Merge tag 'drm-next-2025-03-28' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie: "Outside of drm there are some rust patches from Danilo who maintains that area in here, and some pieces for drm header check tests. The major things in here are a new driver supporting the touchbar displays on M1/M2, the nova-core stub driver which is just the vehicle for adding rust abstractions and start developing a real driver inside of. xe adds support for SVM with a non-driver specific SVM core abstraction that will hopefully be useful for other drivers, along with support for shrinking for TTM devices. I'm sure xe and AMD support new devices, but the pipeline depth on these things is hard to know what they end up being in the marketplace! uapi: - add mediatek tiled fourcc - add support for notifying userspace on device wedged new driver: - appletbdrm: support for Apple Touchbar displays on m1/m2 - nova-core: skeleton rust driver to develop nova inside off firmware: - add some rust firmware pieces rust: - add 'LocalModule' type alias component: - add helper to query bound status fbdev: - fbtft: remove access to page->index media: - cec: tda998x: import driver from drm dma-buf: - add fast path for single fence merging tests: - fix lockdep warnings atomic: - allow full modeset on connector changes - clarify semantics of allow_modeset and drm_atomic_helper_check - async-flip: support on arbitary planes - writeback: fix UAF - Document atomic-state history format-helper: - support ARGB8888 to ARGB4444 conversions buddy: - fix multi-root cleanup ci: - update IGT dp: - support extended wake timeout - mst: fix RAD to string conversion - increase DPCD eDP control CAP size to 5 bytes - add DPCD eDP v1.5 definition - add helpers for LTTPR transparent mode panic: - encode QR code according to Fido 2.2 scheduler: - add parameter struct for init - improve job peek/pop operations - optimise drm_sched_job struct layout ttm: - refactor pool allocation - add helpers for TTM shrinker panel-orientation: - add a bunch of new quirks panel: - convert panels to multi-style functions - edp: Add support for B140UAN04.4, BOE NV140FHM-NZ, CSW MNB601LS1-3, LG LP079QX1-SP0V, MNE007QS3-7, STA 116QHD024002, Starry 116KHD024006, Lenovo T14s Gen6 Snapdragon - himax-hx83102: Add support for CSOT PNA957QT1-1, Kingdisplay kd110n11-51ie, Starry 2082109qfh040022-50e - visionox-r66451: use multi-style MIPI-DSI functions - raydium-rm67200: Add driver for Raydium RM67200 - simple: Add support for BOE AV123Z7M-N17, BOE AV123Z7M-N17 - sony-td4353-jdi: Use MIPI-DSI multi-func interface - summit: Add driver for Apple Summit display panel - visionox-rm692e5: Add driver for Visionox RM692E5 bridge: - pass full atomic state to various callbacks - adv7511: Report correct capabilities - it6505: Fix HDCP V compare - snd65dsi86: fix device IDs - nwl-dsi: set bridge type - ti-sn65si83: add error recovery and set bridge type - synopsys: add HDMI audio support xe: - support device-wedged event - add mmap support for PCI memory barrier - perf pmu integration and expose per-engien activity - add EU stall sampling support - GPU SVM and Xe SVM implementation - use TTM shrinker - add survivability mode to allow the driver to do firmware updates in critical failure states - PXP HWDRM support for MTL and LNL - expose package/vram temps over hwmon - enable DP tunneling - drop mmio_ext abstraction - Reject BO evcition if BO is bound to current VM - Xe suballocator improvements - re-use display vmas when possible - add GuC Buffer Cache abstraction - PCI ID update for Panther Lake and Battlemage - Enable SRIOV for Panther Lake - Refactor VRAM manager location i915: - enable extends wake timeout - support device-wedged event - Enable DP 128b/132b SST DSC - FBC dirty rectangle support for display version 30+ - convert i915/xe to drm client setup - Compute HDMI PLLS for rates not in fixed tables - Allow DSB usage when PSR is enabled on LNL+ - Enable panel replay without full modeset - Enable async flips with compressed buffers on ICL+ - support luminance based brightness via DPCD for eDP - enable VRR enable/disable without full modeset - allow GuC SLPC default strategies on MTL+ for performance - lots of display refactoring in move to struct intel_display amdgpu: - add device wedged event - support async page flips on overlay planes - enable broadcast RGB drm property - add info ioctl for virt mode - OEM i2c support for RGB lights - GC 11.5.2 + 11.5.3 support - SDMA 6.1.3 support - NBIO 7.9.1 + 7.11.2 support - MMHUB 1.8.1 + 3.3.2 support - DCN 3.6.0 support - Add dynamic workload profile switching for GC 10-12 - support larger VBIOS sizes - Mark gttsize parameters as deprecated - Initial JPEG queue resset support amdkfd: - add KFD per process flags for setting precision - sync pasid values between KGD and KFD - improve GTT/VRAM handling for APUs - fix user queue validation on GC7/8 - SDMA queue reset support raedeon: - rs400 hyperz fix i2c: - td998x: drop platform_data, split driver into media and bridge ast: - transmitter chip detection refactoring - vbios display mode refactoring - astdp: fix connection status and filter unsupported modes - cursor handling refactoring imagination: - check job dependencies with sched helper ivpu: - improve command queue handling - use workqueue for IRQ handling - add support HW fault injection - locking fixes mgag200: - add support for G200eH5 msm: - dpu: add concurrent writeback support for DPU 10.x+ - use LTTPR helpers - GPU: - Fix obscure GMU suspend failure - Expose syncobj timeline support - Extend GPU devcoredump with pagetable info - a623 support - Fix a6xx gen1/gen2 indexed-register blocks in gpu snapshot / devcoredump - Display: - Add cpu-cfg interconnect paths on SM8560 and SM8650 - Introduce KMS OMMU fault handler, causing devcoredump snapshot - Fixed error pointer dereference in msm_kms_init_aspace() - DPU: - Fix mode_changing handling - Add writeback support on SM6150 (QCS615) - Fix DSC programming in 1:1:1 topology - Reworked hardware resource allocation, moving it to the CRTC code - Enabled support for Concurrent WriteBack (CWB) on SM8650 - Enabled CDM blocks on all relevant platforms - Reworked debugfs interface for BW/clocks debugging - Clear perf params before calculating bw - Support YUV formats on writeback - Fixed double inclusion - Fixed writeback in YUV formats when using cloned output, Dropped wb2_formats_rgb - Corrected dpu_crtc_check_mode_changed and struct dpu_encoder_virt kerneldocs - Fixed uninitialized variable in dpu_crtc_kickoff_clone_mode() - DSI: - DSC-related fixes - Rework clock programming - DSI PHY: - Fix 7nm (and lower) PHY programming - Add proper DT schema definitions for DSI PHY clocks - HDMI: - Rework the driver, enabling the use of the HDMI Connector framework - Bindings: - Added eDP PHY on SA8775P nouveau: - move drm_slave_encoder interface into driver - nvkm: refactor GSP RPC - use LTTPR helpers mediatek: - HDMI fixup and refinement - add MT8188 dsc compatible - MT8365 SoC support panthor: - Expose sizes of intenral BOs via fdinfo - Fix race between reset and suspend - Improve locking qaic: - Add support for AIC200 renesas: - Fix limits in DT bindings rockchip: - support rk3562-mali - rk3576: Add HDMI support - vop2: Add new display modes on RK3588 HDMI0 up to 4K - Don't change HDMI reference clock rate - Fix DT bindings - analogix_dp: add eDP support - fix shutodnw solomon: - Set SPI device table to silence warnings - Fix pixel and scanline encoding v3d: - handle clock vc4: - Use drm_exec - Use dma-resv for wait-BO ioctl - Remove seqno infrastructure virtgpu: - Support partial mappings of GEM objects - Reserve VGA resources during initialization - Fix UAF in virtgpu_dma_buf_free_obj() - Add panic support vkms: - Switch to a managed modesetting pipeline - Add support for ARGB8888 - fix UAf xlnx: - Set correct DMA segment size - use mutex guards - Fix error handling - Fix docs" * tag 'drm-next-2025-03-28' of https://gitlab.freedesktop.org/drm/kernel: (1762 commits) drm/amd/pm: Update feature list for smu_v13_0_6 drm/amdgpu: Add parameter documentation for amdgpu_sync_fence drm/amdgpu/discovery: optionally use fw based ip discovery drm/amdgpu/discovery: use specific ip_discovery.bin for legacy asics drm/amdgpu/discovery: check ip_discovery fw file available drm/amd/pm: Remove unnecessay UQ10 to UINT conversion drm/amd/pm: Remove unnecessay UQ10 to UINT conversion drm/amdgpu/sdma_v4_4_2: update VM flush implementation for SDMA drm/amdgpu: Optimize VM invalidation engine allocation and synchronize GPU TLB flush drm/amd/amdgpu: Increase max rings to enable SDMA page ring drm/amdgpu: Decode deferred error type in gfx aca bank parser drm/amdgpu/gfx11: Add Cleaner Shader Support for GFX11.5 GPUs drm/amdgpu/mes: clean up SDMA HQD loop drm/amdgpu/mes: enable compute pipes across all MEC drm/amdgpu/mes: drop MES 10.x leftovers drm/amdgpu/mes: optimize compute loop handling drm/amdgpu/sdma: guilty tracking is per instance drm/amdgpu/sdma: fix engine reset handling drm/amdgpu: remove invalid usage of sched.ready drm/amdgpu: add cleaner shader trace point ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2025-03-29 03:44:52 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2025-03-29 03:44:52 +0300
commit: 0c86b42439b6c11d758b3392a21117934fef00c1 (patch)
tree: 6aa7071476067661867af33767cc0e1863397a04 /drivers/gpu/drm/amd/amdgpu
parent: 51aad189f8e0f926c0977d180cae6a78df445f27 (diff)
parent: cf05922d63e2ae6a9b1b52ff5236a44c3b29f78c (diff)
download: linux-0c86b42439b6c11d758b3392a21117934fef00c1.tar.xz
204 files changed, 8774 insertions, 5496 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 5b21674b07fb..aacc810cabb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -65,7 +65,8 @@ amdgpu-y += amdgpu_device.o amdgpu_doorbell_mgr.o amdgpu_kms.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
 	amdgpu_fw_attestation.o amdgpu_securedisplay.o \
 	amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o \
-	amdgpu_ring_mux.o amdgpu_xcp.o amdgpu_seq64.o amdgpu_aca.o amdgpu_dev_coredump.o
+	amdgpu_ring_mux.o amdgpu_xcp.o amdgpu_seq64.o amdgpu_aca.o amdgpu_dev_coredump.o \
+	amdgpu_cper.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 69895fccb474..6d83ccfa42ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -109,6 +109,7 @@
 #include "amdgpu_mca.h"
 #include "amdgpu_aca.h"
 #include "amdgpu_ras.h"
+#include "amdgpu_cper.h"
 #include "amdgpu_xcp.h"
 #include "amdgpu_seq64.h"
 #include "amdgpu_reg_state.h"
@@ -415,6 +416,7 @@ bool amdgpu_get_bios(struct amdgpu_device *adev);
 bool amdgpu_read_bios(struct amdgpu_device *adev);
 bool amdgpu_soc15_read_bios_from_rom(struct amdgpu_device *adev,
 				     u8 *bios, u32 length_bytes);
+void amdgpu_bios_release(struct amdgpu_device *adev);
 /*
  * Clocks
  */
@@ -1090,6 +1092,9 @@ struct amdgpu_device {
 	/* ACA */
 	struct amdgpu_aca		aca;
 
+	/* CPER */
+	struct amdgpu_cper		cper;
+
 	struct amdgpu_ip_block          ip_blocks[AMDGPU_MAX_IP_NUM];
 	uint32_t		        harvest_ip_mask;
 	int				num_ip_blocks;
@@ -1149,6 +1154,7 @@ struct amdgpu_device {
 	struct ratelimit_state		throttling_logging_rs;
 	uint32_t                        ras_hw_enabled;
 	uint32_t                        ras_enabled;
+	bool                            ras_default_ecc_enabled;
 
 	bool                            no_hw_access;
 	struct pci_saved_state          *pci_state;
@@ -1186,12 +1192,24 @@ struct amdgpu_device {
 	bool                            debug_use_vram_fw_buf;
 	bool                            debug_enable_ras_aca;
 	bool                            debug_exp_resets;
+	bool                            debug_disable_gpu_ring_reset;
 
-	bool				enforce_isolation[MAX_XCP];
-	/* Added this mutex for cleaner shader isolation between GFX and compute processes */
+	/* Protection for the following isolation structure */
 	struct mutex                    enforce_isolation_mutex;
+	bool				enforce_isolation[MAX_XCP];
+	struct amdgpu_isolation {
+		void			*owner;
+		struct dma_fence	*spearhead;
+		struct amdgpu_sync	active;
+		struct amdgpu_sync	prev;
+	} isolation[MAX_XCP];
 
 	struct amdgpu_init_level *init_lvl;
+
+	/* This flag is used to determine how VRAM allocations are handled for APUs
+	 * in KFD: VRAM or GTT.
+	 */
+	bool                            apu_prefer_gtt;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
@@ -1470,6 +1488,9 @@ void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev,
 struct dma_fence *amdgpu_device_get_gang(struct amdgpu_device *adev);
 struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 					    struct dma_fence *gang);
+struct dma_fence *amdgpu_device_enforce_isolation(struct amdgpu_device *adev,
+						  struct amdgpu_ring *ring,
+						  struct amdgpu_job *job);
 bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev);
 ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring);
 ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index 9d6345146495..dc47f5fd4ea1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -30,16 +30,6 @@
 
 typedef int bank_handler_t(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type, void *data);
 
-struct aca_banks {
-	int nr_banks;
-	struct list_head list;
-};
-
-struct aca_hwip {
-	int hwid;
-	int mcatype;
-};
-
 static struct aca_hwip aca_hwid_mcatypes[ACA_HWIP_TYPE_COUNT] = {
 	ACA_BANK_HWID(SMU,	0x01,	0x01),
 	ACA_BANK_HWID(PCS_XGMI, 0x50,	0x00),
@@ -111,7 +101,7 @@ static struct aca_regs_dump {
 	{"STATUS",		ACA_REG_IDX_STATUS},
 	{"ADDR",		ACA_REG_IDX_ADDR},
 	{"MISC",		ACA_REG_IDX_MISC0},
-	{"CONFIG",		ACA_REG_IDX_CONFG},
+	{"CONFIG",		ACA_REG_IDX_CONFIG},
 	{"IPID",		ACA_REG_IDX_IPID},
 	{"SYND",		ACA_REG_IDX_SYND},
 	{"DESTAT",		ACA_REG_IDX_DESTAT},
@@ -168,7 +158,7 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 		if (ret)
 			return ret;
 
-		bank.type = type;
+		bank.smu_err_type = type;
 
 		aca_smu_bank_dump(adev, i, count, &bank, qctx);
 
@@ -394,6 +384,56 @@ static bool aca_bank_should_update(struct amdgpu_device *adev, enum aca_smu_type
 	return ret;
 }
 
