Merge tag 'amd-drm-next-5.15-2021-08-06' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.15-2021-08-06:

amdgpu:
- Aldebaran fixes
- Powergating fix for Renoir
- Switch virtual DCE over to vkms based atomic modesetting
- Misc typo fixes
- PSP handling cleanups
- DC FP cleanups
- RAS fixes
- Wave debug improvements
- Freesync fix
- BACO/BOCO fixes
- Misc fixes

amdkfd:
- Expose gfx version in sysfs
- Aldebaran fixes

radeon:
- Coding style fix
- Typo fixes
- Pageflip fix

UAPI:
- amdkfd: SVM address range query
  Proposed userspace: https://github.com/RadeonOpenCompute/ROCR-Runtime/tree/memory_model_queries

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210806205248.3864-1-alexander.deucher@amd.com

96 files changed, 1611 insertions, 1196 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index f089794bbdd5..0d814c957461 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -120,7 +120,7 @@ amdgpu-y += \
 amdgpu-y += \
 	dce_v10_0.o \
 	dce_v11_0.o \
-	dce_virtual.o
+	amdgpu_vkms.o
 
 # add GFX block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d10baa3338bc..96e895d6be35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -916,6 +916,7 @@ struct amdgpu_device {
 
 	/* display */
 	bool				enable_virtual_display;
+	struct amdgpu_vkms_output       *amdgpu_vkms_output;
 	struct amdgpu_mode_info		mode_info;
 	/* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */
 	struct work_struct		hotplug_work;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 58520b0ad0bf..260ba01d303e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1040,7 +1040,7 @@ void amdgpu_acpi_detect(void)
  */
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 {
-#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
+#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_PM_SLEEP)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
 		if (adev->flags & AMD_IS_APU)
 			return pm_suspend_target_state == PM_SUSPEND_TO_IDLE;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 0462d4aceab7..ec028cf963f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -271,7 +271,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
 		uint64_t *size);
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index c4b3eeeab0a1..2d6b2d77b738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1057,7 +1057,8 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 static int update_gpuvm_pte(struct kgd_mem *mem,
 			    struct kfd_mem_attachment *entry,
-			    struct amdgpu_sync *sync)
+			    struct amdgpu_sync *sync,
+			    bool *table_freed)
 {
 	struct amdgpu_bo_va *bo_va = entry->bo_va;
 	struct amdgpu_device *adev = entry->adev;
@@ -1068,7 +1069,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 
 	/* Update the page tables  */
-	ret = amdgpu_vm_bo_update(adev, bo_va, false);
+	ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed);
 	if (ret) {
 		pr_err("amdgpu_vm_bo_update failed\n");
 		return ret;
@@ -1080,7 +1081,8 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
 			   struct kfd_mem_attachment *entry,
 			   struct amdgpu_sync *sync,
-			   bool no_update_pte)
+			   bool no_update_pte,
+			   bool *table_freed)
 {
 	int ret;
 
@@ -1097,7 +1099,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,
 	if (no_update_pte)
 		return 0;
 
-	ret = update_gpuvm_pte(mem, entry, sync);
+	ret = update_gpuvm_pte(mem, entry, sync, table_freed);
 	if (ret) {
 		pr_err("update_gpuvm_pte() failed\n");
 		goto update_gpuvm_pte_failed;
@@ -1605,7 +1607,8 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 }
 
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv)
+		struct kgd_dev *kgd, struct kgd_mem *mem,
+		void *drm_priv, bool *table_freed)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
@@ -1693,7 +1696,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			 entry->va, entry->va + bo_size, entry);
 
 		ret = map_bo_to_gpuvm(mem, entry, ctx.sync,
-				      is_invalid_userptr);
+				      is_invalid_userptr, table_freed);
 		if (ret) {
 			pr_err("Failed to map bo to gpuvm\n");
 			goto out_unreserve;
@@ -1717,6 +1720,12 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 				true);
 	ret = unreserve_bo_and_vms(&ctx, false, false);
 
+	/* Only apply no TLB flush on Aldebaran to
+	 * workaround regressions on other Asics.
+	 */
+	if (table_freed && (adev->asic_type != CHIP_ALDEBARAN))
+		*table_freed = true;
+
 	goto out;
 
 out_unreserve:
@@ -2143,7 +2152,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync);
+			ret = update_gpuvm_pte(mem, attachment, &sync, NULL);
 			if (ret) {
 				pr_err("%s: update PTE failed\n", __func__);
 				/* make sure this gets validated again */
@@ -2349,7 +2358,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync_obj);
+			ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL);
 			if (ret) {
 				pr_debug("Memory eviction: update PTE failed. Try again\n");
 				goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 3b5d13189073..8f53837d4d3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -468,6 +468,46 @@ bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *ade
 	return (fw_cap & ATOM_FIRMWARE_CAP_DYNAMIC_BOOT_CFG_ENABLE) ? true : false;
 }
 
+/*
+ * Helper function to query RAS EEPROM address
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Return true if vbios supports ras rom address reporting
+ */
+bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index;
+	u16 data_offset, size;
+	union firmware_info *firmware_info;
+	u8 frev, crev;
+
+	if (i2c_address == NULL)
+		return false;
+
+	*i2c_address = 0;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+			firmwareinfo);
+
+	if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context,
+				index, &size, &frev, &crev, &data_offset)) {
+		/* support firmware_info 3.4 + */
+		if ((frev == 3 && crev >=4) || (frev > 3)) {
+			firmware_info = (union firmware_info *)
+				(mode_info->atom_context->bios + data_offset);
+			*i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr;
+		}
+	}
+
+	if (*i2c_address != 0)
+		return true;
+
+	return false;
+}
+
+
 union smu_info {
 	struct atom_smu_info_v3_1 v31;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 1bbbb195015d..751248b253de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -36,6 +36,7 @@ int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_sram_ecc_supported(struct amdgpu_device *adev);
+bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address);
 bool amdgpu_atomfirmware_mem_training_supported(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_fw_reserved_fb_size(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a152363b0254..913f9eaa9cd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -799,7 +799,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
+	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL);
 	if (r)
 		return r;
 
@@ -810,7 +810,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
@@ -829,7 +829,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (bo_va == NULL)
 			continue;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6ca9fe54ee0a..d7cc45e68dbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3647,9 +3647,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 fence_driver_init:
 	/* Fence driver */
-	r = amdgpu_fence_driver_init(adev);
+	r = amdgpu_fence_driver_sw_init(adev);
 	if (r) {
-		dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
+		dev_err(adev->dev, "amdgpu_fence_driver_sw_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
 		goto failed;
 	}
@@ -3989,7 +3989,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	}
 	amdgpu_fence_driver_hw_init(adev);
 
-
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index d637b0536f84..febb7b08d19b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1215,6 +1215,13 @@ static const struct pci_device_id pciidlist[] = {
 	/* CYAN_SKILLFISH */
 	{0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 
+	/* BEIGE_GOBY */
+	{0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7422, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+
 	{0, 0, 0}
 };
 
@@ -1231,7 +1238,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	int ret, retry = 0;
 	bool supports_atomic = false;
 
-	if (!amdgpu_virtual_display &&
+	if (amdgpu_virtual_display ||
 	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
 		supports_atomic = true;
 
@@ -1566,6 +1573,8 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 		pci_ignore_hotplug(pdev);
 		pci_set_power_state(pdev, PCI_D3cold);
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	} else if (amdgpu_device_supports_boco(drm_dev)) {
+		/* nothing to do */
 	} else if (amdgpu_device_supports_baco(drm_dev)) {
 		amdgpu_device_baco_enter(drm_dev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 09b048647523..5a143ca02cf9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -344,7 +344,7 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 	}
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
-	if (!amdgpu_device_has_dc_support(adev))
+	if (!amdgpu_device_has_dc_support(adev) && !amdgpu_virtual_display)
 		drm_helper_disable_unused_functions(adev_to_drm(adev));
 
 	drm_fb_helper_initial_config(&rfbdev->helper, bpp_sel);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 0b1c48590c43..6ed53669f3e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -498,7 +498,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 }
 
 /**
- * amdgpu_fence_driver_init - init the fence driver
+ * amdgpu_fence_driver_sw_init - init the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -509,13 +509,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-int amdgpu_fence_driver_init(struct amdgpu_device *adev)
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 {
 	return 0;
 }
 
 /**
- * amdgpu_fence_driver_fini - tear down the fence driver
+ * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -531,8 +531,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
-		if (!ring->no_scheduler)
-			drm_sched_fini(&ring->sched);
+
 		/* You can't wait for HW to signal if it's gone */
 		if (!drm_dev_is_unplugged(&adev->ddev))
 			r = amdgpu_fence_wait_empty(ring);
@@ -560,6 +559,9 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler)
+			drm_sched_fini(&ring->sched);
+
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
 		kfree(ring->fence_drv.fences);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 611fd10c3410..c6f2fb9557ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -621,7 +621,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 
 	if (operation == AMDGPU_VA_OP_MAP ||
 	    operation == AMDGPU_VA_OP_REPLACE) {
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			goto error;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 10b046147190..9dc2d6d9712a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -41,8 +41,6 @@
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_atomfirmware.h"
 
-#include <drm/drm_drv.h>
-
 static int psp_sysfs_init(struct amdgpu_device *adev);
 static void psp_sysfs_fini(struct amdgpu_device *adev);
 
@@ -253,6 +251,12 @@ static int psp_sw_init(void *handle)
 	struct psp_runtime_boot_cfg_entry boot_cfg_entry;
 	struct psp_memory_training_context *mem_training_ctx = &psp->mem_train_ctx;
 
+	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!psp->cmd) {
+		DRM_ERROR("Failed to allocate memory to command buffer!\n");
+		ret = -ENOMEM;
+	}
+
 	if (!amdgpu_sriov_vf(adev)) {
 		ret = psp_init_microcode(psp);
 		if (ret) {
@@ -315,25 +319,30 @@ static int psp_sw_init(void *handle)
 static int psp_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct psp_context *psp = &adev->psp;
+	struct psp_gfx_cmd_resp *cmd = psp->cmd;
 
-	psp_memory_training_fini(&adev->psp);
-	if (adev->psp.sos_fw) {
-		release_firmware(adev->psp.sos_fw);
-		adev->psp.sos_fw = NULL;
+	psp_memory_training_fini(psp);
+	if (psp->sos_fw) {
+		release_firmware(psp->sos_fw);
+		psp->sos_fw = NULL;
 	}
-	if (adev->psp.asd_fw) {
-		release_firmware(adev->psp.asd_fw);
-		adev->psp.asd_fw = NULL;
+	if (psp->asd_fw) {
+		release_firmware(psp->asd_fw);
+		psp->asd_fw = NULL;
 	}
-	if (adev->psp.ta_fw) {
-		release_firmware(adev->psp.ta_fw);
-		adev->psp.ta_fw = NULL;
+	if (psp->ta_fw) {
+		release_firmware(psp->ta_fw);
+		psp->ta_fw = NULL;
 	}
 
 	if (adev->asic_type == CHIP_NAVI10 ||
 	    adev->asic_type == CHIP_SIENNA_CICHLID)
 		psp_sysfs_fini(adev);
 
+	kfree(cmd);
+	cmd = NULL;
+
 	return 0;
 }
 
@@ -417,8 +426,6 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	if (!drm_dev_enter(&psp->adev->ddev, &idx))
 		return 0;
 
-	mutex_lock(&psp->mutex);
-
 	memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE);
 
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
@@ -478,11 +485,26 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	}
 
 exit:
-	mutex_unlock(&psp->mutex);
 	drm_dev_exit(idx);
 	return ret;
 }
 
+static struct psp_gfx_cmd_resp *acquire_psp_cmd_buf(struct psp_context *psp)
+{
+	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+
+	mutex_lock(&psp->mutex);
+
+	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+
+	return cmd;
+}
+
+void release_psp_cmd_buf(struct psp_context *psp)
+{
+	mutex_unlock(&psp->mutex);
+}
+
 static void psp_prep_tmr_cmd_buf(struct psp_context *psp,
 				 struct psp_gfx_cmd_resp *cmd,
 				 uint64_t tmr_mc, struct amdgpu_bo *tmr_bo)
@@ -517,11 +539,8 @@ static int psp_load_toc(struct psp_context *psp,
 			uint32_t *tmr_size)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
 	/* Copy toc to psp firmware private buffer */
 	psp_copy_fw(psp, psp->toc.start_addr, psp->toc.size_bytes);
 
@@ -531,7 +550,9 @@ static int psp_load_toc(struct psp_context *psp,
 				 psp->fence_buf_mc_addr);
 	if (!ret)
 		*tmr_size = psp->cmd_buf_mem->resp.tmr_size;
-	kfree(cmd);
+
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
@@ -596,9 +617,7 @@ static int psp_tmr_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev) && psp_skip_tmr(psp))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_tmr_cmd_buf(psp, cmd, psp->tmr_mc_addr, psp->tmr_bo);
 	DRM_INFO("reserve 0x%lx from 0x%llx for PSP TMR\n",
@@ -607,13 +626,13 @@ static int psp_tmr_load(struct psp_context *psp)
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
 
 static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
-					struct psp_gfx_cmd_resp *cmd)
+				        struct psp_gfx_cmd_resp *cmd)
 {
 	if (amdgpu_sriov_vf(psp->adev))
 		cmd->cmd_id = GFX_CMD_ID_DESTROY_VMR;
@@ -624,11 +643,7 @@ static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
 static int psp_tmr_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_tmr_unload_cmd_buf(psp, cmd);
 	DRM_INFO("free PSP TMR buffer\n");
@@ -636,7 +651,7 @@ static int psp_tmr_unload(struct psp_context *psp)
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -670,9 +685,7 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_GET_FW_ATTESTATION;
 
@@ -684,7 +697,7 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 			      ((uint64_t)cmd->resp.uresp.fwar_db_info.fwar_db_addr_hi << 32);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -692,13 +705,13 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg)
 {
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 	int ret;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
 	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_GET;
@@ -709,47 +722,59 @@ static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg)
 			(cmd->resp.uresp.boot_cfg.boot_cfg & BOOT_CONFIG_GECC) ? 1 : 0;
 	}
 
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
 static int psp_boot_config_set(struct amdgpu_device *adev, uint32_t boot_cfg)
 {
+	int ret;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+	cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
 	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_SET;
 	cmd->cmd.boot_cfg.boot_config = boot_cfg;
 	cmd->cmd.boot_cfg.boot_config_valid = boot_cfg;
 
-	return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	release_psp_cmd_buf(psp);
+
+	return ret;
 }
 
 static int psp_rl_load(struct amdgpu_device *adev)
 {
+	int ret;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	struct psp_gfx_cmd_resp *cmd;
 
 	if (!is_psp_fw_valid(psp->rl))
 		return 0;
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->rl.start_addr, psp->rl.size_bytes);
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
-
 	cmd->cmd_id = GFX_CMD_ID_LOAD_IP_FW;
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_lo = lower_32_bits(psp->fw_pri_mc_addr);
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_hi = upper_32_bits(psp->fw_pri_mc_addr);
 	cmd->cmd.cmd_load_ip_fw.fw_size = psp->rl.size_bytes;
 	cmd->cmd.cmd_load_ip_fw.fw_type = GFX_FW_TYPE_REG_LIST;
 
-	return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	release_psp_cmd_buf(psp);
+
+	return ret;
 }
 
 static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
@@ -777,9 +802,7 @@ static int psp_asd_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev) || !psp->asd_ucode_size)
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_copy_fw(psp, psp->asd_start_addr, psp->asd_ucode_size);
 
@@ -793,7 +816,7 @@ static int psp_asd_load(struct psp_context *psp)
 		psp->asd_context.session_id = cmd->resp.session_id;
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -816,9 +839,7 @@ static int psp_asd_unload(struct psp_context *psp)
 	if (!psp->asd_context.asd_initialized)
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->asd_context.session_id);
 
@@ -827,7 +848,7 @@ static int psp_asd_unload(struct psp_context *psp)
 	if (!ret)
 		psp->asd_context.asd_initialized = false;
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -843,22 +864,21 @@ static void psp_prep_reg_prog_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 		uint32_t value)
 {
-	struct psp_gfx_cmd_resp *cmd = NULL;
+	struct psp_gfx_cmd_resp *cmd;
 	int ret = 0;
 
 	if (reg >= PSP_REG_LAST)
 		return -EINVAL;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_reg_prog_cmd_buf(cmd, reg, value);
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 	if (ret)
 		DRM_ERROR("PSP failed to program reg id %d", reg);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
@@ -909,18 +929,14 @@ static int psp_ta_invoke(struct psp_context *psp,
 		  uint32_t session_id)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_invoke_cmd_buf(cmd, ta_cmd_id, session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -934,9 +950,7 @@ static int psp_xgmi_load(struct psp_context *psp)
 	 * TODO: bypass the loading in sriov for now
 	 */
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_copy_fw(psp, psp->ta_xgmi_start_addr, psp->ta_xgmi_ucode_size);
 
