.c
@@ -194,7 +194,6 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *i915)
 {
 	struct vlv_s0ix_state *s = i915->vlv_s0ix_state;
 	struct intel_uncore *uncore = &i915->uncore;
-	u32 val;
 	int i;
 
 	if (!s)
@@ -262,15 +261,11 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *i915)
 	 * be restored, as they are used to control the s0ix suspend/resume
 	 * sequence by the caller.
 	 */
-	val = intel_uncore_read(uncore, VLV_GTLC_WAKE_CTRL);
-	val &= VLV_GTLC_ALLOWWAKEREQ;
-	val |= s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ;
-	intel_uncore_write(uncore, VLV_GTLC_WAKE_CTRL, val);
+	intel_uncore_rmw(uncore, VLV_GTLC_WAKE_CTRL, ~VLV_GTLC_ALLOWWAKEREQ,
+			 s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ);
 
-	val = intel_uncore_read(uncore, VLV_GTLC_SURVIVABILITY_REG);
-	val &= VLV_GFX_CLK_FORCE_ON_BIT;
-	val |= s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT;
-	intel_uncore_write(uncore, VLV_GTLC_SURVIVABILITY_REG, val);
+	intel_uncore_rmw(uncore, VLV_GTLC_SURVIVABILITY_REG, ~VLV_GFX_CLK_FORCE_ON_BIT,
+			 s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT);
 
 	intel_uncore_write(uncore, VLV_PMWGICZ, s->pmwgicz);
 
@@ -308,14 +303,10 @@ static int vlv_wait_for_pw_status(struct drm_i915_private *i915,
 static int vlv_force_gfx_clock(struct drm_i915_private *i915, bool force_on)
 {
 	struct intel_uncore *uncore = &i915->uncore;
-	u32 val;
 	int err;
 
-	val = intel_uncore_read(uncore, VLV_GTLC_SURVIVABILITY_REG);
-	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
-	if (force_on)
-		val |= VLV_GFX_CLK_FORCE_ON_BIT;
-	intel_uncore_write(uncore, VLV_GTLC_SURVIVABILITY_REG, val);
+	intel_uncore_rmw(uncore, VLV_GTLC_SURVIVABILITY_REG, VLV_GFX_CLK_FORCE_ON_BIT,
+			 force_on ? VLV_GFX_CLK_FORCE_ON_BIT : 0);
 
 	if (!force_on)
 		return 0;
@@ -340,11 +331,8 @@ static int vlv_allow_gt_wake(struct drm_i915_private *i915, bool allow)
 	u32 val;
 	int err;
 
-	val = intel_uncore_read(uncore, VLV_GTLC_WAKE_CTRL);
-	val &= ~VLV_GTLC_ALLOWWAKEREQ;
-	if (allow)
-		val |= VLV_GTLC_ALLOWWAKEREQ;
-	intel_uncore_write(uncore, VLV_GTLC_WAKE_CTRL, val);
+	intel_uncore_rmw(uncore, VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ,
+			 allow ? VLV_GTLC_ALLOWWAKEREQ : 0);
 	intel_uncore_posting_read(uncore, VLV_GTLC_WAKE_CTRL);
 
 	mask = VLV_GTLC_ALLOWWAKEACK;
diff --git a/drivers/gpu/drm/panfrost/panfrost_dump.c b/drivers/gpu/drm/panfrost/panfrost_dump.c
index f62a019cc523..e7942ac449c6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_dump.c
+++ b/drivers/gpu/drm/panfrost/panfrost_dump.c
@@ -63,13 +63,13 @@ static void panfrost_core_dump_header(struct panfrost_dump_iterator *iter,
 {
 	struct panfrost_dump_object_header *hdr = iter->hdr;
 
-	hdr->magic = cpu_to_le32(PANFROSTDUMP_MAGIC);
-	hdr->type = cpu_to_le32(type);
-	hdr->file_offset = cpu_to_le32(iter->data - iter->start);
-	hdr->file_size = cpu_to_le32(data_end - iter->data);
+	hdr->magic = PANFROSTDUMP_MAGIC;
+	hdr->type = type;
+	hdr->file_offset = iter->data - iter->start;
+	hdr->file_size = data_end - iter->data;
 
 	iter->hdr++;
-	iter->data += le32_to_cpu(hdr->file_size);
+	iter->data += hdr->file_size;
 }
 
 static void
@@ -93,8 +93,8 @@ panfrost_core_dump_registers(struct panfrost_dump_iterator *iter,
 
 		reg = panfrost_dump_registers[i] + js_as_offset;
 
-		dumpreg->reg = cpu_to_le32(reg);
-		dumpreg->value = cpu_to_le32(gpu_read(pfdev, reg));
+		dumpreg->reg = reg;
+		dumpreg->value = gpu_read(pfdev, reg);
 	}
 
 	panfrost_core_dump_header(iter, PANFROSTDUMP_BUF_REG, dumpreg);
@@ -106,7 +106,7 @@ void panfrost_core_dump(struct panfrost_job *job)
 	struct panfrost_dump_iterator iter;
 	struct drm_gem_object *dbo;
 	unsigned int n_obj, n_bomap_pages;
-	__le64 *bomap, *bomap_start;
+	u64 *bomap, *bomap_start;
 	size_t file_size;
 	u32 as_nr;
 	int slot;
@@ -177,11 +177,11 @@ void panfrost_core_dump(struct panfrost_job *job)
 	 * For now, we write the job identifier in the register dump header,
 	 * so that we can decode the entire dump later with pandecode
 	 */
-	iter.hdr->reghdr.jc = cpu_to_le64(job->jc);
-	iter.hdr->reghdr.major = cpu_to_le32(PANFROSTDUMP_MAJOR);
-	iter.hdr->reghdr.minor = cpu_to_le32(PANFROSTDUMP_MINOR);
-	iter.hdr->reghdr.gpu_id = cpu_to_le32(pfdev->features.id);
-	iter.hdr->reghdr.nbos = cpu_to_le64(job->bo_count);
+	iter.hdr->reghdr.jc = job->jc;
+	iter.hdr->reghdr.major = PANFROSTDUMP_MAJOR;
+	iter.hdr->reghdr.minor = PANFROSTDUMP_MINOR;
+	iter.hdr->reghdr.gpu_id = pfdev->features.id;
+	iter.hdr->reghdr.nbos = job->bo_count;
 
 	panfrost_core_dump_registers(&iter, pfdev, as_nr, slot);
 
@@ -218,27 +218,27 @@ void panfrost_core_dump(struct panfrost_job *job)
 
 		WARN_ON(!mapping->active);
 
-		iter.hdr->bomap.data[0] = cpu_to_le32((bomap - bomap_start));
+		iter.hdr->bomap.data[0] = bomap - bomap_start;
 
 		for_each_sgtable_page(bo->base.sgt, &page_iter, 0) {
 			struct page *page = sg_page_iter_page(&page_iter);
 
 			if (!IS_ERR(page)) {
-				*bomap++ = cpu_to_le64(page_to_phys(page));
+				*bomap++ = page_to_phys(page);
 			} else {
 				dev_err(pfdev->dev, "Panfrost Dump: wrong page\n");
-				*bomap++ = ~cpu_to_le64(0);
+				*bomap++ = 0;
 			}
 		}
 
-		iter.hdr->bomap.iova = cpu_to_le64(mapping->mmnode.start << PAGE_SHIFT);
+		iter.hdr->bomap.iova = mapping->mmnode.start << PAGE_SHIFT;
 
 		vaddr = map.vaddr;
 		memcpy(iter.data, vaddr, bo->base.base.size);
 
 		drm_gem_vunmap_unlocked(&bo->base.base, &map);
 
-		iter.hdr->bomap.valid = cpu_to_le32(1);
+		iter.hdr->bomap.valid = 1;
 
 dump_header:	panfrost_core_dump_header(&iter, PANFROSTDUMP_BUF_BO, iter.data +
 					  bo->base.base.size);
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 52bf9056807a..fe09e5be79bd 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -363,7 +363,8 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 	}
 
 	s_fence = to_drm_sched_fence(fence);
-	if (s_fence && s_fence->sched == sched) {
+	if (s_fence && s_fence->sched == sched &&
+	    !test_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &fence->flags)) {
 
 		/*
 		 * Fence is from the same scheduler, only need to wait for
diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c
index 8d86c250c2ec..2191e57f2297 100644
--- a/drivers/gpu/drm/tests/drm_format_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_format_helper_test.c
@@ -438,7 +438,7 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test)
 	iosys_map_set_vaddr(&src, xrgb8888);
 
 	drm_fb_xrgb8888_to_xrgb2101010(&dst, &result->dst_pitch, &src, &fb, &params->clip);
-	buf = le32buf_to_cpu(test, buf, TEST_BUF_SIZE);
+	buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32));
 	KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index ffbbb454c9e8..2027063fdc30 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -490,6 +490,7 @@ module_init(vc4_drm_register);
 module_exit(vc4_drm_unregister);
 
 MODULE_ALIAS("platform:vc4-drm");
+MODULE_SOFTDEP("pre: snd-soc-hdmi-codec");
 MODULE_DESCRIPTION("Broadcom VC4 DRM Driver");
 MODULE_AUTHOR("Eric Anholt <eric@anholt.net>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 4a73fafca51b..0d78c800ed51 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -3327,12 +3327,37 @@ static int vc4_hdmi_runtime_resume(struct device *dev)
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 	unsigned long __maybe_unused flags;
 	u32 __maybe_unused value;
+	unsigned long rate;
 	int ret;
 
+	/*
+	 * The HSM clock is in the HDMI power domain, so we need to set
+	 * its frequency while the power domain is active so that it
+	 * keeps its rate.
+	 */
+	ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ);
+	if (ret)
+		return ret;
+
 	ret = clk_prepare_enable(vc4_hdmi->hsm_clock);
 	if (ret)
 		return ret;
 
+	/*
+	 * Whenever the RaspberryPi boots without an HDMI monitor
+	 * plugged in, the firmware won't have initialized the HSM clock
+	 * rate and it will be reported as 0.
+	 *
+	 * If we try to access a register of the controller in such a
+	 * case, it will lead to a silent CPU stall. Let's make sure we
+	 * prevent such a case.
+	 */
+	rate = clk_get_rate(vc4_hdmi->hsm_clock);
+	if (!rate) {
+		ret = -EINVAL;
+		goto err_disable_clk;
+	}
+
 	if (vc4_hdmi->variant->reset)
 		vc4_hdmi->variant->reset(vc4_hdmi);
 
@@ -3354,6 +3379,10 @@ static int vc4_hdmi_runtime_resume(struct device *dev)
 #endif
 
 	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(vc4_hdmi->hsm_clock);
+	return ret;
 }
 
 static void vc4_hdmi_put_ddc_device(void *ptr)
diff --git a/drivers/gpu/drm/xlnx/Makefile b/drivers/gpu/drm/xlnx/Makefile
index 51c24b72217b..ea1422a39502 100644
--- a/drivers/gpu/drm/xlnx/Makefile
+++ b/drivers/gpu/drm/xlnx/Makefile
@@ -1,2 +1,2 @@
-zynqmp-dpsub-y := zynqmp_disp.o zynqmp_dpsub.o zynqmp_dp.o
+zynqmp-dpsub-y := zynqmp_disp.o zynqmp_dpsub.o zynqmp_dp.o zynqmp_kms.o
 obj-$(CONFIG_DRM_ZYNQMP_DPSUB) += zynqmp-dpsub.o
diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.c b/drivers/gpu/drm/xlnx/zynqmp_disp.c
index bbb365f2d087..3b87eebddc97 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_disp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_disp.c
@@ -9,29 +9,19 @@
  * - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
  */
 
-#include <drm/drm_atomic.h>
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_atomic_uapi.h>
-#include <drm/drm_blend.h>
-#include <drm/drm_crtc.h>
-#include <drm/drm_device.h>
 #include <drm/drm_fb_dma_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
-#include <drm/drm_managed.h>
 #include <drm/drm_plane.h>
-#include <drm/drm_vblank.h>
 
 #include <linux/clk.h>
-#include <linux/delay.h>
 #include <linux/dma/xilinx_dpdma.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include <linux/spinlock.h>
+#include <linux/slab.h>
 
 #include "zynqmp_disp.h"
 #include "zynqmp_disp_regs.h"
@@ -72,46 +62,23 @@
 #define ZYNQMP_DISP_AV_BUF_NUM_VID_GFX_BUFFERS		4
 #define ZYNQMP_DISP_AV_BUF_NUM_BUFFERS			6
 
-#define ZYNQMP_DISP_NUM_LAYERS				2
 #define ZYNQMP_DISP_MAX_NUM_SUB_PLANES			3
 
 /**
  * struct zynqmp_disp_format - Display subsystem format information
  * @drm_fmt: DRM format (4CC)
  * @buf_fmt: AV buffer format
- * @bus_fmt: Media bus formats (live formats)
  * @swap: Flag to swap R & B for RGB formats, and U & V for YUV formats
  * @sf: Scaling factors for color components
  */
 struct zynqmp_disp_format {
 	u32 drm_fmt;
 	u32 buf_fmt;
-	u32 bus_fmt;
 	bool swap;
 	const u32 *sf;
 };
 
 /**
- * enum zynqmp_disp_layer_id - Layer identifier
- * @ZYNQMP_DISP_LAYER_VID: Video layer
- * @ZYNQMP_DISP_LAYER_GFX: Graphics layer
- */
-enum zynqmp_disp_layer_id {
-	ZYNQMP_DISP_LAYER_VID,
-	ZYNQMP_DISP_LAYER_GFX
-};
-
-/**
- * enum zynqmp_disp_layer_mode - Layer mode
- * @ZYNQMP_DISP_LAYER_NONLIVE: non-live (memory) mode
- * @ZYNQMP_DISP_LAYER_LIVE: live (stream) mode
- */
-enum zynqmp_disp_layer_mode {
-	ZYNQMP_DISP_LAYER_NONLIVE,
-	ZYNQMP_DISP_LAYER_LIVE
-};
-
-/**
  * struct zynqmp_disp_layer_dma - DMA channel for one data plane of a layer
  * @chan: DMA channel
  * @xt: Interleaved DMA descriptor template
@@ -136,8 +103,7 @@ struct zynqmp_disp_layer_info {
 };
 
 /**
- * struct zynqmp_disp_layer - Display layer (DRM plane)
- * @plane: DRM plane
+ * struct zynqmp_disp_layer - Display layer
  * @id: Layer ID
  * @disp: Back pointer to struct zynqmp_disp
  * @info: Static layer information
@@ -147,8 +113,7 @@ struct zynqmp_disp_layer_info {
  * @mode: Current operation mode
  */
 struct zynqmp_disp_layer {
-	struct drm_plane plane;
-	enum zynqmp_disp_layer_id id;
+	enum zynqmp_dpsub_layer_id id;
 	struct zynqmp_disp *disp;
 	const struct zynqmp_disp_layer_info *info;
 
@@ -156,32 +121,22 @@ struct zynqmp_disp_layer {
 
 	const struct zynqmp_disp_format *disp_fmt;
 	const struct drm_format_info *drm_fmt;
-	enum zynqmp_disp_layer_mode mode;
+	enum zynqmp_dpsub_layer_mode mode;
 };
 