+static void aca_banks_generate_cper(struct amdgpu_device *adev,
+				    enum aca_smu_type type,
+				    struct aca_banks *banks,
+				    int count)
+{
+	struct aca_bank_node *node;
+	struct aca_bank *bank;
+	int r;
+
+	if (!adev->cper.enabled)
+		return;
+
+	if (!banks || !count) {
+		dev_warn(adev->dev, "fail to generate cper records\n");
+		return;
+	}
+
+	/* UEs must be encoded into separate CPER entries */
+	if (type == ACA_SMU_TYPE_UE) {
+		struct aca_banks de_banks;
+
+		aca_banks_init(&de_banks);
+		list_for_each_entry(node, &banks->list, node) {
+			bank = &node->bank;
+			if (bank->aca_err_type == ACA_ERROR_TYPE_DEFERRED) {
+				r = aca_banks_add_bank(&de_banks, bank);
+				if (r)
+					dev_warn(adev->dev, "fail to add de banks, ret = %d\n", r);
+			} else {
+				if (amdgpu_cper_generate_ue_record(adev, bank))
+					dev_warn(adev->dev, "fail to generate ue cper records\n");
+			}
+		}
+
+		if (!list_empty(&de_banks.list)) {
+			if (amdgpu_cper_generate_ce_records(adev, &de_banks, de_banks.nr_banks))
+				dev_warn(adev->dev, "fail to generate de cper records\n");
+		}
+
+		aca_banks_release(&de_banks);
+	} else {
+		/*
+		 * SMU_TYPE_CE banks are combined into 1 CPER entries,
+		 * they could be CEs or DEs or both
+		 */
+		if (amdgpu_cper_generate_ce_records(adev, banks, count))
+			dev_warn(adev->dev, "fail to generate ce cper records\n");
+	}
+}
+
 static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type,
 			    bank_handler_t handler, struct ras_query_context *qctx, void *data)
 {
@@ -431,6 +471,8 @@ static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type,
 	if (ret)
 		goto err_release_banks;
 
+	aca_banks_generate_cper(adev, type, &banks, count);
+
 err_release_banks:
 	aca_banks_release(&banks);
 
@@ -516,6 +558,10 @@ static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *h
 	if (ret)
 		return ret;
 
+	/* DEs may contain in CEs or UEs */
+	if (type != ACA_ERROR_TYPE_DEFERRED)
+		aca_log_aca_error(handle, ACA_ERROR_TYPE_DEFERRED, err_data);
+
 	return aca_log_aca_error(handle, type, err_data);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
index f3289d289913..6b180f1b33fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
@@ -76,12 +76,24 @@ struct ras_query_context;
 #define mmSMNAID_XCD1_MCA_SMU		0x38430400	/* SMN AID XCD1 */
 #define mmSMNXCD_XCD0_MCA_SMU		0x40430400	/* SMN XCD XCD0 */
 
+#define ACA_BANK_ERR_IS_DEFFERED(bank)                                \
+	(ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \
+	 ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS]))
+
+#define ACA_BANK_ERR_CE_DE_DECODE(bank)                             \
+	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
+					  ACA_ERROR_TYPE_CE)
+
+#define ACA_BANK_ERR_UE_DE_DECODE(bank)                             \
+	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
+					  ACA_ERROR_TYPE_UE)
+
 enum aca_reg_idx {
 	ACA_REG_IDX_CTL			= 0,
 	ACA_REG_IDX_STATUS		= 1,
 	ACA_REG_IDX_ADDR		= 2,
 	ACA_REG_IDX_MISC0		= 3,
-	ACA_REG_IDX_CONFG		= 4,
+	ACA_REG_IDX_CONFIG		= 4,
 	ACA_REG_IDX_IPID		= 5,
 	ACA_REG_IDX_SYND		= 6,
 	ACA_REG_IDX_DESTAT		= 8,
@@ -108,13 +120,20 @@ enum aca_error_type {
 };
 
 enum aca_smu_type {
+	ACA_SMU_TYPE_INVALID = -1,
 	ACA_SMU_TYPE_UE = 0,
 	ACA_SMU_TYPE_CE,
 	ACA_SMU_TYPE_COUNT,
 };
 
+struct aca_hwip {
+	int hwid;
+	int mcatype;
+};
+
 struct aca_bank {
-	enum aca_smu_type type;
+	enum aca_error_type aca_err_type;
+	enum aca_smu_type smu_err_type;
 	u64 regs[ACA_MAX_REGS_COUNT];
 };
 
@@ -123,6 +142,11 @@ struct aca_bank_node {
 	struct list_head node;
 };
 
+struct aca_banks {
+	int nr_banks;
+	struct list_head list;
+};
+
 struct aca_bank_info {
 	int die_id;
 	int socket_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index deb0785350e8..4926996f94da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -579,7 +579,7 @@ static int acp_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool acp_is_idle(void *handle)
+static bool acp_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index b8d4e07d2043..b7f8f2ff143d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -394,6 +394,10 @@ static int amdgpu_atif_query_backlight_caps(struct amdgpu_atif *atif)
 			characteristics.max_input_signal;
 	atif->backlight_caps.ac_level = characteristics.ac_level;
 	atif->backlight_caps.dc_level = characteristics.dc_level;
+	atif->backlight_caps.data_points = characteristics.number_of_points;
+	memcpy(atif->backlight_caps.luminance_data,
+	       characteristics.data_points,
+	       sizeof(atif->backlight_caps.luminance_data));
 out:
 	kfree(info);
 	return err;
@@ -1277,11 +1281,7 @@ void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps)
 {
 	struct amdgpu_atif *atif = &amdgpu_acpi_priv.atif;
 
-	caps->caps_valid = atif->backlight_caps.caps_valid;
-	caps->min_input_signal = atif->backlight_caps.min_input_signal;
-	caps->max_input_signal = atif->backlight_caps.max_input_signal;
-	caps->ac_level = atif->backlight_caps.ac_level;
-	caps->dc_level = atif->backlight_caps.dc_level;
+	memcpy(caps, &atif->backlight_caps, sizeof(*caps));
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 2c1b38c5cfc6..4cec3a873995 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -459,7 +459,7 @@ void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev,
 		else
 			mem_info->local_mem_size_private =
 					KFD_XCP_MEMORY_SIZE(adev, xcp->id);
-	} else if (adev->flags & AMD_IS_APU) {
+	} else if (adev->apu_prefer_gtt) {
 		mem_info->local_mem_size_public = (ttm_tt_pages_limit() << PAGE_SHIFT);
 		mem_info->local_mem_size_private = 0;
 	} else {
@@ -555,48 +555,6 @@ out_put:
 	return r;
 }
 
-uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst,
-					  struct amdgpu_device *src)
-{
-	struct amdgpu_device *peer_adev = src;
-	struct amdgpu_device *adev = dst;
-	int ret = amdgpu_xgmi_get_hops_count(adev, peer_adev);
-
-	if (ret < 0) {
-		DRM_ERROR("amdgpu: failed to get  xgmi hops count between node %d and %d. ret = %d\n",
-			adev->gmc.xgmi.physical_node_id,
-			peer_adev->gmc.xgmi.physical_node_id, ret);
-		ret = 0;
-	}
-	return  (uint8_t)ret;
-}
-
-int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
-					    struct amdgpu_device *src,
-					    bool is_min)
-{
-	struct amdgpu_device *adev = dst, *peer_adev;
-	int num_links;
-
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
-		return 0;
-
-	if (src)
-		peer_adev = src;
-
-	/* num links returns 0 for indirect peers since indirect route is unknown. */
-	num_links = is_min ? 1 : amdgpu_xgmi_get_num_links(adev, peer_adev);
-	if (num_links < 0) {
-		DRM_ERROR("amdgpu: failed to get xgmi num links between node %d and %d. ret = %d\n",
-			adev->gmc.xgmi.physical_node_id,
-			peer_adev->gmc.xgmi.physical_node_id, num_links);
-		num_links = 0;
-	}
-
-	/* Aldebaran xGMI DPM is defeatured so assume x16 x 25Gbps for bandwidth. */
-	return (num_links * 16 * 25000)/BITS_PER_BYTE;
-}
-
 int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min)
 {
 	int num_lanes_shift = (is_min ? ffs(adev->pm.pcie_mlw_mask) :
@@ -818,7 +776,7 @@ u64 amdgpu_amdkfd_xcp_memory_size(struct amdgpu_device *adev, int xcp_id)
 		}
 		do_div(tmp, adev->xcp_mgr->num_xcp_per_mem_partition);
 		return ALIGN_DOWN(tmp, PAGE_SIZE);
-	} else if (adev->flags & AMD_IS_APU) {
+	} else if (adev->apu_prefer_gtt) {
 		return (ttm_tt_pages_limit() << PAGE_SHIFT);
 	} else {
 		return adev->gmc.real_vram_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 8af67f18500a..b6ca41859b53 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -47,6 +47,7 @@ enum TLB_FLUSH_TYPE {
 };
 
 struct amdgpu_device;
+struct kfd_process_device;
 struct amdgpu_reset_context;
 
 enum kfd_mem_attachment_type {
@@ -192,7 +193,7 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
 struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo);
 int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni,
 				unsigned long cur_seq, struct kgd_mem *mem);
 int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
@@ -212,9 +213,8 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 }
 
 static inline
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo)
 {
-	return 0;
 }
 
 static inline
@@ -254,11 +254,6 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd,
 				  uint64_t *bo_size, void *metadata_buffer,
 				  size_t buffer_size, uint32_t *metadata_size,
 				  uint32_t *flags, int8_t *xcp_id);
-uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst,
-					  struct amdgpu_device *src);
-int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
-					    struct amdgpu_device *src,
-					    bool is_min);
 int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min);
 int amdgpu_amdkfd_send_close_event_drain_irq(struct amdgpu_device *adev,
 					uint32_t *payload);
@@ -299,14 +294,10 @@ bool amdgpu_amdkfd_compute_active(struct amdgpu_device *adev, uint32_t node_id);
 	(&((struct amdgpu_fpriv *)					\
 		((struct drm_file *)(drm_priv))->driver_priv)->vm)
 
-int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev,
-				     struct amdgpu_vm *avm, u32 pasid);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev,
 					struct amdgpu_vm *avm,
 					void **process_info,
 					struct dma_fence **ef);
-void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev,
-					void *drm_priv);
 uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv);
 size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 					uint8_t xcp_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
index 8dfdb18197c4..7e9f7a280c1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
@@ -189,8 +189,9 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.set_address_watch = kgd_gfx_aldebaran_set_address_watch,
 	.clear_address_watch = kgd_gfx_v9_clear_address_watch,
 	.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
-	.build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info = kgd_gfx_v9_build_dequeue_wait_counts_packet_info,
 	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
 	.hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr,
 	.hqd_reset = kgd_gfx_v9_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 9abf29b58ac7..ffbaa8bc5eea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -415,9 +415,10 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v9_set_address_watch,
 	.clear_address_watch = kgd_gfx_v9_clear_address_watch,
 	.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
-	.build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info = kgd_gfx_v9_build_dequeue_wait_counts_packet_info,
 	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
 	.hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v9_hqd_reset
+	.hqd_reset = kgd_gfx_v9_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
index e2ae714a700f..89a45a9218f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
@@ -509,6 +509,17 @@ static uint32_t kgd_gfx_v9_4_3_clear_address_watch(struct amdgpu_device *adev,
 	return 0;
 }
 
+static uint32_t kgd_gfx_v9_4_3_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+						     int engine, int queue)
+{
+	uint32_t reg_offset = get_sdma_rlc_reg_offset(adev, engine, queue);
+	uint32_t status = RREG32(regSDMA_RLC0_CONTEXT_STATUS + reg_offset);
+	uint32_t doorbell_off = RREG32(regSDMA_RLC0_DOORBELL_OFFSET + reg_offset);
+	bool is_active = !!REG_GET_FIELD(status, SDMA_RLC0_CONTEXT_STATUS, SELECTED);
+
+	return is_active ? doorbell_off >> 2 : 0;
+}
+
 const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_4_3_set_pasid_vmid_mapping,
@@ -530,8 +541,8 @@ const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = {
 	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 	.program_trap_handler_settings =
 				kgd_gfx_v9_program_trap_handler_settings,
-	.build_grace_period_packet_info =
-				kgd_gfx_v9_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info =
+				kgd_gfx_v9_build_dequeue_wait_counts_packet_info,
 	.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
 	.enable_debug_trap = kgd_aldebaran_enable_debug_trap,
 	.disable_debug_trap = kgd_gfx_v9_4_3_disable_debug_trap,
@@ -543,5 +554,6 @@ const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v9_4_3_set_address_watch,
 	.clear_address_watch = kgd_gfx_v9_4_3_clear_address_watch,
 	.hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v9_hqd_reset
+	.hqd_reset = kgd_gfx_v9_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v9_4_3_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 62176d607bef..04ef0ca10541 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -1021,25 +1021,25 @@ void kgd_gfx_v10_get_iq_wait_times(struct amdgpu_device *adev,
 	*wait_times = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_IQ_WAIT_TIME2));
 }
 
-void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
+void kgd_gfx_v10_build_dequeue_wait_counts_packet_info(struct amdgpu_device *adev,
 						uint32_t wait_times,
-						uint32_t grace_period,
+						uint32_t sch_wave,
+						uint32_t que_sleep,
 						uint32_t *reg_offset,
 						uint32_t *reg_data)
 {
 	*reg_data = wait_times;
 
-	/*
-	 * The CP cannont handle a 0 grace period input and will result in
-	 * an infinite grace period being set so set to 1 to prevent this.
-	 */
-	if (grace_period == 0)
-		grace_period = 1;
-
-	*reg_data = REG_SET_FIELD(*reg_data,
-			CP_IQ_WAIT_TIME2,
-			SCH_WAVE,
-			grace_period);
+	if (sch_wave)
+		*reg_data = REG_SET_FIELD(*reg_data,
+				CP_IQ_WAIT_TIME2,
+				SCH_WAVE,
+				sch_wave);
+	if (que_sleep)
+		*reg_data = REG_SET_FIELD(*reg_data,
+				CP_IQ_WAIT_TIME2,
+				QUE_SLEEP,
+				que_sleep);
 
 	*reg_offset = SOC15_REG_OFFSET(GC, 0, mmCP_IQ_WAIT_TIME2);
 }
@@ -1084,6 +1084,12 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev,
 	return 0;
 }
 
+uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					   int engine, int queue)
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -1109,8 +1115,9 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v10_set_address_watch,
 	.clear_address_watch = kgd_gfx_v10_clear_address_watch,
 	.get_iq_wait_times = kgd_gfx_v10_get_iq_wait_times,
-	.build_grace_period_packet_info = kgd_gfx_v10_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info = kgd_gfx_v10_build_dequeue_wait_counts_packet_info,
 	.program_trap_handler_settings = program_trap_handler_settings,
 	.hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v10_hqd_reset
+	.hqd_reset = kgd_gfx_v10_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
index 9efd2dd4fdd7..a4c607c88178 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
@@ -51,9 +51,10 @@ uint32_t kgd_gfx_v10_clear_address_watch(struct amdgpu_device *adev,
 void kgd_gfx_v10_get_iq_wait_times(struct amdgpu_device *adev,
 				uint32_t *wait_times,
 				uint32_t inst);
-void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
+void kgd_gfx_v10_build_dequeue_wait_counts_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
-					       uint32_t grace_period,
+					       uint32_t sch_wave,
+					       uint32_t que_sleep,
 					       uint32_t *reg_offset,
 					       uint32_t *reg_data);
 uint64_t kgd_gfx_v10_hqd_get_pq_addr(struct amdgpu_device *adev,
@@ -65,3 +66,5 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev,
 			      uint32_t queue_id,
 			      uint32_t inst,
 			      unsigned int utimeout);
+uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					   int engine, int queue);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
index c718bedda0ca..6d08bc2781a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
@@ -673,7 +673,7 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = {
 	.set_vm_context_page_table_base = set_vm_context_page_table_base_v10_3,
 	.program_trap_handler_settings = program_trap_handler_settings_v10_3,
 	.get_iq_wait_times = kgd_gfx_v10_get_iq_wait_times,
-	.build_grace_period_packet_info = kgd_gfx_v10_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info = kgd_gfx_v10_build_dequeue_wait_counts_packet_info,
 	.enable_debug_trap = kgd_gfx_v10_enable_debug_trap,
 	.disable_debug_trap = kgd_gfx_v10_disable_debug_trap,
 	.validate_trap_override_request = kgd_gfx_v10_validate_trap_override_request,
@@ -682,5 +682,6 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v10_set_address_watch,
 	.clear_address_watch = kgd_gfx_v10_clear_address_watch,
 	.hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v10_hqd_reset
+	.hqd_reset = kgd_gfx_v10_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
index a4ba49cb22db..e0e6a6a49d90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
@@ -800,6 +800,12 @@ static uint64_t kgd_gfx_v11_hqd_reset(struct amdgpu_device *adev,
 	return 0;
 }
 
+static uint32_t kgd_gfx_v11_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+						  int engine, int queue)
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v11_kfd2kgd = {
 	.program_sh_mem_settings = program_sh_mem_settings_v11,
 	.set_pasid_vmid_mapping = set_pasid_vmid_mapping_v11,
@@ -824,5 +830,6 @@ const struct kfd2kgd_calls gfx_v11_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v11_set_address_watch,
 	.clear_address_watch = kgd_gfx_v11_clear_address_watch,
 	.hqd_get_pq_addr = kgd_gfx_v11_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v11_hqd_reset
+	.hqd_reset = kgd_gfx_v11_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v11_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
index 0dfe7093bd8a..6f0dc23c901b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
@@ -361,6 +361,12 @@ static uint32_t kgd_gfx_v12_clear_address_watch(struct amdgpu_device *adev,
 	return 0;
 }
 
+static uint32_t kgd_gfx_v12_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+						 int engine, int queue)
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v12_kfd2kgd = {
 	.init_interrupts = init_interrupts_v12,
 	.hqd_dump = hqd_dump_v12,
@@ -374,4 +380,5 @@ const struct kfd2kgd_calls gfx_v12_kfd2kgd = {
 	.set_wave_launch_mode = kgd_gfx_v12_set_wave_launch_mode,
 	.set_address_watch = kgd_gfx_v12_set_address_watch,
 	.clear_address_watch = kgd_gfx_v12_clear_address_watch,
+	.hqd_sdma_get_doorbell = kgd_gfx_v12_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 441568163e20..088d09cc7a72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -1077,25 +1077,25 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev,
 				adev->gfx.cu_info.max_waves_per_simd;
 }
 
-void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
+void kgd_gfx_v9_build_dequeue_wait_counts_packet_info(struct amdgpu_device *adev,
 		uint32_t wait_times,
-		uint32_t grace_period,
+		uint32_t sch_wave,
+		uint32_t que_sleep,
 		uint32_t *reg_offset,
 		uint32_t *reg_data)
 {
 	*reg_data = wait_times;
 
-	/*
-	 * The CP cannot handle a 0 grace period input and will result in
-	 * an infinite grace period being set so set to 1 to prevent this.
-	 */
-	if (grace_period == 0)
-		grace_period = 1;
-
-	*reg_data = REG_SET_FIELD(*reg_data,
-			CP_IQ_WAIT_TIME2,
-			SCH_WAVE,
-			grace_period);
+	if (sch_wave)
+		*reg_data = REG_SET_FIELD(*reg_data,
+				CP_IQ_WAIT_TIME2,
+				SCH_WAVE,
+				sch_wave);
+	if (que_sleep)
+		*reg_data = REG_SET_FIELD(*reg_data,
+				CP_IQ_WAIT_TIME2,
+				QUE_SLEEP,
+				que_sleep);
 
 	*reg_offset = SOC15_REG_OFFSET(GC, 0, mmCP_IQ_WAIT_TIME2);
 }
@@ -1131,9 +1131,6 @@ uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev,
 	uint32_t low, high;
 	uint64_t queue_addr = 0;
 
-	if (!amdgpu_gpu_recovery)
-		return 0;
-
 	kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst);
 	amdgpu_gfx_rlc_enter_safe_mode(adev, inst);
 
@@ -1182,9 +1179,6 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev,
 	uint32_t low, high, pipe_reset_data = 0;
 	uint64_t queue_addr = 0;
 
-	if (!amdgpu_gpu_recovery)
-		return 0;
-
 	kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst);
 	amdgpu_gfx_rlc_enter_safe_mode(adev, inst);
 
@@ -1229,6 +1223,13 @@ unlock_out:
 	return queue_addr;
 }
 
+uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					  int engine, int queue)
+
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
@@ -1254,9 +1255,10 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.set_address_watch = kgd_gfx_v9_set_address_watch,
 	.clear_address_watch = kgd_gfx_v9_clear_address_watch,
 	.get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times,
-	.build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info,
+	.build_dequeue_wait_counts_packet_info = kgd_gfx_v9_build_dequeue_wait_counts_packet_info,
 	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
 	.hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr,
-	.hqd_reset = kgd_gfx_v9_hqd_reset
+	.hqd_reset = kgd_gfx_v9_hqd_reset,
+	.hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index b6a91a552aa4..704452ca62f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -97,9 +97,10 @@ uint32_t kgd_gfx_v9_clear_address_watch(struct amdgpu_device *adev,
 void kgd_gfx_v9_get_iq_wait_times(struct amdgpu_device *adev,
 				uint32_t *wait_times,
 				uint32_t inst);
-void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
+void kgd_gfx_v9_build_dequeue_wait_counts_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
-					       uint32_t grace_period,
+					       uint32_t sch_wave,
+					       uint32_t que_sleep,
 					       uint32_t *reg_offset,
 					       uint32_t *reg_data);
 uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev,
@@ -111,3 +112,5 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev,
 			      uint32_t queue_id,
 			      uint32_t inst,
 			      unsigned int utimeout);
+uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					  int engine, int queue);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 1e998f972c30..d2ec4130a316 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -197,7 +197,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 			return -EINVAL;
 
 		vram_size = KFD_XCP_MEMORY_SIZE(adev, xcp_id);
-		if (adev->flags & AMD_IS_APU) {
+		if (adev->apu_prefer_gtt) {
 			system_mem_needed = size;
 			ttm_mem_needed = size;
 		}
@@ -234,7 +234,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	if (adev && xcp_id >= 0) {
 		adev->kfd.vram_used[xcp_id] += vram_needed;
 		adev->kfd.vram_used_aligned[xcp_id] +=
-				(adev->flags & AMD_IS_APU) ?
+				adev->apu_prefer_gtt ?
 				vram_needed :
 				ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
 	}
@@ -262,7 +262,7 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 
 		if (adev) {
 			adev->kfd.vram_used[xcp_id] -= size;
-			if (adev->flags & AMD_IS_APU) {
+			if (adev->apu_prefer_gtt) {
 				adev->kfd.vram_used_aligned[xcp_id] -= size;
 				kfd_mem_limit.system_mem_used -= size;
 				kfd_mem_limit.ttm_mem_used -= size;
@@ -370,40 +370,32 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
 	return 0;
 }
 
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
+/**
+ * amdgpu_amdkfd_remove_all_eviction_fences - Remove all eviction fences
+ * @bo: the BO where to remove the evictions fences from.
+ *
+ * This functions should only be used on release when all references to the BO
+ * are already dropped. We remove the eviction fence from the private copy of
+ * the dma_resv object here since that is what is used during release to
+ * determine of the BO is idle or not.
+ */
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo)
 {
-	struct amdgpu_bo *root = bo;
-	struct amdgpu_vm_bo_base *vm_bo;
-	struct amdgpu_vm *vm;
-	struct amdkfd_process_info *info;
-	struct amdgpu_amdkfd_fence *ef;
-	int ret;
-
-	/* we can always get vm_bo from root PD bo.*/
-	while (root->parent)
-		root = root->parent;
-
-	vm_bo = root->vm_bo;
-	if (!vm_bo)
-		return 0;
-
-	vm = vm_bo->vm;
-	if (!vm)
-		return 0;
-
-	info = vm->process_info;
-	if (!info || !info->eviction_fence)
-		return 0;
+	struct dma_resv *resv = &bo->tbo.base._resv;
+	struct dma_fence *fence, *stub;
+	struct dma_resv_iter cursor;
 
-	ef = container_of(dma_fence_get(&info->eviction_fence->base),
-			struct amdgpu_amdkfd_fence, base);
+	dma_resv_assert_held(resv);
 
-	BUG_ON(!dma_resv_trylock(bo->tbo.base.resv));
-	ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef);
-	dma_resv_unlock(bo->tbo.base.resv);
+	stub = dma_fence_get_stub();
+	dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) {
+		if (!to_amdgpu_amdkfd_fence(fence))
+			continue;
 
-	dma_fence_put(&ef->base);
-	return ret;
+		dma_resv_replace_fences(resv, fence->context, stub,
+					DMA_RESV_USAGE_BOOKKEEP);
+	}
+	dma_fence_put(stub);
 }
 
 static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
@@ -499,7 +491,7 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	if (ret)
 		return ret;
 
-	return amdgpu_sync_fence(sync, vm->last_update);
+	return amdgpu_sync_fence(sync, vm->last_update, GFP_KERNEL);
 }
 
 static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
@@ -603,12 +595,6 @@ kfd_mem_dmamap_dmabuf(struct kfd_mem_attachment *attachment)
 {
 	struct ttm_operation_ctx ctx = {.interruptible = true};
 	struct amdgpu_bo *bo = attachment->bo_va->base.bo;
-	int ret;
-
-	amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
-	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-	if (ret)
-		return ret;
 
 	amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 	return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
@@ -890,7 +876,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	 * if peer device has large BAR. In contrast, access over xGMI is
 	 * allowed for both small and large BAR configurations of peer device
 	 */
-	if ((adev != bo_adev && !(adev->flags & AMD_IS_APU)) &&
+	if ((adev != bo_adev && !adev->apu_prefer_gtt) &&
 	    ((mem->domain == AMDGPU_GEM_DOMAIN_VRAM) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) {
@@ -1263,7 +1249,7 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
-	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update);
+	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
 
 	return 0;
 }
@@ -1287,7 +1273,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 	}
 
-	return amdgpu_sync_fence(sync, bo_va->last_pt_update);
+	return amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
 }
 
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
@@ -1529,27 +1515,6 @@ static void amdgpu_amdkfd_gpuvm_unpin_bo(struct amdgpu_bo *bo)
 	amdgpu_bo_unreserve(bo);
 }
 
-int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev,
-				     struct amdgpu_vm *avm, u32 pasid)
-
-{
-	int ret;
-
-	/* Free the original amdgpu allocated pasid,
-	 * will be replaced with kfd allocated pasid.
-	 */
-	if (avm->pasid) {
-		amdgpu_pasid_free(avm->pasid);
-		amdgpu_vm_set_pasid(adev, avm, 0);
-	}
-
-	ret = amdgpu_vm_set_pasid(adev, avm, pasid);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev,
 					   struct amdgpu_vm *avm,
 					   void **process_info,
@@ -1607,27 +1572,6 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 	}
 }
 
-void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev,
-					    void *drm_priv)
-{
-	struct amdgpu_vm *avm;
-
-	if (WARN_ON(!adev || !drm_priv))
-		return;
-
-	avm = drm_priv_to_vm(drm_priv);
-
-	pr_debug("Releasing process vm %p\n", avm);
-
-	/* The original pasid of amdgpu vm has already been
-	 * released during making a amdgpu vm to a compute vm
-	 * The current pasid is managed by kfd and will be
-	 * released on kfd process destroy. Set amdgpu pasid
-	 * to 0 to avoid duplicate release.
-	 */
-	amdgpu_vm_release_compute(adev, avm);
-}
-
 uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv)
 {
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
@@ -1688,7 +1632,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 		- reserved_for_pt
 		- reserved_for_ras;
 
-	if (adev->flags & AMD_IS_APU) {
+	if (adev->apu_prefer_gtt) {
 		system_mem_available = no_system_mem_limit ?
 					kfd_mem_limit.max_system_mem_limit :
 					kfd_mem_limit.max_system_mem_limit -
@@ -1736,7 +1680,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-		if (adev->flags & AMD_IS_APU) {
+		if (adev->apu_prefer_gtt) {
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_flags = 0;
@@ -1987,7 +1931,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	if (size) {
 		if (!is_imported &&
 		   (mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_VRAM ||
-		   ((adev->flags & AMD_IS_APU) &&
+		   (adev->apu_prefer_gtt &&
 		    mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT)))
 			*size = bo_size;
 		else
@@ -2414,7 +2358,7 @@ static int import_obj_create(struct amdgpu_device *adev,
 	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) &&
-			 !(adev->flags & AMD_IS_APU) ?
+			 !adev->apu_prefer_gtt ?
 			 AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
 
 	(*mem)->mapped_to_gpu_memory = 0;
@@ -2969,7 +2913,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 		}
 		dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
 					DMA_RESV_USAGE_KERNEL, fence) {
-			ret = amdgpu_sync_fence(&sync_obj, fence);
+			ret = amdgpu_sync_fence(&sync_obj, fence, GFP_KERNEL);
 			if (ret) {
 				pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
 				goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 093141ad6ed0..e476e45b996a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -36,13 +36,6 @@
 #include "atombios_encoders.h"
 #include "bif/bif_4_1_d.h"
 
-static void amdgpu_atombios_lookup_i2c_gpio_quirks(struct amdgpu_device *adev,
-					  ATOM_GPIO_I2C_ASSIGMENT *gpio,
-					  u8 index)
-{
-
-}
-
 static struct amdgpu_i2c_bus_rec amdgpu_atombios_get_bus_rec_for_i2c_gpio(ATOM_GPIO_I2C_ASSIGMENT *gpio)
 {
 	struct amdgpu_i2c_bus_rec i2c;
@@ -108,9 +101,6 @@ struct amdgpu_i2c_bus_rec amdgpu_atombios_lookup_i2c_gpio(struct amdgpu_device *
 
 		gpio = &i2c_info->asGPIO_Info[0];
 		for (i = 0; i < num_indices; i++) {
-
-			amdgpu_atombios_lookup_i2c_gpio_quirks(adev, gpio, i);
-
 			if (gpio->sucI2cId.ucAccess == id) {
 				i2c = amdgpu_atombios_get_bus_rec_for_i2c_gpio(gpio);
 				break;
@@ -142,8 +132,6 @@ void amdgpu_atombios_i2c_init(struct amdgpu_device *adev)
 
 		gpio = &i2c_info->asGPIO_Info[0];
 		for (i = 0; i < num_indices; i++) {
-			amdgpu_atombios_lookup_i2c_gpio_quirks(adev, gpio, i);
-
 			i2c = amdgpu_atombios_get_bus_rec_for_i2c_gpio(gpio);
 
 			if (i2c.valid) {
@@ -156,6 +144,38 @@ void amdgpu_atombios_i2c_init(struct amdgpu_device *adev)
 	}
 }
 