@@ -954,7 +968,7 @@ static int psp_xgmi_load(struct psp_context *psp)
 		psp->xgmi_context.session_id = cmd->resp.session_id;
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -974,16 +988,14 @@ static int psp_xgmi_unload(struct psp_context *psp)
 	 * TODO: bypass the unloading in sriov for now
 	 */
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1213,10 +1225,6 @@ static int psp_ras_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
 	psp_copy_fw(psp, psp->ta_ras_start_addr, psp->ta_ras_ucode_size);
 
 	ras_cmd = (struct ta_ras_shared_memory *)psp->ras.ras_shared_buf;
@@ -1226,6 +1234,8 @@ static int psp_ras_load(struct psp_context *psp)
 	else
 		ras_cmd->ras_in_message.init_flags.dgpu_mode = 1;
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
 				 psp->ta_ras_ucode_size,
@@ -1244,11 +1254,11 @@ static int psp_ras_load(struct psp_context *psp)
 			dev_warn(psp->adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
 	}
 
+	release_psp_cmd_buf(psp);
+
 	if (ret || ras_cmd->ras_status)
 		amdgpu_ras_fini(psp->adev);
 
-	kfree(cmd);
-
 	return ret;
 }
 
@@ -1263,16 +1273,14 @@ static int psp_ras_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->ras.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1522,13 +1530,11 @@ static int psp_hdcp_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
 	psp_copy_fw(psp, psp->ta_hdcp_start_addr,
 		    psp->ta_hdcp_ucode_size);
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
 				 psp->ta_hdcp_ucode_size,
@@ -1543,7 +1549,7 @@ static int psp_hdcp_load(struct psp_context *psp)
 		mutex_init(&psp->hdcp_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1587,15 +1593,13 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1673,12 +1677,10 @@ static int psp_dtm_load(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
 	psp_copy_fw(psp, psp->ta_dtm_start_addr, psp->ta_dtm_ucode_size);
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
 				 psp->ta_dtm_ucode_size,
@@ -1693,7 +1695,7 @@ static int psp_dtm_load(struct psp_context *psp)
 		mutex_init(&psp->dtm_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1738,15 +1740,13 @@ static int psp_dtm_unload(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1818,12 +1818,10 @@ static int psp_rap_load(struct psp_context *psp)
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
 	psp_copy_fw(psp, psp->ta_rap_start_addr, psp->ta_rap_ucode_size);
 
+	cmd = acquire_psp_cmd_buf(psp);
+
 	psp_prep_ta_load_cmd_buf(cmd,
 				 psp->fw_pri_mc_addr,
 				 psp->ta_rap_ucode_size,
@@ -1838,7 +1836,7 @@ static int psp_rap_load(struct psp_context *psp)
 		mutex_init(&psp->rap_context.mutex);
 	}
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1846,17 +1844,13 @@ static int psp_rap_load(struct psp_context *psp)
 static int psp_rap_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->rap_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -1982,11 +1976,7 @@ static int psp_securedisplay_init_shared_buf(struct psp_context *psp)
 static int psp_securedisplay_load(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_securedisplay_start_addr, psp->ta_securedisplay_ucode_size);
@@ -1999,32 +1989,27 @@ static int psp_securedisplay_load(struct psp_context *psp)
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	if (ret)
-		goto failed;
+	if (!ret) {
+		psp->securedisplay_context.securedisplay_initialized = true;
+		psp->securedisplay_context.session_id = cmd->resp.session_id;
+		mutex_init(&psp->securedisplay_context.mutex);
+	}
 
-	psp->securedisplay_context.securedisplay_initialized = true;
-	psp->securedisplay_context.session_id = cmd->resp.session_id;
-	mutex_init(&psp->securedisplay_context.mutex);
+	release_psp_cmd_buf(psp);
 
-failed:
-	kfree(cmd);
 	return ret;
 }
 
 static int psp_securedisplay_unload(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	psp_prep_ta_unload_cmd_buf(cmd, psp->securedisplay_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
-	kfree(cmd);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -2400,8 +2385,6 @@ static int psp_prep_load_ip_fw_cmd_buf(struct amdgpu_firmware_info *ucode,
 	int ret;
 	uint64_t fw_mem_mc_addr = ucode->mc_addr;
 
-	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
-
 	cmd->cmd_id = GFX_CMD_ID_LOAD_IP_FW;
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_lo = lower_32_bits(fw_mem_mc_addr);
 	cmd->cmd.cmd_load_ip_fw.fw_phy_addr_hi = upper_32_bits(fw_mem_mc_addr);
@@ -2418,13 +2401,15 @@ static int psp_execute_non_psp_fw_load(struct psp_context *psp,
 			          struct amdgpu_firmware_info *ucode)
 {
 	int ret = 0;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
-	ret = psp_prep_load_ip_fw_cmd_buf(ucode, psp->cmd);
-	if (ret)
-		return ret;
+	ret = psp_prep_load_ip_fw_cmd_buf(ucode, cmd);
+	if (!ret) {
+		ret = psp_cmd_submit_buf(psp, ucode, cmd,
+					 psp->fence_buf_mc_addr);
+	}
 
-	ret = psp_cmd_submit_buf(psp, ucode, psp->cmd,
-				 psp->fence_buf_mc_addr);
+	release_psp_cmd_buf(psp);
 
 	return ret;
 }
@@ -2579,10 +2564,6 @@ static int psp_load_fw(struct amdgpu_device *adev)
 		goto skip_memalloc;
 	}
 
-	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!psp->cmd)
-		return -ENOMEM;
-
 	if (amdgpu_sriov_vf(adev)) {
 		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
 						AMDGPU_GEM_DOMAIN_VRAM,
@@ -2736,9 +2717,6 @@ static int psp_hw_fini(void *handle)
 	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
 			      (void **)&psp->cmd_buf_mem);
 
-	kfree(psp->cmd);
-	psp->cmd = NULL;
-
 	return 0;
 }
 
@@ -2902,17 +2880,15 @@ int psp_gpu_reset(struct amdgpu_device *adev)
 int psp_rlc_autoload_start(struct psp_context *psp)
 {
 	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
 
 	cmd->cmd_id = GFX_CMD_ID_AUTOLOAD_RLC;
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
-	kfree(cmd);
+
+	release_psp_cmd_buf(psp);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 4435b180ace0..6b1645598fa3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -54,9 +54,9 @@ enum psp_bootloader_cmd {
 	PSP_BL__LOAD_SYSDRV		= 0x10000,
 	PSP_BL__LOAD_SOSDRV		= 0x20000,
 	PSP_BL__LOAD_KEY_DATABASE	= 0x80000,
-	PSP_BL__LOAD_SOCDRV             = 0x90000,
-	PSP_BL__LOAD_INTFDRV            = 0xA0000,
-	PSP_BL__LOAD_DBGDRV             = 0xB0000,
+	PSP_BL__LOAD_SOCDRV             = 0xB0000,
+	PSP_BL__LOAD_INTFDRV            = 0xC0000,
+	PSP_BL__LOAD_DBGDRV             = 0xD0000,
 	PSP_BL__DRAM_LONG_TRAIN		= 0x100000,
 	PSP_BL__DRAM_SHORT_TRAIN	= 0x200000,
 	PSP_BL__LOAD_TOS_SPL_TABLE	= 0x10000000,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index d2e5b2567bc1..194590252bb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -27,6 +27,7 @@
 #include <linux/bits.h>
 #include "atom.h"
 #include "amdgpu_eeprom.h"
+#include "amdgpu_atomfirmware.h"
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 
@@ -116,6 +117,22 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 	if (!control)
 		return false;
 
+	control->i2c_address = 0;
+
+	if (amdgpu_atomfirmware_ras_rom_addr(adev, (uint8_t*)&control->i2c_address))
+	{
+		if (control->i2c_address == 0xA0)
+			control->i2c_address = 0;
+		else if (control->i2c_address == 0xA8)
+			control->i2c_address = 0x40000;
+		else {
+			dev_warn(adev->dev, "RAS EEPROM I2C address not supported");
+			return false;
+		}
+
+		return true;
+	}
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
 		control->i2c_address = EEPROM_I2C_MADDR_VEGA20;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index 59e0fefb15aa..acfa207cf970 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -54,11 +54,12 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
 {
 	struct drm_mm_node *node;
 
-	if (!res) {
+	if (!res || res->mem_type == TTM_PL_SYSTEM) {
 		cur->start = start;
 		cur->size = size;
 		cur->remaining = size;
 		cur->node = NULL;
+		WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 27adffa7658d..9c11ced4312c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -106,7 +106,6 @@ struct amdgpu_fence_driver {
 	struct dma_fence		**fences;
 };
 
-int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
@@ -115,9 +114,10 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq_src,
 				   unsigned irq_type);
+void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev);
-void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
 int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
 		      unsigned flags);
 int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9fd5db58067d..38dade421d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1123,7 +1123,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
@@ -1148,7 +1148,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	struct amdgpu_device *adev;
 