 /**
  * struct zynqmp_disp - Display controller
  * @dev: Device structure
- * @drm: DRM core
  * @dpsub: Display subsystem
- * @crtc: DRM CRTC
  * @blend.base: Register I/O base address for the blender
  * @avbuf.base: Register I/O base address for the audio/video buffer manager
  * @audio.base: Registers I/O base address for the audio mixer
- * @audio.clk: Audio clock
- * @audio.clk_from_ps: True of the audio clock comes from PS, false from PL
  * @layers: Layers (planes)
- * @event: Pending vblank event request
- * @pclk: Pixel clock
- * @pclk_from_ps: True of the video clock comes from PS, false from PL
  */
 struct zynqmp_disp {
 	struct device *dev;
-	struct drm_device *drm;
 	struct zynqmp_dpsub *dpsub;
 
-	struct drm_crtc crtc;
-
 	struct {
 		void __iomem *base;
 	} blend;
@@ -190,16 +145,9 @@ struct zynqmp_disp {
 	} avbuf;
 	struct {
 		void __iomem *base;
-		struct clk *clk;
-		bool clk_from_ps;
 	} audio;
 
-	struct zynqmp_disp_layer layers[ZYNQMP_DISP_NUM_LAYERS];
-
-	struct drm_pending_vblank_event *event;
-
-	struct clk *pclk;
-	bool pclk_from_ps;
+	struct zynqmp_disp_layer layers[ZYNQMP_DPSUB_NUM_LAYERS];
 };
 
 /* -----------------------------------------------------------------------------
@@ -416,14 +364,9 @@ static void zynqmp_disp_avbuf_write(struct zynqmp_disp *disp, int reg, u32 val)
 	writel(val, disp->avbuf.base + reg);
 }
 
-static bool zynqmp_disp_layer_is_gfx(const struct zynqmp_disp_layer *layer)
-{
-	return layer->id == ZYNQMP_DISP_LAYER_GFX;
-}
-
 static bool zynqmp_disp_layer_is_video(const struct zynqmp_disp_layer *layer)
 {
-	return layer->id == ZYNQMP_DISP_LAYER_VID;
+	return layer->id == ZYNQMP_DPSUB_LAYER_VID;
 }
 
 /**
@@ -566,27 +509,25 @@ static void zynqmp_disp_avbuf_disable_audio(struct zynqmp_disp *disp)
  * zynqmp_disp_avbuf_enable_video - Enable a video layer
  * @disp: Display controller
  * @layer: The layer
- * @mode: Operating mode of layer
  *
  * Enable the video/graphics buffer for @layer.
  */
 static void zynqmp_disp_avbuf_enable_video(struct zynqmp_disp *disp,
-					   struct zynqmp_disp_layer *layer,
-					   enum zynqmp_disp_layer_mode mode)
+					   struct zynqmp_disp_layer *layer)
 {
 	u32 val;
 
 	val = zynqmp_disp_avbuf_read(disp, ZYNQMP_DISP_AV_BUF_OUTPUT);
 	if (zynqmp_disp_layer_is_video(layer)) {
 		val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_MASK;
-		if (mode == ZYNQMP_DISP_LAYER_NONLIVE)
+		if (layer->mode == ZYNQMP_DPSUB_LAYER_NONLIVE)
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_MEM;
 		else
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID1_LIVE;
 	} else {
 		val &= ~ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_MASK;
 		val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_MEM;
-		if (mode == ZYNQMP_DISP_LAYER_NONLIVE)
+		if (layer->mode == ZYNQMP_DPSUB_LAYER_NONLIVE)
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_MEM;
 		else
 			val |= ZYNQMP_DISP_AV_BUF_OUTPUT_VID2_LIVE;
@@ -758,8 +699,8 @@ static void zynqmp_disp_blend_set_bg_color(struct zynqmp_disp *disp,
  * @enable: True to enable global alpha blending
  * @alpha: Global alpha value (ignored if @enabled is false)
  */
-static void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp *disp,
-					       bool enable, u32 alpha)
+void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp *disp,
+					bool enable, u32 alpha)
 {
 	zynqmp_disp_blend_write(disp, ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA,
 				ZYNQMP_DISP_V_BLEND_SET_GLOBAL_ALPHA_VALUE(alpha) |
@@ -902,80 +843,6 @@ static void zynqmp_disp_audio_disable(struct zynqmp_disp *disp)
 				ZYNQMP_DISP_AUD_SOFT_RESET_AUD_SRST);
 }
 
-static void zynqmp_disp_audio_init(struct zynqmp_disp *disp)
-{
-	/* Try the live PL audio clock. */
-	disp->audio.clk = devm_clk_get(disp->dev, "dp_live_audio_aclk");
-	if (!IS_ERR(disp->audio.clk)) {
-		disp->audio.clk_from_ps = false;
-		return;
-	}
-
-	/* If the live PL audio clock is not valid, fall back to PS clock. */
-	disp->audio.clk = devm_clk_get(disp->dev, "dp_aud_clk");
-	if (!IS_ERR(disp->audio.clk)) {
-		disp->audio.clk_from_ps = true;
-		return;
-	}
-
-	dev_err(disp->dev, "audio disabled due to missing clock\n");
-}
-
-/* -----------------------------------------------------------------------------
- * ZynqMP Display external functions for zynqmp_dp
- */
-
-/**
- * zynqmp_disp_handle_vblank - Handle the vblank event
- * @disp: Display controller
- *
- * This function handles the vblank interrupt, and sends an event to
- * CRTC object. This will be called by the DP vblank interrupt handler.
- */
-void zynqmp_disp_handle_vblank(struct zynqmp_disp *disp)
-{
-	struct drm_crtc *crtc = &disp->crtc;
-
-	drm_crtc_handle_vblank(crtc);
-}
-
-/**
- * zynqmp_disp_audio_enabled - If the audio is enabled
- * @disp: Display controller
- *
- * Return if the audio is enabled depending on the audio clock.
- *
- * Return: true if audio is enabled, or false.
- */
-bool zynqmp_disp_audio_enabled(struct zynqmp_disp *disp)
-{
-	return !!disp->audio.clk;
-}
-
-/**
- * zynqmp_disp_get_audio_clk_rate - Get the current audio clock rate
- * @disp: Display controller
- *
- * Return: the current audio clock rate.
- */
-unsigned int zynqmp_disp_get_audio_clk_rate(struct zynqmp_disp *disp)
-{
-	if (zynqmp_disp_audio_enabled(disp))
-		return 0;
-	return clk_get_rate(disp->audio.clk);
-}
-
-/**
- * zynqmp_disp_get_crtc_mask - Return the CRTC bit mask
- * @disp: Display controller
- *
- * Return: the crtc mask of the zyqnmp_disp CRTC.
- */
-uint32_t zynqmp_disp_get_crtc_mask(struct zynqmp_disp *disp)
-{
-	return drm_crtc_mask(&disp->crtc);
-}
-
 /* -----------------------------------------------------------------------------
  * ZynqMP Display Layer & DRM Plane
  */
@@ -1006,19 +873,46 @@ zynqmp_disp_layer_find_format(struct zynqmp_disp_layer *layer,
 }
 
 /**
+ * zynqmp_disp_layer_drm_formats - Return the DRM formats supported by the layer
+ * @layer: The layer
+ * @num_formats: Pointer to the returned number of formats
+ *
+ * Return: A newly allocated u32 array that stores all the DRM formats
+ * supported by the layer. The number of formats in the array is returned
+ * through the num_formats argument.
+ */
+u32 *zynqmp_disp_layer_drm_formats(struct zynqmp_disp_layer *layer,
+				   unsigned int *num_formats)
+{
+	unsigned int i;
+	u32 *formats;
+
+	formats = kcalloc(layer->info->num_formats, sizeof(*formats),
+			  GFP_KERNEL);
+	if (!formats)
+		return NULL;
+
+	for (i = 0; i < layer->info->num_formats; ++i)
+		formats[i] = layer->info->formats[i].drm_fmt;
+
+	*num_formats = layer->info->num_formats;
+	return formats;
+}
+
+/**
  * zynqmp_disp_layer_enable - Enable a layer
  * @layer: The layer
+ * @mode: Operating mode of layer
  *
  * Enable the @layer in the audio/video buffer manager and the blender. DMA
  * channels are started separately by zynqmp_disp_layer_update().
  */
-static void zynqmp_disp_layer_enable(struct zynqmp_disp_layer *layer)
+void zynqmp_disp_layer_enable(struct zynqmp_disp_layer *layer,
+			      enum zynqmp_dpsub_layer_mode mode)
 {
-	zynqmp_disp_avbuf_enable_video(layer->disp, layer,
-				       ZYNQMP_DISP_LAYER_NONLIVE);
+	layer->mode = mode;
+	zynqmp_disp_avbuf_enable_video(layer->disp, layer);
 	zynqmp_disp_blend_layer_enable(layer->disp, layer);
-
-	layer->mode = ZYNQMP_DISP_LAYER_NONLIVE;
 }
 
 /**
@@ -1028,12 +922,14 @@ static void zynqmp_disp_layer_enable(struct zynqmp_disp_layer *layer)
  * Disable the layer by stopping its DMA channels and disabling it in the
  * audio/video buffer manager and the blender.
  */
-static void zynqmp_disp_layer_disable(struct zynqmp_disp_layer *layer)
+void zynqmp_disp_layer_disable(struct zynqmp_disp_layer *layer)
 {
 	unsigned int i;
 
-	for (i = 0; i < layer->drm_fmt->num_planes; i++)
-		dmaengine_terminate_sync(layer->dmas[i].chan);
+	if (layer->disp->dpsub->dma_enabled) {
+		for (i = 0; i < layer->drm_fmt->num_planes; i++)
+			dmaengine_terminate_sync(layer->dmas[i].chan);
+	}
 
 	zynqmp_disp_avbuf_disable_video(layer->disp, layer);
 	zynqmp_disp_blend_layer_disable(layer->disp, layer);
@@ -1042,15 +938,13 @@ static void zynqmp_disp_layer_disable(struct zynqmp_disp_layer *layer)
 /**
  * zynqmp_disp_layer_set_format - Set the layer format
  * @layer: The layer
- * @state: The plane state
+ * @info: The format info
  *
- * Set the format for @layer based on @state->fb->format. The layer must be
- * disabled.
+ * Set the format for @layer to @info. The layer must be disabled.
  */
-static void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
-					 struct drm_plane_state *state)
+void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
+				  const struct drm_format_info *info)
 {
-	const struct drm_format_info *info = state->fb->format;
 	unsigned int i;
 
 	layer->disp_fmt = zynqmp_disp_layer_find_format(layer, info->format);
@@ -1058,6 +952,9 @@ static void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
 
 	zynqmp_disp_avbuf_set_format(layer->disp, layer, layer->disp_fmt);
 
+	if (!layer->disp->dpsub->dma_enabled)
+		return;
+
 	/*
 	 * Set pconfig for each DMA channel to indicate they're part of a
 	 * video group.
@@ -1087,13 +984,16 @@ static void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
  *
  * Return: 0 on success, or the DMA descriptor failure error otherwise
  */
-static int zynqmp_disp_layer_update(struct zynqmp_disp_layer *layer,
-				    struct drm_plane_state *state)
+int zynqmp_disp_layer_update(struct zynqmp_disp_layer *layer,
+			     struct drm_plane_state *state)
 {
 	const struct drm_format_info *info = layer->drm_fmt;
 	unsigned int i;
 
-	for (i = 0; i < layer->drm_fmt->num_planes; i++) {
+	if (!layer->disp->dpsub->dma_enabled)
+		return 0;
+
+	for (i = 0; i < info->num_planes; i++) {
 		unsigned int width = state->crtc_w / (i ? info->hsub : 1);
 		unsigned int height = state->crtc_h / (i ? info->vsub : 1);
 		struct zynqmp_disp_layer_dma *dma = &layer->dmas[i];
@@ -1128,143 +1028,6 @@ static int zynqmp_disp_layer_update(struct zynqmp_disp_layer *layer,
 	return 0;
 }
 
-static inline struct zynqmp_disp_layer *plane_to_layer(struct drm_plane *plane)
-{
-	return container_of(plane, struct zynqmp_disp_layer, plane);
-}
-
-static int
-zynqmp_disp_plane_atomic_check(struct drm_plane *plane,
-			       struct drm_atomic_state *state)
-{
-	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
-										 plane);
-	struct drm_crtc_state *crtc_state;
-
-	if (!new_plane_state->crtc)
-		return 0;
-
-	crtc_state = drm_atomic_get_crtc_state(state, new_plane_state->crtc);
-	if (IS_ERR(crtc_state))
-		return PTR_ERR(crtc_state);
-
-	return drm_atomic_helper_check_plane_state(new_plane_state,
-						   crtc_state,
-						   DRM_PLANE_NO_SCALING,
-						   DRM_PLANE_NO_SCALING,
-						   false, false);
-}
-
-static void
-zynqmp_disp_plane_atomic_disable(struct drm_plane *plane,
-				 struct drm_atomic_state *state)
-{
-	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state,
-									   plane);
-	struct zynqmp_disp_layer *layer = plane_to_layer(plane);
-
-	if (!old_state->fb)
-		return;
-
-	zynqmp_disp_layer_disable(layer);
-
-	if (zynqmp_disp_layer_is_gfx(layer))
-		zynqmp_disp_blend_set_global_alpha(layer->disp, false,
-						   plane->state->alpha >> 8);
-}
-
-static void
-zynqmp_disp_plane_atomic_update(struct drm_plane *plane,
-				struct drm_atomic_state *state)
-{
-	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, plane);
-	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
-	struct zynqmp_disp_layer *layer = plane_to_layer(plane);
-	bool format_changed = false;
-
-	if (!old_state->fb ||
-	    old_state->fb->format->format != new_state->fb->format->format)
-		format_changed = true;
-
-	/*
-	 * If the format has changed (including going from a previously
-	 * disabled state to any format), reconfigure the format. Disable the
-	 * plane first if needed.
-	 */
-	if (format_changed) {
-		if (old_state->fb)
-			zynqmp_disp_layer_disable(layer);
-
-		zynqmp_disp_layer_set_format(layer, new_state);
-	}
-
-	zynqmp_disp_layer_update(layer, new_state);
-
-	if (zynqmp_disp_layer_is_gfx(layer))
-		zynqmp_disp_blend_set_global_alpha(layer->disp, true,
-						   plane->state->alpha >> 8);
-
-	/* Enable or re-enable the plane is the format has changed. */
-	if (format_changed)
-		zynqmp_disp_layer_enable(layer);
-}
-
-static const struct drm_plane_helper_funcs zynqmp_disp_plane_helper_funcs = {
-	.atomic_check		= zynqmp_disp_plane_atomic_check,
-	.atomic_update		= zynqmp_disp_plane_atomic_update,
-	.atomic_disable		= zynqmp_disp_plane_atomic_disable,
-};
-
-static const struct drm_plane_funcs zynqmp_disp_plane_funcs = {
-	.update_plane		= drm_atomic_helper_update_plane,
-	.disable_plane		= drm_atomic_helper_disable_plane,
-	.destroy		= drm_plane_cleanup,
-	.reset			= drm_atomic_helper_plane_reset,
-	.atomic_duplicate_state	= drm_atomic_helper_plane_duplicate_state,
-	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
-};
-
-static int zynqmp_disp_create_planes(struct zynqmp_disp *disp)
-{
-	unsigned int i, j;
-	int ret;
-
-	for (i = 0; i < ZYNQMP_DISP_NUM_LAYERS; i++) {
-		struct zynqmp_disp_layer *layer = &disp->layers[i];
-		enum drm_plane_type type;
-		u32 *drm_formats;
-
-		drm_formats = drmm_kcalloc(disp->drm, sizeof(*drm_formats),
-					   layer->info->num_formats,
-					   GFP_KERNEL);
-		if (!drm_formats)
-			return -ENOMEM;
-
-		for (j = 0; j < layer->info->num_formats; ++j)
-			drm_formats[j] = layer->info->formats[j].drm_fmt;
-
-		/* Graphics layer is primary, and video layer is overlay. */
-		type = zynqmp_disp_layer_is_video(layer)
-		     ? DRM_PLANE_TYPE_OVERLAY : DRM_PLANE_TYPE_PRIMARY;
-		ret = drm_universal_plane_init(disp->drm, &layer->plane, 0,
-					       &zynqmp_disp_plane_funcs,
-					       drm_formats,
-					       layer->info->num_formats,
-					       NULL, type, NULL);
-		if (ret)
-			return ret;
-
-		drm_plane_helper_add(&layer->plane,
-				     &zynqmp_disp_plane_helper_funcs);
-
-		drm_plane_create_zpos_immutable_property(&layer->plane, i);
-		if (zynqmp_disp_layer_is_gfx(layer))
-			drm_plane_create_alpha_property(&layer->plane);
-	}
-
-	return 0;
-}
-
 /**
  * zynqmp_disp_layer_release_dma - Release DMA channels for a layer
  * @disp: Display controller
@@ -1277,7 +1040,7 @@ static void zynqmp_disp_layer_release_dma(struct zynqmp_disp *disp,
 {
 	unsigned int i;
 