+void amdgpu_atombios_oem_i2c_init(struct amdgpu_device *adev, u8 i2c_id)
+{
+	struct atom_context *ctx = adev->mode_info.atom_context;
+	ATOM_GPIO_I2C_ASSIGMENT *gpio;
+	struct amdgpu_i2c_bus_rec i2c;
+	int index = GetIndexIntoMasterTable(DATA, GPIO_I2C_Info);
+	struct _ATOM_GPIO_I2C_INFO *i2c_info;
+	uint16_t data_offset, size;
+	int i, num_indices;
+	char stmp[32];
+
+	if (amdgpu_atom_parse_data_header(ctx, index, &size, NULL, NULL, &data_offset)) {
+		i2c_info = (struct _ATOM_GPIO_I2C_INFO *)(ctx->bios + data_offset);
+
+		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
+			sizeof(ATOM_GPIO_I2C_ASSIGMENT);
+
+		gpio = &i2c_info->asGPIO_Info[0];
+		for (i = 0; i < num_indices; i++) {
+			i2c = amdgpu_atombios_get_bus_rec_for_i2c_gpio(gpio);
+
+			if (i2c.valid && i2c.i2c_id == i2c_id) {
+				sprintf(stmp, "OEM 0x%x", i2c.i2c_id);
+				adev->i2c_bus[i] = amdgpu_i2c_create(adev_to_drm(adev), &i2c, stmp);
+				break;
+			}
+			gpio = (ATOM_GPIO_I2C_ASSIGMENT *)
+				((u8 *)gpio + sizeof(ATOM_GPIO_I2C_ASSIGMENT));
+		}
+	}
+}
+
 struct amdgpu_gpio_rec
 amdgpu_atombios_lookup_gpio(struct amdgpu_device *adev,
 			    u8 id)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
index 0e16432d9a72..867bc5c5ce67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
@@ -136,6 +136,7 @@ amdgpu_atombios_lookup_gpio(struct amdgpu_device *adev,
 struct amdgpu_i2c_bus_rec amdgpu_atombios_lookup_i2c_gpio(struct amdgpu_device *adev,
 							  uint8_t id);
 void amdgpu_atombios_i2c_init(struct amdgpu_device *adev);
+void amdgpu_atombios_oem_i2c_init(struct amdgpu_device *adev, u8 i2c_id);
 
 bool amdgpu_atombios_has_dce_engine_info(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index f873dd3cae16..eb015bdda8a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -549,9 +549,10 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 	u16 data_offset, size;
 	union umc_info *umc_info;
 	u8 frev, crev;
-	bool ecc_default_enabled = false;
+	bool mem_ecc_enabled = false;
 	u8 umc_config;
 	u32 umc_config1;
+	adev->ras_default_ecc_enabled = false;
 
 	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
 			umc_info);
@@ -563,20 +564,22 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 			switch (crev) {
 			case 1:
 				umc_config = le32_to_cpu(umc_info->v31.umc_config);
-				ecc_default_enabled =
+				mem_ecc_enabled =
 					(umc_config & UMC_CONFIG__DEFAULT_MEM_ECC_ENABLE) ? true : false;
 				break;
 			case 2:
 				umc_config = le32_to_cpu(umc_info->v32.umc_config);
-				ecc_default_enabled =
+				mem_ecc_enabled =
 					(umc_config & UMC_CONFIG__DEFAULT_MEM_ECC_ENABLE) ? true : false;
 				break;
 			case 3:
 				umc_config = le32_to_cpu(umc_info->v33.umc_config);
 				umc_config1 = le32_to_cpu(umc_info->v33.umc_config1);
-				ecc_default_enabled =
+				mem_ecc_enabled =
 					((umc_config & UMC_CONFIG__DEFAULT_MEM_ECC_ENABLE) ||
 					 (umc_config1 & UMC_CONFIG1__ENABLE_ECC_CAPABLE)) ? true : false;
+				adev->ras_default_ecc_enabled =
+					(umc_config & UMC_CONFIG__DEFAULT_MEM_ECC_ENABLE) ? true : false;
 				break;
 			default:
 				/* unsupported crev */
@@ -585,9 +588,12 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 		} else if (frev == 4) {
 			switch (crev) {
 			case 0:
+				umc_config = le32_to_cpu(umc_info->v40.umc_config);
 				umc_config1 = le32_to_cpu(umc_info->v40.umc_config1);
-				ecc_default_enabled =
+				mem_ecc_enabled =
 					(umc_config1 & UMC_CONFIG1__ENABLE_ECC_CAPABLE) ? true : false;
+				adev->ras_default_ecc_enabled =
+					(umc_config & UMC_CONFIG__DEFAULT_MEM_ECC_ENABLE) ? true : false;
 				break;
 			default:
 				/* unsupported crev */
@@ -599,7 +605,7 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 		}
 	}
 
-	return ecc_default_enabled;
+	return mem_ecc_enabled;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 423fd2eebe1e..75fcc521c171 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -84,6 +84,13 @@ static bool check_atom_bios(struct amdgpu_device *adev, size_t size)
 	return false;
 }
 
+void amdgpu_bios_release(struct amdgpu_device *adev)
+{
+	kfree(adev->bios);
+	adev->bios = NULL;
+	adev->bios_size = 0;
+}
+
 /* If you boot an IGP board with a discrete card as the primary,
  * the IGP rom is not accessible via the rom bar as the IGP rom is
  * part of the system bios.  On boot, the system bios puts a
@@ -121,7 +128,7 @@ static bool amdgpu_read_bios_from_vram(struct amdgpu_device *adev)
 	iounmap(bios);
 
 	if (!check_atom_bios(adev, size)) {
-		kfree(adev->bios);
+		amdgpu_bios_release(adev);
 		return false;
 	}
 
@@ -149,7 +156,7 @@ bool amdgpu_read_bios(struct amdgpu_device *adev)
 	pci_unmap_rom(adev->pdev, bios);
 
 	if (!check_atom_bios(adev, size)) {
-		kfree(adev->bios);
+		amdgpu_bios_release(adev);
 		return false;
 	}
 
@@ -189,7 +196,7 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev)
 	amdgpu_asic_read_bios_from_rom(adev, adev->bios, len);
 
 	if (!check_atom_bios(adev, len)) {
-		kfree(adev->bios);
+		amdgpu_bios_release(adev);
 		return false;
 	}
 
@@ -225,7 +232,8 @@ static bool amdgpu_read_platform_bios(struct amdgpu_device *adev)
 
 	return true;
 free_bios:
-	kfree(adev->bios);
+	amdgpu_bios_release(adev);
+
 	return false;
 }
 
@@ -327,7 +335,7 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev)
 	}
 
 	if (!check_atom_bios(adev, size)) {
-		kfree(adev->bios);
+		amdgpu_bios_release(adev);
 		return false;
 	}
 	adev->bios_size = size;
@@ -392,7 +400,7 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
 					     GFP_KERNEL);
 
 			if (!check_atom_bios(adev, vhdr->ImageLength)) {
-				kfree(adev->bios);
+				amdgpu_bios_release(adev);
 				return false;
 			}
 			adev->bios_size = vhdr->ImageLength;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 344e0a9ee08a..5e375e9c4f5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -674,7 +674,7 @@ static int amdgpu_connector_lvds_get_modes(struct drm_connector *connector)
 }
 
 static enum drm_mode_status amdgpu_connector_lvds_mode_valid(struct drm_connector *connector,
-					     struct drm_display_mode *mode)
+					     const struct drm_display_mode *mode)
 {
 	struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector);
 
@@ -839,7 +839,7 @@ static int amdgpu_connector_vga_get_modes(struct drm_connector *connector)
 }
 
 static enum drm_mode_status amdgpu_connector_vga_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
+					    const struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
@@ -1196,7 +1196,7 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector)
 }
 
 static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
+					    const struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
@@ -1464,7 +1464,7 @@ out:
 }
 