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
 		kfree(ttm->sg);
 		ttm->sg = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
new file mode 100644
index 000000000000..ce982afeff91
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+#include <drm/drm_vblank.h>
+
+#include "amdgpu.h"
+#ifdef CONFIG_DRM_AMDGPU_SI
+#include "dce_v6_0.h"
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+#include "dce_v8_0.h"
+#endif
+#include "dce_v10_0.h"
+#include "dce_v11_0.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
+#include "amdgpu_vkms.h"
+#include "amdgpu_display.h"
+
+/**
+ * DOC: amdgpu_vkms
+ *
+ * The amdgpu vkms interface provides a virtual KMS interface for several use
+ * cases: devices without display hardware, platforms where the actual display
+ * hardware is not useful (e.g., servers), SR-IOV virtual functions, device
+ * emulation/simulation, and device bring up prior to display hardware being
+ * usable. We previously emulated a legacy KMS interface, but there was a desire
+ * to move to the atomic KMS interface. The vkms driver did everything we
+ * needed, but we wanted KMS support natively in the driver without buffer
+ * sharing and the ability to support an instance of VKMS per device. We first
+ * looked at splitting vkms into a stub driver and a helper module that other
+ * drivers could use to implement a virtual display, but this strategy ended up
+ * being messy due to driver specific callbacks needed for buffer management.
+ * Ultimately, it proved easier to import the vkms code as it mostly used core
+ * drm helpers anyway.
+ */
+
+static const u32 amdgpu_vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+static enum hrtimer_restart amdgpu_vkms_vblank_simulate(struct hrtimer *timer)
+{
+	struct amdgpu_vkms_output *output = container_of(timer,
+							 struct amdgpu_vkms_output,
+							 vblank_hrtimer);
+	struct drm_crtc *crtc = &output->crtc;
+	u64 ret_overrun;
+	bool ret;
+
+	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
+					  output->period_ns);
+	WARN_ON(ret_overrun != 1);
+
+	ret = drm_crtc_handle_vblank(crtc);
+	if (!ret)
+		DRM_ERROR("amdgpu_vkms failure on handling vblank");
+
+	return HRTIMER_RESTART;
+}
+
+static int amdgpu_vkms_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+	struct amdgpu_vkms_output *out = drm_crtc_to_amdgpu_vkms_output(crtc);
+
+	drm_calc_timestamping_constants(crtc, &crtc->mode);
+
+	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	out->vblank_hrtimer.function = &amdgpu_vkms_vblank_simulate;
+	out->period_ns = ktime_set(0, vblank->framedur_ns);
+	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void amdgpu_vkms_disable_vblank(struct drm_crtc *crtc)
+{
+	struct amdgpu_vkms_output *out = drm_crtc_to_amdgpu_vkms_output(crtc);
+
+	hrtimer_cancel(&out->vblank_hrtimer);
+}
+
+static bool amdgpu_vkms_get_vblank_timestamp(struct drm_crtc *crtc,
+					     int *max_error,
+					     ktime_t *vblank_time,
+					     bool in_vblank_irq)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = crtc->index;
+	struct amdgpu_vkms_output *output = drm_crtc_to_amdgpu_vkms_output(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+
+	if (!READ_ONCE(vblank->enabled)) {
+		*vblank_time = ktime_get();
+		return true;
+	}
+
+	*vblank_time = READ_ONCE(output->vblank_hrtimer.node.expires);
+
+	if (WARN_ON(*vblank_time == vblank->time))
+		return true;
+
+	/*
+	 * To prevent races we roll the hrtimer forward before we do any
+	 * interrupt processing - this is how real hw works (the interrupt is
+	 * only generated after all the vblank registers are updated) and what
+	 * the vblank core expects. Therefore we need to always correct the
+	 * timestampe by one frame.
+	 */
+	*vblank_time -= output->period_ns;
+
+	return true;
+}
+
+static const struct drm_crtc_funcs amdgpu_vkms_crtc_funcs = {
+	.set_config             = drm_atomic_helper_set_config,
+	.destroy                = drm_crtc_cleanup,
+	.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		= amdgpu_vkms_enable_vblank,
+	.disable_vblank		= amdgpu_vkms_disable_vblank,
+	.get_vblank_timestamp	= amdgpu_vkms_get_vblank_timestamp,
+};
+
+static void amdgpu_vkms_crtc_atomic_enable(struct drm_crtc *crtc,
+					   struct drm_atomic_state *state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void amdgpu_vkms_crtc_atomic_disable(struct drm_crtc *crtc,
+					    struct drm_atomic_state *state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void amdgpu_vkms_crtc_atomic_flush(struct drm_crtc *crtc,
+					  struct drm_atomic_state *state)
+{
+	if (crtc->state->event) {
+		spin_lock(&crtc->dev->event_lock);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		else
+			drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+
+		spin_unlock(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
+}
+
+static const struct drm_crtc_helper_funcs amdgpu_vkms_crtc_helper_funcs = {
+	.atomic_flush	= amdgpu_vkms_crtc_atomic_flush,
+	.atomic_enable	= amdgpu_vkms_crtc_atomic_enable,
+	.atomic_disable	= amdgpu_vkms_crtc_atomic_disable,
+};
+
+static int amdgpu_vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+			  struct drm_plane *primary, struct drm_plane *cursor)
+{
+	int ret;
+
+	ret = drm_crtc_init_with_planes(dev, crtc, primary, cursor,
+					&amdgpu_vkms_crtc_funcs, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init CRTC\n");
+		return ret;
+	}
+
+	drm_crtc_helper_add(crtc, &amdgpu_vkms_crtc_helper_funcs);
+
+	return ret;
+}
+
+static const struct drm_connector_funcs amdgpu_vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int amdgpu_vkms_conn_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_display_mode *mode = NULL;
+	unsigned i;
+	static const struct mode_size {
+		int w;
+		int h;
+	} common_modes[] = {
+		{ 640,  480},
+		{ 720,  480},
+		{ 800,  600},
+		{ 848,  480},
+		{1024,  768},
+		{1152,  768},
+		{1280,  720},
+		{1280,  800},
+		{1280,  854},
+		{1280,  960},
+		{1280, 1024},
+		{1440,  900},
+		{1400, 1050},
+		{1680, 1050},
+		{1600, 1200},
+		{1920, 1080},
+		{1920, 1200},
+		{2560, 1440},
+		{4096, 3112},
+		{3656, 2664},
+		{3840, 2160},
+		{4096, 2160},
+	};
+
+	for (i = 0; i < ARRAY_SIZE(common_modes); i++) {
+		mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false);
+		drm_mode_probed_add(connector, mode);
+	}
+
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+
+	return ARRAY_SIZE(common_modes);
+}
+
+static const struct drm_connector_helper_funcs amdgpu_vkms_conn_helper_funcs = {
+	.get_modes    = amdgpu_vkms_conn_get_modes,
+};
+
+static const struct drm_plane_funcs amdgpu_vkms_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 void amdgpu_vkms_plane_atomic_update(struct drm_plane *plane,
+					    struct drm_atomic_state *old_state)
+{
+	return;
+}
+
+static int amdgpu_vkms_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;
+	int ret;
+
+	if (!new_plane_state->fb || WARN_ON(!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);
+
+	ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, true);
+	if (ret != 0)
+		return ret;
+
+	/* for now primary plane must be visible and full screen */
+	if (!new_plane_state->visible)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
+				  struct drm_plane_state *new_state)
+{
+	struct amdgpu_framebuffer *afb;
+	struct drm_gem_object *obj;
+	struct amdgpu_device *adev;
+	struct amdgpu_bo *rbo;
+	struct list_head list;
+	struct ttm_validate_buffer tv;
+	struct ww_acquire_ctx ticket;
+	uint32_t domain;
+	int r;
+
+	if (!new_state->fb) {
+		DRM_DEBUG_KMS("No FB bound\n");
+		return 0;
+	}
+	afb = to_amdgpu_framebuffer(new_state->fb);
+	obj = new_state->fb->obj[0];
+	rbo = gem_to_amdgpu_bo(obj);
+	adev = amdgpu_ttm_adev(rbo->tbo.bdev);
+	INIT_LIST_HEAD(&list);
+
+	tv.bo = &rbo->tbo;
+	tv.num_shared = 1;
+	list_add(&tv.head, &list);
+
+	r = ttm_eu_reserve_buffers(&ticket, &list, false, NULL);
+	if (r) {
+		dev_err(adev->dev, "fail to reserve bo (%d)\n", r);
+		return r;
+	}
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR)
+		domain = amdgpu_display_supported_domains(adev, rbo->flags);
+	else
+		domain = AMDGPU_GEM_DOMAIN_VRAM;
+
+	r = amdgpu_bo_pin(rbo, domain);
+	if (unlikely(r != 0)) {
+		if (r != -ERESTARTSYS)
+			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		return r;
+	}
+
+	r = amdgpu_ttm_alloc_gart(&rbo->tbo);
+	if (unlikely(r != 0)) {
+		amdgpu_bo_unpin(rbo);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		DRM_ERROR("%p bind failed\n", rbo);
+		return r;
+	}
+
+	ttm_eu_backoff_reservation(&ticket, &list);
+
+	afb->address = amdgpu_bo_gpu_offset(rbo);
+
+	amdgpu_bo_ref(rbo);
+
+	return 0;
+}
+
+static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane,
+				   struct drm_plane_state *old_state)
+{
+	struct amdgpu_bo *rbo;
+	int r;
+
+	if (!old_state->fb)
+		return;
+
+	rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]);
+	r = amdgpu_bo_reserve(rbo, false);
+	if (unlikely(r)) {
+		DRM_ERROR("failed to reserve rbo before unpin\n");
+		return;
+	}
+
+	amdgpu_bo_unpin(rbo);
+	amdgpu_bo_unreserve(rbo);
+	amdgpu_bo_unref(&rbo);
+}
+
+static const struct drm_plane_helper_funcs amdgpu_vkms_primary_helper_funcs = {
+	.atomic_update		= amdgpu_vkms_plane_atomic_update,
+	.atomic_check		= amdgpu_vkms_plane_atomic_check,
+	.prepare_fb		= amdgpu_vkms_prepare_fb,
+	.cleanup_fb		= amdgpu_vkms_cleanup_fb,
+};
+
+static struct drm_plane *amdgpu_vkms_plane_init(struct drm_device *dev,
+						enum drm_plane_type type,
+						int index)
+{
+	struct drm_plane *plane;
+	int ret;
+
+	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+	if (!plane)
+		return ERR_PTR(-ENOMEM);
+
+	ret = drm_universal_plane_init(dev, plane, 1 << index,
+				       &amdgpu_vkms_plane_funcs,
+				       amdgpu_vkms_formats,
+				       ARRAY_SIZE(amdgpu_vkms_formats),
+				       NULL, type, NULL);
+	if (ret) {
+		kfree(plane);
+		return ERR_PTR(ret);
+	}
+
+	drm_plane_helper_add(plane, &amdgpu_vkms_primary_helper_funcs);
+
+	return plane;
+}
+
+int amdgpu_vkms_output_init(struct drm_device *dev,
+			    struct amdgpu_vkms_output *output, int index)
+{
+	struct drm_connector *connector = &output->connector;
+	struct drm_encoder *encoder = &output->encoder;
+	struct drm_crtc *crtc = &output->crtc;
+	struct drm_plane *primary, *cursor = NULL;
+	int ret;
+
+	primary = amdgpu_vkms_plane_init(dev, DRM_PLANE_TYPE_PRIMARY, index);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+
+	ret = amdgpu_vkms_crtc_init(dev, crtc, primary, cursor);
+	if (ret)
+		goto err_crtc;
+
+	ret = drm_connector_init(dev, connector, &amdgpu_vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init connector\n");
+		goto err_connector;
+	}
+
+	drm_connector_helper_add(connector, &amdgpu_vkms_conn_helper_funcs);
+
+	ret = drm_simple_encoder_init(dev, encoder, DRM_MODE_ENCODER_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init encoder\n");
+		goto err_encoder;
+	}
+	encoder->possible_crtcs = 1 << index;
+
+	ret = drm_connector_attach_encoder(connector, encoder);
+	if (ret) {
+		DRM_ERROR("Failed to attach connector to encoder\n");
+		goto err_attach;
+	}
+
+	drm_mode_config_reset(dev);
+
+	return 0;
+
+err_attach:
+	drm_encoder_cleanup(encoder);
+
+err_encoder:
+	drm_connector_cleanup(connector);
+
+err_connector:
+	drm_crtc_cleanup(crtc);
+
+err_crtc:
+	drm_plane_cleanup(primary);
+
+	return ret;
+}
+
+const struct drm_mode_config_funcs amdgpu_vkms_mode_funcs = {
+	.fb_create = amdgpu_display_user_framebuffer_create,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int amdgpu_vkms_sw_init(void *handle)
+{
+	int r, i;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev_to_drm(adev)->max_vblank_count = 0;
+
+	adev_to_drm(adev)->mode_config.funcs = &amdgpu_vkms_mode_funcs;
+
+	adev_to_drm(adev)->mode_config.max_width = XRES_MAX;
+	adev_to_drm(adev)->mode_config.max_height = YRES_MAX;
+
+	adev_to_drm(adev)->mode_config.preferred_depth = 24;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
+
+	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
+
+	r = amdgpu_display_modeset_create_props(adev);
+	if (r)
+		return r;
+
+	adev->amdgpu_vkms_output = kcalloc(adev->mode_info.num_crtc, sizeof(struct amdgpu_vkms_output), GFP_KERNEL);
+	if (!adev->amdgpu_vkms_output)
+		return -ENOMEM;
+
+	/* allocate crtcs, encoders, connectors */
+	for (i = 0; i < adev->mode_info.num_crtc; i++) {
+		r = amdgpu_vkms_output_init(adev_to_drm(adev), &adev->amdgpu_vkms_output[i], i);
+		if (r)
+			return r;
+	}
+
+	drm_kms_helper_poll_init(adev_to_drm(adev));
+
+	adev->mode_info.mode_config_initialized = true;
+	return 0;
+}
+
+static int amdgpu_vkms_sw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i = 0;
+
+	for (i = 0; i < adev->mode_info.num_crtc; i++)
+		if (adev->mode_info.crtcs[i])
+			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
+
+	kfree(adev->mode_info.bios_hardcoded_edid);
+	kfree(adev->amdgpu_vkms_output);
+
+	drm_kms_helper_poll_fini(adev_to_drm(adev));
+
+	adev->mode_info.mode_config_initialized = false;
+	return 0;
+}
+
+static int amdgpu_vkms_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	switch (adev->asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+		dce_v6_0_disable_dce(adev);
+		break;
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+	case CHIP_KAVERI:
+	case CHIP_KABINI:
+	case CHIP_MULLINS:
+		dce_v8_0_disable_dce(adev);
+		break;
+#endif
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+		dce_v10_0_disable_dce(adev);
+		break;
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_VEGAM:
+		dce_v11_0_disable_dce(adev);
+		break;
+	case CHIP_TOPAZ:
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_HAINAN:
+#endif
+		/* no DCE */
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int amdgpu_vkms_hw_fini(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = drm_mode_config_helper_suspend(adev_to_drm(adev));
+	if (r)
+		return r;
+	return amdgpu_vkms_hw_fini(handle);
+}
+
+static int amdgpu_vkms_resume(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_vkms_hw_init(handle);
+	if (r)
+		return r;
+	return drm_mode_config_helper_resume(adev_to_drm(adev));
+}
+
+static bool amdgpu_vkms_is_idle(void *handle)
+{
+	return true;
+}
+
+static int amdgpu_vkms_wait_for_idle(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_soft_reset(void *handle)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	return 0;
+}
+
+static int amdgpu_vkms_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	return 0;
+}
+
+static const struct amd_ip_funcs amdgpu_vkms_ip_funcs = {
+	.name = "amdgpu_vkms",
+	.early_init = NULL,
+	.late_init = NULL,
+	.sw_init = amdgpu_vkms_sw_init,
+	.sw_fini = amdgpu_vkms_sw_fini,
+	.hw_init = amdgpu_vkms_hw_init,
+	.hw_fini = amdgpu_vkms_hw_fini,
+	.suspend = amdgpu_vkms_suspend,
+	.resume = amdgpu_vkms_resume,
+	.is_idle = amdgpu_vkms_is_idle,
+	.wait_for_idle = amdgpu_vkms_wait_for_idle,
+	.soft_reset = amdgpu_vkms_soft_reset,
+	.set_clockgating_state = amdgpu_vkms_set_clockgating_state,
+	.set_powergating_state = amdgpu_vkms_set_powergating_state,
+};
+
+const struct amdgpu_ip_block_version amdgpu_vkms_ip_block =
+{
+	.type = AMD_IP_BLOCK_TYPE_DCE,
+	.major = 1,
+	.minor = 0,
+	.rev = 0,
+	.funcs = &amdgpu_vkms_ip_funcs,
+};
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h
new file mode 100644
index 000000000000..97f1b79c0724
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _AMDGPU_VKMS_H_
+#define _AMDGPU_VKMS_H_
+
+#define XRES_DEF  1024
+#define YRES_DEF   768
+
+#define XRES_MAX  16384
+#define YRES_MAX  16384
+
+#define drm_crtc_to_amdgpu_vkms_output(target) \
+	container_of(target, struct amdgpu_vkms_output, crtc)
+
+extern const struct amdgpu_ip_block_version amdgpu_vkms_ip_block;
+
+struct amdgpu_vkms_output {
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+	struct hrtimer vblank_hrtimer;
+	ktime_t period_ns;
+	struct drm_pending_vblank_event *event;
+};
+
+#endif /* _AMDGPU_VKMS_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6362e861a3f5..2a88ed5d983b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1798,7 +1798,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	r = vm->update_funcs->commit(&params, fence);
 
 	if (table_freed)
-		*table_freed = params.table_freed;
+		*table_freed = *table_freed || params.table_freed;
 
 error_unlock:
 	amdgpu_vm_eviction_unlock(vm);
@@ -1856,6 +1856,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * @adev: amdgpu_device pointer
  * @bo_va: requested BO and VM object
  * @clear: if true clear the entries
+ * @table_freed: return true if page table is freed
  *
  * Fill in the page table entries for @bo_va.
  *
@@ -1863,7 +1864,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * 0 for success, -EINVAL for failure.
  */
 int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
-			bool clear)
+			bool clear, bool *table_freed)
 {
 	struct amdgpu_bo *bo = bo_va->base.bo;
 	struct amdgpu_vm *vm = bo_va->base.vm;
@@ -1942,7 +1943,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 						resv, mapping->start,
 						mapping->last, update_flags,
 						mapping->offset, mem,
-						pages_addr, last_update, NULL);
+						pages_addr, last_update, table_freed);
 		if (r)
 			return r;
 	}
@@ -2194,7 +2195,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 
 	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
 		/* Per VM BOs never need to bo cleared in the page tables */
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 	}
@@ -2213,7 +2214,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		else
 			clear = true;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, clear);
+		r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL);
 		if (r)
 			return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index ee0028ec2c4f..80cc9ab2c1d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -408,7 +408,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 				struct dma_fence **fence, bool *free_table);
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
-			bool clear);
+			bool clear, bool *table_freed);
 bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
 void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 			     struct amdgpu_bo *bo, bool evicted);
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index c0fcc41ee574..54f28c075f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -70,7 +70,7 @@
 