-	if (!layer->info)
+	if (!layer->info || !disp->dpsub->dma_enabled)
 		return;
 
 	for (i = 0; i < layer->info->num_channels; i++) {
@@ -1300,7 +1063,7 @@ static void zynqmp_disp_destroy_layers(struct zynqmp_disp *disp)
 {
 	unsigned int i;
 
-	for (i = 0; i < ZYNQMP_DISP_NUM_LAYERS; i++)
+	for (i = 0; i < ARRAY_SIZE(disp->layers); i++)
 		zynqmp_disp_layer_release_dma(disp, &disp->layers[i]);
 }
 
@@ -1320,6 +1083,9 @@ static int zynqmp_disp_layer_request_dma(struct zynqmp_disp *disp,
 	unsigned int i;
 	int ret;
 
+	if (!disp->dpsub->dma_enabled)
+		return 0;
+
 	for (i = 0; i < layer->info->num_channels; i++) {
 		struct zynqmp_disp_layer_dma *dma = &layer->dmas[i];
 		char dma_channel_name[16];
@@ -1347,12 +1113,12 @@ static int zynqmp_disp_layer_request_dma(struct zynqmp_disp *disp,
 static int zynqmp_disp_create_layers(struct zynqmp_disp *disp)
 {
 	static const struct zynqmp_disp_layer_info layer_info[] = {
-		[ZYNQMP_DISP_LAYER_VID] = {
+		[ZYNQMP_DPSUB_LAYER_VID] = {
 			.formats = avbuf_vid_fmts,
 			.num_formats = ARRAY_SIZE(avbuf_vid_fmts),
 			.num_channels = 3,
 		},
-		[ZYNQMP_DISP_LAYER_GFX] = {
+		[ZYNQMP_DPSUB_LAYER_GFX] = {
 			.formats = avbuf_gfx_fmts,
 			.num_formats = ARRAY_SIZE(avbuf_gfx_fmts),
 			.num_channels = 1,
@@ -1362,7 +1128,7 @@ static int zynqmp_disp_create_layers(struct zynqmp_disp *disp)
 	unsigned int i;
 	int ret;
 
-	for (i = 0; i < ZYNQMP_DISP_NUM_LAYERS; i++) {
+	for (i = 0; i < ARRAY_SIZE(disp->layers); i++) {
 		struct zynqmp_disp_layer *layer = &disp->layers[i];
 
 		layer->id = i;
@@ -1372,6 +1138,8 @@ static int zynqmp_disp_create_layers(struct zynqmp_disp *disp)
 		ret = zynqmp_disp_layer_request_dma(disp, layer);
 		if (ret)
 			goto err;
+
+		disp->dpsub->layers[i] = layer;
 	}
 
 	return 0;
@@ -1382,19 +1150,23 @@ err:
 }
 
 /* -----------------------------------------------------------------------------
- * ZynqMP Display & DRM CRTC
+ * ZynqMP Display
  */
 
 /**
  * zynqmp_disp_enable - Enable the display controller
  * @disp: Display controller
  */
-static void zynqmp_disp_enable(struct zynqmp_disp *disp)
+void zynqmp_disp_enable(struct zynqmp_disp *disp)
 {
+	zynqmp_disp_blend_set_output_format(disp, ZYNQMP_DPSUB_FORMAT_RGB);
+	zynqmp_disp_blend_set_bg_color(disp, 0, 0, 0);
+
 	zynqmp_disp_avbuf_enable(disp);
 	/* Choose clock source based on the DT clock handle. */
-	zynqmp_disp_avbuf_set_clocks_sources(disp, disp->pclk_from_ps,
-					     disp->audio.clk_from_ps, true);
+	zynqmp_disp_avbuf_set_clocks_sources(disp, disp->dpsub->vid_clk_from_ps,
+					     disp->dpsub->aud_clk_from_ps,
+					     true);
 	zynqmp_disp_avbuf_enable_channels(disp);
 	zynqmp_disp_avbuf_enable_audio(disp);
 
@@ -1405,7 +1177,7 @@ static void zynqmp_disp_enable(struct zynqmp_disp *disp)
  * zynqmp_disp_disable - Disable the display controller
  * @disp: Display controller
  */
-static void zynqmp_disp_disable(struct zynqmp_disp *disp)
+void zynqmp_disp_disable(struct zynqmp_disp *disp)
 {
 	zynqmp_disp_audio_disable(disp);
 
@@ -1414,27 +1186,27 @@ static void zynqmp_disp_disable(struct zynqmp_disp *disp)
 	zynqmp_disp_avbuf_disable(disp);
 }
 
-static inline struct zynqmp_disp *crtc_to_disp(struct drm_crtc *crtc)
-{
-	return container_of(crtc, struct zynqmp_disp, crtc);
-}
-
-static int zynqmp_disp_crtc_setup_clock(struct drm_crtc *crtc,
-					struct drm_display_mode *adjusted_mode)
+/**
+ * zynqmp_disp_setup_clock - Configure the display controller pixel clock rate
+ * @disp: Display controller
+ * @mode_clock: The pixel clock rate, in Hz
+ *
+ * Return: 0 on success, or a negative error clock otherwise
+ */
+int zynqmp_disp_setup_clock(struct zynqmp_disp *disp,
+			    unsigned long mode_clock)
 {
-	struct zynqmp_disp *disp = crtc_to_disp(crtc);
-	unsigned long mode_clock = adjusted_mode->clock * 1000;
 	unsigned long rate;
 	long diff;
 	int ret;
 
-	ret = clk_set_rate(disp->pclk, mode_clock);
+	ret = clk_set_rate(disp->dpsub->vid_clk, mode_clock);
 	if (ret) {
-		dev_err(disp->dev, "failed to set a pixel clock\n");
+		dev_err(disp->dev, "failed to set the video clock\n");
 		return ret;
 	}
 
-	rate = clk_get_rate(disp->pclk);
+	rate = clk_get_rate(disp->dpsub->vid_clk);
 	diff = rate - mode_clock;
 	if (abs(diff) > mode_clock / 20)
 		dev_info(disp->dev,
@@ -1448,245 +1220,63 @@ static int zynqmp_disp_crtc_setup_clock(struct drm_crtc *crtc,
 	return 0;
 }
 
-static void
-zynqmp_disp_crtc_atomic_enable(struct drm_crtc *crtc,
-			       struct drm_atomic_state *state)
-{
-	struct zynqmp_disp *disp = crtc_to_disp(crtc);
-	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
-	int ret, vrefresh;
-
-	pm_runtime_get_sync(disp->dev);
-
-	zynqmp_disp_crtc_setup_clock(crtc, adjusted_mode);
-
-	ret = clk_prepare_enable(disp->pclk);
-	if (ret) {
-		dev_err(disp->dev, "failed to enable a pixel clock\n");
-		pm_runtime_put_sync(disp->dev);
-		return;
-	}
-
-	zynqmp_disp_blend_set_output_format(disp, ZYNQMP_DPSUB_FORMAT_RGB);
-	zynqmp_disp_blend_set_bg_color(disp, 0, 0, 0);
-
-	zynqmp_disp_enable(disp);
-
-	/* Delay of 3 vblank intervals for timing gen to be stable */
-	vrefresh = (adjusted_mode->clock * 1000) /
-		   (adjusted_mode->vtotal * adjusted_mode->htotal);
-	msleep(3 * 1000 / vrefresh);
-}
-
-static void
-zynqmp_disp_crtc_atomic_disable(struct drm_crtc *crtc,
-				struct drm_atomic_state *state)
-{
-	struct zynqmp_disp *disp = crtc_to_disp(crtc);
-	struct drm_plane_state *old_plane_state;
-
-	/*
-	 * Disable the plane if active. The old plane state can be NULL in the
-	 * .shutdown() path if the plane is already disabled, skip
-	 * zynqmp_disp_plane_atomic_disable() in that case.
-	 */
-	old_plane_state = drm_atomic_get_old_plane_state(state, crtc->primary);
-	if (old_plane_state)
-		zynqmp_disp_plane_atomic_disable(crtc->primary, state);
-
-	zynqmp_disp_disable(disp);
-
-	drm_crtc_vblank_off(&disp->crtc);
-
-	spin_lock_irq(&crtc->dev->event_lock);
-	if (crtc->state->event) {
-		drm_crtc_send_vblank_event(crtc, crtc->state->event);
-		crtc->state->event = NULL;
-	}
-	spin_unlock_irq(&crtc->dev->event_lock);
-
-	clk_disable_unprepare(disp->pclk);
-	pm_runtime_put_sync(disp->dev);
-}
-
-static int zynqmp_disp_crtc_atomic_check(struct drm_crtc *crtc,
-					 struct drm_atomic_state *state)
-{
-	return drm_atomic_add_affected_planes(state, crtc);
-}
-
-static void
-zynqmp_disp_crtc_atomic_begin(struct drm_crtc *crtc,
-			      struct drm_atomic_state *state)
-{
-	drm_crtc_vblank_on(crtc);
-}
-
-static void
-zynqmp_disp_crtc_atomic_flush(struct drm_crtc *crtc,
-			      struct drm_atomic_state *state)
-{
-	if (crtc->state->event) {
-		struct drm_pending_vblank_event *event;
-
-		/* Consume the flip_done event from atomic helper. */
-		event = crtc->state->event;
-		crtc->state->event = NULL;
-
-		event->pipe = drm_crtc_index(crtc);
-
-		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
-
-		spin_lock_irq(&crtc->dev->event_lock);
-		drm_crtc_arm_vblank_event(crtc, event);
-		spin_unlock_irq(&crtc->dev->event_lock);
-	}
-}
-
-static const struct drm_crtc_helper_funcs zynqmp_disp_crtc_helper_funcs = {
-	.atomic_enable	= zynqmp_disp_crtc_atomic_enable,
-	.atomic_disable	= zynqmp_disp_crtc_atomic_disable,
-	.atomic_check	= zynqmp_disp_crtc_atomic_check,
-	.atomic_begin	= zynqmp_disp_crtc_atomic_begin,
-	.atomic_flush	= zynqmp_disp_crtc_atomic_flush,
-};
-
-static int zynqmp_disp_crtc_enable_vblank(struct drm_crtc *crtc)
-{
-	struct zynqmp_disp *disp = crtc_to_disp(crtc);
-
-	zynqmp_dp_enable_vblank(disp->dpsub->dp);
-
-	return 0;
-}
-
-static void zynqmp_disp_crtc_disable_vblank(struct drm_crtc *crtc)
-{
-	struct zynqmp_disp *disp = crtc_to_disp(crtc);
-
-	zynqmp_dp_disable_vblank(disp->dpsub->dp);
-}
-
-static const struct drm_crtc_funcs zynqmp_disp_crtc_funcs = {
-	.destroy		= drm_crtc_cleanup,
-	.set_config		= drm_atomic_helper_set_config,
-	.page_flip		= drm_atomic_helper_page_flip,
-	.reset			= drm_atomic_helper_crtc_reset,
-	.atomic_duplicate_state	= drm_atomic_helper_crtc_duplicate_state,
-	.atomic_destroy_state	= drm_atomic_helper_crtc_destroy_state,
-	.enable_vblank		= zynqmp_disp_crtc_enable_vblank,
-	.disable_vblank		= zynqmp_disp_crtc_disable_vblank,
-};
-
-static int zynqmp_disp_create_crtc(struct zynqmp_disp *disp)
-{
-	struct drm_plane *plane = &disp->layers[ZYNQMP_DISP_LAYER_GFX].plane;
-	int ret;
-
-	ret = drm_crtc_init_with_planes(disp->drm, &disp->crtc, plane,
-					NULL, &zynqmp_disp_crtc_funcs, NULL);
-	if (ret < 0)
-		return ret;
-
-	drm_crtc_helper_add(&disp->crtc, &zynqmp_disp_crtc_helper_funcs);
-
-	/* Start with vertical blanking interrupt reporting disabled. */
-	drm_crtc_vblank_off(&disp->crtc);
-
-	return 0;
-}
-
-static void zynqmp_disp_map_crtc_to_plane(struct zynqmp_disp *disp)
-{
-	u32 possible_crtcs = drm_crtc_mask(&disp->crtc);
-	unsigned int i;
-
-	for (i = 0; i < ZYNQMP_DISP_NUM_LAYERS; i++)
-		disp->layers[i].plane.possible_crtcs = possible_crtcs;
-}
-
 /* -----------------------------------------------------------------------------
  * Initialization & Cleanup
  */
 
-int zynqmp_disp_drm_init(struct zynqmp_dpsub *dpsub)
-{
-	struct zynqmp_disp *disp = dpsub->disp;
-	int ret;
-
-	ret = zynqmp_disp_create_planes(disp);
-	if (ret)
-		return ret;
-
-	ret = zynqmp_disp_create_crtc(disp);
-	if (ret < 0)
-		return ret;
-
-	zynqmp_disp_map_crtc_to_plane(disp);
-
-	return 0;
-}
-
-int zynqmp_disp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
+int zynqmp_disp_probe(struct zynqmp_dpsub *dpsub)
 {
 	struct platform_device *pdev = to_platform_device(dpsub->dev);
 	struct zynqmp_disp *disp;
-	struct zynqmp_disp_layer *layer;
 	struct resource *res;
 	int ret;
 