 static enum drm_mode_status amdgpu_connector_dp_mode_valid(struct drm_connector *connector,
-					   struct drm_display_mode *mode)
+					   const struct drm_display_mode *mode)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *amdgpu_dig_connector = amdgpu_connector->con_priv;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
new file mode 100644
index 000000000000..360e07a5c7c1
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -0,0 +1,581 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2025 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 <linux/list.h>
+#include "amdgpu.h"
+
+static const guid_t MCE			= CPER_NOTIFY_MCE;
+static const guid_t CMC			= CPER_NOTIFY_CMC;
+static const guid_t BOOT		= BOOT_TYPE;
+
+static const guid_t CRASHDUMP		= AMD_CRASHDUMP;
+static const guid_t RUNTIME		= AMD_GPU_NONSTANDARD_ERROR;
+
+static void __inc_entry_length(struct cper_hdr *hdr, uint32_t size)
+{
+	hdr->record_length += size;
+}
+
+static void amdgpu_cper_get_timestamp(struct cper_timestamp *timestamp)
+{
+	struct tm tm;
+	time64_t now = ktime_get_real_seconds();
+
+	time64_to_tm(now, 0, &tm);
+	timestamp->seconds = tm.tm_sec;
+	timestamp->minutes = tm.tm_min;
+	timestamp->hours = tm.tm_hour;
+	timestamp->flag = 0;
+	timestamp->day = tm.tm_mday;
+	timestamp->month = 1 + tm.tm_mon;
+	timestamp->year = (1900 + tm.tm_year) % 100;
+	timestamp->century = (1900 + tm.tm_year) / 100;
+}
+
+void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev,
+				struct cper_hdr *hdr,
+				enum amdgpu_cper_type type,
+				enum cper_error_severity sev)
+{
+	char record_id[16];
+
+	hdr->signature[0]		= 'C';
+	hdr->signature[1]		= 'P';
+	hdr->signature[2]		= 'E';
+	hdr->signature[3]		= 'R';
+	hdr->revision			= CPER_HDR_REV_1;
+	hdr->signature_end		= 0xFFFFFFFF;
+	hdr->error_severity		= sev;
+
+	hdr->valid_bits.platform_id	= 1;
+	hdr->valid_bits.partition_id	= 1;
+	hdr->valid_bits.timestamp	= 1;
+
+	amdgpu_cper_get_timestamp(&hdr->timestamp);
+
+	snprintf(record_id, 9, "%d:%X",
+		 (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ?
+			 adev->smuio.funcs->get_socket_id(adev) :
+			 0,
+		 atomic_inc_return(&adev->cper.unique_id));
+	memcpy(hdr->record_id, record_id, 8);
+
+	snprintf(hdr->platform_id, 16, "0x%04X:0x%04X",
+		 adev->pdev->vendor, adev->pdev->device);
+	/* pmfw version should be part of creator_id according to CPER spec */
+	snprintf(hdr->creator_id, 16, "%s", CPER_CREATOR_ID_AMDGPU);
+
+	switch (type) {
+	case AMDGPU_CPER_TYPE_BOOT:
+		hdr->notify_type = BOOT;
+		break;
+	case AMDGPU_CPER_TYPE_FATAL:
+	case AMDGPU_CPER_TYPE_BP_THRESHOLD:
+		hdr->notify_type = MCE;
+		break;
+	case AMDGPU_CPER_TYPE_RUNTIME:
+		if (sev == CPER_SEV_NON_FATAL_CORRECTED)
+			hdr->notify_type = CMC;
+		else
+			hdr->notify_type = MCE;
+		break;
+	default:
+		dev_err(adev->dev, "Unknown CPER Type\n");
+		break;
+	}
+
+	__inc_entry_length(hdr, HDR_LEN);
+}
+
+static int amdgpu_cper_entry_fill_section_desc(struct amdgpu_device *adev,
+					       struct cper_sec_desc *section_desc,
+					       bool bp_threshold,
+					       bool poison,
+					       enum cper_error_severity sev,
+					       guid_t sec_type,
+					       uint32_t section_length,
+					       uint32_t section_offset)
+{
+	section_desc->revision_minor		= CPER_SEC_MINOR_REV_1;
+	section_desc->revision_major		= CPER_SEC_MAJOR_REV_22;
+	section_desc->sec_offset		= section_offset;
+	section_desc->sec_length		= section_length;
+	section_desc->valid_bits.fru_text	= 1;
+	section_desc->flag_bits.primary		= 1;
+	section_desc->severity			= sev;
+	section_desc->sec_type			= sec_type;
+
+	snprintf(section_desc->fru_text, 20, "OAM%d",
+		 (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ?
+			 adev->smuio.funcs->get_socket_id(adev) :
+			 0);
+
+	if (bp_threshold)
+		section_desc->flag_bits.exceed_err_threshold = 1;
+	if (poison)
+		section_desc->flag_bits.latent_err = 1;
+
+	return 0;
+}
+
+int amdgpu_cper_entry_fill_fatal_section(struct amdgpu_device *adev,
+					 struct cper_hdr *hdr,
+					 uint32_t idx,
+					 struct cper_sec_crashdump_reg_data reg_data)
+{
+	struct cper_sec_desc *section_desc;
+	struct cper_sec_crashdump_fatal *section;
+
+	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
+	section = (struct cper_sec_crashdump_fatal *)((uint8_t *)hdr +
+		   FATAL_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	amdgpu_cper_entry_fill_section_desc(adev, section_desc, false, false,
+					    CPER_SEV_FATAL, CRASHDUMP, FATAL_SEC_LEN,
+					    FATAL_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	section->body.reg_ctx_type = CPER_CTX_TYPE_CRASH;
+	section->body.reg_arr_size = sizeof(reg_data);
+	section->body.data = reg_data;
+
+	__inc_entry_length(hdr, SEC_DESC_LEN + FATAL_SEC_LEN);
+
+	return 0;
+}
+
+int amdgpu_cper_entry_fill_runtime_section(struct amdgpu_device *adev,
+					   struct cper_hdr *hdr,
+					   uint32_t idx,
+					   enum cper_error_severity sev,
+					   uint32_t *reg_dump,
+					   uint32_t reg_count)
+{
+	struct cper_sec_desc *section_desc;
+	struct cper_sec_nonstd_err *section;
+	bool poison;
+
+	poison = (sev == CPER_SEV_NON_FATAL_CORRECTED) ? false : true;
+	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
+	section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr +
+		   NONSTD_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	amdgpu_cper_entry_fill_section_desc(adev, section_desc, false, poison,
+					    sev, RUNTIME, NONSTD_SEC_LEN,
+					    NONSTD_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	reg_count = umin(reg_count, CPER_ACA_REG_COUNT);
+
+	section->hdr.valid_bits.err_info_cnt = 1;
+	section->hdr.valid_bits.err_context_cnt = 1;
+
+	section->info.error_type = RUNTIME;
+	section->info.ms_chk_bits.err_type_valid = 1;
+	section->ctx.reg_ctx_type = CPER_CTX_TYPE_CRASH;
+	section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump);
+
+	memcpy(section->ctx.reg_dump, reg_dump, reg_count * sizeof(uint32_t));
+
+	__inc_entry_length(hdr, SEC_DESC_LEN + NONSTD_SEC_LEN);
+
+	return 0;
+}
+
+int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev,
+						      struct cper_hdr *hdr,
+						      uint32_t idx)
+{
+	struct cper_sec_desc *section_desc;
+	struct cper_sec_nonstd_err *section;
+
+	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
+	section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr +
+		   NONSTD_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	amdgpu_cper_entry_fill_section_desc(adev, section_desc, true, false,
+					    CPER_SEV_NUM, RUNTIME, NONSTD_SEC_LEN,
+					    NONSTD_SEC_OFFSET(hdr->sec_cnt, idx));
+
+	section->hdr.valid_bits.err_info_cnt = 1;
+	section->hdr.valid_bits.err_context_cnt = 1;
+
+	section->info.error_type = RUNTIME;
+	section->info.ms_chk_bits.err_type_valid = 1;
+	section->ctx.reg_ctx_type = CPER_CTX_TYPE_CRASH;
+	section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump);
+
+	/* Hardcoded Reg dump for bad page threshold CPER */
+	section->ctx.reg_dump[CPER_ACA_REG_CTL_LO]    = 0x1;
+	section->ctx.reg_dump[CPER_ACA_REG_CTL_HI]    = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_STATUS_LO] = 0x137;
+	section->ctx.reg_dump[CPER_ACA_REG_STATUS_HI] = 0xB0000000;
+	section->ctx.reg_dump[CPER_ACA_REG_ADDR_LO]   = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_ADDR_HI]   = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_MISC0_LO]  = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_MISC0_HI]  = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_LO] = 0x2;
+	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_HI] = 0x1ff;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_LO]   = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_HI]   = 0x96;
+	section->ctx.reg_dump[CPER_ACA_REG_SYND_LO]   = 0x0;
+	section->ctx.reg_dump[CPER_ACA_REG_SYND_HI]   = 0x0;
+
+	__inc_entry_length(hdr, SEC_DESC_LEN + NONSTD_SEC_LEN);
+
+	return 0;
+}
+
+struct cper_hdr *amdgpu_cper_alloc_entry(struct amdgpu_device *adev,
+					 enum amdgpu_cper_type type,
+					 uint16_t section_count)
+{
+	struct cper_hdr *hdr;
+	uint32_t size = 0;
+
+	size += HDR_LEN;
+	size += (SEC_DESC_LEN * section_count);
+
+	switch (type) {
+	case AMDGPU_CPER_TYPE_RUNTIME:
+	case AMDGPU_CPER_TYPE_BP_THRESHOLD:
+		size += (NONSTD_SEC_LEN * section_count);
+		break;
+	case AMDGPU_CPER_TYPE_FATAL:
+		size += (FATAL_SEC_LEN * section_count);
+		break;
+	case AMDGPU_CPER_TYPE_BOOT:
+		size += (BOOT_SEC_LEN * section_count);
+		break;
+	default:
+		dev_err(adev->dev, "Unknown CPER Type!\n");
+		return NULL;
+	}
+
+	hdr = kzalloc(size, GFP_KERNEL);
+	if (!hdr)
+		return NULL;
+
+	/* Save this early */
+	hdr->sec_cnt = section_count;
+
+	return hdr;
+}
+
+int amdgpu_cper_generate_ue_record(struct amdgpu_device *adev,
+				   struct aca_bank *bank)
+{
+	struct cper_hdr *fatal = NULL;
+	struct cper_sec_crashdump_reg_data reg_data = { 0 };
+	struct amdgpu_ring *ring = &adev->cper.ring_buf;
+	int ret;
+
+	fatal = amdgpu_cper_alloc_entry(adev, AMDGPU_CPER_TYPE_FATAL, 1);
+	if (!fatal) {
+		dev_err(adev->dev, "fail to alloc cper entry for ue record\n");
+		return -ENOMEM;
+	}
+
+	reg_data.status_lo = lower_32_bits(bank->regs[ACA_REG_IDX_STATUS]);
+	reg_data.status_hi = upper_32_bits(bank->regs[ACA_REG_IDX_STATUS]);
+	reg_data.addr_lo   = lower_32_bits(bank->regs[ACA_REG_IDX_ADDR]);
+	reg_data.addr_hi   = upper_32_bits(bank->regs[ACA_REG_IDX_ADDR]);
+	reg_data.ipid_lo   = lower_32_bits(bank->regs[ACA_REG_IDX_IPID]);
+	reg_data.ipid_hi   = upper_32_bits(bank->regs[ACA_REG_IDX_IPID]);
+	reg_data.synd_lo   = lower_32_bits(bank->regs[ACA_REG_IDX_SYND]);
+	reg_data.synd_hi   = upper_32_bits(bank->regs[ACA_REG_IDX_SYND]);
+
+	amdgpu_cper_entry_fill_hdr(adev, fatal, AMDGPU_CPER_TYPE_FATAL, CPER_SEV_FATAL);
+	ret = amdgpu_cper_entry_fill_fatal_section(adev, fatal, 0, reg_data);
+	if (ret)
+		return ret;
+
+	amdgpu_cper_ring_write(ring, fatal, fatal->record_length);
+	kfree(fatal);
+
+	return 0;
+}
+
+int amdgpu_cper_generate_bp_threshold_record(struct amdgpu_device *adev)
+{
+	struct cper_hdr *bp_threshold = NULL;
+	struct amdgpu_ring *ring = &adev->cper.ring_buf;
+	int ret;
+
+	bp_threshold = amdgpu_cper_alloc_entry(adev, AMDGPU_CPER_TYPE_BP_THRESHOLD, 1);
+	if (!bp_threshold) {
+		dev_err(adev->dev, "fail to alloc cper entry for bad page threshold record\n");
+		return -ENOMEM;
+	}
+
+	amdgpu_cper_entry_fill_hdr(adev, bp_threshold, AMDGPU_CPER_TYPE_BP_THRESHOLD, CPER_SEV_NUM);
+	ret = amdgpu_cper_entry_fill_bad_page_threshold_section(adev, bp_threshold, 0);
+	if (ret)
+		return ret;
+
+	amdgpu_cper_ring_write(ring, bp_threshold, bp_threshold->record_length);
+	kfree(bp_threshold);
+
+	return 0;
+}
+
+static enum cper_error_severity amdgpu_aca_err_type_to_cper_sev(struct amdgpu_device *adev,
+								enum aca_error_type aca_err_type)
+{
+	switch (aca_err_type) {
+	case ACA_ERROR_TYPE_UE:
+		return CPER_SEV_FATAL;
+	case ACA_ERROR_TYPE_CE:
+		return CPER_SEV_NON_FATAL_CORRECTED;
+	case ACA_ERROR_TYPE_DEFERRED:
+		return CPER_SEV_NON_FATAL_UNCORRECTED;
+	default:
+		dev_err(adev->dev, "Unknown ACA error type!\n");
+		return CPER_SEV_FATAL;
+	}
+}
+
+int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev,
+				    struct aca_banks *banks,
+				    uint16_t bank_count)
+{
+	struct cper_hdr *corrected = NULL;
+	enum cper_error_severity sev = CPER_SEV_NON_FATAL_CORRECTED;
+	struct amdgpu_ring *ring = &adev->cper.ring_buf;
+	uint32_t reg_data[CPER_ACA_REG_COUNT] = { 0 };
+	struct aca_bank_node *node;
+	struct aca_bank *bank;
+	uint32_t i = 0;
+	int ret;
+
+	corrected = amdgpu_cper_alloc_entry(adev, AMDGPU_CPER_TYPE_RUNTIME, bank_count);
+	if (!corrected) {
+		dev_err(adev->dev, "fail to allocate cper entry for ce records\n");
+		return -ENOMEM;
+	}
+
+	/* Raise severity if any DE is detected in the ACA bank list */
+	list_for_each_entry(node, &banks->list, node) {
+		bank = &node->bank;
+		if (bank->aca_err_type == ACA_ERROR_TYPE_DEFERRED) {
+			sev = CPER_SEV_NON_FATAL_UNCORRECTED;
+			break;
+		}
+	}
+
+	amdgpu_cper_entry_fill_hdr(adev, corrected, AMDGPU_CPER_TYPE_RUNTIME, sev);
+
+	/* Combine CE and DE in cper record */
+	list_for_each_entry(node, &banks->list, node) {
+		bank = &node->bank;
+		reg_data[CPER_ACA_REG_CTL_LO]    = lower_32_bits(bank->regs[ACA_REG_IDX_CTL]);
+		reg_data[CPER_ACA_REG_CTL_HI]    = upper_32_bits(bank->regs[ACA_REG_IDX_CTL]);
+		reg_data[CPER_ACA_REG_STATUS_LO] = lower_32_bits(bank->regs[ACA_REG_IDX_STATUS]);
+		reg_data[CPER_ACA_REG_STATUS_HI] = upper_32_bits(bank->regs[ACA_REG_IDX_STATUS]);
+		reg_data[CPER_ACA_REG_ADDR_LO]   = lower_32_bits(bank->regs[ACA_REG_IDX_ADDR]);
+		reg_data[CPER_ACA_REG_ADDR_HI]   = upper_32_bits(bank->regs[ACA_REG_IDX_ADDR]);
+		reg_data[CPER_ACA_REG_MISC0_LO]  = lower_32_bits(bank->regs[ACA_REG_IDX_MISC0]);
+		reg_data[CPER_ACA_REG_MISC0_HI]  = upper_32_bits(bank->regs[ACA_REG_IDX_MISC0]);
+		reg_data[CPER_ACA_REG_CONFIG_LO] = lower_32_bits(bank->regs[ACA_REG_IDX_CONFIG]);
+		reg_data[CPER_ACA_REG_CONFIG_HI] = upper_32_bits(bank->regs[ACA_REG_IDX_CONFIG]);
+		reg_data[CPER_ACA_REG_IPID_LO]   = lower_32_bits(bank->regs[ACA_REG_IDX_IPID]);
+		reg_data[CPER_ACA_REG_IPID_HI]   = upper_32_bits(bank->regs[ACA_REG_IDX_IPID]);
+		reg_data[CPER_ACA_REG_SYND_LO]   = lower_32_bits(bank->regs[ACA_REG_IDX_SYND]);
+		reg_data[CPER_ACA_REG_SYND_HI]   = upper_32_bits(bank->regs[ACA_REG_IDX_SYND]);
+
+		ret = amdgpu_cper_entry_fill_runtime_section(adev, corrected, i++,
+				amdgpu_aca_err_type_to_cper_sev(adev, bank->aca_err_type),
+				reg_data, CPER_ACA_REG_COUNT);
+		if (ret)
+			return ret;
+	}
+
+	amdgpu_cper_ring_write(ring, corrected, corrected->record_length);
+	kfree(corrected);
+
+	return 0;
+}
+
+static bool amdgpu_cper_is_hdr(struct amdgpu_ring *ring, u64 pos)
+{
+	struct cper_hdr *chdr;
+
+	chdr = (struct cper_hdr *)&(ring->ring[pos]);
+	return strcmp(chdr->signature, "CPER") ? false : true;
+}
+
+static u32 amdgpu_cper_ring_get_ent_sz(struct amdgpu_ring *ring, u64 pos)
+{
+	struct cper_hdr *chdr;
+	u64 p;
+	u32 chunk, rec_len = 0;
+
+	chdr = (struct cper_hdr *)&(ring->ring[pos]);
+	chunk = ring->ring_size - (pos << 2);
+
+	if (!strcmp(chdr->signature, "CPER")) {
+		rec_len = chdr->record_length;
+		goto calc;
+	}
+
+	/* ring buffer is not full, no cper data after ring->wptr */
+	if (ring->count_dw)
+		goto calc;
+
+	for (p = pos + 1; p <= ring->buf_mask; p++) {
+		chdr = (struct cper_hdr *)&(ring->ring[p]);
+		if (!strcmp(chdr->signature, "CPER")) {
+			rec_len = (p - pos) << 2;
+			goto calc;
+		}
+	}
+
+calc:
+	if (!rec_len)
+		return chunk;
+	else
+		return umin(rec_len, chunk);
+}
+
+void amdgpu_cper_ring_write(struct amdgpu_ring *ring, void *src, int count)
+{
+	u64 pos, wptr_old, rptr = *ring->rptr_cpu_addr & ring->ptr_mask;
+	int rec_cnt_dw = count >> 2;
+	u32 chunk, ent_sz;
+	u8 *s = (u8 *)src;
+
+	if (count >= ring->ring_size - 4) {
+		dev_err(ring->adev->dev,
+			"CPER data size(%d) is larger than ring size(%d)\n",
+			count, ring->ring_size - 4);
+
+		return;
+	}
+
+	wptr_old = ring->wptr;
+
+	mutex_lock(&ring->adev->cper.ring_lock);
+	while (count) {
+		ent_sz = amdgpu_cper_ring_get_ent_sz(ring, ring->wptr);
+		chunk = umin(ent_sz, count);
+
+		memcpy(&ring->ring[ring->wptr], s, chunk);
+
+		ring->wptr += (chunk >> 2);
+		ring->wptr &= ring->ptr_mask;
+		count -= chunk;
+		s += chunk;
+	}
+
+	if (ring->count_dw < rec_cnt_dw)
+		ring->count_dw = 0;
+
+	/* the buffer is overflow, adjust rptr */
+	if (((wptr_old < rptr) && (rptr <= ring->wptr)) ||
+	    ((ring->wptr < wptr_old) && (wptr_old < rptr)) ||
+	    ((rptr <= ring->wptr) && (ring->wptr < wptr_old))) {
+		pos = (ring->wptr + 1) & ring->ptr_mask;
+
+		do {
+			ent_sz = amdgpu_cper_ring_get_ent_sz(ring, pos);
+
+			rptr += (ent_sz >> 2);
+			rptr &= ring->ptr_mask;
+			*ring->rptr_cpu_addr = rptr;
+
+			pos = rptr;
+		} while (!amdgpu_cper_is_hdr(ring, rptr));
+	}
+
+	if (ring->count_dw >= rec_cnt_dw)
+		ring->count_dw -= rec_cnt_dw;
+	mutex_unlock(&ring->adev->cper.ring_lock);
+}
+
+static u64 amdgpu_cper_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	return *(ring->rptr_cpu_addr);
+}
+
+static u64 amdgpu_cper_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	return ring->wptr;
+}
+
+static const struct amdgpu_ring_funcs cper_ring_funcs = {
+	.type = AMDGPU_RING_TYPE_CPER,
+	.align_mask = 0xff,
+	.support_64bit_ptrs = false,
+	.get_rptr = amdgpu_cper_ring_get_rptr,
+	.get_wptr = amdgpu_cper_ring_get_wptr,
+};
+
+static int amdgpu_cper_ring_init(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring = &(adev->cper.ring_buf);
+
+	mutex_init(&adev->cper.ring_lock);
+
+	ring->adev = NULL;
+	ring->ring_obj = NULL;
+	ring->use_doorbell = false;
+	ring->no_scheduler = true;
+	ring->funcs = &cper_ring_funcs;
+
+	sprintf(ring->name, "cper");
+	return amdgpu_ring_init(adev, ring, CPER_MAX_RING_SIZE, NULL, 0,
+				AMDGPU_RING_PRIO_DEFAULT, NULL);
+}
+
+int amdgpu_cper_init(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (!amdgpu_aca_is_enabled(adev))
+		return 0;
+
+	r = amdgpu_cper_ring_init(adev);
+	if (r) {
+		dev_err(adev->dev, "failed to initialize cper ring, r = %d\n", r);
+		return r;
+	}
+
+	mutex_init(&adev->cper.cper_lock);
+
+	adev->cper.enabled = true;
+	adev->cper.max_count = CPER_MAX_ALLOWED_COUNT;
+
+	return 0;
+}
+
+int amdgpu_cper_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_aca_is_enabled(adev))
+		return 0;
+
+	adev->cper.enabled = false;
+
+	amdgpu_ring_fini(&(adev->cper.ring_buf));
+	adev->cper.count = 0;
+	adev->cper.wptr = 0;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h
new file mode 100644
index 000000000000..bcb97d245673
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2025 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.
+ *
+ */
+
+#ifndef __AMDGPU_CPER_H__
+#define __AMDGPU_CPER_H__
+
+#include "amd_cper.h"
+#include "amdgpu_aca.h"
+
+#define CPER_MAX_ALLOWED_COUNT		0x1000
+#define CPER_MAX_RING_SIZE		0X100000
+#define HDR_LEN				(sizeof(struct cper_hdr))
+#define SEC_DESC_LEN			(sizeof(struct cper_sec_desc))
+
+#define BOOT_SEC_LEN			(sizeof(struct cper_sec_crashdump_boot))
+#define FATAL_SEC_LEN			(sizeof(struct cper_sec_crashdump_fatal))
+#define NONSTD_SEC_LEN			(sizeof(struct cper_sec_nonstd_err))
+
+#define SEC_DESC_OFFSET(idx)		(HDR_LEN + (SEC_DESC_LEN * idx))
+
+#define BOOT_SEC_OFFSET(count, idx)	(HDR_LEN + (SEC_DESC_LEN * count) + (BOOT_SEC_LEN * idx))
+#define FATAL_SEC_OFFSET(count, idx)	(HDR_LEN + (SEC_DESC_LEN * count) + (FATAL_SEC_LEN * idx))
+#define NONSTD_SEC_OFFSET(count, idx)	(HDR_LEN + (SEC_DESC_LEN * count) + (NONSTD_SEC_LEN * idx))
+
+enum amdgpu_cper_type {
+	AMDGPU_CPER_TYPE_RUNTIME,
+	AMDGPU_CPER_TYPE_FATAL,
+	AMDGPU_CPER_TYPE_BOOT,
+	AMDGPU_CPER_TYPE_BP_THRESHOLD,
+};
+
+struct amdgpu_cper {
+	bool enabled;
+
+	atomic_t unique_id;
+	struct mutex cper_lock;
+
+	/* Lifetime CPERs generated */
+	uint32_t count;
+	uint32_t max_count;
+
+	uint32_t wptr;
+
+	void *ring[CPER_MAX_ALLOWED_COUNT];
+	struct amdgpu_ring ring_buf;
+	struct mutex ring_lock;
+};
+
+void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev,
+				struct cper_hdr *hdr,
+				enum amdgpu_cper_type type,
+				enum cper_error_severity sev);
+int amdgpu_cper_entry_fill_fatal_section(struct amdgpu_device *adev,
+					 struct cper_hdr *hdr,
+					 uint32_t idx,
+					 struct cper_sec_crashdump_reg_data reg_data);
+int amdgpu_cper_entry_fill_runtime_section(struct amdgpu_device *adev,
+					   struct cper_hdr *hdr,
+					   uint32_t idx,
+					   enum cper_error_severity sev,
+					   uint32_t *reg_dump,
+					   uint32_t reg_count);
+int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev,
+						      struct cper_hdr *hdr,
+						      uint32_t section_idx);
+
+struct cper_hdr *amdgpu_cper_alloc_entry(struct amdgpu_device *adev,
+					 enum amdgpu_cper_type type,
+					 uint16_t section_count);
+/* UE must be encoded into separated cper entries, 1 UE 1 cper */
+int amdgpu_cper_generate_ue_record(struct amdgpu_device *adev,
+				   struct aca_bank *bank);
+/* CEs and DEs are combined into 1 cper entry */
+int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev,
+				    struct aca_banks *banks,
+				    uint16_t bank_count);
+/* Bad page threshold is encoded into separated cper entry */
+int amdgpu_cper_generate_bp_threshold_record(struct amdgpu_device *adev);
+void amdgpu_cper_ring_write(struct amdgpu_ring *ring,
+			void *src, int count);
+int amdgpu_cper_init(struct amdgpu_device *adev);
+int amdgpu_cper_fini(struct amdgpu_device *adev);
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5cc5f59e3018..82df06a72ee0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -428,7 +428,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p,
 			dma_fence_put(old);
 		}
 