 #include "amdgpu_dm.h"
 #include "amdgpu_amdkfd.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 
 static const struct amdgpu_video_codec_info cik_video_codecs_encode_array[] =
 {
@@ -2259,7 +2259,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2277,7 +2277,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2295,7 +2295,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2315,7 +2315,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
deleted file mode 100644
index 7e0d8c092c7e..000000000000
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ /dev/null
@@ -1,780 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include <drm/drm_vblank.h>
-
-#include "amdgpu.h"
-#include "amdgpu_pm.h"
-#include "amdgpu_i2c.h"
-#include "atom.h"
-#include "amdgpu_pll.h"
-#include "amdgpu_connectors.h"
-#ifdef CONFIG_DRM_AMDGPU_SI
-#include "dce_v6_0.h"
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-#include "dce_v8_0.h"
-#endif
-#include "dce_v10_0.h"
-#include "dce_v11_0.h"
-#include "dce_virtual.h"
-#include "ivsrcid/ivsrcid_vislands30.h"
-#include "amdgpu_display.h"
-
-#define DCE_VIRTUAL_VBLANK_PERIOD 16666666
-
-
-static void dce_virtual_set_display_funcs(struct amdgpu_device *adev);
-static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev);
-static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
-					      int index);
-static int dce_virtual_pageflip(struct amdgpu_device *adev,
-				unsigned crtc_id);
-static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer);
-static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
-							int crtc,
-							enum amdgpu_interrupt_state state);
-
-static u32 dce_virtual_vblank_get_counter(struct amdgpu_device *adev, int crtc)
-{
-	return 0;
-}
-
-static void dce_virtual_page_flip(struct amdgpu_device *adev,
-			      int crtc_id, u64 crtc_base, bool async)
-{
-	return;
-}
-
-static int dce_virtual_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
-					u32 *vbl, u32 *position)
-{
-	*vbl = 0;
-	*position = 0;
-
-	return -EINVAL;
-}
-
-static bool dce_virtual_hpd_sense(struct amdgpu_device *adev,
-			       enum amdgpu_hpd_id hpd)
-{
-	return true;
-}
-
-static void dce_virtual_hpd_set_polarity(struct amdgpu_device *adev,
-				      enum amdgpu_hpd_id hpd)
-{
-	return;
-}
-
-static u32 dce_virtual_hpd_get_gpio_reg(struct amdgpu_device *adev)
-{
-	return 0;
-}
-
-/**
- * dce_virtual_bandwidth_update - program display watermarks
- *
- * @adev: amdgpu_device pointer
- *
- * Calculate and program the display watermarks and line
- * buffer allocation (CIK).
- */
-static void dce_virtual_bandwidth_update(struct amdgpu_device *adev)
-{
-	return;
-}
-
-static int dce_virtual_crtc_gamma_set(struct drm_crtc *crtc, u16 *red,
-				      u16 *green, u16 *blue, uint32_t size,
-				      struct drm_modeset_acquire_ctx *ctx)
-{
-	return 0;
-}
-
-static void dce_virtual_crtc_destroy(struct drm_crtc *crtc)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-	drm_crtc_cleanup(crtc);
-	kfree(amdgpu_crtc);
-}
-
-static const struct drm_crtc_funcs dce_virtual_crtc_funcs = {
-	.cursor_set2 = NULL,
-	.cursor_move = NULL,
-	.gamma_set = dce_virtual_crtc_gamma_set,
-	.set_config = amdgpu_display_crtc_set_config,
-	.destroy = dce_virtual_crtc_destroy,
-	.page_flip_target = amdgpu_display_crtc_page_flip_target,
-	.get_vblank_counter = amdgpu_get_vblank_counter_kms,
-	.enable_vblank = amdgpu_enable_vblank_kms,
-	.disable_vblank = amdgpu_disable_vblank_kms,
-	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-};
-
-static void dce_virtual_crtc_dpms(struct drm_crtc *crtc, int mode)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	unsigned type;
-
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-		amdgpu_crtc->enabled = true;
-		/* Make sure VBLANK interrupts are still enabled */
-		type = amdgpu_display_crtc_idx_to_irq_type(adev,
-						amdgpu_crtc->crtc_id);
-		amdgpu_irq_update(adev, &adev->crtc_irq, type);
-		drm_crtc_vblank_on(crtc);
-		break;
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-	case DRM_MODE_DPMS_OFF:
-		drm_crtc_vblank_off(crtc);
-		amdgpu_crtc->enabled = false;
-		break;
-	}
-}
-
-
-static void dce_virtual_crtc_prepare(struct drm_crtc *crtc)
-{
-	dce_virtual_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void dce_virtual_crtc_commit(struct drm_crtc *crtc)
-{
-	dce_virtual_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-static void dce_virtual_crtc_disable(struct drm_crtc *crtc)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct drm_device *dev = crtc->dev;
-
-	if (dev->num_crtcs)
-		drm_crtc_vblank_off(crtc);
-
-	amdgpu_crtc->enabled = false;
-	amdgpu_crtc->pll_id = ATOM_PPLL_INVALID;
-	amdgpu_crtc->encoder = NULL;
-	amdgpu_crtc->connector = NULL;
-}
-
-static int dce_virtual_crtc_mode_set(struct drm_crtc *crtc,
-				  struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode,
-				  int x, int y, struct drm_framebuffer *old_fb)
-{
-	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-	/* update the hw version fpr dpm */
-	amdgpu_crtc->hw_mode = *adjusted_mode;
-
-	return 0;
-}
-
-static bool dce_virtual_crtc_mode_fixup(struct drm_crtc *crtc,
-				     const struct drm_display_mode *mode,
-				     struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-
-static int dce_virtual_crtc_set_base(struct drm_crtc *crtc, int x, int y,
-				  struct drm_framebuffer *old_fb)
-{
-	return 0;
-}
-
-static int dce_virtual_crtc_set_base_atomic(struct drm_crtc *crtc,
-					 struct drm_framebuffer *fb,
-					 int x, int y, enum mode_set_atomic state)
-{
-	return 0;
-}
-
-static const struct drm_crtc_helper_funcs dce_virtual_crtc_helper_funcs = {
-	.dpms = dce_virtual_crtc_dpms,
-	.mode_fixup = dce_virtual_crtc_mode_fixup,
-	.mode_set = dce_virtual_crtc_mode_set,
-	.mode_set_base = dce_virtual_crtc_set_base,
-	.mode_set_base_atomic = dce_virtual_crtc_set_base_atomic,
-	.prepare = dce_virtual_crtc_prepare,
-	.commit = dce_virtual_crtc_commit,
-	.disable = dce_virtual_crtc_disable,
-	.get_scanout_position = amdgpu_crtc_get_scanout_position,
-};
-
-static int dce_virtual_crtc_init(struct amdgpu_device *adev, int index)
-{
-	struct amdgpu_crtc *amdgpu_crtc;
-
-	amdgpu_crtc = kzalloc(sizeof(struct amdgpu_crtc) +
-			      (AMDGPUFB_CONN_LIMIT * sizeof(struct drm_connector *)), GFP_KERNEL);
-	if (amdgpu_crtc == NULL)
-		return -ENOMEM;
-
-	drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_virtual_crtc_funcs);
-
-	drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256);
-	amdgpu_crtc->crtc_id = index;
-	adev->mode_info.crtcs[index] = amdgpu_crtc;
-
-	amdgpu_crtc->pll_id = ATOM_PPLL_INVALID;
-	amdgpu_crtc->encoder = NULL;
-	amdgpu_crtc->connector = NULL;
-	amdgpu_crtc->vsync_timer_enabled = AMDGPU_IRQ_STATE_DISABLE;
-	drm_crtc_helper_add(&amdgpu_crtc->base, &dce_virtual_crtc_helper_funcs);
-
-	hrtimer_init(&amdgpu_crtc->vblank_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer_set_expires(&amdgpu_crtc->vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD);
-	amdgpu_crtc->vblank_timer.function = dce_virtual_vblank_timer_handle;
-	hrtimer_start(&amdgpu_crtc->vblank_timer,
-		      DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL);
-	return 0;
-}
-
-static int dce_virtual_early_init(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	dce_virtual_set_display_funcs(adev);
-	dce_virtual_set_irq_funcs(adev);
-
-	adev->mode_info.num_hpd = 1;
-	adev->mode_info.num_dig = 1;
-	return 0;
-}
-
-static struct drm_encoder *
-dce_virtual_encoder(struct drm_connector *connector)
-{
-	struct drm_encoder *encoder;
-
-	drm_connector_for_each_possible_encoder(connector, encoder) {
-		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
-			return encoder;
-	}
-
-	/* pick the first one */
-	drm_connector_for_each_possible_encoder(connector, encoder)
-		return encoder;
-
-	return NULL;
-}
-
-static int dce_virtual_get_modes(struct drm_connector *connector)
-{
-	struct drm_device *dev = connector->dev;
-	struct drm_display_mode *mode = NULL;
-	unsigned i;
-	static const struct mode_size {
-		int w;
-		int h;
-	} common_modes[] = {
-		{ 640,  480},
-		{ 720,  480},
-		{ 800,  600},
-		{ 848,  480},
-		{1024,  768},
-		{1152,  768},
-		{1280,  720},
-		{1280,  800},
-		{1280,  854},
-		{1280,  960},
-		{1280, 1024},
-		{1440,  900},
-		{1400, 1050},
-		{1680, 1050},
-		{1600, 1200},
-		{1920, 1080},
-		{1920, 1200},
-		{2560, 1440},
-		{4096, 3112},
-		{3656, 2664},
-		{3840, 2160},
-		{4096, 2160},
-	};
-
-	for (i = 0; i < ARRAY_SIZE(common_modes); i++) {
-		mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false);
-		drm_mode_probed_add(connector, mode);
-	}
-
-	return 0;
-}
-
-static enum drm_mode_status dce_virtual_mode_valid(struct drm_connector *connector,
-				  struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
-static int
-dce_virtual_dpms(struct drm_connector *connector, int mode)
-{
-	return 0;
-}
-
-static int
-dce_virtual_set_property(struct drm_connector *connector,
-			 struct drm_property *property,
-			 uint64_t val)
-{
-	return 0;
-}
-
-static void dce_virtual_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(connector);
-}
-
-static void dce_virtual_force(struct drm_connector *connector)
-{
-	return;
-}
-
-static const struct drm_connector_helper_funcs dce_virtual_connector_helper_funcs = {
-	.get_modes = dce_virtual_get_modes,
-	.mode_valid = dce_virtual_mode_valid,
-	.best_encoder = dce_virtual_encoder,
-};
-
-static const struct drm_connector_funcs dce_virtual_connector_funcs = {
-	.dpms = dce_virtual_dpms,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.set_property = dce_virtual_set_property,
-	.destroy = dce_virtual_destroy,
-	.force = dce_virtual_force,
-};
-
-static int dce_virtual_sw_init(void *handle)
-{
-	int r, i;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER, &adev->crtc_irq);
-	if (r)
-		return r;
-
-	adev_to_drm(adev)->max_vblank_count = 0;
-
-	adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs;
-
-	adev_to_drm(adev)->mode_config.max_width = 16384;
-	adev_to_drm(adev)->mode_config.max_height = 16384;
-
-	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-
-	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
-
-	r = amdgpu_display_modeset_create_props(adev);
-	if (r)
-		return r;
-
-	adev_to_drm(adev)->mode_config.max_width = 16384;
-	adev_to_drm(adev)->mode_config.max_height = 16384;
-
-	/* allocate crtcs, encoders, connectors */
-	for (i = 0; i < adev->mode_info.num_crtc; i++) {
-		r = dce_virtual_crtc_init(adev, i);
-		if (r)
-			return r;
-		r = dce_virtual_connector_encoder_init(adev, i);
-		if (r)
-			return r;
-	}
-
-	drm_kms_helper_poll_init(adev_to_drm(adev));
-
-	adev->mode_info.mode_config_initialized = true;
-	return 0;
-}
-
-static int dce_virtual_sw_fini(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int i = 0;
-
-	for (i = 0; i < adev->mode_info.num_crtc; i++)
-		if (adev->mode_info.crtcs[i])
-			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
-
-	kfree(adev->mode_info.bios_hardcoded_edid);
-
-	drm_kms_helper_poll_fini(adev_to_drm(adev));
-
-	drm_mode_config_cleanup(adev_to_drm(adev));
-	/* clear crtcs pointer to avoid dce irq finish routine access freed data */
-	memset(adev->mode_info.crtcs, 0, sizeof(adev->mode_info.crtcs[0]) * AMDGPU_MAX_CRTCS);
-	adev->mode_info.mode_config_initialized = false;
-	return 0;
-}
-
-static int dce_virtual_hw_init(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	switch (adev->asic_type) {
-#ifdef CONFIG_DRM_AMDGPU_SI
-	case CHIP_TAHITI:
-	case CHIP_PITCAIRN:
-	case CHIP_VERDE:
-	case CHIP_OLAND:
-		dce_v6_0_disable_dce(adev);
-		break;
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	case CHIP_BONAIRE:
-	case CHIP_HAWAII:
-	case CHIP_KAVERI:
-	case CHIP_KABINI:
-	case CHIP_MULLINS:
-		dce_v8_0_disable_dce(adev);
-		break;
-#endif
-	case CHIP_FIJI:
-	case CHIP_TONGA:
-		dce_v10_0_disable_dce(adev);
-		break;
-	case CHIP_CARRIZO:
-	case CHIP_STONEY:
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_VEGAM:
-		dce_v11_0_disable_dce(adev);
-		break;
-	case CHIP_TOPAZ:
-#ifdef CONFIG_DRM_AMDGPU_SI
-	case CHIP_HAINAN:
-#endif
-		/* no DCE */
-		break;
-	default:
-		break;
-	}
-	return 0;
-}
-
-static int dce_virtual_hw_fini(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_suspend(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = amdgpu_display_suspend_helper(adev);
-	if (r)
-		return r;
-	return dce_virtual_hw_fini(handle);
-}
-
-static int dce_virtual_resume(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = dce_virtual_hw_init(handle);
-	if (r)
-		return r;
-	return amdgpu_display_resume_helper(adev);
-}
-
-static bool dce_virtual_is_idle(void *handle)
-{
-	return true;
-}
-
-static int dce_virtual_wait_for_idle(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_soft_reset(void *handle)
-{
-	return 0;
-}
-
-static int dce_virtual_set_clockgating_state(void *handle,
-					  enum amd_clockgating_state state)
-{
-	return 0;
-}
-
-static int dce_virtual_set_powergating_state(void *handle,
-					  enum amd_powergating_state state)
-{
-	return 0;
-}
-
-static const struct amd_ip_funcs dce_virtual_ip_funcs = {
-	.name = "dce_virtual",
-	.early_init = dce_virtual_early_init,
-	.late_init = NULL,
-	.sw_init = dce_virtual_sw_init,
-	.sw_fini = dce_virtual_sw_fini,
-	.hw_init = dce_virtual_hw_init,
-	.hw_fini = dce_virtual_hw_fini,
-	.suspend = dce_virtual_suspend,
-	.resume = dce_virtual_resume,
-	.is_idle = dce_virtual_is_idle,
-	.wait_for_idle = dce_virtual_wait_for_idle,
-	.soft_reset = dce_virtual_soft_reset,
-	.set_clockgating_state = dce_virtual_set_clockgating_state,
-	.set_powergating_state = dce_virtual_set_powergating_state,
-};
-
-/* these are handled by the primary encoders */
-static void dce_virtual_encoder_prepare(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void dce_virtual_encoder_commit(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void
-dce_virtual_encoder_mode_set(struct drm_encoder *encoder,
-			     struct drm_display_mode *mode,
-			     struct drm_display_mode *adjusted_mode)
-{
-	return;
-}
-
-static void dce_virtual_encoder_disable(struct drm_encoder *encoder)
-{
-	return;
-}
-
-static void
-dce_virtual_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	return;
-}
-
-static bool dce_virtual_encoder_mode_fixup(struct drm_encoder *encoder,
-				    const struct drm_display_mode *mode,
-				    struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-static const struct drm_encoder_helper_funcs dce_virtual_encoder_helper_funcs = {
-	.dpms = dce_virtual_encoder_dpms,
-	.mode_fixup = dce_virtual_encoder_mode_fixup,
-	.prepare = dce_virtual_encoder_prepare,
-	.mode_set = dce_virtual_encoder_mode_set,
-	.commit = dce_virtual_encoder_commit,
-	.disable = dce_virtual_encoder_disable,
-};
-
-static void dce_virtual_encoder_destroy(struct drm_encoder *encoder)
-{
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static const struct drm_encoder_funcs dce_virtual_encoder_funcs = {
-	.destroy = dce_virtual_encoder_destroy,
-};
-
-static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
-					      int index)
-{
-	struct drm_encoder *encoder;
-	struct drm_connector *connector;
-
-	/* add a new encoder */
-	encoder = kzalloc(sizeof(struct drm_encoder), GFP_KERNEL);
-	if (!encoder)
-		return -ENOMEM;
-	encoder->possible_crtcs = 1 << index;
-	drm_encoder_init(adev_to_drm(adev), encoder, &dce_virtual_encoder_funcs,
-			 DRM_MODE_ENCODER_VIRTUAL, NULL);
-	drm_encoder_helper_add(encoder, &dce_virtual_encoder_helper_funcs);
-
-	connector = kzalloc(sizeof(struct drm_connector), GFP_KERNEL);
-	if (!connector) {
-		kfree(encoder);
-		return -ENOMEM;
-	}
-
-	/* add a new connector */
-	drm_connector_init(adev_to_drm(adev), connector, &dce_virtual_connector_funcs,
-			   DRM_MODE_CONNECTOR_VIRTUAL);
-	drm_connector_helper_add(connector, &dce_virtual_connector_helper_funcs);
-	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
-
-	/* link them */
-	drm_connector_attach_encoder(connector, encoder);
-
-	return 0;
-}
-
-static const struct amdgpu_display_funcs dce_virtual_display_funcs = {
-	.bandwidth_update = &dce_virtual_bandwidth_update,
-	.vblank_get_counter = &dce_virtual_vblank_get_counter,
-	.backlight_set_level = NULL,
-	.backlight_get_level = NULL,
-	.hpd_sense = &dce_virtual_hpd_sense,
-	.hpd_set_polarity = &dce_virtual_hpd_set_polarity,
-	.hpd_get_gpio_reg = &dce_virtual_hpd_get_gpio_reg,
-	.page_flip = &dce_virtual_page_flip,
-	.page_flip_get_scanoutpos = &dce_virtual_crtc_get_scanoutpos,
-	.add_encoder = NULL,
-	.add_connector = NULL,
-};
-
-static void dce_virtual_set_display_funcs(struct amdgpu_device *adev)
-{
-	adev->mode_info.funcs = &dce_virtual_display_funcs;
-}
-
-static int dce_virtual_pageflip(struct amdgpu_device *adev,
-				unsigned crtc_id)
-{
-	unsigned long flags;
-	struct amdgpu_crtc *amdgpu_crtc;
-	struct amdgpu_flip_work *works;
-
-	amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
-
-	if (crtc_id >= adev->mode_info.num_crtc) {
-		DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
-		return -EINVAL;
-	}
-
-	/* IRQ could occur when in initial stage */
-	if (amdgpu_crtc == NULL)
-		return 0;
-
-	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
-	works = amdgpu_crtc->pflip_works;
-	if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED) {
-		DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != "
-			"AMDGPU_FLIP_SUBMITTED(%d)\n",
-			amdgpu_crtc->pflip_status,
-			AMDGPU_FLIP_SUBMITTED);
-		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
-		return 0;
-	}
-
-	/* page flip completed. clean up */
-	amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE;
-	amdgpu_crtc->pflip_works = NULL;
-
-	/* wakeup usersapce */
-	if (works->event)
-		drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event);
-
-	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
-
-	drm_crtc_vblank_put(&amdgpu_crtc->base);
-	amdgpu_bo_unref(&works->old_abo);
-	kfree(works->shared);
-	kfree(works);
-
-	return 0;
-}
-
-static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer)
-{
-	struct amdgpu_crtc *amdgpu_crtc = container_of(vblank_timer,
-						       struct amdgpu_crtc, vblank_timer);
-	struct drm_device *ddev = amdgpu_crtc->base.dev;
-	struct amdgpu_device *adev = drm_to_adev(ddev);
-	struct amdgpu_irq_src *source = adev->irq.client[AMDGPU_IRQ_CLIENTID_LEGACY].sources
-		[VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER];
-	int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev,
-						amdgpu_crtc->crtc_id);
-
-	if (amdgpu_irq_enabled(adev, source, irq_type)) {
-		drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
-		dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
-	}
-	hrtimer_start(vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD,
-		      HRTIMER_MODE_REL);
-
-	return HRTIMER_NORESTART;
-}
-
-static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
-							int crtc,
-							enum amdgpu_interrupt_state state)
-{
-	if (crtc >= adev->mode_info.num_crtc || !adev->mode_info.crtcs[crtc]) {
-		DRM_DEBUG("invalid crtc %d\n", crtc);
-		return;
-	}
-
-	adev->mode_info.crtcs[crtc]->vsync_timer_enabled = state;
-	DRM_DEBUG("[FM]set crtc %d vblank interrupt state %d\n", crtc, state);
-}
-
-
-static int dce_virtual_set_crtc_irq_state(struct amdgpu_device *adev,
-					  struct amdgpu_irq_src *source,
-					  unsigned type,
-					  enum amdgpu_interrupt_state state)
-{
-	if (type > AMDGPU_CRTC_IRQ_VBLANK6)
-		return -EINVAL;
-
-	dce_virtual_set_crtc_vblank_interrupt_state(adev, type, state);
-
-	return 0;
-}
-
-static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = {
-	.set = dce_virtual_set_crtc_irq_state,
-	.process = NULL,
-};
-
-static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev)
-{
-	adev->crtc_irq.num_types = adev->mode_info.num_crtc;
-	adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs;
-}
-
-const struct amdgpu_ip_block_version dce_virtual_ip_block =
-{
-	.type = AMD_IP_BLOCK_TYPE_DCE,
-	.major = 1,
-	.minor = 0,
-	.rev = 0,
-	.funcs = &dce_virtual_ip_funcs,
-};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 24b0195fe665..16dbe593cba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4621,6 +4621,7 @@ static void gfx_v10_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd,
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_STS2);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_DBG1);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v10_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 3a8d52a54873..6a8dadea40f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3027,6 +3027,7 @@ static void gfx_v6_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 685212c3ddae..37b4a3db6360 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4198,6 +4198,7 @@ static void gfx_v7_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v7_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index c26e06059466..e0302c23e9a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5279,6 +5279,7 @@ static void gfx_v8_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TMA_HI);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v8_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 03acc777adf7..603c259b073b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1295,6 +1295,16 @@ static bool is_raven_kicker(struct amdgpu_device *adev)
 		return false;
 }
 