-	disp = drmm_kzalloc(drm, sizeof(*disp), GFP_KERNEL);
+	disp = kzalloc(sizeof(*disp), GFP_KERNEL);
 	if (!disp)
 		return -ENOMEM;
 
 	disp->dev = &pdev->dev;
 	disp->dpsub = dpsub;
-	disp->drm = drm;
-
-	dpsub->disp = disp;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "blend");
 	disp->blend.base = devm_ioremap_resource(disp->dev, res);
-	if (IS_ERR(disp->blend.base))
-		return PTR_ERR(disp->blend.base);
+	if (IS_ERR(disp->blend.base)) {
+		ret = PTR_ERR(disp->blend.base);
+		goto error;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "av_buf");
 	disp->avbuf.base = devm_ioremap_resource(disp->dev, res);
-	if (IS_ERR(disp->avbuf.base))
-		return PTR_ERR(disp->avbuf.base);
+	if (IS_ERR(disp->avbuf.base)) {
+		ret = PTR_ERR(disp->avbuf.base);
+		goto error;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "aud");
 	disp->audio.base = devm_ioremap_resource(disp->dev, res);
-	if (IS_ERR(disp->audio.base))
-		return PTR_ERR(disp->audio.base);
-
-	/* Try the live PL video clock */
-	disp->pclk = devm_clk_get(disp->dev, "dp_live_video_in_clk");
-	if (!IS_ERR(disp->pclk))
-		disp->pclk_from_ps = false;
-	else if (PTR_ERR(disp->pclk) == -EPROBE_DEFER)
-		return PTR_ERR(disp->pclk);
-
-	/* If the live PL video clock is not valid, fall back to PS clock */
-	if (IS_ERR_OR_NULL(disp->pclk)) {
-		disp->pclk = devm_clk_get(disp->dev, "dp_vtc_pixel_clk_in");
-		if (IS_ERR(disp->pclk)) {
-			dev_err(disp->dev, "failed to init any video clock\n");
-			return PTR_ERR(disp->pclk);
-		}
-		disp->pclk_from_ps = true;
+	if (IS_ERR(disp->audio.base)) {
+		ret = PTR_ERR(disp->audio.base);
+		goto error;
 	}
 
-	zynqmp_disp_audio_init(disp);
-
 	ret = zynqmp_disp_create_layers(disp);
 	if (ret)
-		return ret;
+		goto error;
+
+	if (disp->dpsub->dma_enabled) {
+		struct zynqmp_disp_layer *layer;
 
-	layer = &disp->layers[ZYNQMP_DISP_LAYER_VID];
-	dpsub->dma_align = 1 << layer->dmas[0].chan->device->copy_align;
+		layer = &disp->layers[ZYNQMP_DPSUB_LAYER_VID];
+		dpsub->dma_align = 1 << layer->dmas[0].chan->device->copy_align;
+	}
+
+	dpsub->disp = disp;
 
 	return 0;
+
+error:
+	kfree(disp);
+	return ret;
 }
 
 void zynqmp_disp_remove(struct zynqmp_dpsub *dpsub)
diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.h b/drivers/gpu/drm/xlnx/zynqmp_disp.h
index f402901afb23..123cffac08be 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_disp.h
+++ b/drivers/gpu/drm/xlnx/zynqmp_disp.h
@@ -25,18 +25,52 @@
 #define ZYNQMP_DISP_MAX_DMA_BIT				44
 
 struct device;
-struct drm_device;
+struct drm_format_info;
+struct drm_plane_state;
 struct platform_device;
 struct zynqmp_disp;
+struct zynqmp_disp_layer;
 struct zynqmp_dpsub;
 
-void zynqmp_disp_handle_vblank(struct zynqmp_disp *disp);
-bool zynqmp_disp_audio_enabled(struct zynqmp_disp *disp);
-unsigned int zynqmp_disp_get_audio_clk_rate(struct zynqmp_disp *disp);
-uint32_t zynqmp_disp_get_crtc_mask(struct zynqmp_disp *disp);
+/**
+ * enum zynqmp_dpsub_layer_id - Layer identifier
+ * @ZYNQMP_DPSUB_LAYER_VID: Video layer
+ * @ZYNQMP_DPSUB_LAYER_GFX: Graphics layer
+ */
+enum zynqmp_dpsub_layer_id {
+	ZYNQMP_DPSUB_LAYER_VID,
+	ZYNQMP_DPSUB_LAYER_GFX,
+};
+
+/**
+ * enum zynqmp_dpsub_layer_mode - Layer mode
+ * @ZYNQMP_DPSUB_LAYER_NONLIVE: non-live (memory) mode
+ * @ZYNQMP_DPSUB_LAYER_LIVE: live (stream) mode
+ */
+enum zynqmp_dpsub_layer_mode {
+	ZYNQMP_DPSUB_LAYER_NONLIVE,
+	ZYNQMP_DPSUB_LAYER_LIVE,
+};
+
+void zynqmp_disp_enable(struct zynqmp_disp *disp);
+void zynqmp_disp_disable(struct zynqmp_disp *disp);
+int zynqmp_disp_setup_clock(struct zynqmp_disp *disp,
+			    unsigned long mode_clock);
+
+void zynqmp_disp_blend_set_global_alpha(struct zynqmp_disp *disp,
+					bool enable, u32 alpha);
+
+u32 *zynqmp_disp_layer_drm_formats(struct zynqmp_disp_layer *layer,
+				   unsigned int *num_formats);
+void zynqmp_disp_layer_enable(struct zynqmp_disp_layer *layer,
+			      enum zynqmp_dpsub_layer_mode mode);
+void zynqmp_disp_layer_disable(struct zynqmp_disp_layer *layer);
+void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer,
+				  const struct drm_format_info *info);
+int zynqmp_disp_layer_update(struct zynqmp_disp_layer *layer,
+			     struct drm_plane_state *state);
 
-int zynqmp_disp_drm_init(struct zynqmp_dpsub *dpsub);
-int zynqmp_disp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm);
+int zynqmp_disp_probe(struct zynqmp_dpsub *dpsub);
 void zynqmp_disp_remove(struct zynqmp_dpsub *dpsub);
 
 #endif /* _ZYNQMP_DISP_H_ */
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index d14612b34796..7c9ae167eac7 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -11,16 +11,12 @@
 
 #include <drm/display/drm_dp_helper.h>
 #include <drm/drm_atomic_helper.h>
-#include <drm/drm_connector.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_encoder.h>
-#include <drm/drm_managed.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_modes.h>
 #include <drm/drm_of.h>
-#include <drm/drm_probe_helper.h>
-#include <drm/drm_simple_kms_helper.h>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -31,10 +27,12 @@
 #include <linux/pm_runtime.h>
 #include <linux/phy/phy.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 
 #include "zynqmp_disp.h"
 #include "zynqmp_dp.h"
 #include "zynqmp_dpsub.h"
+#include "zynqmp_kms.h"
 
 static uint zynqmp_dp_aux_timeout_ms = 50;
 module_param_named(aux_timeout_ms, zynqmp_dp_aux_timeout_ms, uint, 0444);
@@ -277,14 +275,13 @@ struct zynqmp_dp_config {
 
 /**
  * struct zynqmp_dp - Xilinx DisplayPort core
- * @encoder: the drm encoder structure
- * @connector: the drm connector structure
  * @dev: device structure
  * @dpsub: Display subsystem
- * @drm: DRM core
  * @iomem: device I/O memory for register access
  * @reset: reset controller
  * @irq: irq
+ * @bridge: DRM bridge for the DP encoder
+ * @next_bridge: The downstream bridge
  * @config: IP core configuration from DTS
  * @aux: aux channel
  * @phy: PHY handles for DP lanes
@@ -298,15 +295,15 @@ struct zynqmp_dp_config {
  * @train_set: set of training data
  */
 struct zynqmp_dp {
-	struct drm_encoder encoder;
-	struct drm_connector connector;
 	struct device *dev;
 	struct zynqmp_dpsub *dpsub;
-	struct drm_device *drm;
 	void __iomem *iomem;
 	struct reset_control *reset;
 	int irq;
 
+	struct drm_bridge bridge;
+	struct drm_bridge *next_bridge;
+
 	struct zynqmp_dp_config config;
 	struct drm_dp_aux aux;
 	struct phy *phy[ZYNQMP_DP_MAX_LANES];
@@ -321,14 +318,9 @@ struct zynqmp_dp {
 	u8 train_set[ZYNQMP_DP_MAX_LANES];
 };
 
-static inline struct zynqmp_dp *encoder_to_dp(struct drm_encoder *encoder)
-{
-	return container_of(encoder, struct zynqmp_dp, encoder);
-}
-
-static inline struct zynqmp_dp *connector_to_dp(struct drm_connector *connector)
+static inline struct zynqmp_dp *bridge_to_dp(struct drm_bridge *bridge)
 {
-	return container_of(connector, struct zynqmp_dp, connector);
+	return container_of(bridge, struct zynqmp_dp, bridge);
 }
 
 static void zynqmp_dp_write(struct zynqmp_dp *dp, int offset, u32 val)
@@ -1064,7 +1056,7 @@ static int zynqmp_dp_aux_init(struct zynqmp_dp *dp)
 
 	dp->aux.name = "ZynqMP DP AUX";
 	dp->aux.dev = dp->dev;
-	dp->aux.drm_dev = dp->drm;
+	dp->aux.drm_dev = dp->bridge.dev;
 	dp->aux.transfer = zynqmp_dp_aux_transfer;
 
 	return drm_dp_aux_register(&dp->aux);
@@ -1101,6 +1093,7 @@ static void zynqmp_dp_update_misc(struct zynqmp_dp *dp)
 /**
  * zynqmp_dp_set_format - Set the input format
  * @dp: DisplayPort IP core structure
+ * @info: Display info
  * @format: input format
  * @bpc: bits per component
  *
@@ -1109,10 +1102,10 @@ static void zynqmp_dp_update_misc(struct zynqmp_dp *dp)
  * Return: 0 on success, or -EINVAL.
  */
 static int zynqmp_dp_set_format(struct zynqmp_dp *dp,
+				const struct drm_display_info *info,
 				enum zynqmp_dpsub_format format,
 				unsigned int bpc)
 {
-	static const struct drm_display_info *display;
 	struct zynqmp_dp_config *config = &dp->config;
 	unsigned int num_colors;
 
@@ -1145,12 +1138,11 @@ static int zynqmp_dp_set_format(struct zynqmp_dp *dp,
 		return -EINVAL;
 	}
 
-	display = &dp->connector.display_info;
-	if (display->bpc && bpc > display->bpc) {
+	if (info && info->bpc && bpc > info->bpc) {
 		dev_warn(dp->dev,
 			 "downgrading requested %ubpc to display limit %ubpc\n",
-			 bpc, display->bpc);
-		bpc = display->bpc;
+			 bpc, info->bpc);
+		bpc = info->bpc;
 	}
 
 	config->misc0 &= ~ZYNQMP_DP_MAIN_STREAM_MISC0_BPC_MASK;
@@ -1195,7 +1187,7 @@ static int zynqmp_dp_set_format(struct zynqmp_dp *dp,
  */
 static void
 zynqmp_dp_encoder_mode_set_transfer_unit(struct zynqmp_dp *dp,
-					 struct drm_display_mode *mode)
+					 const struct drm_display_mode *mode)
 {
 	u32 tu = ZYNQMP_DP_MSA_TRANSFER_UNIT_SIZE_TU_SIZE_DEF;
 	u32 bw, vid_kbytes, avg_bytes_per_tu, init_wait;
@@ -1255,12 +1247,12 @@ static void zynqmp_dp_encoder_mode_set_stream(struct zynqmp_dp *dp,
 	zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_VSTART,
 			mode->vtotal - mode->vsync_start);
 
-	/* In synchronous mode, set the diviers */
+	/* In synchronous mode, set the dividers */
 	if (dp->config.misc0 & ZYNQMP_DP_MAIN_STREAM_MISC0_SYNC_LOCK) {
 		reg = drm_dp_bw_code_to_link_rate(dp->mode.bw_code);
 		zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_N_VID, reg);
 		zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_M_VID, mode->clock);
-		rate = zynqmp_disp_get_audio_clk_rate(dp->dpsub->disp);
+		rate = zynqmp_dpsub_get_audio_clk_rate(dp->dpsub);
 		if (rate) {
 			dev_dbg(dp->dev, "Audio rate: %d\n", rate / 512);
 			zynqmp_dp_write(dp, ZYNQMP_DP_TX_N_AUD, reg);
@@ -1269,7 +1261,7 @@ static void zynqmp_dp_encoder_mode_set_stream(struct zynqmp_dp *dp,
 	}
 
 	/* Only 2 channel audio is supported now */
-	if (zynqmp_disp_audio_enabled(dp->dpsub->disp))
+	if (zynqmp_dpsub_audio_enabled(dp->dpsub))
 		zynqmp_dp_write(dp, ZYNQMP_DP_TX_AUDIO_CHANNELS, 1);
 
 	zynqmp_dp_write(dp, ZYNQMP_DP_USER_PIX_WIDTH, 1);
@@ -1281,97 +1273,114 @@ static void zynqmp_dp_encoder_mode_set_stream(struct zynqmp_dp *dp,
 }
 
 /* -----------------------------------------------------------------------------
- * DRM Connector
+ * DISP Configuration
  */
 
-static enum drm_connector_status
-zynqmp_dp_connector_detect(struct drm_connector *connector, bool force)
+static void zynqmp_dp_disp_enable(struct zynqmp_dp *dp,
+				  struct drm_bridge_state *old_bridge_state)
 {
-	struct zynqmp_dp *dp = connector_to_dp(connector);
-	struct zynqmp_dp_link_config *link_config = &dp->link_config;
-	u32 state, i;
-	int ret;
+	enum zynqmp_dpsub_layer_id layer_id;
+	struct zynqmp_disp_layer *layer;
+	const struct drm_format_info *info;
+
+	if (dp->dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_VIDEO))
+		layer_id = ZYNQMP_DPSUB_LAYER_VID;
+	else if (dp->dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_GFX))
+		layer_id = ZYNQMP_DPSUB_LAYER_GFX;
+	else
+		return;
 
-	/*
-	 * This is from heuristic. It takes some delay (ex, 100 ~ 500 msec) to
-	 * get the HPD signal with some monitors.
-	 */
-	for (i = 0; i < 10; i++) {
-		state = zynqmp_dp_read(dp, ZYNQMP_DP_INTERRUPT_SIGNAL_STATE);
-		if (state & ZYNQMP_DP_INTERRUPT_SIGNAL_STATE_HPD)
-			break;
-		msleep(100);
-	}
+	layer = dp->dpsub->layers[layer_id];
 
-	if (state & ZYNQMP_DP_INTERRUPT_SIGNAL_STATE_HPD) {
-		ret = drm_dp_dpcd_read(&dp->aux, 0x0, dp->dpcd,
-				       sizeof(dp->dpcd));
-		if (ret < 0) {
-			dev_dbg(dp->dev, "DPCD read failed");
-			goto disconnected;
-		}
+	/* TODO: Make the format configurable. */
+	info = drm_format_info(DRM_FORMAT_YUV422);
+	zynqmp_disp_layer_set_format(layer, info);
+	zynqmp_disp_layer_enable(layer, ZYNQMP_DPSUB_LAYER_LIVE);
 
-		link_config->max_rate = min_t(int,
-					      drm_dp_max_link_rate(dp->dpcd),
-					      DP_HIGH_BIT_RATE2);
-		link_config->max_lanes = min_t(u8,
-					       drm_dp_max_lane_count(dp->dpcd),
-					       dp->num_lanes);
+	if (layer_id == ZYNQMP_DPSUB_LAYER_GFX)
+		zynqmp_disp_blend_set_global_alpha(dp->dpsub->disp, true, 255);
+	else
+		zynqmp_disp_blend_set_global_alpha(dp->dpsub->disp, false, 0);
 
-		dp->status = connector_status_connected;
-		return connector_status_connected;
-	}
+	zynqmp_disp_enable(dp->dpsub->disp);
+}
 
-disconnected:
-	dp->status = connector_status_disconnected;
-	return connector_status_disconnected;
+static void zynqmp_dp_disp_disable(struct zynqmp_dp *dp,
+				   struct drm_bridge_state *old_bridge_state)
+{
+	struct zynqmp_disp_layer *layer;
+
+	if (dp->dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_VIDEO))
+		layer = dp->dpsub->layers[ZYNQMP_DPSUB_LAYER_VID];
+	else if (dp->dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_GFX))
+		layer = dp->dpsub->layers[ZYNQMP_DPSUB_LAYER_GFX];
+	else
+		return;
+
+	zynqmp_disp_disable(dp->dpsub->disp);
+	zynqmp_disp_layer_disable(layer);
 }
 