-		r = amdgpu_sync_fence(&p->sync, fence);
+		r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
 		dma_fence_put(fence);
 		if (r)
 			return r;
@@ -450,7 +450,7 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p,
 		return r;
 	}
 
-	r = amdgpu_sync_fence(&p->sync, fence);
+	r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
 	dma_fence_put(fence);
 	return r;
 }
@@ -1111,7 +1111,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			struct drm_gpu_scheduler *sched = entity->rq->sched;
 			struct amdgpu_ring *ring = to_amdgpu_ring(sched);
 
-			if (amdgpu_vmid_uses_reserved(adev, vm, ring->vm_hub))
+			if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub))
 				return -EINVAL;
 		}
 	}
@@ -1124,7 +1124,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update);
+	r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update,
+			      GFP_KERNEL);
 	if (r)
 		return r;
 
@@ -1135,7 +1136,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+				      GFP_KERNEL);
 		if (r)
 			return r;
 	}
@@ -1154,7 +1156,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+				      GFP_KERNEL);
 		if (r)
 			return r;
 	}
@@ -1167,7 +1170,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(&p->sync, vm->last_update);
+	r = amdgpu_sync_fence(&p->sync, vm->last_update, GFP_KERNEL);
 	if (r)
 		return r;
 
@@ -1248,7 +1251,8 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
 			continue;
 		}
 
-		r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+		r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence,
+				      GFP_KERNEL);
 		dma_fence_put(fence);
 		if (r)
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 49ca8c814455..a1450f13d963 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1990,7 +1990,7 @@ static int amdgpu_debugfs_sclk_set(void *data, u64 val)
 	uint32_t max_freq, min_freq;
 	struct amdgpu_device *adev = (struct amdgpu_device *)data;
 
-	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+	if (amdgpu_sriov_multi_vf_mode(adev))
 		return -EINVAL;
 
 	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
index 824f9da5b6ce..7b50741dc097 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
@@ -364,5 +364,9 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check,
 
 	dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT,
 		      amdgpu_devcoredump_read, amdgpu_devcoredump_free);
+
+	drm_info(dev, "AMDGPU device coredump file has been created\n");
+	drm_info(dev, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
+		 dev->primary->index);
 }
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 018dfccd771b..6ebf6179064b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -102,6 +102,9 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 #define AMDGPU_PCIE_INDEX_HI_FALLBACK (0x44 >> 2)
 #define AMDGPU_PCIE_DATA_FALLBACK (0x3C >> 2)
 
+#define AMDGPU_VBIOS_SKIP (1U << 0)
+#define AMDGPU_VBIOS_OPTIONAL (1U << 1)
+
 static const struct drm_driver amdgpu_kms_driver;
 
 const char *amdgpu_asic_name[] = {
@@ -224,6 +227,24 @@ static ssize_t amdgpu_device_get_pcie_replay_count(struct device *dev,
 static DEVICE_ATTR(pcie_replay_count, 0444,
 		amdgpu_device_get_pcie_replay_count, NULL);
 
+static int amdgpu_device_attr_sysfs_init(struct amdgpu_device *adev)
+{
+	int ret = 0;
+
+	if (!amdgpu_sriov_vf(adev))
+		ret = sysfs_create_file(&adev->dev->kobj,
+					&dev_attr_pcie_replay_count.attr);
+
+	return ret;
+}
+
+static void amdgpu_device_attr_sysfs_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_sriov_vf(adev))
+		sysfs_remove_file(&adev->dev->kobj,
+				  &dev_attr_pcie_replay_count.attr);
+}
+
 static ssize_t amdgpu_sysfs_reg_state_get(struct file *f, struct kobject *kobj,
 					  struct bin_attribute *attr, char *buf,
 					  loff_t ppos, size_t count)
@@ -1389,6 +1410,17 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
 	BUG();
 }
 
+static uint32_t amdgpu_device_get_vbios_flags(struct amdgpu_device *adev)
+{
+	if (hweight32(adev->aid_mask) && (adev->flags & AMD_IS_APU))
+		return AMDGPU_VBIOS_SKIP;
+
+	if (hweight32(adev->aid_mask) && amdgpu_passthrough(adev))
+		return AMDGPU_VBIOS_OPTIONAL;
+
+	return 0;
+}
+
 /**
  * amdgpu_device_asic_init - Wrapper for atom asic_init
  *
@@ -1398,18 +1430,28 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
  */
 static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 {
+	uint32_t flags;
+	bool optional;
 	int ret;
 
 	amdgpu_asic_pre_asic_init(adev);
+	flags = amdgpu_device_get_vbios_flags(adev);
+	optional = !!(flags & (AMDGPU_VBIOS_OPTIONAL | AMDGPU_VBIOS_SKIP));
 
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0)) {
 		amdgpu_psp_wait_for_bootloader(adev);
+		if (optional && !adev->bios)
+			return 0;
+
 		ret = amdgpu_atomfirmware_asic_init(adev, true);
 		return ret;
 	} else {
+		if (optional && !adev->bios)
+			return 0;
+
 		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
 	}
 
@@ -1705,14 +1747,6 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	return 0;
 }
 
-static bool amdgpu_device_read_bios(struct amdgpu_device *adev)
-{
-	if (hweight32(adev->aid_mask) && (adev->flags & AMD_IS_APU))
-		return false;
-
-	return true;
-}
-
 /*
  * GPU helpers function.
  */
@@ -1727,12 +1761,15 @@ static bool amdgpu_device_read_bios(struct amdgpu_device *adev)
  */
 bool amdgpu_device_need_post(struct amdgpu_device *adev)
 {
-	uint32_t reg;
+	uint32_t reg, flags;
 
 	if (amdgpu_sriov_vf(adev))
 		return false;
 
-	if (!amdgpu_device_read_bios(adev))
+	flags = amdgpu_device_get_vbios_flags(adev);
+	if (flags & AMDGPU_VBIOS_SKIP)
+		return false;
+	if ((flags & AMDGPU_VBIOS_OPTIONAL) && !adev->bios)
 		return false;
 
 	if (amdgpu_passthrough(adev)) {
@@ -2240,7 +2277,8 @@ void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
 		if (adev->ip_blocks[i].version->funcs->get_clockgating_state)
-			adev->ip_blocks[i].version->funcs->get_clockgating_state((void *)adev, flags);
+			adev->ip_blocks[i].version->funcs->get_clockgating_state(
+				&adev->ip_blocks[i], flags);
 	}
 }
 
@@ -2585,8 +2623,9 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ip_block *ip_block;
 	struct pci_dev *parent;
+	bool total, skip_bios;
+	uint32_t bios_flags;
 	int i, r;
-	bool total;
 
 	amdgpu_device_enable_virtual_display(adev);
 
@@ -2699,16 +2738,31 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 			if (r)
 				return r;
 
+			bios_flags = amdgpu_device_get_vbios_flags(adev);
+			skip_bios = !!(bios_flags & AMDGPU_VBIOS_SKIP);
 			/* Read BIOS */
-			if (amdgpu_device_read_bios(adev)) {
-				if (!amdgpu_get_bios(adev))
+			if (!skip_bios) {
+				bool optional =
+					!!(bios_flags & AMDGPU_VBIOS_OPTIONAL);
+				if (!amdgpu_get_bios(adev) && !optional)
 					return -EINVAL;
 
-				r = amdgpu_atombios_init(adev);
-				if (r) {
-					dev_err(adev->dev, "amdgpu_atombios_init failed\n");
-					amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0);
-					return r;
+				if (optional && !adev->bios)
+					dev_info(
+						adev->dev,
+						"VBIOS image optional, proceeding without VBIOS image");
+
+				if (adev->bios) {
+					r = amdgpu_atombios_init(adev);
+					if (r) {
+						dev_err(adev->dev,
+							"amdgpu_atombios_init failed\n");
+						amdgpu_vf_error_put(
+							adev,
+							AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL,
+							0, 0);
+						return r;
+					}
 				}
 			}
 
@@ -2721,6 +2775,9 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (!total)
 		return -ENODEV;
 
+	if (adev->gmc.xgmi.supported)
+		amdgpu_xgmi_early_init(adev);
+
 	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
 	if (ip_block->status.valid != false)
 		amdgpu_amdkfd_device_probe(adev);
@@ -2830,6 +2887,12 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 
 static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 {
+	struct drm_sched_init_args args = {
+		.ops = &amdgpu_sched_ops,
+		.num_rqs = DRM_SCHED_PRIORITY_COUNT,
+		.timeout_wq = adev->reset_domain->wq,
+		.dev = adev->dev,
+	};
 	long timeout;
 	int r, i;
 
@@ -2855,12 +2918,12 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 			break;
 		}
 
-		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL,
-				   DRM_SCHED_PRIORITY_COUNT,
-				   ring->num_hw_submission, 0,
-				   timeout, adev->reset_domain->wq,
-				   ring->sched_score, ring->name,
-				   adev->dev);
+		args.timeout = timeout;
+		args.credit_limit = ring->num_hw_submission;
+		args.score = ring->sched_score;
+		args.name = ring->name;
+
+		r = drm_sched_init(&ring->sched, &args);
 		if (r) {
 			DRM_ERROR("Failed to create scheduler on ring %s.\n",
 				  ring->name);
@@ -3063,6 +3126,9 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 
 	amdgpu_fru_get_product_info(adev);
 
+	if (!amdgpu_sriov_vf(adev) || amdgpu_sriov_ras_cper_en(adev))
+		r = amdgpu_cper_init(adev);
+
 init_failed:
 
 	return r;
@@ -3423,6 +3489,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	amdgpu_cper_fini(adev);
+
 	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
 		amdgpu_virt_release_ras_err_handler_data(adev);
 
@@ -4122,11 +4190,6 @@ static bool amdgpu_device_check_iommu_remap(struct amdgpu_device *adev)
 }
 #endif
 
-static const struct attribute *amdgpu_dev_attributes[] = {
-	&dev_attr_pcie_replay_count.attr,
-	NULL
-};
-
 static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 {
 	if (amdgpu_mcbp == 1)
@@ -4223,7 +4286,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->grbm_idx_mutex);
 	mutex_init(&adev->mn_lock);
 	mutex_init(&adev->virt.vf_errors.lock);
-	mutex_init(&adev->virt.rlcg_reg_lock);
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
@@ -4232,7 +4294,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->gfx.reset_sem_mutex);
 	/* Initialize the mutex for cleaner shader isolation between GFX and compute processes */
 	mutex_init(&adev->enforce_isolation_mutex);
+	for (i = 0; i < MAX_XCP; ++i) {
+		adev->isolation[i].spearhead = dma_fence_get_stub();
+		amdgpu_sync_create(&adev->isolation[i].active);
+		amdgpu_sync_create(&adev->isolation[i].prev);
+	}
 	mutex_init(&adev->gfx.kfd_sch_mutex);
+	mutex_init(&adev->gfx.workload_profile_mutex);
+	mutex_init(&adev->vcn.workload_profile_mutex);
 
 	amdgpu_device_init_apu_flags(adev);
 
@@ -4249,6 +4318,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->se_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 	spin_lock_init(&adev->mm_stats.lock);
+	spin_lock_init(&adev->virt.rlcg_reg_lock);
 	spin_lock_init(&adev->wb.lock);
 