+static bool check_if_enlarge_doorbell_range(struct amdgpu_device *adev)
+{
+	if ((adev->asic_type == CHIP_RENOIR) &&
+	    (adev->gfx.me_fw_version >= 0x000000a5) &&
+	    (adev->gfx.me_feature_version >= 52))
+		return true;
+	else
+		return false;
+}
+
 static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 {
 	if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
@@ -2080,6 +2090,7 @@ static void gfx_v9_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_STS);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_DBG0);
 	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v9_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
@@ -3675,7 +3686,16 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
 					(adev->doorbell_index.kiq * 2) << 2);
-		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+		/* If GC has entered CGPG, ringing doorbell > first page
+		 * doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to
+		 * workaround this issue. And this change has to align with firmware
+		 * update.
+		 */
+		if (check_if_enlarge_doorbell_range(adev))
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+					(adev->doorbell.size - 4));
+		else
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
 					(adev->doorbell_index.userqueue_end * 2) << 2);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 7cf653f9e9a7..097230b5e946 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1171,8 +1171,8 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 		break;
 	case CHIP_ALDEBARAN:
 		adev->umc.max_ras_err_cnt_per_query = UMC_V6_7_TOTAL_CHANNEL_NUM;
-		adev->umc.channel_inst_num = UMC_V6_7_UMC_INSTANCE_NUM;
-		adev->umc.umc_inst_num = UMC_V6_7_CHANNEL_INSTANCE_NUM;
+		adev->umc.channel_inst_num = UMC_V6_7_CHANNEL_INSTANCE_NUM;
+		adev->umc.umc_inst_num = UMC_V6_7_UMC_INSTANCE_NUM;
 		adev->umc.channel_offs = UMC_V6_7_PER_CHANNEL_OFFSET;
 		if (!adev->gmc.xgmi.connected_to_cpu)
 			adev->umc.ras_funcs = &umc_v6_7_ras_funcs;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 436fb13e32f0..ff80786e3918 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -58,7 +58,7 @@
 #include "jpeg_v2_0.h"
 #include "vcn_v3_0.h"
 #include "jpeg_v3_0.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mes_v10_1.h"
 #include "mxgpu_nv.h"
 #include "smuio_v11_0.h"
@@ -721,7 +721,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -749,7 +749,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -779,7 +779,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -802,7 +802,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -823,7 +823,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -843,7 +843,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		    is_support_sw_smu(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -865,7 +865,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -883,11 +883,11 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -905,7 +905,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 7cbc2bb03bc6..e6d2f74a7976 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -44,7 +44,7 @@
 #include "dce_v6_0.h"
 #include "si.h"
 #include "uvd_v3_1.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "gca/gfx_6_0_d.h"
 #include "oss/oss_1_0_d.h"
 #include "oss/oss_1_0_sh_mask.h"
@@ -2759,7 +2759,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2777,7 +2777,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC) && defined(CONFIG_DRM_AMD_DC_SI)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2795,7 +2795,7 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index a5e085e570f7..f7b56a746c15 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -74,7 +74,7 @@
 #include "smuio_v9_0.h"
 #include "smuio_v11_0.h"
 #include "smuio_v13_0.h"
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mxgpu_ai.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_xgmi.h"
@@ -843,7 +843,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -863,7 +863,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -885,7 +885,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		}
 
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
@@ -909,7 +909,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 7da12110425c..bb30336b1e8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -30,17 +30,17 @@
 
 const uint32_t
 	umc_v6_7_channel_idx_tbl_second[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM] = {
-		{28, 12, 6, 22},	{19, 3, 9, 25},
-		{20, 4, 30, 14},	{11, 27, 1, 17},
-		{24, 8, 2, 18},		{15, 31, 5, 21},
-		{16, 0, 26, 10},	{7, 23, 29, 13}
+		{28, 20, 24, 16, 12, 4, 8, 0},
+		{6, 30, 2, 26, 22, 14, 18, 10},
+		{19, 11, 15, 7, 3, 27, 31, 23},
+		{9, 1, 5, 29, 25, 17, 21, 13}
 };
 const uint32_t
 	umc_v6_7_channel_idx_tbl_first[UMC_V6_7_UMC_INSTANCE_NUM][UMC_V6_7_CHANNEL_INSTANCE_NUM] = {
-		{19, 3, 9, 25},		{28, 12, 6, 22},
-		{11, 27, 1, 17},	{20, 4, 30, 14},
-		{15, 31, 5, 21},	{24, 8, 2, 18},
-		{7, 23, 29, 13},	{16, 0, 26, 10}
+		{19, 11, 15, 7,	3, 27, 31, 23},
+		{9, 1, 5, 29, 25, 17, 21, 13},
+		{28, 20, 24, 16, 12, 4, 8, 0},
+		{6, 30, 2, 26, 22, 14, 18, 10},
 };
 
 static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
index 81b8f1844091..57f2557e7aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h
@@ -36,9 +36,9 @@
 #define UMC_V6_7_INST_DIST	0x40000
 
 /* number of umc channel instance with memory map register access */
-#define UMC_V6_7_CHANNEL_INSTANCE_NUM		4
+#define UMC_V6_7_UMC_INSTANCE_NUM		4
 /* number of umc instance with memory map register access */
-#define UMC_V6_7_UMC_INSTANCE_NUM		8
+#define UMC_V6_7_CHANNEL_INSTANCE_NUM		8
 /* total channel instances in one umc block */
 #define UMC_V6_7_TOTAL_CHANNEL_NUM	(UMC_V6_7_CHANNEL_INSTANCE_NUM * UMC_V6_7_UMC_INSTANCE_NUM)
 /* UMC regiser per channel offset */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 2f017560948e..3d18aab88b4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -90,9 +90,7 @@ static int vcn_v3_0_early_init(void *handle)
 	int i;
 
 	if (amdgpu_sriov_vf(adev)) {
-		for (i = 0; i < VCN_INSTANCES_SIENNA_CICHLID; i++)
-			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i))
-				adev->vcn.num_vcn_inst++;
+		adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
 		adev->vcn.harvest_config = 0;
 		adev->vcn.num_enc_rings = 1;
 
@@ -153,8 +151,7 @@ static int vcn_v3_0_sw_init(void *handle)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 
-		if ((adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) ||
-		    (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)) {
+		if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) {
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1;
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw;
 			adev->firmware.fw_size +=
@@ -328,18 +325,28 @@ static int vcn_v3_0_hw_init(void *handle)
 				continue;
 
 			ring = &adev->vcn.inst[i].ring_dec;
-			ring->wptr = 0;
-			ring->wptr_old = 0;
-			vcn_v3_0_dec_ring_set_wptr(ring);
-			ring->sched.ready = true;
-
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
-				ring = &adev->vcn.inst[i].ring_enc[j];
+			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) {
+				ring->sched.ready = false;
+				dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
+			} else {
 				ring->wptr = 0;
 				ring->wptr_old = 0;
-				vcn_v3_0_enc_ring_set_wptr(ring);
+				vcn_v3_0_dec_ring_set_wptr(ring);
 				ring->sched.ready = true;
 			}
+
+			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+				ring = &adev->vcn.inst[i].ring_enc[j];
+				if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) {
+					ring->sched.ready = false;
+					dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
+				} else {
+					ring->wptr = 0;
+					ring->wptr_old = 0;
+					vcn_v3_0_enc_ring_set_wptr(ring);
+					ring->sched.ready = true;
+				}
+			}
 		}
 	} else {
 		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 3d21c0799037..fe9a7cc8d9eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -77,7 +77,7 @@
 #if defined(CONFIG_DRM_AMD_ACP)
 #include "amdgpu_acp.h"
 #endif
-#include "dce_virtual.h"
+#include "amdgpu_vkms.h"
 #include "mxgpu_vi.h"
 #include "amdgpu_dm.h"
 
@@ -2102,7 +2102,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v2_4_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 		break;
 	case CHIP_FIJI:
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
@@ -2112,7 +2112,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2132,7 +2132,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2155,7 +2155,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2173,7 +2173,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
@@ -2194,7 +2194,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e48acdd03c1a..86afd37b098d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1393,6 +1393,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	long err = 0;
 	int i;
 	uint32_t *devices_arr = NULL;
+	bool table_freed = false;
 
 	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
 	if (!dev)
@@ -1450,7 +1451,8 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 			goto get_mem_obj_from_handle_failed;
 		}
 		err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-			peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+			peer->kgd, (struct kgd_mem *)mem,
+			peer_pdd->drm_priv, &table_freed);
 		if (err) {
 			pr_err("Failed to map to gpu %d/%d\n",
 			       i, args->n_devices);
@@ -1468,16 +1470,17 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	}
 
 	/* Flush TLBs after waiting for the page table updates to complete */
-	for (i = 0; i < args->n_devices; i++) {
-		peer = kfd_device_by_id(devices_arr[i]);
-		if (WARN_ON_ONCE(!peer))
-			continue;
-		peer_pdd = kfd_get_process_device_data(peer, p);
-		if (WARN_ON_ONCE(!peer_pdd))
-			continue;
-		kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+	if (table_freed) {
+		for (i = 0; i < args->n_devices; i++) {
+			peer = kfd_device_by_id(devices_arr[i]);
+			if (WARN_ON_ONCE(!peer))
+				continue;
+			peer_pdd = kfd_get_process_device_data(peer, p);
+			if (WARN_ON_ONCE(!peer_pdd))
+				continue;
+			kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+		}
 	}
-
 	kfree(devices_arr);
 
 	return err;
@@ -1565,10 +1568,29 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 		}
 		args->n_success = i+1;
 	}
-	kfree(devices_arr);
-
 	mutex_unlock(&p->mutex);
 
+	if (dev->device_info->asic_family == CHIP_ALDEBARAN) {
+		err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd,
+				(struct kgd_mem *) mem, true);
+		if (err) {
+			pr_debug("Sync memory failed, wait interrupted by user signal\n");
+			goto sync_memory_failed;
+		}
+
+		/* Flush TLBs after waiting for the page table updates to complete */
+		for (i = 0; i < args->n_devices; i++) {
+			peer = kfd_device_by_id(devices_arr[i]);
+			if (WARN_ON_ONCE(!peer))
+				continue;
+			peer_pdd = kfd_get_process_device_data(peer, p);
+			if (WARN_ON_ONCE(!peer_pdd))
+				continue;
+			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
+		}
+	}
+	kfree(devices_arr);
+
 	return 0;
 
 bind_process_to_device_failed:
@@ -1576,6 +1598,7 @@ get_mem_obj_from_handle_failed:
 unmap_memory_from_gpu_failed:
 	mutex_unlock(&p->mutex);
 copy_from_user_failed:
+sync_memory_failed:
 	kfree(devices_arr);
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index b551dd675085..16a57b70cc1a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -91,6 +91,7 @@ static const struct kfd2kgd_calls *kfd2kgd_funcs[] = {
 static const struct kfd_device_info kaveri_device_info = {
 	.asic_family = CHIP_KAVERI,
 	.asic_name = "kaveri",
+	.gfx_target_version = 70000,
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -110,6 +111,7 @@ static const struct kfd_device_info kaveri_device_info = {
 static const struct kfd_device_info carrizo_device_info = {
 	.asic_family = CHIP_CARRIZO,
 	.asic_name = "carrizo",
+	.gfx_target_version = 80001,
 	.max_pasid_bits = 16,
 	/* max num of queues for CZ.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -130,6 +132,7 @@ static const struct kfd_device_info carrizo_device_info = {
 static const struct kfd_device_info raven_device_info = {
 	.asic_family = CHIP_RAVEN,
 	.asic_name = "raven",
+	.gfx_target_version = 90002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -148,6 +151,7 @@ static const struct kfd_device_info raven_device_info = {
 static const struct kfd_device_info hawaii_device_info = {
 	.asic_family = CHIP_HAWAII,
 	.asic_name = "hawaii",
+	.gfx_target_version = 70001,
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
@@ -167,6 +171,7 @@ static const struct kfd_device_info hawaii_device_info = {
 static const struct kfd_device_info tonga_device_info = {
 	.asic_family = CHIP_TONGA,
 	.asic_name = "tonga",
+	.gfx_target_version = 80002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -185,6 +190,7 @@ static const struct kfd_device_info tonga_device_info = {
 static const struct kfd_device_info fiji_device_info = {
 	.asic_family = CHIP_FIJI,
 	.asic_name = "fiji",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -203,6 +209,7 @@ static const struct kfd_device_info fiji_device_info = {
 static const struct kfd_device_info fiji_vf_device_info = {
 	.asic_family = CHIP_FIJI,
 	.asic_name = "fiji",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -222,6 +229,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 static const struct kfd_device_info polaris10_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.asic_name = "polaris10",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -240,6 +248,7 @@ static const struct kfd_device_info polaris10_device_info = {
 static const struct kfd_device_info polaris10_vf_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.asic_name = "polaris10",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -258,6 +267,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 static const struct kfd_device_info polaris11_device_info = {
 	.asic_family = CHIP_POLARIS11,
 	.asic_name = "polaris11",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -276,6 +286,7 @@ static const struct kfd_device_info polaris11_device_info = {
 static const struct kfd_device_info polaris12_device_info = {
 	.asic_family = CHIP_POLARIS12,
 	.asic_name = "polaris12",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -294,6 +305,7 @@ static const struct kfd_device_info polaris12_device_info = {
 static const struct kfd_device_info vegam_device_info = {
 	.asic_family = CHIP_VEGAM,
 	.asic_name = "vegam",
+	.gfx_target_version = 80003,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 4,
@@ -312,6 +324,7 @@ static const struct kfd_device_info vegam_device_info = {
 static const struct kfd_device_info vega10_device_info = {
 	.asic_family = CHIP_VEGA10,
 	.asic_name = "vega10",
+	.gfx_target_version = 90000,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -330,6 +343,7 @@ static const struct kfd_device_info vega10_device_info = {
 static const struct kfd_device_info vega10_vf_device_info = {
 	.asic_family = CHIP_VEGA10,
 	.asic_name = "vega10",
+	.gfx_target_version = 90000,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -348,6 +362,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 static const struct kfd_device_info vega12_device_info = {
 	.asic_family = CHIP_VEGA12,
 	.asic_name = "vega12",
+	.gfx_target_version = 90004,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -366,6 +381,7 @@ static const struct kfd_device_info vega12_device_info = {
 static const struct kfd_device_info vega20_device_info = {
 	.asic_family = CHIP_VEGA20,
 	.asic_name = "vega20",
+	.gfx_target_version = 90006,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -384,6 +400,7 @@ static const struct kfd_device_info vega20_device_info = {
 static const struct kfd_device_info arcturus_device_info = {
 	.asic_family = CHIP_ARCTURUS,
 	.asic_name = "arcturus",
+	.gfx_target_version = 90008,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -402,6 +419,7 @@ static const struct kfd_device_info arcturus_device_info = {
 static const struct kfd_device_info aldebaran_device_info = {
 	.asic_family = CHIP_ALDEBARAN,
 	.asic_name = "aldebaran",
+	.gfx_target_version = 90010,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd	= 24,
 	.doorbell_size	= 8,
@@ -420,6 +438,7 @@ static const struct kfd_device_info aldebaran_device_info = {
 static const struct kfd_device_info renoir_device_info = {
 	.asic_family = CHIP_RENOIR,
 	.asic_name = "renoir",
+	.gfx_target_version = 90002,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -438,6 +457,7 @@ static const struct kfd_device_info renoir_device_info = {
 static const struct kfd_device_info navi10_device_info = {
 	.asic_family = CHIP_NAVI10,
 	.asic_name = "navi10",
+	.gfx_target_version = 100100,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -456,6 +476,7 @@ static const struct kfd_device_info navi10_device_info = {
 static const struct kfd_device_info navi12_device_info = {
 	.asic_family = CHIP_NAVI12,
 	.asic_name = "navi12",
+	.gfx_target_version = 100101,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -474,6 +495,7 @@ static const struct kfd_device_info navi12_device_info = {
 static const struct kfd_device_info navi14_device_info = {
 	.asic_family = CHIP_NAVI14,
 	.asic_name = "navi14",
+	.gfx_target_version = 100102,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -492,6 +514,7 @@ static const struct kfd_device_info navi14_device_info = {
 static const struct kfd_device_info sienna_cichlid_device_info = {
 	.asic_family = CHIP_SIENNA_CICHLID,
 	.asic_name = "sienna_cichlid",
+	.gfx_target_version = 100300,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -510,6 +533,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = {
 static const struct kfd_device_info navy_flounder_device_info = {
 	.asic_family = CHIP_NAVY_FLOUNDER,
 	.asic_name = "navy_flounder",
+	.gfx_target_version = 100301,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -528,6 +552,7 @@ static const struct kfd_device_info navy_flounder_device_info = {
 static const struct kfd_device_info vangogh_device_info = {
 	.asic_family = CHIP_VANGOGH,
 	.asic_name = "vangogh",
+	.gfx_target_version = 100303,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -546,6 +571,7 @@ static const struct kfd_device_info vangogh_device_info = {
 static const struct kfd_device_info dimgrey_cavefish_device_info = {
 	.asic_family = CHIP_DIMGREY_CAVEFISH,
 	.asic_name = "dimgrey_cavefish",
+	.gfx_target_version = 100302,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -564,6 +590,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = {
 static const struct kfd_device_info beige_goby_device_info = {
 	.asic_family = CHIP_BEIGE_GOBY,
 	.asic_name = "beige_goby",
+	.gfx_target_version = 100304,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -582,6 +609,7 @@ static const struct kfd_device_info beige_goby_device_info = {
 static const struct kfd_device_info yellow_carp_device_info = {
 	.asic_family = CHIP_YELLOW_CARP,
 	.asic_name = "yellow_carp",
+	.gfx_target_version = 100305,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
@@ -600,6 +628,7 @@ static const struct kfd_device_info yellow_carp_device_info = {
 static const struct kfd_device_info cyan_skillfish_device_info = {
 	.asic_family = CHIP_CYAN_SKILLFISH,
 	.asic_name = "cyan_skillfish",
+	.gfx_target_version = 100103,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 8a5dfda224bf..ab83b0de6b22 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -196,6 +196,7 @@ struct kfd_event_interrupt_class {
 struct kfd_device_info {
 	enum amd_asic_type asic_family;
 	const char *asic_name;
+	uint32_t gfx_target_version;
 	const struct kfd_event_interrupt_class *event_interrupt_class;
 	unsigned int max_pasid_bits;
 	unsigned int max_no_of_hqd;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 8a2c6fc438c0..21ec8a18cad2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -714,7 +714,8 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd,
 	if (err)
 		goto err_alloc_mem;
 