-static int zynqmp_dp_connector_get_modes(struct drm_connector *connector)
+/* -----------------------------------------------------------------------------
+ * DRM Bridge
+ */
+
+static int zynqmp_dp_bridge_attach(struct drm_bridge *bridge,
+				   enum drm_bridge_attach_flags flags)
 {
-	struct zynqmp_dp *dp = connector_to_dp(connector);
-	struct edid *edid;
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
 	int ret;
 
-	edid = drm_get_edid(connector, &dp->aux.ddc);
-	if (!edid)
-		return 0;
+	/* Initialize and register the AUX adapter. */
+	ret = zynqmp_dp_aux_init(dp);
+	if (ret) {
+		dev_err(dp->dev, "failed to initialize DP aux\n");
+		return ret;
+	}
 
-	drm_connector_update_edid_property(connector, edid);
-	ret = drm_add_edid_modes(connector, edid);
-	kfree(edid);
+	if (dp->next_bridge) {
+		ret = drm_bridge_attach(bridge->encoder, dp->next_bridge,
+					bridge, flags);
+		if (ret < 0)
+			goto error;
+	}
 
+	/* Now that initialisation is complete, enable interrupts. */
+	zynqmp_dp_write(dp, ZYNQMP_DP_INT_EN, ZYNQMP_DP_INT_ALL);
+
+	return 0;
+
+error:
+	zynqmp_dp_aux_cleanup(dp);
 	return ret;
 }
 
-static struct drm_encoder *
-zynqmp_dp_connector_best_encoder(struct drm_connector *connector)
+static void zynqmp_dp_bridge_detach(struct drm_bridge *bridge)
 {
-	struct zynqmp_dp *dp = connector_to_dp(connector);
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
 
-	return &dp->encoder;
+	zynqmp_dp_aux_cleanup(dp);
 }
 
-static int zynqmp_dp_connector_mode_valid(struct drm_connector *connector,
-					  struct drm_display_mode *mode)
+static int zynqmp_dp_bridge_mode_valid(struct drm_bridge *bridge,
+				       const struct drm_display_info *info,
+				       const struct drm_display_mode *mode)
 {
-	struct zynqmp_dp *dp = connector_to_dp(connector);
-	u8 max_lanes = dp->link_config.max_lanes;
-	u8 bpp = dp->config.bpp;
-	int max_rate = dp->link_config.max_rate;
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
 	int rate;
 
 	if (mode->clock > ZYNQMP_MAX_FREQ) {
-		dev_dbg(dp->dev, "filtered the mode, %s,for high pixel rate\n",
+		dev_dbg(dp->dev, "filtered mode %s for high pixel rate\n",
 			mode->name);
 		drm_mode_debug_printmodeline(mode);
 		return MODE_CLOCK_HIGH;
 	}
 
 	/* Check with link rate and lane count */
-	rate = zynqmp_dp_max_rate(max_rate, max_lanes, bpp);
+	rate = zynqmp_dp_max_rate(dp->link_config.max_rate,
+				  dp->link_config.max_lanes, dp->config.bpp);
 	if (mode->clock > rate) {
-		dev_dbg(dp->dev, "filtered the mode, %s,for high pixel rate\n",
+		dev_dbg(dp->dev, "filtered mode %s for high pixel rate\n",
 			mode->name);
 		drm_mode_debug_printmodeline(mode);
 		return MODE_CLOCK_HIGH;
@@ -1380,36 +1389,62 @@ static int zynqmp_dp_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static const struct drm_connector_funcs zynqmp_dp_connector_funcs = {
-	.detect			= zynqmp_dp_connector_detect,
-	.fill_modes		= drm_helper_probe_single_connector_modes,
-	.destroy		= drm_connector_cleanup,
-	.atomic_duplicate_state	= drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state	= drm_atomic_helper_connector_destroy_state,
-	.reset			= drm_atomic_helper_connector_reset,
-};
-
-static const struct drm_connector_helper_funcs
-zynqmp_dp_connector_helper_funcs = {
-	.get_modes	= zynqmp_dp_connector_get_modes,
-	.best_encoder	= zynqmp_dp_connector_best_encoder,
-	.mode_valid	= zynqmp_dp_connector_mode_valid,
-};
-
-/* -----------------------------------------------------------------------------
- * DRM Encoder
- */
-
-static void zynqmp_dp_encoder_enable(struct drm_encoder *encoder)
+static void zynqmp_dp_bridge_atomic_enable(struct drm_bridge *bridge,
+					   struct drm_bridge_state *old_bridge_state)
 {
-	struct zynqmp_dp *dp = encoder_to_dp(encoder);
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
+	struct drm_atomic_state *state = old_bridge_state->base.state;
+	const struct drm_crtc_state *crtc_state;
+	const struct drm_display_mode *adjusted_mode;
+	const struct drm_display_mode *mode;
+	struct drm_connector *connector;
+	struct drm_crtc *crtc;
 	unsigned int i;
-	int ret = 0;
+	int rate;
+	int ret;
 
 	pm_runtime_get_sync(dp->dev);
+
+	zynqmp_dp_disp_enable(dp, old_bridge_state);
+
+	/*
+	 * Retrieve the CRTC mode and adjusted mode. This requires a little
+	 * dance to go from the bridge to the encoder, to the connector and to
+	 * the CRTC.
+	 */
+	connector = drm_atomic_get_new_connector_for_encoder(state,
+							     bridge->encoder);
+	crtc = drm_atomic_get_new_connector_state(state, connector)->crtc;
+	crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
+	adjusted_mode = &crtc_state->adjusted_mode;
+	mode = &crtc_state->mode;
+
+	zynqmp_dp_set_format(dp, &connector->display_info,
+			     ZYNQMP_DPSUB_FORMAT_RGB, 8);
+
+	/* Check again as bpp or format might have been changed */
+	rate = zynqmp_dp_max_rate(dp->link_config.max_rate,
+				  dp->link_config.max_lanes, dp->config.bpp);
+	if (mode->clock > rate) {
+		dev_err(dp->dev, "mode %s has too high pixel rate\n",
+			mode->name);
+		drm_mode_debug_printmodeline(mode);
+	}
+
+	/* Configure the mode */
+	ret = zynqmp_dp_mode_configure(dp, adjusted_mode->clock, 0);
+	if (ret < 0) {
+		pm_runtime_put_sync(dp->dev);
+		return;
+	}
+
+	zynqmp_dp_encoder_mode_set_transfer_unit(dp, adjusted_mode);
+	zynqmp_dp_encoder_mode_set_stream(dp, adjusted_mode);
+
+	/* Enable the encoder */
 	dp->enabled = true;
 	zynqmp_dp_update_misc(dp);
-	if (zynqmp_disp_audio_enabled(dp->dpsub->disp))
+	if (zynqmp_dpsub_audio_enabled(dp->dpsub))
 		zynqmp_dp_write(dp, ZYNQMP_DP_TX_AUDIO_CONTROL, 1);
 	zynqmp_dp_write(dp, ZYNQMP_DP_TX_PHY_POWER_DOWN, 0);
 	if (dp->status == connector_status_connected) {
@@ -1432,9 +1467,10 @@ static void zynqmp_dp_encoder_enable(struct drm_encoder *encoder)
 	zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_ENABLE, 1);
 }
 
-static void zynqmp_dp_encoder_disable(struct drm_encoder *encoder)
+static void zynqmp_dp_bridge_atomic_disable(struct drm_bridge *bridge,
+					    struct drm_bridge_state *old_bridge_state)
 {
-	struct zynqmp_dp *dp = encoder_to_dp(encoder);
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
 
 	dp->enabled = false;
 	cancel_delayed_work(&dp->hpd_work);
@@ -1442,49 +1478,22 @@ static void zynqmp_dp_encoder_disable(struct drm_encoder *encoder)
 	drm_dp_dpcd_writeb(&dp->aux, DP_SET_POWER, DP_SET_POWER_D3);
 	zynqmp_dp_write(dp, ZYNQMP_DP_TX_PHY_POWER_DOWN,
 			ZYNQMP_DP_TX_PHY_POWER_DOWN_ALL);
-	if (zynqmp_disp_audio_enabled(dp->dpsub->disp))
+	if (zynqmp_dpsub_audio_enabled(dp->dpsub))
 		zynqmp_dp_write(dp, ZYNQMP_DP_TX_AUDIO_CONTROL, 0);
-	pm_runtime_put_sync(dp->dev);
-}
-
-static void
-zynqmp_dp_encoder_atomic_mode_set(struct drm_encoder *encoder,
-				  struct drm_crtc_state *crtc_state,
-				  struct drm_connector_state *connector_state)
-{
-	struct zynqmp_dp *dp = encoder_to_dp(encoder);
-	struct drm_display_mode *mode = &crtc_state->mode;
-	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
-	u8 max_lanes = dp->link_config.max_lanes;
-	u8 bpp = dp->config.bpp;
-	int rate, max_rate = dp->link_config.max_rate;
-	int ret;
 
-	zynqmp_dp_set_format(dp, ZYNQMP_DPSUB_FORMAT_RGB, 8);
+	zynqmp_dp_disp_disable(dp, old_bridge_state);
 
-	/* Check again as bpp or format might have been chagned */
-	rate = zynqmp_dp_max_rate(max_rate, max_lanes, bpp);
-	if (mode->clock > rate) {
-		dev_err(dp->dev, "the mode, %s,has too high pixel rate\n",
-			mode->name);
-		drm_mode_debug_printmodeline(mode);
-	}
-
-	ret = zynqmp_dp_mode_configure(dp, adjusted_mode->clock, 0);
-	if (ret < 0)
-		return;
-
-	zynqmp_dp_encoder_mode_set_transfer_unit(dp, adjusted_mode);
-	zynqmp_dp_encoder_mode_set_stream(dp, adjusted_mode);
+	pm_runtime_put_sync(dp->dev);
 }
 
 #define ZYNQMP_DP_MIN_H_BACKPORCH	20
 
-static int
-zynqmp_dp_encoder_atomic_check(struct drm_encoder *encoder,
-			       struct drm_crtc_state *crtc_state,
-			       struct drm_connector_state *conn_state)
+static int zynqmp_dp_bridge_atomic_check(struct drm_bridge *bridge,
+					 struct drm_bridge_state *bridge_state,
+					 struct drm_crtc_state *crtc_state,
+					 struct drm_connector_state *conn_state)
 {
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
 	struct drm_display_mode *mode = &crtc_state->mode;
 	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
 	int diff = mode->htotal - mode->hsync_end;
@@ -1497,7 +1506,7 @@ zynqmp_dp_encoder_atomic_check(struct drm_encoder *encoder,
 		int vrefresh = (adjusted_mode->clock * 1000) /
 			       (adjusted_mode->vtotal * adjusted_mode->htotal);
 
-		dev_dbg(encoder->dev->dev, "hbackporch adjusted: %d to %d",
+		dev_dbg(dp->dev, "hbackporch adjusted: %d to %d",
 			diff, ZYNQMP_DP_MIN_H_BACKPORCH - diff);
 		diff = ZYNQMP_DP_MIN_H_BACKPORCH - diff;
 		adjusted_mode->htotal += diff;
@@ -1508,11 +1517,68 @@ zynqmp_dp_encoder_atomic_check(struct drm_encoder *encoder,
 	return 0;
 }
 
-static const struct drm_encoder_helper_funcs zynqmp_dp_encoder_helper_funcs = {
-	.enable			= zynqmp_dp_encoder_enable,
-	.disable		= zynqmp_dp_encoder_disable,
-	.atomic_mode_set	= zynqmp_dp_encoder_atomic_mode_set,
-	.atomic_check		= zynqmp_dp_encoder_atomic_check,
+static enum drm_connector_status zynqmp_dp_bridge_detect(struct drm_bridge *bridge)
+{
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
+	struct zynqmp_dp_link_config *link_config = &dp->link_config;
+	u32 state, i;
+	int ret;
+
+	/*
+	 * This is from heuristic. It takes some delay (ex, 100 ~ 500 msec) to
+	 * get the HPD signal with some monitors.
+	 */
+	for (i = 0; i < 10; i++) {
+		state = zynqmp_dp_read(dp, ZYNQMP_DP_INTERRUPT_SIGNAL_STATE);
+		if (state & ZYNQMP_DP_INTERRUPT_SIGNAL_STATE_HPD)
+			break;
+		msleep(100);
+	}
+
+	if (state & ZYNQMP_DP_INTERRUPT_SIGNAL_STATE_HPD) {
+		ret = drm_dp_dpcd_read(&dp->aux, 0x0, dp->dpcd,
+				       sizeof(dp->dpcd));
+		if (ret < 0) {
+			dev_dbg(dp->dev, "DPCD read failed");
+			goto disconnected;
+		}
+
+		link_config->max_rate = min_t(int,
+					      drm_dp_max_link_rate(dp->dpcd),
+					      DP_HIGH_BIT_RATE2);
+		link_config->max_lanes = min_t(u8,
+					       drm_dp_max_lane_count(dp->dpcd),
+					       dp->num_lanes);
+
+		dp->status = connector_status_connected;
+		return connector_status_connected;
+	}
+
+disconnected:
+	dp->status = connector_status_disconnected;
+	return connector_status_disconnected;
+}
+
+static struct edid *zynqmp_dp_bridge_get_edid(struct drm_bridge *bridge,
+					      struct drm_connector *connector)
+{
+	struct zynqmp_dp *dp = bridge_to_dp(bridge);
+
+	return drm_get_edid(connector, &dp->aux.ddc);
+}
+
+static const struct drm_bridge_funcs zynqmp_dp_bridge_funcs = {
+	.attach = zynqmp_dp_bridge_attach,
+	.detach = zynqmp_dp_bridge_detach,
+	.mode_valid = zynqmp_dp_bridge_mode_valid,
+	.atomic_enable = zynqmp_dp_bridge_atomic_enable,
+	.atomic_disable = zynqmp_dp_bridge_atomic_disable,
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+	.atomic_reset = drm_atomic_helper_bridge_reset,
+	.atomic_check = zynqmp_dp_bridge_atomic_check,
+	.detect = zynqmp_dp_bridge_detect,
+	.get_edid = zynqmp_dp_bridge_get_edid,
 };
 
 /* -----------------------------------------------------------------------------
@@ -1543,12 +1609,12 @@ void zynqmp_dp_disable_vblank(struct zynqmp_dp *dp)
 
 static void zynqmp_dp_hpd_work_func(struct work_struct *work)
 {
-	struct zynqmp_dp *dp;
-
-	dp = container_of(work, struct zynqmp_dp, hpd_work.work);
+	struct zynqmp_dp *dp = container_of(work, struct zynqmp_dp,
+					    hpd_work.work);
+	enum drm_connector_status status;
 
-	if (dp->drm)
-		drm_helper_hpd_irq_event(dp->drm);
+	status = zynqmp_dp_bridge_detect(&dp->bridge);
+	drm_bridge_hpd_notify(&dp->bridge, status);
 }
 
 static irqreturn_t zynqmp_dp_irq_handler(int irq, void *data)
@@ -1570,7 +1636,7 @@ static irqreturn_t zynqmp_dp_irq_handler(int irq, void *data)
 	zynqmp_dp_write(dp, ZYNQMP_DP_INT_STATUS, status);
 
 	if (status & ZYNQMP_DP_INT_VBLANK_START)
-		zynqmp_disp_handle_vblank(dp->dpsub->disp);
+		zynqmp_dpsub_drm_handle_vblank(dp->dpsub);
 
 	if (status & ZYNQMP_DP_INT_HPD_EVENT)
 		schedule_delayed_work(&dp->hpd_work, 0);
@@ -1599,94 +1665,76 @@ handled:
  * Initialization & Cleanup
  */
 