 	INIT_LIST_HEAD(&adev->reset_list);
@@ -4293,10 +4363,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * for throttling interrupt) = 60 seconds.
 	 */
 	ratelimit_state_init(&adev->throttling_logging_rs, (60 - 1) * HZ, 1);
-	ratelimit_state_init(&adev->virt.ras_telemetry_rs, 5 * HZ, 1);
 
 	ratelimit_set_flags(&adev->throttling_logging_rs, RATELIMIT_MSG_ON_RELEASE);
-	ratelimit_set_flags(&adev->virt.ras_telemetry_rs, RATELIMIT_MSG_ON_RELEASE);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
@@ -4328,7 +4396,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		return -ENOMEM;
 
 	/* detect hw virtualization here */
-	amdgpu_detect_virtualization(adev);
+	amdgpu_virt_init(adev);
 
 	amdgpu_device_get_pcie_info(adev);
 
@@ -4351,10 +4419,17 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	/* Get rid of things like offb */
-	r = aperture_remove_conflicting_pci_devices(adev->pdev, amdgpu_kms_driver.name);
-	if (r)
-		return r;
+	/*
+	 * No need to remove conflicting FBs for non-display class devices.
+	 * This prevents the sysfb from being freed accidently.
+	 */
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA ||
+	    (pdev->class >> 8) == PCI_CLASS_DISPLAY_OTHER) {
+		/* Get rid of things like offb */
+		r = aperture_remove_conflicting_pci_devices(adev->pdev, amdgpu_kms_driver.name);
+		if (r)
+			return r;
+	}
 
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
@@ -4472,8 +4547,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				goto failed;
 			}
 			/* init i2c buses */
-			if (!amdgpu_device_has_dc_support(adev))
-				amdgpu_atombios_i2c_init(adev);
+			amdgpu_i2c_init(adev);
 		}
 	}
 
@@ -4566,7 +4640,7 @@ fence_driver_init:
 	} else
 		adev->ucode_sysfs_en = true;
 
-	r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes);
+	r = amdgpu_device_attr_sysfs_init(adev);
 	if (r)
 		dev_err(adev->dev, "Could not create amdgpu device attr\n");
 
@@ -4703,7 +4777,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		amdgpu_pm_sysfs_fini(adev);
 	if (adev->ucode_sysfs_en)
 		amdgpu_ucode_sysfs_fini(adev);
-	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
+	amdgpu_device_attr_sysfs_fini(adev);
 	amdgpu_fru_sysfs_fini(adev);
 
 	amdgpu_reg_state_sysfs_fini(adev);
@@ -4730,7 +4804,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 {
-	int idx;
+	int i, idx;
 	bool px;
 
 	amdgpu_device_ip_fini(adev);
@@ -4738,22 +4812,29 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 	amdgpu_ucode_release(&adev->firmware.gpu_info_fw);
 	adev->accel_working = false;
 	dma_fence_put(rcu_dereference_protected(adev->gang_submit, true));
+	for (i = 0; i < MAX_XCP; ++i) {
+		dma_fence_put(adev->isolation[i].spearhead);
+		amdgpu_sync_free(&adev->isolation[i].active);
+		amdgpu_sync_free(&adev->isolation[i].prev);
+	}
 
 	amdgpu_reset_fini(adev);
 
 	/* free i2c buses */
-	if (!amdgpu_device_has_dc_support(adev))
-		amdgpu_i2c_fini(adev);
-
-	if (amdgpu_emu_mode != 1)
-		amdgpu_atombios_fini(adev);
+	amdgpu_i2c_fini(adev);
 
-	kfree(adev->bios);
-	adev->bios = NULL;
+	if (adev->bios) {
+		if (amdgpu_emu_mode != 1)
+			amdgpu_atombios_fini(adev);
+		amdgpu_bios_release(adev);
+	}
 
 	kfree(adev->fru_info);
 	adev->fru_info = NULL;
 
+	kfree(adev->xcp_mgr);
+	adev->xcp_mgr = NULL;
+
 	px = amdgpu_device_supports_px(adev_to_drm(adev));
 
 	if (px || (!dev_is_removable(&adev->pdev->dev) &&
@@ -5285,6 +5366,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 0, 3))
 		amdgpu_ras_resume(adev);
 
@@ -5375,7 +5457,8 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 	u32 i;
 	int ret = 0;
 
-	amdgpu_atombios_scratch_regs_engine_hung(adev, true);
+	if (adev->bios)
+		amdgpu_atombios_scratch_regs_engine_hung(adev, true);
 
 	dev_info(adev->dev, "GPU mode1 reset\n");
 
@@ -5417,7 +5500,8 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 		goto mode1_reset_failed;
 	}
 
-	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
+	if (adev->bios)
+		amdgpu_atombios_scratch_regs_engine_hung(adev, false);
 
 	return 0;
 
@@ -6123,6 +6207,10 @@ end_reset:
 		dev_info(adev->dev, "GPU reset end with ret = %d\n", r);
 
 	atomic_set(&adev->reset_domain->reset_res, r);
+
+	if (!r)
+		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
+
 	return r;
 }
 
@@ -6851,22 +6939,117 @@ struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 {
 	struct dma_fence *old = NULL;
 
+	dma_fence_get(gang);
 	do {
 		dma_fence_put(old);
 		old = amdgpu_device_get_gang(adev);
 		if (old == gang)
 			break;
 
-		if (!dma_fence_is_signaled(old))
+		if (!dma_fence_is_signaled(old)) {
+			dma_fence_put(gang);
 			return old;
+		}
 
 	} while (cmpxchg((struct dma_fence __force **)&adev->gang_submit,
 			 old, gang) != old);
 
+	/*
+	 * Drop it once for the exchanged reference in adev and once for the
+	 * thread local reference acquired in amdgpu_device_get_gang().
+	 */
+	dma_fence_put(old);
 	dma_fence_put(old);
 	return NULL;
 }
 
+/**
+ * amdgpu_device_enforce_isolation - enforce HW isolation
+ * @adev: the amdgpu device pointer
+ * @ring: the HW ring the job is supposed to run on
+ * @job: the job which is about to be pushed to the HW ring
+ *
+ * Makes sure that only one client at a time can use the GFX block.
+ * Returns: The dependency to wait on before the job can be pushed to the HW.
+ * The function is called multiple times until NULL is returned.
+ */
+struct dma_fence *amdgpu_device_enforce_isolation(struct amdgpu_device *adev,
+						  struct amdgpu_ring *ring,
+						  struct amdgpu_job *job)
+{
+	struct amdgpu_isolation *isolation = &adev->isolation[ring->xcp_id];
+	struct drm_sched_fence *f = job->base.s_fence;
+	struct dma_fence *dep;
+	void *owner;
+	int r;
+
+	/*
+	 * For now enforce isolation only for the GFX block since we only need
+	 * the cleaner shader on those rings.
+	 */
+	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX &&
+	    ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
+		return NULL;
+
+	/*
+	 * All submissions where enforce isolation is false are handled as if
+	 * they come from a single client. Use ~0l as the owner to distinct it
+	 * from kernel submissions where the owner is NULL.
+	 */
+	owner = job->enforce_isolation ? f->owner : (void *)~0l;
+
+	mutex_lock(&adev->enforce_isolation_mutex);
+
+	/*
+	 * The "spearhead" submission is the first one which changes the
+	 * ownership to its client. We always need to wait for it to be
+	 * pushed to the HW before proceeding with anything.
+	 */
+	if (&f->scheduled != isolation->spearhead &&
+	    !dma_fence_is_signaled(isolation->spearhead)) {
+		dep = isolation->spearhead;
+		goto out_grab_ref;
+	}
+
+	if (isolation->owner != owner) {
+
+		/*
+		 * Wait for any gang to be assembled before switching to a
+		 * different owner or otherwise we could deadlock the
+		 * submissions.
+		 */
+		if (!job->gang_submit) {
+			dep = amdgpu_device_get_gang(adev);
+			if (!dma_fence_is_signaled(dep))
+				goto out_return_dep;
+			dma_fence_put(dep);
+		}
+
+		dma_fence_put(isolation->spearhead);
+		isolation->spearhead = dma_fence_get(&f->scheduled);
+		amdgpu_sync_move(&isolation->active, &isolation->prev);
+		trace_amdgpu_isolation(isolation->owner, owner);
+		isolation->owner = owner;
+	}
+
+	/*
+	 * Specifying the ring here helps to pipeline submissions even when
+	 * isolation is enabled. If that is not desired for testing NULL can be
+	 * used instead of the ring to enforce a CPU round trip while switching
+	 * between clients.
+	 */
+	dep = amdgpu_sync_peek_fence(&isolation->prev, ring);
+	r = amdgpu_sync_fence(&isolation->active, &f->finished, GFP_NOWAIT);
+	if (r)
+		DRM_WARN("OOM tracking isolation\n");
+
+out_grab_ref:
+	dma_fence_get(dep);
+out_return_dep:
+	mutex_unlock(&adev->enforce_isolation_mutex);
+	return dep;
+}
+
 bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 949d74eff294..dc2713ec95a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -113,8 +113,13 @@
 #include "amdgpu_isp.h"
 #endif
 
-#define FIRMWARE_IP_DISCOVERY "amdgpu/ip_discovery.bin"
-MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY);
+MODULE_FIRMWARE("amdgpu/ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega10_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega12_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega20_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/raven_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/raven2_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/picasso_ip_discovery.bin");
 
 #define mmIP_DISCOVERY_VERSION  0x16A00
 #define mmRCC_CONFIG_MEMSIZE	0xde3
@@ -297,21 +302,13 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 	return ret;
 }
 
-static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, uint8_t *binary)
+static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev,
+							uint8_t *binary,
+							const char *fw_name)
 {
 	const struct firmware *fw;
-	const char *fw_name;
 	int r;
 
-	switch (amdgpu_discovery) {
-	case 2:
-		fw_name = FIRMWARE_IP_DISCOVERY;
-		break;
-	default:
-		dev_warn(adev->dev, "amdgpu_discovery is not set properly\n");
-		return -EINVAL;
-	}
-
 	r = request_firmware(&fw, fw_name, adev->dev);
 	if (r) {
 		dev_err(adev->dev, "can't load firmware \"%s\"\n",
@@ -404,10 +401,39 @@ static int amdgpu_discovery_verify_npsinfo(struct amdgpu_device *adev,
 	return 0;
 }
 
+static const char *amdgpu_discovery_get_fw_name(struct amdgpu_device *adev)
+{
+	if (amdgpu_discovery == 2)
+		return "amdgpu/ip_discovery.bin";
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+		return "amdgpu/vega10_ip_discovery.bin";
+	case CHIP_VEGA12:
+		return "amdgpu/vega12_ip_discovery.bin";
+	case CHIP_RAVEN:
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			return "amdgpu/raven2_ip_discovery.bin";
+		else if (adev->apu_flags & AMD_APU_IS_PICASSO)
+			return "amdgpu/picasso_ip_discovery.bin";
+		else
+			return "amdgpu/raven_ip_discovery.bin";
+	case CHIP_VEGA20:
+		return "amdgpu/vega20_ip_discovery.bin";
+	case CHIP_ARCTURUS:
+		return "amdgpu/arcturus_ip_discovery.bin";
+	case CHIP_ALDEBARAN:
+		return "amdgpu/aldebaran_ip_discovery.bin";
+	default:
+		return NULL;
+	}
+}
+
 static int amdgpu_discovery_init(struct amdgpu_device *adev)
 {
 	struct table_info *info;
 	struct binary_header *bhdr;
+	const char *fw_name;
 	uint16_t offset;
 	uint16_t size;
 	uint16_t checksum;
@@ -419,9 +445,10 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 		return -ENOMEM;
 
 	/* Read from file if it is the preferred option */
-	if (amdgpu_discovery == 2) {
+	fw_name = amdgpu_discovery_get_fw_name(adev);
+	if (fw_name != NULL) {
 		dev_info(adev->dev, "use ip discovery information from file");
-		r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin);
+		r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name);
 
 		if (r) {
 			dev_err(adev->dev, "failed to read ip discovery binary from file\n");
@@ -587,16 +614,19 @@ void amdgpu_discovery_fini(struct amdgpu_device *adev)
 	adev->mman.discovery_bin = NULL;
 }
 
-static int amdgpu_discovery_validate_ip(const struct ip_v4 *ip)
+static int amdgpu_discovery_validate_ip(struct amdgpu_device *adev,
+					uint8_t instance, uint16_t hw_id)
 {
-	if (ip->instance_number >= HWIP_MAX_INSTANCE) {
-		DRM_ERROR("Unexpected instance_number (%d) from ip discovery blob\n",
-			  ip->instance_number);
+	if (instance >= HWIP_MAX_INSTANCE) {
+		dev_err(adev->dev,
+			"Unexpected instance_number (%d) from ip discovery blob\n",
+			instance);
 		return -EINVAL;
 	}
-	if (le16_to_cpu(ip->hw_id) >= HW_ID_MAX) {
-		DRM_ERROR("Unexpected hw_id (%d) from ip discovery blob\n",
-			  le16_to_cpu(ip->hw_id));
+	if (hw_id >= HW_ID_MAX) {
+		dev_err(adev->dev,
+			"Unexpected hw_id (%d) from ip discovery blob\n",
+			hw_id);
 		return -EINVAL;
 	}
 
@@ -609,8 +639,10 @@ static void amdgpu_discovery_read_harvest_bit_per_ip(struct amdgpu_device *adev,
 	struct binary_header *bhdr;
 	struct ip_discovery_header *ihdr;
 	struct die_header *dhdr;
-	struct ip_v4 *ip;
+	struct ip *ip;
 	uint16_t die_offset, ip_offset, num_dies, num_ips;
+	uint16_t hw_id;
+	uint8_t inst;
 	int i, j;
 
 	bhdr = (struct binary_header *)adev->mman.discovery_bin;
@@ -626,16 +658,18 @@ static void amdgpu_discovery_read_harvest_bit_per_ip(struct amdgpu_device *adev,
 		ip_offset = die_offset + sizeof(*dhdr);
 
 		for (j = 0; j < num_ips; j++) {
-			ip = (struct ip_v4 *)(adev->mman.discovery_bin + ip_offset);
-
-			if (amdgpu_discovery_validate_ip(ip))
+			ip = (struct ip *)(adev->mman.discovery_bin +
+					   ip_offset);
+			inst = ip->number_instance;
+			hw_id = le16_to_cpu(ip->hw_id);
+			if (amdgpu_discovery_validate_ip(adev, inst, hw_id))
 				goto next_ip;
 
-			if (le16_to_cpu(ip->variant) == 1) {
-				switch (le16_to_cpu(ip->hw_id)) {
+			if (ip->harvest == 1) {
+				switch (hw_id) {
 				case VCN_HWID:
 					(*vcn_harvest_count)++;
-					if (ip->instance_number == 0) {
+					if (inst == 0) {
 						adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN0;
 						adev->vcn.inst_mask &=
 							~AMDGPU_VCN_HARVEST_VCN0;
@@ -657,10 +691,8 @@ static void amdgpu_discovery_read_harvest_bit_per_ip(struct amdgpu_device *adev,
 				}
 			}
 next_ip:
-			if (ihdr->base_addr_64_bit)
-				ip_offset += struct_size(ip, base_address_64, ip->num_base_address);
-			else
-				ip_offset += struct_size(ip, base_address, ip->num_base_address);
+			ip_offset += struct_size(ip, base_address,
+						 ip->num_base_address);
 		}
 	}
 }
@@ -1019,6 +1051,8 @@ static int amdgpu_discovery_sysfs_ips(struct amdgpu_device *adev,
 				      bool reg_base_64)
 {
 	int ii, jj, kk, res;
+	uint16_t hw_id;
+	uint8_t inst;
 