-	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv);
+	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem,
+			pdd->drm_priv, NULL);
 	if (err)
 		goto err_map_mem;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index c7b364e4a287..7df69b77bc5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3019,7 +3019,8 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	struct svm_range *prange;
 	uint32_t prefetch_loc = KFD_IOCTL_SVM_LOCATION_UNDEFINED;
 	uint32_t location = KFD_IOCTL_SVM_LOCATION_UNDEFINED;
-	uint32_t flags = 0xffffffff;
+	uint32_t flags_and = 0xffffffff;
+	uint32_t flags_or = 0;
 	int gpuidx;
 	uint32_t i;
 
@@ -3046,12 +3047,12 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 			get_accessible = true;
 			break;
 		case KFD_IOCTL_SVM_ATTR_SET_FLAGS:
+		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
 			get_flags = true;
 			break;
 		case KFD_IOCTL_SVM_ATTR_GRANULARITY:
 			get_granularity = true;
 			break;
-		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
 		case KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE:
 		case KFD_IOCTL_SVM_ATTR_NO_ACCESS:
 			fallthrough;
@@ -3069,7 +3070,8 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	if (!node) {
 		pr_debug("range attrs not found return default values\n");
 		svm_range_set_default_attributes(&location, &prefetch_loc,
-						 &granularity, &flags);
+						 &granularity, &flags_and);
+		flags_or = flags_and;
 		if (p->xnack_enabled)
 			bitmap_copy(bitmap_access, svms->bitmap_supported,
 				    MAX_GPU_INSTANCE);
@@ -3115,8 +3117,10 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 			bitmap_and(bitmap_aip, bitmap_aip,
 				   prange->bitmap_aip, MAX_GPU_INSTANCE);
 		}
-		if (get_flags)
-			flags &= prange->flags;
+		if (get_flags) {
+			flags_and &= prange->flags;
+			flags_or |= prange->flags;
+		}
 
 		if (get_granularity && prange->granularity < granularity)
 			granularity = prange->granularity;
@@ -3150,7 +3154,10 @@ fill_values:
 				attrs[i].type = KFD_IOCTL_SVM_ATTR_NO_ACCESS;
 			break;
 		case KFD_IOCTL_SVM_ATTR_SET_FLAGS:
-			attrs[i].value = flags;
+			attrs[i].value = flags_and;
+			break;
+		case KFD_IOCTL_SVM_ATTR_CLR_FLAGS:
+			attrs[i].value = ~flags_or;
 			break;
 		case KFD_IOCTL_SVM_ATTR_GRANULARITY:
 			attrs[i].value = (uint32_t)granularity;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index ef992dd2da3a..98cca5f2b27f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -478,6 +478,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			      dev->node_props.simd_per_cu);
 	sysfs_show_32bit_prop(buffer, offs, "max_slots_scratch_cu",
 			      dev->node_props.max_slots_scratch_cu);
+	sysfs_show_32bit_prop(buffer, offs, "gfx_target_version",
+			      dev->node_props.gfx_target_version);
 	sysfs_show_32bit_prop(buffer, offs, "vendor_id",
 			      dev->node_props.vendor_id);
 	sysfs_show_32bit_prop(buffer, offs, "device_id",
@@ -1360,6 +1362,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	dev->node_props.simd_arrays_per_engine =
 		cu_info.num_shader_arrays_per_engine;
 
+	dev->node_props.gfx_target_version = gpu->device_info->gfx_target_version;
 	dev->node_props.vendor_id = gpu->pdev->vendor;
 	dev->node_props.device_id = gpu->pdev->device;
 	dev->node_props.capability |=
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index 8b48c6692007..a8db017c9b8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -78,6 +78,7 @@ struct kfd_node_properties {
 	uint32_t simd_per_cu;
 	uint32_t max_slots_scratch_cu;
 	uint32_t engine_id;
+	uint32_t gfx_target_version;
 	uint32_t vendor_id;
 	uint32_t device_id;
 	uint32_t location_id;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 91fb72c96545..718e123a3230 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -27,6 +27,10 @@
 
 AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o
 
+ifdef CONFIG_DRM_AMD_DC_DCN
+AMDGPUDM += dc_fpu.o
+endif
+
 ifneq ($(CONFIG_DRM_AMD_DC),)
 AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o amdgpu_dm_psr.o
 endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 986c9d29d686..3e28f17c84fa 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1066,19 +1066,15 @@ static void event_mall_stutter(struct work_struct *work)
 
 static struct vblank_workqueue *vblank_create_workqueue(struct amdgpu_device *adev, struct dc *dc)
 {
-
-	int max_caps = dc->caps.max_links;
 	struct vblank_workqueue *vblank_work;
-	int i = 0;
 
-	vblank_work = kcalloc(max_caps, sizeof(*vblank_work), GFP_KERNEL);
+	vblank_work = kzalloc(sizeof(*vblank_work), GFP_KERNEL);
 	if (ZERO_OR_NULL_PTR(vblank_work)) {
 		kfree(vblank_work);
 		return NULL;
 	}
 
-	for (i = 0; i < max_caps; i++)
-		INIT_WORK(&vblank_work[i].mall_work, event_mall_stutter);
+	INIT_WORK(&vblank_work->mall_work, event_mall_stutter);
 
 	return vblank_work;
 }
@@ -1548,6 +1544,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 	}
 
 	hdr = (const struct dmcub_firmware_header_v1_0 *)adev->dm.dmub_fw->data;
+	adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].ucode_id =
@@ -1561,7 +1558,6 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 			 adev->dm.dmcub_fw_version);
 	}
 
-	adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
 
 	adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL);
 	dmub_srv = adev->dm.dmub_srv;
@@ -9620,7 +9616,12 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
 		} else if (amdgpu_freesync_vid_mode && aconnector &&
 			   is_freesync_video_mode(&new_crtc_state->mode,
 						  aconnector)) {
-			set_freesync_fixed_config(dm_new_crtc_state);
+			struct drm_display_mode *high_mode;
+
+			high_mode = get_highest_refresh_rate_mode(aconnector, false);
+			if (!drm_mode_equal(&new_crtc_state->mode, high_mode)) {
+				set_freesync_fixed_config(dm_new_crtc_state);
+			}
 		}
 
 		ret = dm_atomic_get_state(state, &dm_state);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
index 46a33f64cf8e..fdcaea22b456 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
@@ -637,6 +637,30 @@ TRACE_EVENT(amdgpu_refresh_rate_track,
 		  __entry->refresh_rate_ns)
 );
 
+TRACE_EVENT(dcn_fpu,
+	    TP_PROTO(bool begin, const char *function, const int line, const int recursion_depth),
+	    TP_ARGS(begin, function, line, recursion_depth),
+
+	    TP_STRUCT__entry(
+			     __field(bool, begin)
+			     __field(const char *, function)
+			     __field(int, line)
+			     __field(int, recursion_depth)
+	    ),
+	    TP_fast_assign(
+			   __entry->begin = begin;
+			   __entry->function = function;
+			   __entry->line = line;
+			   __entry->recursion_depth = recursion_depth;
+	    ),
+	    TP_printk("%s: recursion_depth: %d: %s()+%d:",
+		      __entry->begin ? "begin" : "end",
+		      __entry->recursion_depth,
+		      __entry->function,
+		      __entry->line
+	    )
+);
+
 #endif /* _AMDGPU_DM_TRACE_H_ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
new file mode 100644
index 000000000000..c9f47d167472
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dc_trace.h"
+
+#if defined(CONFIG_X86)
+#include <asm/fpu/api.h>
+#elif defined(CONFIG_PPC64)
+#include <asm/switch_to.h>
+#include <asm/cputable.h>
+#endif
+
+/**
+ * DOC: DC FPU manipulation overview
+ *
+ * DC core uses FPU operations in multiple parts of the code, which requires a
+ * more specialized way to manage these areas' entrance. To fulfill this
+ * requirement, we created some wrapper functions that encapsulate
+ * kernel_fpu_begin/end to better fit our need in the display component. In
+ * summary, in this file, you can find functions related to FPU operation
+ * management.
+ */
+
+static DEFINE_PER_CPU(int, fpu_recursion_depth);
+
+/**
+ * dc_assert_fp_enabled - Check if FPU protection is enabled
+ *
+ * This function tells if the code is already under FPU protection or not. A
+ * function that works as an API for a set of FPU operations can use this
+ * function for checking if the caller invoked it after DC_FP_START(). For
+ * example, take a look at dcn2x.c file.
+ */
+inline void dc_assert_fp_enabled(void)
+{
+	int *pcpu, depth = 0;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	depth = *pcpu;
+	put_cpu_ptr(&fpu_recursion_depth);
+
+	ASSERT(depth > 1);
+}
+
+/**
+ * dc_fpu_begin - Enables FPU protection
+ * @function_name: A string containing the function name for debug purposes
+ *   (usually __func__)
+ *
+ * @line: A line number where DC_FP_START was invoked for debug purpose
+ *   (usually __LINE__)
+ *
+ * This function is responsible for managing the use of kernel_fpu_begin() with
+ * the advantage of providing an event trace for debugging.
+ *
+ * Note: Do not call this function directly; always use DC_FP_START().
+ */
+void dc_fpu_begin(const char *function_name, const int line)
+{
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu += 1;
+
+	if (*pcpu == 1) {
+#if defined(CONFIG_X86)
+		kernel_fpu_begin();
+#elif defined(CONFIG_PPC64)
+		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
+			preempt_disable();
+			enable_kernel_vsx();
+		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
+			preempt_disable();
+			enable_kernel_altivec();
+		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
+			preempt_disable();
+			enable_kernel_fp();
+		}
+#endif
+	}
+
+	TRACE_DCN_FPU(true, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
+}
+
+/**
+ * dc_fpu_end - Disable FPU protection
+ * @function_name: A string containing the function name for debug purposes
+ * @line: A-line number where DC_FP_END was invoked for debug purpose
+ *
+ * This function is responsible for managing the use of kernel_fpu_end() with
+ * the advantage of providing an event trace for debugging.
+ *
+ * Note: Do not call this function directly; always use DC_FP_END().
+ */
+void dc_fpu_end(const char *function_name, const int line)
+{
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu -= 1;
+	if (*pcpu <= 0) {
+#if defined(CONFIG_X86)
+		kernel_fpu_end();
+#elif defined(CONFIG_PPC64)
+		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
+			disable_kernel_vsx();
+			preempt_enable();
+		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
+			disable_kernel_altivec();
+			preempt_enable();
+		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
+			disable_kernel_fp();
+			preempt_enable();
+		}
+#endif
+	}
+
+	TRACE_DCN_FPU(false, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h
new file mode 100644
index 000000000000..b8275b397920
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_FPU_H__
+#define __DC_FPU_H__
+
+void dc_assert_fp_enabled(void);
+void dc_fpu_begin(const char *function_name, const int line);
+void dc_fpu_end(const char *function_name, const int line);
+
+#endif /* __DC_FPU_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index c6f494f0dcea..6185f9475fa2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -66,9 +66,11 @@ int rn_get_active_display_cnt_wa(
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_stream_state *stream = context->streams[i];
 
+		/* Extend the WA to DP for Linux*/
 		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A ||
 				stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
-				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK ||
+				stream->signal == SIGNAL_TYPE_DISPLAY_PORT)
 			tmds_present = true;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index f56e061d35bc..cd025c12f17b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -3595,29 +3595,12 @@ static bool dpcd_read_sink_ext_caps(struct dc_link *link)
 bool dp_retrieve_lttpr_cap(struct dc_link *link)
 {
 	uint8_t lttpr_dpcd_data[6];
-	bool vbios_lttpr_enable = false;
-	bool vbios_lttpr_interop = false;
-	struct dc_bios *bios = link->dc->ctx->dc_bios;
+	bool vbios_lttpr_enable = link->dc->caps.vbios_lttpr_enable;
+	bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware;
 	enum dc_status status = DC_ERROR_UNEXPECTED;
 	bool is_lttpr_present = false;
 
 	memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data));
-	/* Query BIOS to determine if LTTPR functionality is forced on by system */
-	if (bios->funcs->get_lttpr_caps) {
-		enum bp_result bp_query_result;
-		uint8_t is_vbios_lttpr_enable = 0;
-
-		bp_query_result = bios->funcs->get_lttpr_caps(bios, &is_vbios_lttpr_enable);
-		vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
-	}
-
-	if (bios->funcs->get_lttpr_interop) {
-		enum bp_result bp_query_result;
-		uint8_t is_vbios_interop_enabled = 0;
-
-		bp_query_result = bios->funcs->get_lttpr_interop(bios, &is_vbios_interop_enabled);
-		vbios_lttpr_interop = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled;
-	}
 
 	/*
 	 * Logic to determine LTTPR mode
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
index 1a89d565c92e..de80a9ea4cfa 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
@@ -305,7 +305,7 @@ struct link_encoder *link_enc_cfg_get_next_avail_link_enc(
 	const struct dc_state *state)
 {
 	struct link_encoder *link_enc = NULL;
-	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
+	enum engine_id eng_id;
 
 	eng_id = find_first_avail_link_enc(dc->ctx, state);
 	if (eng_id != ENGINE_ID_UNKNOWN)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 1596f6b7fed7..a60396d5be44 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1030,7 +1030,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 
 	/* Timing borders are part of vactive that we are also supposed to skip in addition
 	 * to any stream dst offset. Since dm logic assumes dst is in addressable
-	 * space we need to add the the left and top borders to dst offsets temporarily.
+	 * space we need to add the left and top borders to dst offsets temporarily.
 	 * TODO: fix in DM, stream dst is supposed to be in vactive
 	 */
 	pipe_ctx->stream->dst.x += timing->h_border_left;
@@ -1051,6 +1051,11 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	/* depends on scaling ratios and recout, does not calculate offset yet */
 	calculate_viewport_size(pipe_ctx);
 
+	/* Stopgap for validation of ODM + MPO on one side of screen case */
+	if (pipe_ctx->plane_res.scl_data.viewport.height < 1 ||
+			pipe_ctx->plane_res.scl_data.viewport.width < 1)
+		return false;
+
 	/*
 	 * LB calculations depend on vp size, h/v_active and scaling ratios
 	 * Setting line buffer pixel depth to 24bpp yields banding
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index a948f4f48935..62c222d0402f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -45,7 +45,7 @@
 /* forward declaration */
 struct aux_payload;
 
-#define DC_VER "3.2.146"
+#define DC_VER "3.2.147"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -183,6 +183,8 @@ struct dc_caps {
 	unsigned int cursor_cache_size;
 	struct dc_plane_cap planes[MAX_PLANES];
 	struct dc_color_caps color;
+	bool vbios_lttpr_aware;
+	bool vbios_lttpr_enable;
 };
 
 struct dc_bug_wa {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_trace.h b/drivers/gpu/drm/amd/display/dc/dc_trace.h
index d2615357269b..c711797e5c9e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_trace.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_trace.h
@@ -37,3 +37,6 @@
 
 #define TRACE_DCN_CLOCK_STATE(dcn_clocks) \
 	trace_amdgpu_dm_dc_clocks_state(dcn_clocks)
+
+#define TRACE_DCN_FPU(begin, function, line, ref_count) \
+	trace_dcn_fpu(begin, function, line, ref_count)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 7fa9fc656b0c..f6e747f25ebe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -464,7 +464,7 @@ void optc2_lock_doublebuffer_enable(struct timing_generator *optc)
 