-int zynqmp_dp_drm_init(struct zynqmp_dpsub *dpsub)
-{
-	struct zynqmp_dp *dp = dpsub->dp;
-	struct drm_encoder *encoder = &dp->encoder;
-	struct drm_connector *connector = &dp->connector;
-	int ret;
-
-	dp->config.misc0 &= ~ZYNQMP_DP_MAIN_STREAM_MISC0_SYNC_LOCK;
-	zynqmp_dp_set_format(dp, ZYNQMP_DPSUB_FORMAT_RGB, 8);
-
-	/* Create the DRM encoder and connector. */
-	encoder->possible_crtcs |= zynqmp_disp_get_crtc_mask(dpsub->disp);
-	drm_simple_encoder_init(dp->drm, encoder, DRM_MODE_ENCODER_TMDS);
-	drm_encoder_helper_add(encoder, &zynqmp_dp_encoder_helper_funcs);
-
-	connector->polled = DRM_CONNECTOR_POLL_HPD;
-	ret = drm_connector_init(encoder->dev, connector,
-				 &zynqmp_dp_connector_funcs,
-				 DRM_MODE_CONNECTOR_DisplayPort);
-	if (ret) {
-		dev_err(dp->dev, "failed to create the DRM connector\n");
-		return ret;
-	}
-
-	drm_connector_helper_add(connector, &zynqmp_dp_connector_helper_funcs);
-	drm_connector_register(connector);
-	drm_connector_attach_encoder(connector, encoder);
-
-	/* Initialize and register the AUX adapter. */
-	ret = zynqmp_dp_aux_init(dp);
-	if (ret) {
-		dev_err(dp->dev, "failed to initialize DP aux\n");
-		return ret;
-	}
-
-	/* Now that initialisation is complete, enable interrupts. */
-	zynqmp_dp_write(dp, ZYNQMP_DP_INT_EN, ZYNQMP_DP_INT_ALL);
-
-	return 0;
-}
-
-int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
+int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub)
 {
 	struct platform_device *pdev = to_platform_device(dpsub->dev);
+	struct drm_bridge *bridge;
 	struct zynqmp_dp *dp;
 	struct resource *res;
 	int ret;
 
-	dp = drmm_kzalloc(drm, sizeof(*dp), GFP_KERNEL);
+	dp = kzalloc(sizeof(*dp), GFP_KERNEL);
 	if (!dp)
 		return -ENOMEM;
 
 	dp->dev = &pdev->dev;
 	dp->dpsub = dpsub;
 	dp->status = connector_status_disconnected;
-	dp->drm = drm;
 
 	INIT_DELAYED_WORK(&dp->hpd_work, zynqmp_dp_hpd_work_func);
 
-	dpsub->dp = dp;
-
 	/* Acquire all resources (IOMEM, IRQ and PHYs). */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dp");
 	dp->iomem = devm_ioremap_resource(dp->dev, res);
-	if (IS_ERR(dp->iomem))
-		return PTR_ERR(dp->iomem);
+	if (IS_ERR(dp->iomem)) {
+		ret = PTR_ERR(dp->iomem);
+		goto err_free;
+	}
 
 	dp->irq = platform_get_irq(pdev, 0);
-	if (dp->irq < 0)
-		return dp->irq;
+	if (dp->irq < 0) {
+		ret = dp->irq;
+		goto err_free;
+	}
 
 	dp->reset = devm_reset_control_get(dp->dev, NULL);
 	if (IS_ERR(dp->reset)) {
 		if (PTR_ERR(dp->reset) != -EPROBE_DEFER)
 			dev_err(dp->dev, "failed to get reset: %ld\n",
 				PTR_ERR(dp->reset));
-		return PTR_ERR(dp->reset);
+		ret = PTR_ERR(dp->reset);
+		goto err_free;
 	}
 
 	ret = zynqmp_dp_reset(dp, false);
 	if (ret < 0)
-		return ret;
+		goto err_free;
 
 	ret = zynqmp_dp_phy_probe(dp);
 	if (ret)
 		goto err_reset;
 
+	/* Initialize the bridge. */
+	bridge = &dp->bridge;
+	bridge->funcs = &zynqmp_dp_bridge_funcs;
+	bridge->ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID
+		    | DRM_BRIDGE_OP_HPD;
+	bridge->type = DRM_MODE_CONNECTOR_DisplayPort;
+	dpsub->bridge = bridge;
+
+	/*
+	 * Acquire the next bridge in the chain. Ignore errors caused by port@5
+	 * not being connected for backward-compatibility with older DTs.
+	 */
+	ret = drm_of_find_panel_or_bridge(dp->dev->of_node, 5, 0, NULL,
+					  &dp->next_bridge);
+	if (ret < 0 && ret != -ENODEV)
+		goto err_reset;
+
 	/* Initialize the hardware. */
+	dp->config.misc0 &= ~ZYNQMP_DP_MAIN_STREAM_MISC0_SYNC_LOCK;
+	zynqmp_dp_set_format(dp, NULL, ZYNQMP_DPSUB_FORMAT_RGB, 8);
+
 	zynqmp_dp_write(dp, ZYNQMP_DP_TX_PHY_POWER_DOWN,
 			ZYNQMP_DP_TX_PHY_POWER_DOWN_ALL);
 	zynqmp_dp_set(dp, ZYNQMP_DP_PHY_RESET, ZYNQMP_DP_PHY_RESET_ALL_RESET);
@@ -1710,6 +1758,8 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 	if (ret < 0)
 		goto err_phy_exit;
 
+	dpsub->dp = dp;
+
 	dev_dbg(dp->dev, "ZynqMP DisplayPort Tx probed with %u lanes\n",
 		dp->num_lanes);
 
@@ -1719,7 +1769,8 @@ err_phy_exit:
 	zynqmp_dp_phy_exit(dp);
 err_reset:
 	zynqmp_dp_reset(dp, true);
-
+err_free:
+	kfree(dp);
 	return ret;
 }
 
@@ -1731,7 +1782,6 @@ void zynqmp_dp_remove(struct zynqmp_dpsub *dpsub)
 	disable_irq(dp->irq);
 
 	cancel_delayed_work_sync(&dp->hpd_work);
-	zynqmp_dp_aux_cleanup(dp);
 
 	zynqmp_dp_write(dp, ZYNQMP_DP_TRANSMITTER_ENABLE, 0);
 	zynqmp_dp_write(dp, ZYNQMP_DP_INT_DS, 0xffffffff);
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.h b/drivers/gpu/drm/xlnx/zynqmp_dp.h
index 4507740093f6..f077d7fbd0ad 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.h
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.h
@@ -12,7 +12,6 @@
 #ifndef _ZYNQMP_DP_H_
 #define _ZYNQMP_DP_H_
 
-struct drm_device;
 struct platform_device;
 struct zynqmp_dp;
 struct zynqmp_dpsub;
@@ -20,8 +19,7 @@ struct zynqmp_dpsub;
 void zynqmp_dp_enable_vblank(struct zynqmp_dp *dp);
 void zynqmp_dp_disable_vblank(struct zynqmp_dp *dp);
 
-int zynqmp_dp_drm_init(struct zynqmp_dpsub *dpsub);
-int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm);
+int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub);
 void zynqmp_dp_remove(struct zynqmp_dpsub *dpsub);
 
 #endif /* _ZYNQMP_DP_H_ */
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
index 1de2d927c32b..bab862484d42 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
@@ -12,191 +12,217 @@
 #include <linux/clk.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
+#include <linux/of_graph.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/slab.h>
 
 #include <drm/drm_atomic_helper.h>
-#include <drm/drm_device.h>
-#include <drm/drm_drv.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_gem_dma_helper.h>
-#include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_managed.h>
-#include <drm/drm_mode_config.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_modeset_helper.h>
 #include <drm/drm_module.h>
-#include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "zynqmp_disp.h"
 #include "zynqmp_dp.h"
 #include "zynqmp_dpsub.h"
+#include "zynqmp_kms.h"
 
 /* -----------------------------------------------------------------------------
- * Dumb Buffer & Framebuffer Allocation
+ * Power Management
  */
 
-static int zynqmp_dpsub_dumb_create(struct drm_file *file_priv,
-				    struct drm_device *drm,
-				    struct drm_mode_create_dumb *args)
+static int __maybe_unused zynqmp_dpsub_suspend(struct device *dev)
 {
-	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(drm);
-	unsigned int pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+	struct zynqmp_dpsub *dpsub = dev_get_drvdata(dev);
 
-	/* Enforce the alignment constraints of the DMA engine. */
-	args->pitch = ALIGN(pitch, dpsub->dma_align);
+	if (!dpsub->drm)
+		return 0;
 
-	return drm_gem_dma_dumb_create_internal(file_priv, drm, args);
+	return drm_mode_config_helper_suspend(&dpsub->drm->dev);
 }
 
-static struct drm_framebuffer *
-zynqmp_dpsub_fb_create(struct drm_device *drm, struct drm_file *file_priv,
-		       const struct drm_mode_fb_cmd2 *mode_cmd)
+static int __maybe_unused zynqmp_dpsub_resume(struct device *dev)
 {
-	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(drm);
-	struct drm_mode_fb_cmd2 cmd = *mode_cmd;
-	unsigned int i;
+	struct zynqmp_dpsub *dpsub = dev_get_drvdata(dev);
 
-	/* Enforce the alignment constraints of the DMA engine. */
-	for (i = 0; i < ARRAY_SIZE(cmd.pitches); ++i)
-		cmd.pitches[i] = ALIGN(cmd.pitches[i], dpsub->dma_align);
+	if (!dpsub->drm)
+		return 0;
 
-	return drm_gem_fb_create(drm, file_priv, &cmd);
+	return drm_mode_config_helper_resume(&dpsub->drm->dev);
 }
 
-static const struct drm_mode_config_funcs zynqmp_dpsub_mode_config_funcs = {
-	.fb_create		= zynqmp_dpsub_fb_create,
-	.atomic_check		= drm_atomic_helper_check,
-	.atomic_commit		= drm_atomic_helper_commit,
+static const struct dev_pm_ops zynqmp_dpsub_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_dpsub_suspend, zynqmp_dpsub_resume)
 };
 
 /* -----------------------------------------------------------------------------
- * DRM/KMS Driver
+ * DPSUB Configuration
  */
 
-DEFINE_DRM_GEM_DMA_FOPS(zynqmp_dpsub_drm_fops);
-
-static const struct drm_driver zynqmp_dpsub_drm_driver = {
-	.driver_features		= DRIVER_MODESET | DRIVER_GEM |
-					  DRIVER_ATOMIC,
-
-	DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(zynqmp_dpsub_dumb_create),
+/**
+ * zynqmp_dpsub_audio_enabled - If the audio is enabled
+ * @dpsub: DisplayPort subsystem
+ *
+ * Return if the audio is enabled depending on the audio clock.
+ *
+ * Return: true if audio is enabled, or false.
+ */
+bool zynqmp_dpsub_audio_enabled(struct zynqmp_dpsub *dpsub)
+{
+	return !!dpsub->aud_clk;
+}
 
-	.fops				= &zynqmp_dpsub_drm_fops,
+/**
+ * zynqmp_dpsub_get_audio_clk_rate - Get the current audio clock rate
+ * @dpsub: DisplayPort subsystem
+ *
+ * Return: the current audio clock rate.
+ */
+unsigned int zynqmp_dpsub_get_audio_clk_rate(struct zynqmp_dpsub *dpsub)
+{
+	if (zynqmp_dpsub_audio_enabled(dpsub))
+		return 0;
+	return clk_get_rate(dpsub->aud_clk);
+}
 
-	.name				= "zynqmp-dpsub",
-	.desc				= "Xilinx DisplayPort Subsystem Driver",
-	.date				= "20130509",
-	.major				= 1,
-	.minor				= 0,
-};
+/* -----------------------------------------------------------------------------
+ * Probe & Remove
+ */
 
-static int zynqmp_dpsub_drm_init(struct zynqmp_dpsub *dpsub)
+static int zynqmp_dpsub_init_clocks(struct zynqmp_dpsub *dpsub)
 {
-	struct drm_device *drm = &dpsub->drm;
 	int ret;
 
-	/* Initialize mode config, vblank and the KMS poll helper. */
-	ret = drmm_mode_config_init(drm);
-	if (ret < 0)
-		return ret;
-
-	drm->mode_config.funcs = &zynqmp_dpsub_mode_config_funcs;
-	drm->mode_config.min_width = 0;
-	drm->mode_config.min_height = 0;
-	drm->mode_config.max_width = ZYNQMP_DISP_MAX_WIDTH;
-	drm->mode_config.max_height = ZYNQMP_DISP_MAX_HEIGHT;
+	dpsub->apb_clk = devm_clk_get(dpsub->dev, "dp_apb_clk");
+	if (IS_ERR(dpsub->apb_clk))
+		return PTR_ERR(dpsub->apb_clk);
 
-	ret = drm_vblank_init(drm, 1);
-	if (ret)
+	ret = clk_prepare_enable(dpsub->apb_clk);
+	if (ret) {
+		dev_err(dpsub->dev, "failed to enable the APB clock\n");
 		return ret;
-
-	drm_kms_helper_poll_init(drm);
+	}
 
 	/*
-	 * Initialize the DISP and DP components. This will creates planes,
-	 * CRTC, encoder and connector. The DISP should be initialized first as
-	 * the DP encoder needs the CRTC.
+	 * Try the live PL video clock, and fall back to the PS clock if the
+	 * live PL video clock isn't valid.
 	 */
-	ret = zynqmp_disp_drm_init(dpsub);
-	if (ret)
-		goto err_poll_fini;
-
-	ret = zynqmp_dp_drm_init(dpsub);
-	if (ret)
-		goto err_poll_fini;
-
-	/* Reset all components and register the DRM device. */
-	drm_mode_config_reset(drm);
+	dpsub->vid_clk = devm_clk_get(dpsub->dev, "dp_live_video_in_clk");
+	if (!IS_ERR(dpsub->vid_clk))
+		dpsub->vid_clk_from_ps = false;
+	else if (PTR_ERR(dpsub->vid_clk) == -EPROBE_DEFER)
+		return PTR_ERR(dpsub->vid_clk);
+
+	if (IS_ERR_OR_NULL(dpsub->vid_clk)) {
+		dpsub->vid_clk = devm_clk_get(dpsub->dev, "dp_vtc_pixel_clk_in");
+		if (IS_ERR(dpsub->vid_clk)) {
+			dev_err(dpsub->dev, "failed to init any video clock\n");
+			return PTR_ERR(dpsub->vid_clk);
+		}
+		dpsub->vid_clk_from_ps = true;
+	}
 
-	ret = drm_dev_register(drm, 0);
-	if (ret < 0)
-		goto err_poll_fini;
+	/*
+	 * Try the live PL audio clock, and fall back to the PS clock if the
+	 * live PL audio clock isn't valid. Missing audio clock disables audio
+	 * but isn't an error.
+	 */
+	dpsub->aud_clk = devm_clk_get(dpsub->dev, "dp_live_audio_aclk");
+	if (!IS_ERR(dpsub->aud_clk)) {
+		dpsub->aud_clk_from_ps = false;
+		return 0;
+	}
 
-	/* Initialize fbdev generic emulation. */
-	drm_fbdev_generic_setup(drm, 24);
+	dpsub->aud_clk = devm_clk_get(dpsub->dev, "dp_aud_clk");
+	if (!IS_ERR(dpsub->aud_clk)) {
+		dpsub->aud_clk_from_ps = true;
+		return 0;
+	}
 
+	dev_info(dpsub->dev, "audio disabled due to missing clock\n");
 	return 0;
-
-err_poll_fini:
-	drm_kms_helper_poll_fini(drm);
-	return ret;
 }
 
-/* -----------------------------------------------------------------------------
- * Power Management
- */
-
-static int __maybe_unused zynqmp_dpsub_suspend(struct device *dev)
+static int zynqmp_dpsub_parse_dt(struct zynqmp_dpsub *dpsub)
 {
-	struct zynqmp_dpsub *dpsub = dev_get_drvdata(dev);
+	struct device_node *np;
+	unsigned int i;
 
-	return drm_mode_config_helper_suspend(&dpsub->drm);
-}
+	/*
+	 * For backward compatibility with old device trees that don't contain
+	 * ports, consider that only the DP output port is connected if no
+	 * ports child no exists.
+	 */
+	np = of_get_child_by_name(dpsub->dev->of_node, "ports");
+	of_node_put(np);
+	if (!np) {
+		dev_warn(dpsub->dev, "missing ports, update DT bindings\n");
+		dpsub->connected_ports = BIT(ZYNQMP_DPSUB_PORT_OUT_DP);
+		dpsub->dma_enabled = true;
+		return 0;
+	}
 
-static int __maybe_unused zynqmp_dpsub_resume(struct device *dev)
-{
-	struct zynqmp_dpsub *dpsub = dev_get_drvdata(dev);
+	/* Check which ports are connected. */
+	for (i = 0; i < ZYNQMP_DPSUB_NUM_PORTS; ++i) {
+		struct device_node *np;
 
-	return drm_mode_config_helper_resume(&dpsub->drm);
-}
+		np = of_graph_get_remote_node(dpsub->dev->of_node, i, -1);
+		if (np) {
+			dpsub->connected_ports |= BIT(i);
+			of_node_put(np);
+		}
+	}
 
-static const struct dev_pm_ops zynqmp_dpsub_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_dpsub_suspend, zynqmp_dpsub_resume)
-};
+	/* Sanity checks. */
+	if ((dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_VIDEO)) &&
+	    (dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_GFX))) {
+		dev_err(dpsub->dev, "only one live video input is supported\n");
+		return -EINVAL;
+	}
 
-/* -----------------------------------------------------------------------------
- * Probe & Remove
- */
+	if ((dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_VIDEO)) ||
+	    (dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_GFX))) {
+		if (dpsub->vid_clk_from_ps) {
+			dev_err(dpsub->dev,
+				"live video input requires PL clock\n");
+			return -EINVAL;
+		}
+	} else {
+		dpsub->dma_enabled = true;
+	}
 
-static int zynqmp_dpsub_init_clocks(struct zynqmp_dpsub *dpsub)
-{
-	int ret;
+	if (dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_LIVE_AUDIO))
+		dev_warn(dpsub->dev, "live audio unsupported, ignoring\n");
 
-	dpsub->apb_clk = devm_clk_get(dpsub->dev, "dp_apb_clk");
-	if (IS_ERR(dpsub->apb_clk))
-		return PTR_ERR(dpsub->apb_clk);
+	if ((dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_OUT_VIDEO)) ||
+	    (dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_OUT_AUDIO)))
+		dev_warn(dpsub->dev, "output to PL unsupported, ignoring\n");
 
-	ret = clk_prepare_enable(dpsub->apb_clk);
-	if (ret) {
-		dev_err(dpsub->dev, "failed to enable the APB clock\n");
-		return ret;
+	if (!(dpsub->connected_ports & BIT(ZYNQMP_DPSUB_PORT_OUT_DP))) {
+		dev_err(dpsub->dev, "DP output port not connected\n");
+		return -EINVAL;
 	}
 
 	return 0;
 }
 
+void zynqmp_dpsub_release(struct zynqmp_dpsub *dpsub)
+{
+	kfree(dpsub->disp);
+	kfree(dpsub->dp);
+	kfree(dpsub);
+}
+
 static int zynqmp_dpsub_probe(struct platform_device *pdev)
 {
 	struct zynqmp_dpsub *dpsub;
 	int ret;
 
 	/* Allocate private data. */
-	dpsub = devm_drm_dev_alloc(&pdev->dev, &zynqmp_dpsub_drm_driver,
-				   struct zynqmp_dpsub, drm);
-	if (IS_ERR(dpsub))
-		return PTR_ERR(dpsub);
+	dpsub = kzalloc(sizeof(*dpsub), GFP_KERNEL);
+	if (!dpsub)
+		return -ENOMEM;
 
 	dpsub->dev = &pdev->dev;
 	platform_set_drvdata(pdev, dpsub);
@@ -210,23 +236,31 @@ static int zynqmp_dpsub_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_mem;
 
+	ret = zynqmp_dpsub_parse_dt(dpsub);
+	if (ret < 0)
+		goto err_mem;
+
 	pm_runtime_enable(&pdev->dev);
 
 	/*
 	 * DP should be probed first so that the zynqmp_disp can set the output
 	 * format accordingly.
 	 */
-	ret = zynqmp_dp_probe(dpsub, &dpsub->drm);
+	ret = zynqmp_dp_probe(dpsub);
 	if (ret)
 		goto err_pm;
 
-	ret = zynqmp_disp_probe(dpsub, &dpsub->drm);
+	ret = zynqmp_disp_probe(dpsub);
 	if (ret)
 		goto err_dp;
 
-	ret = zynqmp_dpsub_drm_init(dpsub);
-	if (ret)
-		goto err_disp;
+	if (dpsub->dma_enabled) {
+		ret = zynqmp_dpsub_drm_init(dpsub);
+		if (ret)
+			goto err_disp;
+	} else {
+		drm_bridge_add(dpsub->bridge);
+	}
 
 	dev_info(&pdev->dev, "ZynqMP DisplayPort Subsystem driver probed");
 
@@ -241,17 +275,19 @@ err_pm:
 	clk_disable_unprepare(dpsub->apb_clk);
 err_mem:
 	of_reserved_mem_device_release(&pdev->dev);
+	if (!dpsub->drm)
+		zynqmp_dpsub_release(dpsub);
 	return ret;
 }
 
 static int zynqmp_dpsub_remove(struct platform_device *pdev)
 {
 	struct zynqmp_dpsub *dpsub = platform_get_drvdata(pdev);
-	struct drm_device *drm = &dpsub->drm;
 
-	drm_dev_unregister(drm);
-	drm_atomic_helper_shutdown(drm);
-	drm_kms_helper_poll_fini(drm);
+	if (dpsub->drm)
+		zynqmp_dpsub_drm_cleanup(dpsub);
+	else
+		drm_bridge_remove(dpsub->bridge);
 
 	zynqmp_disp_remove(dpsub);
 	zynqmp_dp_remove(dpsub);
@@ -260,6 +296,9 @@ static int zynqmp_dpsub_remove(struct platform_device *pdev)
 	clk_disable_unprepare(dpsub->apb_clk);
 	of_reserved_mem_device_release(&pdev->dev);
 
+	if (!dpsub->drm)
+		zynqmp_dpsub_release(dpsub);
+
 	return 0;
 }
 
@@ -267,7 +306,10 @@ static void zynqmp_dpsub_shutdown(struct platform_device *pdev)
 {
 	struct zynqmp_dpsub *dpsub = platform_get_drvdata(pdev);
 
-	drm_atomic_helper_shutdown(&dpsub->drm);
+	if (!dpsub->drm)
+		return;
+
+	drm_atomic_helper_shutdown(&dpsub->drm->dev);
 }
 
 static const struct of_device_id zynqmp_dpsub_of_match[] = {
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
index c04026d82639..09ea01878f2a 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
+++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
@@ -14,9 +14,23 @@
 
 struct clk;
 struct device;
-struct drm_device;
+struct drm_bridge;
 struct zynqmp_disp;
+struct zynqmp_disp_layer;
 struct zynqmp_dp;
+struct zynqmp_dpsub_drm;
+
+#define ZYNQMP_DPSUB_NUM_LAYERS				2
+
+enum zynqmp_dpsub_port {
+	ZYNQMP_DPSUB_PORT_LIVE_VIDEO,
+	ZYNQMP_DPSUB_PORT_LIVE_GFX,
+	ZYNQMP_DPSUB_PORT_LIVE_AUDIO,
+	ZYNQMP_DPSUB_PORT_OUT_VIDEO,
+	ZYNQMP_DPSUB_PORT_OUT_AUDIO,
+	ZYNQMP_DPSUB_PORT_OUT_DP,
+	ZYNQMP_DPSUB_NUM_PORTS,
+};
 
 enum zynqmp_dpsub_format {
 	ZYNQMP_DPSUB_FORMAT_RGB,
@@ -27,28 +41,46 @@ enum zynqmp_dpsub_format {
 
 /**
  * struct zynqmp_dpsub - ZynqMP DisplayPort Subsystem
- * @drm: The DRM/KMS device
  * @dev: The physical device
  * @apb_clk: The APB clock
+ * @vid_clk: Video clock
+ * @vid_clk_from_ps: True of the video clock comes from PS, false from PL
+ * @aud_clk: Audio clock
+ * @aud_clk_from_ps: True of the audio clock comes from PS, false from PL
+ * @connected_ports: Bitmask of connected ports in the device tree
+ * @dma_enabled: True if the DMA interface is enabled, false if the DPSUB is
+ *	driven by the live input
+ * @drm: The DRM/KMS device data
+ * @bridge: The DP encoder bridge
  * @disp: The display controller
  * @dp: The DisplayPort controller
  * @dma_align: DMA alignment constraint (must be a power of 2)
  */
 struct zynqmp_dpsub {
-	struct drm_device drm;
 	struct device *dev;
 
 	struct clk *apb_clk;
+	struct clk *vid_clk;
+	bool vid_clk_from_ps;
+	struct clk *aud_clk;
+	bool aud_clk_from_ps;
+
+	unsigned int connected_ports;
+	bool dma_enabled;
+
+	struct zynqmp_dpsub_drm *drm;
+	struct drm_bridge *bridge;
 
 	struct zynqmp_disp *disp;
+	struct zynqmp_disp_layer *layers[ZYNQMP_DPSUB_NUM_LAYERS];
 	struct zynqmp_dp *dp;
 
 	unsigned int dma_align;
 };
 
-static inline struct zynqmp_dpsub *to_zynqmp_dpsub(struct drm_device *drm)
-{
-	return container_of(drm, struct zynqmp_dpsub, drm);
-}
+bool zynqmp_dpsub_audio_enabled(struct zynqmp_dpsub *dpsub);
+unsigned int zynqmp_dpsub_get_audio_clk_rate(struct zynqmp_dpsub *dpsub);
+
+void zynqmp_dpsub_release(struct zynqmp_dpsub *dpsub);
 