 	REG_UPDATE_2(OTG_GLOBAL_CONTROL1,
 			MASTER_UPDATE_LOCK_DB_X,
-			h_blank_start - 200 - 1,
+			(h_blank_start - 200 - 1) / optc1->opp_count,
 			MASTER_UPDATE_LOCK_DB_Y,
 			v_blank_start - 1);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 0b1cd1dbed8b..e3e01b17c164 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -35,6 +35,8 @@
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
 
+#include "dml/dcn2x/dcn2x.h"
+
 #include "dcn10/dcn10_hubp.h"
 #include "dcn10/dcn10_ipp.h"
 #include "dcn20_hubbub.h"
@@ -1974,43 +1976,6 @@ void dcn20_split_stream_for_mpc(
 	ASSERT(primary_pipe->plane_state);
 }
 
-void dcn20_populate_dml_writeback_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
-{
-	int pipe_cnt, i;
-
-	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
-		struct dc_writeback_info *wb_info = &res_ctx->pipe_ctx[i].stream->writeback_info[0];
-
-		if (!res_ctx->pipe_ctx[i].stream)
-			continue;
-
-		/* Set writeback information */
-		pipes[pipe_cnt].dout.wb_enable = (wb_info->wb_enabled == true) ? 1 : 0;
-		pipes[pipe_cnt].dout.num_active_wb++;
-		pipes[pipe_cnt].dout.wb.wb_src_height = wb_info->dwb_params.cnv_params.crop_height;
-		pipes[pipe_cnt].dout.wb.wb_src_width = wb_info->dwb_params.cnv_params.crop_width;
-		pipes[pipe_cnt].dout.wb.wb_dst_width = wb_info->dwb_params.dest_width;
-		pipes[pipe_cnt].dout.wb.wb_dst_height = wb_info->dwb_params.dest_height;
-		pipes[pipe_cnt].dout.wb.wb_htaps_luma = 1;
-		pipes[pipe_cnt].dout.wb.wb_vtaps_luma = 1;
-		pipes[pipe_cnt].dout.wb.wb_htaps_chroma = wb_info->dwb_params.scaler_taps.h_taps_c;
-		pipes[pipe_cnt].dout.wb.wb_vtaps_chroma = wb_info->dwb_params.scaler_taps.v_taps_c;
-		pipes[pipe_cnt].dout.wb.wb_hratio = 1.0;
-		pipes[pipe_cnt].dout.wb.wb_vratio = 1.0;
-		if (wb_info->dwb_params.out_format == dwb_scaler_mode_yuv420) {
-			if (wb_info->dwb_params.output_depth == DWB_OUTPUT_PIXEL_DEPTH_8BPC)
-				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_8;
-			else
-				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_10;
-		} else
-			pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_444_32;
-
-		pipe_cnt++;
-	}
-
-}
-
 int dcn20_populate_dml_pipes_from_context(
 		struct dc *dc,
 		struct dc_state *context,
@@ -2392,7 +2357,9 @@ int dcn20_populate_dml_pipes_from_context(
 	}
 
 	/* populate writeback information */
+	DC_FP_START();
 	dc->res_pool->funcs->populate_dml_writeback_from_context(dc, res_ctx, pipes);
+	DC_FP_END();
 
 	return pipe_cnt;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index c8f3127bbcdf..6ec8ff45f0f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -58,8 +58,6 @@ struct pipe_ctx *dcn20_acquire_idle_pipe_for_layer(
 		struct dc_state *state,
 		const struct resource_pool *pool,
 		struct dc_stream_state *stream);
-void dcn20_populate_dml_writeback_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
 
 struct stream_encoder *dcn20_stream_encoder_create(
 	enum engine_id eng_id,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index f27fc2acac57..fbbdf9976183 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -35,6 +35,8 @@
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
 
+#include "dml/dcn2x/dcn2x.h"
+
 #include "clk_mgr.h"
 #include "dcn10/dcn10_hubp.h"
 #include "dcn10/dcn10_ipp.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 596c97dce67e..253654d605c2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -2617,6 +2617,26 @@ static bool dcn30_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	/* read VBIOS LTTPR caps */
+	{
+		if (ctx->dc_bios->funcs->get_lttpr_caps) {
+			enum bp_result bp_query_result;
+			uint8_t is_vbios_lttpr_enable = 0;
+
+			bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable);
+			dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
+		}
+
+		if (ctx->dc_bios->funcs->get_lttpr_interop) {
+			enum bp_result bp_query_result;
+			uint8_t is_vbios_interop_enabled = 0;
+
+			bp_query_result = ctx->dc_bios->funcs->get_lttpr_interop(ctx->dc_bios,
+					&is_vbios_interop_enabled);
+			dc->caps.vbios_lttpr_aware = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled;
+		}
+	}
+
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
 	else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 833ab13fa834..dc7823d23ba8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -146,8 +146,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc = {
 
 		.min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */
 		.num_states = 1,
-		.sr_exit_time_us = 26.5,
-		.sr_enter_plus_exit_time_us = 31,
+		.sr_exit_time_us = 35.5,
+		.sr_enter_plus_exit_time_us = 40,
 		.urgent_latency_us = 4.0,
 		.urgent_latency_pixel_data_only_us = 4.0,
 		.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 38c010afade1..cd3248dc31d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -1968,6 +1968,22 @@ static bool dcn31_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	/* read VBIOS LTTPR caps */
+	{
+		if (ctx->dc_bios->funcs->get_lttpr_caps) {
+			enum bp_result bp_query_result;
+			uint8_t is_vbios_lttpr_enable = 0;
+
+			bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable);
+			dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
+		}
+
+		/* interop bit is implicit */
+		{
+			dc->caps.vbios_lttpr_aware = true;
+		}
+	}
+
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
 	else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 45862167e6ce..56055df2e8d2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -58,6 +58,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
@@ -70,6 +72,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(fram
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_rcflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_rcflags)
@@ -91,6 +94,7 @@ DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
+DML += dcn2x/dcn2x.o
 DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 DML += dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 799bae229e67..2091dd8c252d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -488,7 +488,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index 6a6d5970d1d5..1a0c14e465fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -488,7 +488,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index dc1c81a6e377..287e31052b30 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -482,7 +482,7 @@ static void get_meta_and_pte_attr(
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 			- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c
new file mode 100644
index 000000000000..c58522436291
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "resource.h"
+
+#include "dcn2x.h"
+
+/**
+ * DOC: DCN2x FPU manipulation Overview
+ *
+ * The DCN architecture relies on FPU operations, which require special
+ * compilation flags and the use of kernel_fpu_begin/end functions; ideally, we
+ * want to avoid spreading FPU access across multiple files. With this idea in
+ * mind, this file aims to centralize all DCN20 and DCN2.1 (DCN2x) functions
+ * that require FPU access in a single place. Code in this file follows the
+ * following code pattern:
+ *
+ * 1. Functions that use FPU operations should be isolated in static functions.
+ * 2. The FPU functions should have the noinline attribute to ensure anything
+ *    that deals with FP register is contained within this call.
+ * 3. All function that needs to be accessed outside this file requires a
+ *    public interface that not uses any FPU reference.
+ * 4. Developers **must not** use DC_FP_START/END in this file, but they need
+ *    to ensure that the caller invokes it before access any function available
+ *    in this file. For this reason, public functions in this file must invoke
+ *    dc_assert_fp_enabled();
+ *
+ * Let's expand a little bit more the idea in the code pattern. To fully
+ * isolate FPU operations in a single place, we must avoid situations where
+ * compilers spill FP values to registers due to FP enable in a specific C
+ * file. Note that even if we isolate all FPU functions in a single file and
+ * call its interface from other files, the compiler might enable the use of
+ * FPU before we call DC_FP_START. Nevertheless, it is the programmer's
+ * responsibility to invoke DC_FP_START/END in the correct place. To highlight
+ * situations where developers forgot to use the FP protection before calling
+ * the DC FPU interface functions, we introduce a helper that checks if the
+ * function is invoked under FP protection. If not, it will trigger a kernel
+ * warning.
+ */
+
+void dcn20_populate_dml_writeback_from_context(struct dc *dc,
+					       struct resource_context *res_ctx,
+					       display_e2e_pipe_params_st *pipes)
+{
+	int pipe_cnt, i;
+
+	dc_assert_fp_enabled();
+
+	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_writeback_info *wb_info = &res_ctx->pipe_ctx[i].stream->writeback_info[0];
+
+		if (!res_ctx->pipe_ctx[i].stream)
+			continue;
+
+		/* Set writeback information */
+		pipes[pipe_cnt].dout.wb_enable = (wb_info->wb_enabled == true) ? 1 : 0;
+		pipes[pipe_cnt].dout.num_active_wb++;
+		pipes[pipe_cnt].dout.wb.wb_src_height = wb_info->dwb_params.cnv_params.crop_height;
+		pipes[pipe_cnt].dout.wb.wb_src_width = wb_info->dwb_params.cnv_params.crop_width;
+		pipes[pipe_cnt].dout.wb.wb_dst_width = wb_info->dwb_params.dest_width;
+		pipes[pipe_cnt].dout.wb.wb_dst_height = wb_info->dwb_params.dest_height;
+		pipes[pipe_cnt].dout.wb.wb_htaps_luma = 1;
+		pipes[pipe_cnt].dout.wb.wb_vtaps_luma = 1;
+		pipes[pipe_cnt].dout.wb.wb_htaps_chroma = wb_info->dwb_params.scaler_taps.h_taps_c;
+		pipes[pipe_cnt].dout.wb.wb_vtaps_chroma = wb_info->dwb_params.scaler_taps.v_taps_c;
+		pipes[pipe_cnt].dout.wb.wb_hratio = 1.0;
+		pipes[pipe_cnt].dout.wb.wb_vratio = 1.0;
+		if (wb_info->dwb_params.out_format == dwb_scaler_mode_yuv420) {
+			if (wb_info->dwb_params.output_depth == DWB_OUTPUT_PIXEL_DEPTH_8BPC)
+				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_8;
+			else
+				pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_420_10;
+		} else {
+			pipes[pipe_cnt].dout.wb.wb_pixel_format = dm_444_32;
+		}
+
+		pipe_cnt++;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.h b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.h
index ed422012c8c6..331547ba0713 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn2x/dcn2x.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: MIT */
 /*
- * Copyright 2014 Advanced Micro Devices, Inc.
+ * Copyright 2021 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -19,12 +20,15 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
+ * Authors: AMD
+ *
  */
 
-#ifndef __DCE_VIRTUAL_H__
-#define __DCE_VIRTUAL_H__
-
-extern const struct amdgpu_ip_block_version dce_virtual_ip_block;
+#ifndef __DCN2X_H__
+#define __DCN2X_H__
 
-#endif
+void dcn20_populate_dml_writeback_from_context(struct dc *dc,
+					       struct resource_context *res_ctx,
+					       display_e2e_pipe_params_st *pipes);
 
+#endif /* __DCN2X_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
index 04601a767a8f..0d934fae1c3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
@@ -549,7 +549,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	log2_meta_req_bytes = 6; // meta request is 64b and is 8x8byte meta element
 
 				 // each 64b meta request for dcn is 8x8 meta elements and
-				 // a meta element covers one 256b block of the the data surface.
+				 // a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3; // meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
 		- log2_meta_req_height;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index 3def093ef88e..c23905bc733a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -563,7 +563,7 @@ static void get_meta_and_pte_attr(
 	log2_meta_req_bytes = 6;	// meta request is 64b and is 8x8byte meta element
 
 	// each 64b meta request for dcn is 8x8 meta elements and
-	// a meta element covers one 256b block of the the data surface.
+	// a meta element covers one 256b block of the data surface.
 	log2_meta_req_height = log2_blk256_height + 3;	// meta req is 8x8 byte, each byte represent 1 blk256
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element - log2_meta_req_height;
 	meta_req_width = 1 << log2_meta_req_width;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index 414da64f5734..8f2b1684c231 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -456,7 +456,7 @@ static void dml1_rq_dlg_get_row_heights(
 	log2_meta_req_bytes = 6; /* meta request is 64b and is 8x8byte meta element */
 
 	/* each 64b meta request for dcn is 8x8 meta elements and
-	 * a meta element covers one 256b block of the the data surface.
+	 * a meta element covers one 256b block of the data surface.
 	 */
 	log2_meta_req_height = log2_blk256_height + 3; /* meta req is 8x8 */
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
@@ -718,7 +718,7 @@ static void get_surf_rq_param(
 	log2_meta_req_bytes = 6; /* meta request is 64b and is 8x8byte meta element */
 
 	/* each 64b meta request for dcn is 8x8 meta elements and
-	 * a meta element covers one 256b block of the the data surface.
+	 * a meta element covers one 256b block of the data surface.
 	 */
 	log2_meta_req_height = log2_blk256_height + 3; /* meta req is 8x8 byte, each byte represent 1 blk256 */
 	log2_meta_req_width = log2_meta_req_bytes + 8 - log2_bytes_per_element
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 126c2f3a4dd3..f50cae252de4 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -51,38 +51,9 @@
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-#if defined(CONFIG_X86)
-#include <asm/fpu/api.h>
-#define DC_FP_START() kernel_fpu_begin()
-#define DC_FP_END() kernel_fpu_end()
-#elif defined(CONFIG_PPC64)
-#include <asm/switch_to.h>
-#include <asm/cputable.h>
-#define DC_FP_START() { \
-	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
-		preempt_disable(); \
-		enable_kernel_vsx(); \
-	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
-		preempt_disable(); \
-		enable_kernel_altivec(); \
-	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
-		preempt_disable(); \
-		enable_kernel_fp(); \
-	} \
-}
-#define DC_FP_END() { \
-	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
-		disable_kernel_vsx(); \
-		preempt_enable(); \
-	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
-		disable_kernel_altivec(); \
-		preempt_enable(); \
-	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
-		disable_kernel_fp(); \
-		preempt_enable(); \
-	} \
-}
-#endif
+#include "amdgpu_dm/dc_fpu.h"
+#define DC_FP_START() dc_fpu_begin(__func__, __LINE__)
+#define DC_FP_END() dc_fpu_end(__func__, __LINE__)
 #endif
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 02921ad22310..aa2707e469c1 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -47,10 +47,10 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0xe599e0896
+#define DMUB_FW_VERSION_GIT_HASH 0x6d13d5e2c
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 76
+#define DMUB_FW_VERSION_REVISION 77
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 61446170056e..6820012e3b6e 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -270,11 +270,13 @@ void dmub_dcn31_set_outbox1_rptr(struct dmub_srv *dmub, uint32_t rptr_offset)
 
 bool dmub_dcn31_is_hw_init(struct dmub_srv *dmub)
 {
-	uint32_t is_hw_init;
+	union dmub_fw_boot_status status;
+	uint32_t is_enable;
 
-	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_hw_init);
+	status.all = REG_READ(DMCUB_SCRATCH0);
+	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enable);
 