 #endif /* _ZYNQMP_DPSUB_H_ */
diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.c b/drivers/gpu/drm/xlnx/zynqmp_kms.c
new file mode 100644
index 000000000000..1847792cf13d
--- /dev/null
+++ b/drivers/gpu/drm/xlnx/zynqmp_kms.c
@@ -0,0 +1,534 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ZynqMP DisplayPort Subsystem - KMS API
+ *
+ * Copyright (C) 2017 - 2021 Xilinx, Inc.
+ *
+ * Authors:
+ * - Hyun Woo Kwon <hyun.kwon@xilinx.com>
+ * - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_blend.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_bridge_connector.h>
+#include <drm/drm_connector.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_framebuffer.h>
+#include <drm/drm_gem_dma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_mode_config.h>
+#include <drm/drm_plane.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+#include <drm/drm_vblank.h>
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/pm_runtime.h>
+#include <linux/spinlock.h>
+
+#include "zynqmp_disp.h"
+#include "zynqmp_dp.h"
+#include "zynqmp_dpsub.h"
+#include "zynqmp_kms.h"
+
+static inline struct zynqmp_dpsub *to_zynqmp_dpsub(struct drm_device *drm)
+{
+	return container_of(drm, struct zynqmp_dpsub_drm, dev)->dpsub;
+}
+
+/* -----------------------------------------------------------------------------
+ * DRM Planes
+ */
+
+static int zynqmp_dpsub_plane_atomic_check(struct drm_plane *plane,
+					   struct drm_atomic_state *state)
+{
+	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
+										 plane);
+	struct drm_crtc_state *crtc_state;
+
+	if (!new_plane_state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state, new_plane_state->crtc);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
+
+	return drm_atomic_helper_check_plane_state(new_plane_state,
+						   crtc_state,
+						   DRM_PLANE_NO_SCALING,
+						   DRM_PLANE_NO_SCALING,
+						   false, false);
+}
+
+static void zynqmp_dpsub_plane_atomic_disable(struct drm_plane *plane,
+					      struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state,
+									   plane);
+	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(plane->dev);
+	struct zynqmp_disp_layer *layer = dpsub->layers[plane->index];
+
+	if (!old_state->fb)
+		return;
+
+	zynqmp_disp_layer_disable(layer);
+
+	if (plane->index == ZYNQMP_DPSUB_LAYER_GFX)
+		zynqmp_disp_blend_set_global_alpha(dpsub->disp, false,
+						   plane->state->alpha >> 8);
+}
+
+static void zynqmp_dpsub_plane_atomic_update(struct drm_plane *plane,
+					     struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, plane);
+	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
+	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(plane->dev);
+	struct zynqmp_disp_layer *layer = dpsub->layers[plane->index];
+	bool format_changed = false;
+
+	if (!old_state->fb ||
+	    old_state->fb->format->format != new_state->fb->format->format)
+		format_changed = true;
+
+	/*
+	 * If the format has changed (including going from a previously
+	 * disabled state to any format), reconfigure the format. Disable the
+	 * plane first if needed.
+	 */
+	if (format_changed) {
+		if (old_state->fb)
+			zynqmp_disp_layer_disable(layer);
+
+		zynqmp_disp_layer_set_format(layer, new_state->fb->format);
+	}
+
+	zynqmp_disp_layer_update(layer, new_state);
+
+	if (plane->index == ZYNQMP_DPSUB_LAYER_GFX)
+		zynqmp_disp_blend_set_global_alpha(dpsub->disp, true,
+						   plane->state->alpha >> 8);
+
+	/* Enable or re-enable the plane if the format has changed. */
+	if (format_changed)
+		zynqmp_disp_layer_enable(layer, ZYNQMP_DPSUB_LAYER_NONLIVE);
+}
+
+static const struct drm_plane_helper_funcs zynqmp_dpsub_plane_helper_funcs = {
+	.atomic_check		= zynqmp_dpsub_plane_atomic_check,
+	.atomic_update		= zynqmp_dpsub_plane_atomic_update,
+	.atomic_disable		= zynqmp_dpsub_plane_atomic_disable,
+};
+
+static const struct drm_plane_funcs zynqmp_dpsub_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state	= drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static int zynqmp_dpsub_create_planes(struct zynqmp_dpsub *dpsub)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(dpsub->drm->planes); i++) {
+		struct zynqmp_disp_layer *layer = dpsub->layers[i];
+		struct drm_plane *plane = &dpsub->drm->planes[i];
+		enum drm_plane_type type;
+		unsigned int num_formats;
+		u32 *formats;
+
+		formats = zynqmp_disp_layer_drm_formats(layer, &num_formats);
+		if (!formats)
+			return -ENOMEM;
+
+		/* Graphics layer is primary, and video layer is overlay. */
+		type = i == ZYNQMP_DPSUB_LAYER_VID
+		     ? DRM_PLANE_TYPE_OVERLAY : DRM_PLANE_TYPE_PRIMARY;
+		ret = drm_universal_plane_init(&dpsub->drm->dev, plane, 0,
+					       &zynqmp_dpsub_plane_funcs,
+					       formats, num_formats,
+					       NULL, type, NULL);
+		kfree(formats);
+		if (ret)
+			return ret;
+
+		drm_plane_helper_add(plane, &zynqmp_dpsub_plane_helper_funcs);
+
+		drm_plane_create_zpos_immutable_property(plane, i);
+		if (i == ZYNQMP_DPSUB_LAYER_GFX)
+			drm_plane_create_alpha_property(plane);
+	}
+
+	return 0;
+}
+
+/* -----------------------------------------------------------------------------
+ * DRM CRTC
+ */
+
+static inline struct zynqmp_dpsub *crtc_to_dpsub(struct drm_crtc *crtc)
+{
+	return container_of(crtc, struct zynqmp_dpsub_drm, crtc)->dpsub;
+}
+
+static void zynqmp_dpsub_crtc_atomic_enable(struct drm_crtc *crtc,
+					    struct drm_atomic_state *state)
+{
+	struct zynqmp_dpsub *dpsub = crtc_to_dpsub(crtc);
+	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
+	int ret, vrefresh;
+
+	pm_runtime_get_sync(dpsub->dev);
+
+	zynqmp_disp_setup_clock(dpsub->disp, adjusted_mode->clock * 1000);
+
+	ret = clk_prepare_enable(dpsub->vid_clk);
+	if (ret) {
+		dev_err(dpsub->dev, "failed to enable a pixel clock\n");
+		pm_runtime_put_sync(dpsub->dev);
+		return;
+	}
+
+	zynqmp_disp_enable(dpsub->disp);
+
+	/* Delay of 3 vblank intervals for timing gen to be stable */
+	vrefresh = (adjusted_mode->clock * 1000) /
+		   (adjusted_mode->vtotal * adjusted_mode->htotal);
+	msleep(3 * 1000 / vrefresh);
+}
+
+static void zynqmp_dpsub_crtc_atomic_disable(struct drm_crtc *crtc,
+					     struct drm_atomic_state *state)
+{
+	struct zynqmp_dpsub *dpsub = crtc_to_dpsub(crtc);
+	struct drm_plane_state *old_plane_state;
+
+	/*
+	 * Disable the plane if active. The old plane state can be NULL in the
+	 * .shutdown() path if the plane is already disabled, skip
+	 * zynqmp_disp_plane_atomic_disable() in that case.
+	 */
+	old_plane_state = drm_atomic_get_old_plane_state(state, crtc->primary);
+	if (old_plane_state)
+		zynqmp_dpsub_plane_atomic_disable(crtc->primary, state);
+
+	zynqmp_disp_disable(dpsub->disp);
+
+	drm_crtc_vblank_off(crtc);
+
+	spin_lock_irq(&crtc->dev->event_lock);
+	if (crtc->state->event) {
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+	}
+	spin_unlock_irq(&crtc->dev->event_lock);
+
+	clk_disable_unprepare(dpsub->vid_clk);
+	pm_runtime_put_sync(dpsub->dev);
+}
+
+static int zynqmp_dpsub_crtc_atomic_check(struct drm_crtc *crtc,
+					  struct drm_atomic_state *state)
+{
+	return drm_atomic_add_affected_planes(state, crtc);
+}
+
+static void zynqmp_dpsub_crtc_atomic_begin(struct drm_crtc *crtc,
+					   struct drm_atomic_state *state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void zynqmp_dpsub_crtc_atomic_flush(struct drm_crtc *crtc,
+					   struct drm_atomic_state *state)
+{
+	if (crtc->state->event) {
+		struct drm_pending_vblank_event *event;
+
+		/* Consume the flip_done event from atomic helper. */
+		event = crtc->state->event;
+		crtc->state->event = NULL;
+
+		event->pipe = drm_crtc_index(crtc);
+
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_arm_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
+}
+
+static const struct drm_crtc_helper_funcs zynqmp_dpsub_crtc_helper_funcs = {
+	.atomic_enable	= zynqmp_dpsub_crtc_atomic_enable,
+	.atomic_disable	= zynqmp_dpsub_crtc_atomic_disable,
+	.atomic_check	= zynqmp_dpsub_crtc_atomic_check,
+	.atomic_begin	= zynqmp_dpsub_crtc_atomic_begin,
+	.atomic_flush	= zynqmp_dpsub_crtc_atomic_flush,
+};
+
+static int zynqmp_dpsub_crtc_enable_vblank(struct drm_crtc *crtc)
+{
+	struct zynqmp_dpsub *dpsub = crtc_to_dpsub(crtc);
+
+	zynqmp_dp_enable_vblank(dpsub->dp);
+
+	return 0;
+}
+
+static void zynqmp_dpsub_crtc_disable_vblank(struct drm_crtc *crtc)
+{
+	struct zynqmp_dpsub *dpsub = crtc_to_dpsub(crtc);
+
+	zynqmp_dp_disable_vblank(dpsub->dp);
+}
+
+static const struct drm_crtc_funcs zynqmp_dpsub_crtc_funcs = {
+	.destroy		= drm_crtc_cleanup,
+	.set_config		= drm_atomic_helper_set_config,
+	.page_flip		= drm_atomic_helper_page_flip,
+	.reset			= drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state	= drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank		= zynqmp_dpsub_crtc_enable_vblank,
+	.disable_vblank		= zynqmp_dpsub_crtc_disable_vblank,
+};
+
+static int zynqmp_dpsub_create_crtc(struct zynqmp_dpsub *dpsub)
+{
+	struct drm_plane *plane = &dpsub->drm->planes[ZYNQMP_DPSUB_LAYER_GFX];
+	struct drm_crtc *crtc = &dpsub->drm->crtc;
+	int ret;
+
+	ret = drm_crtc_init_with_planes(&dpsub->drm->dev, crtc, plane,
+					NULL, &zynqmp_dpsub_crtc_funcs, NULL);
+	if (ret < 0)
+		return ret;
+
+	drm_crtc_helper_add(crtc, &zynqmp_dpsub_crtc_helper_funcs);
+
+	/* Start with vertical blanking interrupt reporting disabled. */
+	drm_crtc_vblank_off(crtc);
+
+	return 0;
+}
+
+static void zynqmp_dpsub_map_crtc_to_plane(struct zynqmp_dpsub *dpsub)
+{
+	u32 possible_crtcs = drm_crtc_mask(&dpsub->drm->crtc);
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(dpsub->drm->planes); i++)
+		dpsub->drm->planes[i].possible_crtcs = possible_crtcs;
+}
+
+/**
+ * zynqmp_dpsub_drm_handle_vblank - Handle the vblank event
+ * @dpsub: DisplayPort subsystem
+ *
+ * This function handles the vblank interrupt, and sends an event to
+ * CRTC object. This will be called by the DP vblank interrupt handler.
+ */
+void zynqmp_dpsub_drm_handle_vblank(struct zynqmp_dpsub *dpsub)
+{
+	drm_crtc_handle_vblank(&dpsub->drm->crtc);
+}
+
+/* -----------------------------------------------------------------------------
+ * Dumb Buffer & Framebuffer Allocation
+ */
+
+static int zynqmp_dpsub_dumb_create(struct drm_file *file_priv,
+				    struct drm_device *drm,
+				    struct drm_mode_create_dumb *args)
+{
+	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(drm);
+	unsigned int pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+
+	/* Enforce the alignment constraints of the DMA engine. */
+	args->pitch = ALIGN(pitch, dpsub->dma_align);
+
+	return drm_gem_dma_dumb_create_internal(file_priv, drm, args);
+}
+
+static struct drm_framebuffer *
+zynqmp_dpsub_fb_create(struct drm_device *drm, struct drm_file *file_priv,
+		       const struct drm_mode_fb_cmd2 *mode_cmd)
+{
+	struct zynqmp_dpsub *dpsub = to_zynqmp_dpsub(drm);
+	struct drm_mode_fb_cmd2 cmd = *mode_cmd;
+	unsigned int i;
+
+	/* Enforce the alignment constraints of the DMA engine. */
+	for (i = 0; i < ARRAY_SIZE(cmd.pitches); ++i)
+		cmd.pitches[i] = ALIGN(cmd.pitches[i], dpsub->dma_align);
+
+	return drm_gem_fb_create(drm, file_priv, &cmd);
+}
+
+static const struct drm_mode_config_funcs zynqmp_dpsub_mode_config_funcs = {
+	.fb_create		= zynqmp_dpsub_fb_create,
+	.atomic_check		= drm_atomic_helper_check,
+	.atomic_commit		= drm_atomic_helper_commit,
+};
+
+/* -----------------------------------------------------------------------------
+ * DRM/KMS Driver
+ */
+
+DEFINE_DRM_GEM_DMA_FOPS(zynqmp_dpsub_drm_fops);
+
+static const struct drm_driver zynqmp_dpsub_drm_driver = {
+	.driver_features		= DRIVER_MODESET | DRIVER_GEM |
+					  DRIVER_ATOMIC,
+
+	DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(zynqmp_dpsub_dumb_create),
+
+	.fops				= &zynqmp_dpsub_drm_fops,
+
+	.name				= "zynqmp-dpsub",
+	.desc				= "Xilinx DisplayPort Subsystem Driver",
+	.date				= "20130509",
+	.major				= 1,
+	.minor				= 0,
+};
+
+static int zynqmp_dpsub_kms_init(struct zynqmp_dpsub *dpsub)
+{
+	struct drm_encoder *encoder = &dpsub->drm->encoder;
+	struct drm_connector *connector;
+	int ret;
+
+	/* Create the planes and the CRTC. */
+	ret = zynqmp_dpsub_create_planes(dpsub);
+	if (ret)
+		return ret;
+
+	ret = zynqmp_dpsub_create_crtc(dpsub);
+	if (ret < 0)
+		return ret;
+
+	zynqmp_dpsub_map_crtc_to_plane(dpsub);
+
+	/* Create the encoder and attach the bridge. */
+	encoder->possible_crtcs |= drm_crtc_mask(&dpsub->drm->crtc);
+	drm_simple_encoder_init(&dpsub->drm->dev, encoder, DRM_MODE_ENCODER_NONE);
+
+	ret = drm_bridge_attach(encoder, dpsub->bridge, NULL,
+				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+	if (ret) {
+		dev_err(dpsub->dev, "failed to attach bridge to encoder\n");
+		return ret;
+	}
+
+	/* Create the connector for the chain of bridges. */
+	connector = drm_bridge_connector_init(&dpsub->drm->dev, encoder);
+	if (IS_ERR(connector)) {
+		dev_err(dpsub->dev, "failed to created connector\n");
+		return PTR_ERR(connector);
+	}
+
+	ret = drm_connector_attach_encoder(connector, encoder);
+	if (ret < 0) {
+		dev_err(dpsub->dev, "failed to attach connector to encoder\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void zynqmp_dpsub_drm_release(struct drm_device *drm, void *res)
+{
+	struct zynqmp_dpsub_drm *dpdrm = res;
+
+	zynqmp_dpsub_release(dpdrm->dpsub);
+}
+
+int zynqmp_dpsub_drm_init(struct zynqmp_dpsub *dpsub)
+{
+	struct zynqmp_dpsub_drm *dpdrm;
+	struct drm_device *drm;
+	int ret;
+
+	/*
+	 * Allocate the drm_device and immediately add a cleanup action to
+	 * release the zynqmp_dpsub instance. If any of those operations fail,
+	 * dpsub->drm will remain NULL, which tells the caller that it must
+	 * cleanup manually.
+	 */
+	dpdrm = devm_drm_dev_alloc(dpsub->dev, &zynqmp_dpsub_drm_driver,
+				   struct zynqmp_dpsub_drm, dev);
+	if (IS_ERR(dpdrm))
+		return PTR_ERR(dpdrm);
+
+	dpdrm->dpsub = dpsub;
+	drm = &dpdrm->dev;
+
+	ret = drmm_add_action(drm, zynqmp_dpsub_drm_release, dpdrm);
+	if (ret < 0)
+		return ret;
+
+	dpsub->drm = dpdrm;
+
+	/* Initialize mode config, vblank and the KMS poll helper. */
+	ret = drmm_mode_config_init(drm);
+	if (ret < 0)
+		return ret;
+
+	drm->mode_config.funcs = &zynqmp_dpsub_mode_config_funcs;
+	drm->mode_config.min_width = 0;
+	drm->mode_config.min_height = 0;
+	drm->mode_config.max_width = ZYNQMP_DISP_MAX_WIDTH;
+	drm->mode_config.max_height = ZYNQMP_DISP_MAX_HEIGHT;
+
+	ret = drm_vblank_init(drm, 1);
+	if (ret)
+		return ret;
+
+	drm_kms_helper_poll_init(drm);
+
+	ret = zynqmp_dpsub_kms_init(dpsub);
+	if (ret < 0)
+		goto err_poll_fini;
+
+	/* Reset all components and register the DRM device. */
+	drm_mode_config_reset(drm);
+
+	ret = drm_dev_register(drm, 0);
+	if (ret < 0)
+		goto err_poll_fini;
+
+	/* Initialize fbdev generic emulation. */
+	drm_fbdev_generic_setup(drm, 24);
+
+	return 0;
+
+err_poll_fini:
+	drm_kms_helper_poll_fini(drm);
+	return ret;
+}
+
+void zynqmp_dpsub_drm_cleanup(struct zynqmp_dpsub *dpsub)
+{
+	struct drm_device *drm = &dpsub->drm->dev;
+
+	drm_dev_unregister(drm);
+	drm_atomic_helper_shutdown(drm);
+	drm_kms_helper_poll_fini(drm);
+}
diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.h b/drivers/gpu/drm/xlnx/zynqmp_kms.h
new file mode 100644
index 000000000000..01be96b00e3f
--- /dev/null
+++ b/drivers/gpu/drm/xlnx/zynqmp_kms.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ZynqMP DisplayPort Subsystem - KMS API
+ *
+ * Copyright (C) 2017 - 2021 Xilinx, Inc.
+ *
+ * Authors:
+ * - Hyun Woo Kwon <hyun.kwon@xilinx.com>
+ * - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#ifndef _ZYNQMP_KMS_H_
+#define _ZYNQMP_KMS_H_
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_device.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_plane.h>
+
+#include "zynqmp_dpsub.h"
+
+struct zynqmp_dpsub;
+
+/**
+ * struct zynqmp_dpsub - ZynqMP DisplayPort Subsystem DRM/KMS data
+ * @dpsub: Backpointer to the DisplayPort subsystem
+ * @drm: The DRM/KMS device
+ * @planes: The DRM planes
+ * @crtc: The DRM CRTC
+ * @encoder: The dummy DRM encoder
+ */
+struct zynqmp_dpsub_drm {
+	struct zynqmp_dpsub *dpsub;
+
+	struct drm_device dev;
+	struct drm_plane planes[ZYNQMP_DPSUB_NUM_LAYERS];
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+};
+
+void zynqmp_dpsub_drm_handle_vblank(struct zynqmp_dpsub *dpsub);
+
+int zynqmp_dpsub_drm_init(struct zynqmp_dpsub *dpsub);
+void zynqmp_dpsub_drm_cleanup(struct zynqmp_dpsub *dpsub);
+
+#endif /* _ZYNQMP_KMS_H_ */