-	return is_hw_init != 0;
+	return is_enable != 0 && status.bits.dal_fw;
 }
 
 bool dmub_dcn31_is_supported(struct dmub_srv *dmub)
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
index a9ad00e017a5..1a8a6a350789 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_offset.h
@@ -508,6 +508,10 @@
 #define regCP_ME2_PIPE2_INT_STATUS_BASE_IDX                                                             0
 #define regCP_ME2_PIPE3_INT_STATUS                                                                      0x1094
 #define regCP_ME2_PIPE3_INT_STATUS_BASE_IDX                                                             0
+#define regCP_ME1_INT_STAT_DEBUG                                                                        0x1095
+#define regCP_ME1_INT_STAT_DEBUG_BASE_IDX                                                               0
+#define regCP_ME2_INT_STAT_DEBUG                                                                        0x1096
+#define regCP_ME2_INT_STAT_DEBUG_BASE_IDX                                                               0
 #define regCC_GC_EDC_CONFIG                                                                             0x1098
 #define regCC_GC_EDC_CONFIG_BASE_IDX                                                                    0
 #define regCP_ME1_PIPE_PRIORITY_CNTS                                                                    0x1099
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
index bc4d2997cb51..049221262e5c 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_2_sh_mask.h
@@ -2989,6 +2989,60 @@
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC2_INT_STATUS_MASK                                                     0x20000000L
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC1_INT_STATUS_MASK                                                     0x40000000L
 #define CP_ME1_PIPE3_INT_STATUS__GENERIC0_INT_STATUS_MASK                                                     0x80000000L
+//CP_ME1_INT_STAT_DEBUG
+#define CP_ME1_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED__SHIFT                                           0xc
+#define CP_ME1_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED__SHIFT                                            0xd
+#define CP_ME1_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED__SHIFT                                               0xe
+#define CP_ME1_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS__SHIFT                                                0xf
+#define CP_ME1_INT_STAT_DEBUG__GPF_INT_ASSERTED__SHIFT                                                        0x10
+#define CP_ME1_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED__SHIFT                                           0x11
+#define CP_ME1_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED__SHIFT                                                   0x17
+#define CP_ME1_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED__SHIFT                                               0x18
+#define CP_ME1_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED__SHIFT                                                 0x1a
+#define CP_ME1_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED__SHIFT                                         0x1b
+#define CP_ME1_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED__SHIFT                                                   0x1d
+#define CP_ME1_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED__SHIFT                                                   0x1e
+#define CP_ME1_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED__SHIFT                                                   0x1f
+#define CP_ME1_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED_MASK                                             0x00001000L
+#define CP_ME1_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED_MASK                                              0x00002000L
+#define CP_ME1_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED_MASK                                                 0x00004000L
+#define CP_ME1_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS_MASK                                                  0x00008000L
+#define CP_ME1_INT_STAT_DEBUG__GPF_INT_ASSERTED_MASK                                                          0x00010000L
+#define CP_ME1_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED_MASK                                             0x00020000L
+#define CP_ME1_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED_MASK                                                     0x00800000L
+#define CP_ME1_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED_MASK                                                 0x01000000L
+#define CP_ME1_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED_MASK                                                   0x04000000L
+#define CP_ME1_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED_MASK                                           0x08000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED_MASK                                                     0x20000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED_MASK                                                     0x40000000L
+#define CP_ME1_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED_MASK                                                     0x80000000L
+//CP_ME2_INT_STAT_DEBUG
+#define CP_ME2_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED__SHIFT                                           0xc
+#define CP_ME2_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED__SHIFT                                            0xd
+#define CP_ME2_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED__SHIFT                                               0xe
+#define CP_ME2_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS__SHIFT                                                0xf
+#define CP_ME2_INT_STAT_DEBUG__GPF_INT_ASSERTED__SHIFT                                                        0x10
+#define CP_ME2_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED__SHIFT                                           0x11
+#define CP_ME2_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED__SHIFT                                                   0x17
+#define CP_ME2_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED__SHIFT                                               0x18
+#define CP_ME2_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED__SHIFT                                                 0x1a
+#define CP_ME2_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED__SHIFT                                         0x1b
+#define CP_ME2_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED__SHIFT                                                   0x1d
+#define CP_ME2_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED__SHIFT                                                   0x1e
+#define CP_ME2_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED__SHIFT                                                   0x1f
+#define CP_ME2_INT_STAT_DEBUG__CMP_QUERY_STATUS_INT_ASSERTED_MASK                                             0x00001000L
+#define CP_ME2_INT_STAT_DEBUG__DEQUEUE_REQUEST_INT_ASSERTED_MASK                                              0x00002000L
+#define CP_ME2_INT_STAT_DEBUG__CP_ECC_ERROR_INT_ASSERTED_MASK                                                 0x00004000L
+#define CP_ME2_INT_STAT_DEBUG__SUA_VIOLATION_INT_STATUS_MASK                                                  0x00008000L
+#define CP_ME2_INT_STAT_DEBUG__GPF_INT_ASSERTED_MASK                                                          0x00010000L
+#define CP_ME2_INT_STAT_DEBUG__WRM_POLL_TIMEOUT_INT_ASSERTED_MASK                                             0x00020000L
+#define CP_ME2_INT_STAT_DEBUG__PRIV_REG_INT_ASSERTED_MASK                                                     0x00800000L
+#define CP_ME2_INT_STAT_DEBUG__OPCODE_ERROR_INT_ASSERTED_MASK                                                 0x01000000L
+#define CP_ME2_INT_STAT_DEBUG__TIME_STAMP_INT_ASSERTED_MASK                                                   0x04000000L
+#define CP_ME2_INT_STAT_DEBUG__RESERVED_BIT_ERROR_INT_ASSERTED_MASK                                           0x08000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC2_INT_ASSERTED_MASK                                                     0x20000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC1_INT_ASSERTED_MASK                                                     0x40000000L
+#define CP_ME2_INT_STAT_DEBUG__GENERIC0_INT_ASSERTED_MASK                                                     0x80000000L
 //CP_ME2_PIPE0_INT_STATUS
 #define CP_ME2_PIPE0_INT_STATUS__CMP_QUERY_STATUS_INT_STATUS__SHIFT                                           0xc
 #define CP_ME2_PIPE0_INT_STATUS__DEQUEUE_REQUEST_INT_STATUS__SHIFT                                            0xd
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 3811e58dd857..44955458fe38 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -590,7 +590,7 @@ struct atom_firmware_info_v3_4 {
 	uint8_t  board_i2c_feature_id;            // enum of atom_board_i2c_feature_id_def
 	uint8_t  board_i2c_feature_gpio_id;       // i2c id find in gpio_lut data table gpio_id
 	uint8_t  board_i2c_feature_slave_addr;
-	uint8_t  reserved3;
+	uint8_t  ras_rom_i2c_slave_addr;
 	uint16_t bootup_mvddq_mv;
 	uint16_t bootup_mvpp_mv;
 	uint32_t zfbstartaddrin16mb;
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 1d3765b873df..6239c30fcd5f 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -282,6 +282,7 @@ enum smu_clk_type {
        __SMU_DUMMY_MAP(TDC),                           	\
        __SMU_DUMMY_MAP(THERMAL),                       	\
        __SMU_DUMMY_MAP(GFX_PER_CU_CG),                 	\
+       __SMU_DUMMY_MAP(DATA_CALCULATIONS),                 	\
        __SMU_DUMMY_MAP(RM),                            	\
        __SMU_DUMMY_MAP(DS_DCEFCLK),                    	\
        __SMU_DUMMY_MAP(ACDC),                          	\
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
index 3fea2430dec0..dc91eb608791 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h
@@ -26,7 +26,7 @@
 #include "amdgpu_smu.h"
 
 #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
-#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x03
+#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x07
 
 /* MP Apertures */
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h
index 5627de734246..c5e26d619bf0 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h
@@ -111,7 +111,9 @@ typedef struct {
   uint32_t InWhisperMode        : 1;
   uint32_t spare0               : 1;
   uint32_t ZstateStatus         : 4;
-  uint32_t spare1               :12;
+  uint32_t spare1               : 4;
+  uint32_t DstateFun            : 4;
+  uint32_t DstateDev            : 4;
   // MP1_EXT_SCRATCH2
   uint32_t P2JobHandler         :24;
   uint32_t RsmuPmiP2FinishedCnt : 8;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 43c3f6e755e7..7dd92bdf7ffb 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1580,7 +1580,7 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
 		}
 
 		if (smu10_data->gfx_actual_soft_min_freq > smu10_data->gfx_actual_soft_max_freq) {
-			pr_err("The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+			pr_err("The setting minimum sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
 					smu10_data->gfx_actual_soft_min_freq, smu10_data->gfx_actual_soft_max_freq);
 			return -EINVAL;
 		}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 90e40aacb8f6..261ef8ca862e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -353,8 +353,7 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t val;
 
-	if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO ||
-	    powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) {
+	if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO) {
 		val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0);
 		smu_baco->platform_support =
 			(val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true :
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 18681dc458da..bcaaa086fc2f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -256,7 +256,7 @@ static int vangogh_tables_init(struct smu_context *smu)
 	return 0;
 
 err3_out:
-	kfree(smu_table->clocks_table);
+	kfree(smu_table->watermarks_table);
 err2_out:
 	kfree(smu_table->gpu_metrics_table);
 err1_out:
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 856eeaf293b8..562783d0302f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -150,7 +150,7 @@ static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = {
 };
 
 static const struct cmn2asic_mapping aldebaran_feature_mask_map[SMU_FEATURE_COUNT] = {
-	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_PREFETCHER_BIT, 		FEATURE_DATA_CALCULATIONS),
+	ALDEBARAN_FEA_MAP(SMU_FEATURE_DATA_CALCULATIONS_BIT, 		FEATURE_DATA_CALCULATIONS),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_GFXCLK_BIT, 			FEATURE_DPM_GFXCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_UCLK_BIT, 			FEATURE_DPM_UCLK_BIT),
 	ALDEBARAN_FEA_MAP(SMU_FEATURE_DPM_SOCCLK_BIT, 			FEATURE_DPM_SOCCLK_BIT),
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 4b86e8b45009..83e8b8547f9b 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -2802,8 +2802,8 @@ ucMaxNBVoltageHigh:     Voltage regulator dependent PWM value. High 8 bits of  t
 ucMinNBVoltageHigh:     Voltage regulator dependent PWM value. High 8 bits of the value for the min voltage.Set this one to 0x00 if VC without PWM or no VC at all.
 
 
-usInterNBVoltageLow:    Voltage regulator dependent PWM value. The value makes the the voltage >=Min NB voltage but <=InterNBVoltageHigh. Set this to 0x0000 if VC without PWM or no VC at all.
-usInterNBVoltageHigh:   Voltage regulator dependent PWM value. The value makes the the voltage >=InterNBVoltageLow but <=Max NB voltage.Set this to 0x0000 if VC without PWM or no VC at all.
+usInterNBVoltageLow:    Voltage regulator dependent PWM value. The value makes the voltage >=Min NB voltage but <=InterNBVoltageHigh. Set this to 0x0000 if VC without PWM or no VC at all.
+usInterNBVoltageHigh:   Voltage regulator dependent PWM value. The value makes the voltage >=InterNBVoltageLow but <=Max NB voltage.Set this to 0x0000 if VC without PWM or no VC at all.
 */
 
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 36a888e1b179..eeb590d2dec2 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -28,6 +28,7 @@
 
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "avivod.h"
@@ -1414,10 +1415,15 @@ void evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base,
 			 bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(EVERGREEN_GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? EVERGREEN_GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(EVERGREEN_GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ba724198b72e..2dd85ba1faa2 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -162,6 +162,8 @@ void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
 void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	uint32_t crtc_pitch, pitch_pixels;
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
 	int i;
 
@@ -169,6 +171,13 @@ void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool
 	/* update the scanout addresses */
 	WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
 
+	/* update pitch */
+	pitch_pixels = fb->pitches[0] / fb->format->cpp[0];
+	crtc_pitch = DIV_ROUND_UP(pitch_pixels * fb->format->cpp[0] * 8,
+				  fb->format->cpp[0] * 8 * 8);
+	crtc_pitch |= crtc_pitch << 16;
+	WREG32(RADEON_CRTC_PITCH + radeon_crtc->crtc_offset, crtc_pitch);
+
 	/* Wait for update_pending to go high. */
 	for (i = 0; i < rdev->usec_timeout; i++) {
 		if (RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET)
diff --git a/drivers/gpu/drm/radeon/r300_reg.h b/drivers/gpu/drm/radeon/r300_reg.h
index 00c0d2ba22d3..60d5413bafa1 100644
--- a/drivers/gpu/drm/radeon/r300_reg.h
+++ b/drivers/gpu/drm/radeon/r300_reg.h
@@ -353,7 +353,7 @@
 #       define R300_PVS_CNTL_1_PROGRAM_START_SHIFT   0
 #       define R300_PVS_CNTL_1_POS_END_SHIFT         10
 #       define R300_PVS_CNTL_1_PROGRAM_END_SHIFT     20
-/* Addresses are relative the the vertex program parameters area. */
+/* Addresses are relative the vertex program parameters area. */
 #define R300_VAP_PVS_CNTL_2                 0x22D4
 #       define R300_PVS_CNTL_2_PARAM_OFFSET_SHIFT 0
 #       define R300_PVS_CNTL_2_PARAM_COUNT_SHIFT  16
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index cec03238e14d..ac8c3251b616 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -406,7 +406,7 @@ void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell)
 
 /*
  * radeon_wb_*()
- * Writeback is the the method by which the the GPU updates special pages
+ * Writeback is the method by which the GPU updates special pages
  * in memory with the status of certain GPU events (fences, ring pointers,
  * etc.).
  */
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 0b206b052972..6640b7c947fe 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -54,6 +54,7 @@ radeonfb_open(struct fb_info *info, int user)
 	struct radeon_fbdev *rfbdev = info->par;
 	struct radeon_device *rdev = rfbdev->rdev;
 	int ret = pm_runtime_get_sync(rdev->ddev->dev);
+
 	if (ret < 0 && ret != -EACCES) {
 		pm_runtime_mark_last_busy(rdev->ddev->dev);
 		pm_runtime_put_autosuspend(rdev->ddev->dev);
@@ -196,9 +197,8 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
 		radeon_bo_check_tiling(rbo, 0, 0);
 	ret = radeon_bo_kmap(rbo, NULL);
 	radeon_bo_unreserve(rbo);
-	if (ret) {
+	if (ret)
 		goto out_unref;
-	}
 
 	*gobj_p = gobj;
 	return 0;
@@ -294,9 +294,6 @@ static int radeonfb_create(struct drm_fb_helper *helper,
 	return 0;
 
 out:
-	if (rbo) {
-
-	}
 	if (fb && ret) {
 		drm_gem_object_put(gobj);
 		drm_framebuffer_unregister_private(fb);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 18f2c2e0dfb3..e9c47ec28ade 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -50,7 +50,7 @@
  * for GPU/CPU synchronization.  When the fence is written,
  * it is expected that all buffers associated with that fence
  * are no longer in use by the associated ring on the GPU and
- * that the the relevant GPU caches have been flushed.  Whether
+ * that the relevant GPU caches have been flushed.  Whether
  * we use a scratch register or memory location depends on the asic
  * and whether writeback is enabled.
  */
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 36a38adaaea9..bb53016f3138 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -41,7 +41,7 @@
  * (uncached system pages).
  * Each VM has an ID associated with it and there is a page table
  * associated with each VMID.  When execting a command buffer,
- * the kernel tells the the ring what VMID to use for that command
+ * the kernel tells the ring what VMID to use for that command
  * buffer.  VMIDs are allocated dynamically as commands are submitted.
  * The userspace drivers maintain their own address space and the kernel
  * sets up their pages tables accordingly when they submit their
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index b2d22e25eee1..b87dd551e939 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -41,6 +41,7 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "radeon.h"
@@ -118,6 +119,7 @@ void avivo_wait_for_vblank(struct radeon_device *rdev, int crtc)
 void rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
 	int i;
 
@@ -125,9 +127,13 @@ void rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, boo
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(AVIVO_D1GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	WREG32(AVIVO_D1GRPH_SECONDARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
 	       (u32)crtc_base);
 	WREG32(AVIVO_D1GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 74499307285b..e592e57be1bb 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -32,6 +32,7 @@
 
 #include <drm/drm_device.h>
 #include <drm/radeon_drm.h>
+#include <drm/drm_fourcc.h>
 
 #include "atom.h"
 #include "avivod.h"
@@ -809,6 +810,7 @@ u32 rv770_get_xclk(struct radeon_device *rdev)
 void rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, bool async)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct drm_framebuffer *fb = radeon_crtc->base.primary->fb;
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
 	int i;
 
@@ -816,9 +818,13 @@ void rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base, boo
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
 
-	/* update the scanout addresses */
+	/* flip at hsync for async, default is vsync */
 	WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset,
 	       async ? AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN : 0);
+	/* update pitch */
+	WREG32(AVIVO_D1GRPH_PITCH + radeon_crtc->crtc_offset,
+	       fb->pitches[0] / fb->format->cpp[0]);
+	/* update the scanout addresses */
 	if (radeon_crtc->crtc_id) {
 		WREG32(D2GRPH_SECONDARY_SURFACE_ADDRESS_HIGH, upper_32_bits(crtc_base));
 		WREG32(D2GRPH_PRIMARY_SURFACE_ADDRESS_HIGH, upper_32_bits(crtc_base));
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 3cb5b5dd9f77..af96af174dc4 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -31,9 +31,10 @@
  * - 1.3 - Add SMI events support
  * - 1.4 - Indicate new SRAM EDC bit in device properties
  * - 1.5 - Add SVM API
+ * - 1.6 - Query clear flags in SVM get_attr API
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 5
+#define KFD_IOCTL_MINOR_VERSION 6
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -575,18 +576,19 @@ struct kfd_ioctl_svm_attribute {
  * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC or
  * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC resepctively. For
  * @KFD_IOCTL_SVM_ATTR_SET_FLAGS, flags of all pages will be
- * aggregated by bitwise AND. The minimum  migration granularity
- * throughout the range will be returned for
- * @KFD_IOCTL_SVM_ATTR_GRANULARITY.
+ * aggregated by bitwise AND. That means, a flag will be set in the
+ * output, if that flag is set for all pages in the range. For
+ * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS, flags of all pages will be
+ * aggregated by bitwise NOR. That means, a flag will be set in the
+ * output, if that flag is clear for all pages in the range.
+ * The minimum migration granularity throughout the range will be
+ * returned for @KFD_IOCTL_SVM_ATTR_GRANULARITY.
  *
  * Querying of accessibility attributes works by initializing the
  * attribute type to @KFD_IOCTL_SVM_ATTR_ACCESS and the value to the
  * GPUID being queried. Multiple attributes can be given to allow
  * querying multiple GPUIDs. The ioctl function overwrites the
  * attribute type to indicate the access for the specified GPU.
- *
- * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS is invalid for
- * @KFD_IOCTL_SVM_OP_GET_ATTR.
  */
 struct kfd_ioctl_svm_args {
 	__u64 start_addr;