 	DRM_DEBUG("num_ips:%d", num_ips);
 
@@ -1034,8 +1068,10 @@ static int amdgpu_discovery_sysfs_ips(struct amdgpu_device *adev,
 			struct ip_hw_instance *ip_hw_instance;
 
 			ip = (struct ip_v4 *)(adev->mman.discovery_bin + ip_offset);
-			if (amdgpu_discovery_validate_ip(ip) ||
-			    le16_to_cpu(ip->hw_id) != ii)
+			inst = ip->instance_number;
+			hw_id = le16_to_cpu(ip->hw_id);
+			if (amdgpu_discovery_validate_ip(adev, inst, hw_id) ||
+			    hw_id != ii)
 				goto next_ip;
 
 			DRM_DEBUG("match:%d @ ip_offset:%zu", ii, ip_offset);
@@ -1281,7 +1317,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 	uint16_t die_offset;
 	uint16_t ip_offset;
 	uint16_t num_dies;
+	uint32_t wafl_ver;
 	uint16_t num_ips;
+	uint16_t hw_id;
+	uint8_t inst;
 	int hw_ip;
 	int i, j, k;
 	int r;
@@ -1292,6 +1331,7 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 		return r;
 	}
 
+	wafl_ver = 0;
 	adev->gfx.xcc_mask = 0;
 	adev->sdma.sdma_mask = 0;
 	adev->vcn.inst_mask = 0;
@@ -1321,7 +1361,9 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 		for (j = 0; j < num_ips; j++) {
 			ip = (struct ip_v4 *)(adev->mman.discovery_bin + ip_offset);
 
-			if (amdgpu_discovery_validate_ip(ip))
+			inst = ip->instance_number;
+			hw_id = le16_to_cpu(ip->hw_id);
+			if (amdgpu_discovery_validate_ip(adev, inst, hw_id))
 				goto next_ip;
 
 			num_base_address = ip->num_base_address;
@@ -1390,6 +1432,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 				adev->gfx.xcc_mask |=
 					(1U << ip->instance_number);
 
+			if (!wafl_ver && le16_to_cpu(ip->hw_id) == WAFLC_HWID)
+				wafl_ver = IP_VERSION_FULL(ip->major, ip->minor,
+							   ip->revision, 0, 0);
+
 			for (k = 0; k < num_base_address; k++) {
 				/*
 				 * convert the endianness of base addresses in place,
@@ -1455,22 +1501,32 @@ next_ip:
 		}
 	}
 
+	if (wafl_ver && !adev->ip_versions[XGMI_HWIP][0])
+		adev->ip_versions[XGMI_HWIP][0] = wafl_ver;
+
 	return 0;
 }
 
 static void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 {
+	struct ip_discovery_header *ihdr;
+	struct binary_header *bhdr;
 	int vcn_harvest_count = 0;
 	int umc_harvest_count = 0;
+	uint16_t offset, ihdr_ver;
 
+	bhdr = (struct binary_header *)adev->mman.discovery_bin;
+	offset = le16_to_cpu(bhdr->table_list[IP_DISCOVERY].offset);
+	ihdr = (struct ip_discovery_header *)(adev->mman.discovery_bin +
+					      offset);
+	ihdr_ver = le16_to_cpu(ihdr->version);
 	/*
 	 * Harvest table does not fit Navi1x and legacy GPUs,
 	 * so read harvest bit per IP data structure to set
 	 * harvest configuration.
 	 */
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 2, 0) &&
-	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 3) &&
-	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 4)) {
+	    ihdr_ver <= 2) {
 		if ((adev->pdev->device == 0x731E &&
 			(adev->pdev->revision == 0xC6 ||
 			 adev->pdev->revision == 0xC7)) ||
@@ -1864,6 +1920,7 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		amdgpu_device_ip_block_add(adev, &soc21_common_ip_block);
 		break;
 	case IP_VERSION(12, 0, 0):
@@ -1919,6 +1976,7 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		amdgpu_device_ip_block_add(adev, &gmc_v11_0_ip_block);
 		break;
 	case IP_VERSION(12, 0, 0):
@@ -1998,6 +2056,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 12):
 	case IP_VERSION(11, 0, 13):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		break;
 	case IP_VERSION(11, 0, 8):
@@ -2029,6 +2088,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
 		break;
 	case IP_VERSION(14, 0, 2):
 	case IP_VERSION(14, 0, 3):
+	case IP_VERSION(14, 0, 5):
 		amdgpu_device_ip_block_add(adev, &psp_v14_0_ip_block);
 		break;
 	default:
@@ -2061,6 +2121,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 12):
 	case IP_VERSION(11, 0, 13):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		break;
 	case IP_VERSION(12, 0, 0):
@@ -2079,6 +2140,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 10):
 	case IP_VERSION(13, 0, 11):
 	case IP_VERSION(13, 0, 14):
+	case IP_VERSION(13, 0, 12):
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	case IP_VERSION(14, 0, 0):
@@ -2086,6 +2148,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(14, 0, 2):
 	case IP_VERSION(14, 0, 3):
 	case IP_VERSION(14, 0, 4):
+	case IP_VERSION(14, 0, 5):
 		amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block);
 		break;
 	default:
@@ -2137,6 +2200,7 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(3, 2, 1):
 		case IP_VERSION(3, 5, 0):
 		case IP_VERSION(3, 5, 1):
+		case IP_VERSION(3, 6, 0):
 		case IP_VERSION(4, 1, 0):
 			/* TODO: Fix IP version. DC code expects version 4.0.1 */
 			if (adev->ip_versions[DCE_HWIP][0] == IP_VERSION(4, 1, 0))
@@ -2215,6 +2279,7 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		amdgpu_device_ip_block_add(adev, &gfx_v11_0_ip_block);
 		break;
 	case IP_VERSION(12, 0, 0):
@@ -2270,6 +2335,7 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(6, 1, 0):
 	case IP_VERSION(6, 1, 1):
 	case IP_VERSION(6, 1, 2):
+	case IP_VERSION(6, 1, 3):
 		amdgpu_device_ip_block_add(adev, &sdma_v6_0_ip_block);
 		break;
 	case IP_VERSION(7, 0, 0):
@@ -2393,6 +2459,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		amdgpu_device_ip_block_add(adev, &mes_v11_0_ip_block);
 		adev->enable_mes = true;
 		adev->enable_mes_kiq = true;
@@ -2480,6 +2547,38 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
+	case CHIP_VEGA12:
+	case CHIP_RAVEN:
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+	case CHIP_ALDEBARAN:
+		/* this is not fatal.  We have a fallback below
+		 * if the new firmwares are not present. some of
+		 * this will be overridden below to keep things
+		 * consistent with the current behavior.
+		 */
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (!r) {
+			amdgpu_discovery_harvest_ip(adev);
+			amdgpu_discovery_get_gfx_info(adev);
+			amdgpu_discovery_get_mall_info(adev);
+			amdgpu_discovery_get_vcn_info(adev);
+		}
+		break;
+	default:
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (r)
+			return -EINVAL;
+
+		amdgpu_discovery_harvest_ip(adev);
+		amdgpu_discovery_get_gfx_info(adev);
+		amdgpu_discovery_get_mall_info(adev);
+		amdgpu_discovery_get_vcn_info(adev);
+		break;
+	}
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2642,14 +2741,6 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
 		break;
 	default:
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (r)
-			return -EINVAL;
-
-		amdgpu_discovery_harvest_ip(adev);
-		amdgpu_discovery_get_gfx_info(adev);
-		amdgpu_discovery_get_mall_info(adev);
-		amdgpu_discovery_get_vcn_info(adev);
 		break;
 	}
 
@@ -2708,6 +2799,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		adev->family = AMDGPU_FAMILY_GC_11_5_0;
 		break;
 	case IP_VERSION(12, 0, 0):
@@ -2733,19 +2825,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		adev->flags |= AMD_IS_APU;
 		break;
 	default:
 		break;
 	}
 
-	if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(4, 8, 0))
-		adev->gmc.xgmi.supported = true;
-
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4))
-		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 4, 0);
-
 	/* set NBIO version */
 	switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
 	case IP_VERSION(6, 1, 0):
@@ -2766,11 +2852,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg;
 		break;
 	case IP_VERSION(7, 9, 0):
+	case IP_VERSION(7, 9, 1):
 		adev->nbio.funcs = &nbio_v7_9_funcs;
 		adev->nbio.hdp_flush_reg = &nbio_v7_9_hdp_flush_reg;
 		break;
 	case IP_VERSION(7, 11, 0):
 	case IP_VERSION(7, 11, 1):
+	case IP_VERSION(7, 11, 2):
 	case IP_VERSION(7, 11, 3):
 		adev->nbio.funcs = &nbio_v7_11_funcs;
 		adev->nbio.hdp_flush_reg = &nbio_v7_11_hdp_flush_reg;
@@ -2898,6 +2986,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 10):
 	case IP_VERSION(11, 0, 11):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 	case IP_VERSION(13, 0, 1):
 	case IP_VERSION(13, 0, 9):
 	case IP_VERSION(13, 0, 10):
@@ -2907,6 +2996,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->smuio.funcs = &smuio_v13_0_funcs;
 		break;
 	case IP_VERSION(13, 0, 3):
+	case IP_VERSION(13, 0, 11):
 		adev->smuio.funcs = &smuio_v13_0_3_funcs;
 		if (adev->smuio.funcs->get_pkg_type(adev) == AMDGPU_PKG_TYPE_APU) {
 			adev->flags |= AMD_IS_APU;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index c0ddbe7d6f0b..23cfce5aa1fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -121,9 +121,11 @@
  * - 3.59.0 - Cleared VRAM
  * - 3.60.0 - Add AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE (Vulkan requirement)
  * - 3.61.0 - Contains fix for RV/PCO compute queues
+ * - 3.62.0 - Add AMDGPU_IDS_FLAGS_MODE_PF, AMDGPU_IDS_FLAGS_MODE_VF & AMDGPU_IDS_FLAGS_MODE_PT
+ * - 3.63.0 - GFX12 display DCC supports 256B max compressed block size
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	61
+#define KMS_DRIVER_MINOR	63
 #define KMS_DRIVER_PATCHLEVEL	0
 
 /*
@@ -136,6 +138,8 @@ enum AMDGPU_DEBUG_MASK {
 	AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
 	AMDGPU_DEBUG_ENABLE_RAS_ACA = BIT(4),
 	AMDGPU_DEBUG_ENABLE_EXP_RESETS = BIT(5),
+	AMDGPU_DEBUG_DISABLE_GPU_RING_RESET = BIT(6),
+	AMDGPU_DEBUG_SMU_POOL = BIT(7),
 };
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -173,6 +177,7 @@ uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu;
 char *amdgpu_virtual_display;
 bool enforce_isolation;
+int amdgpu_modeset = -1;
 
 /* Specifies the default granularity for SVM, used in buffer
  * migration and restoration of backing memory when handling
@@ -283,6 +288,7 @@ module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
  * DOC: gttsize (int)
  * Restrict the size of GTT domain (for userspace use) in MiB for testing.
  * The default is -1 (Use value specified by TTM).
+ * This parameter is deprecated and will be removed in the future.
  */
 MODULE_PARM_DESC(gttsize, "Size of the GTT userspace domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
@@ -963,7 +969,7 @@ module_param_named_unsafe(reset_method, amdgpu_reset_method, int, 0644);
  * result in the GPU entering bad status when the number of total
  * faulty pages by ECC exceeds the threshold value.
  */
-MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = ignore threshold (default value), 0 = disable bad page retirement, -2 = driver sets threshold)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = ignore threshold (default value), 0 = disable bad page retirement, -2 = threshold determined by a formula, 0 < threshold < max records, user-defined threshold)");
 module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
 
 MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
@@ -1034,6 +1040,13 @@ module_param(enforce_isolation, bool, 0444);
 MODULE_PARM_DESC(enforce_isolation, "enforce process isolation between graphics and compute . enforce_isolation = on");
 
 /**
+ * DOC: modeset (int)
+ * Override nomodeset (1 = override, -1 = auto). The default is -1 (auto).
+ */
+MODULE_PARM_DESC(modeset, "Override nomodeset (1 = enable, -1 = auto)");
+module_param_named(modeset, amdgpu_modeset, int, 0444);
+
+/**
  * DOC: seamless (int)
  * Seamless boot will keep the image on the screen during the boot process.
  */
@@ -1049,6 +1062,11 @@ module_param_named(seamless, amdgpu_seamless, int, 0444);
  *   limits the VRAM size reported to ROCm applications to the visible
  *   size, usually 256MB.
  * - 0x4: Disable GPU soft recovery, always do a full reset
+ * - 0x8: Use VRAM for firmware loading
+ * - 0x10: Enable ACA based RAS logging
+ * - 0x20: Enable experimental resets
+ * - 0x40: Disable ring resets
+ * - 0x80: Use VRAM for SMU pool
  */
 MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default");
 module_param_named_unsafe(debug_mask, amdgpu_debug_mask, uint, 0444);
@@ -2221,6 +2239,15 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 		pr_info("debug: enable experimental reset features\n");
 		adev->debug_exp_resets = true;
 	}
+
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_DISABLE_GPU_RING_RESET) {
+		pr_info("debug: ring reset disabled\n");
+		adev->debug_disable_gpu_ring_reset = true;
+	}
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_SMU_POOL) {
+		pr_info("debug: use vram for smu pool\n");
+		adev->pm.smu_debug_mask |= SMU_DEBUG_POOL_USE_VRAM;
+	}
 }
 
 static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
@@ -2248,6 +2275,12 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	int ret, retry = 0, i;
 	bool supports_atomic = false;
 
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA ||
+	    (pdev->class >> 8) == PCI_CLASS_DISPLAY_OTHER) {
+		if (drm_firmware_drivers_only() && amdgpu_modeset == -1)
+			return -EINVAL;
+	}
+
 	/* skip devices which are owned by radeon */
 	for (i = 0; i < ARRAY_SIZE(amdgpu_unsupported_pciidlist); i++) {
 		if (amdgpu_unsupported_pciidlist[i] == pdev->device)
@@ -2981,9 +3014,6 @@ static int __init amdgpu_init(void)
 {
 	int r;
 
-	if (drm_firmware_drivers_only())
-		return -EINVAL;
-
 	r = amdgpu_sync_init();
 	if (r)
 		goto error_sync;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index 09c9194d5bd5..1ae88c459da5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -31,6 +31,7 @@
 
 #define FRU_EEPROM_MADDR_6      0x60000
 #define FRU_EEPROM_MADDR_8      0x80000
+#define FRU_EEPROM_MADDR_INV    0xFFFFF
 
 static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr)
 {
@@ -63,10 +64,10 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr)
 		switch (adev->asic_type) {
 		case CHIP_VEGA20:
 			/* D161 and D163 are the VG20 server SKUs */
-			if (strnstr(atom_ctx->vbios_pn, "D161",
-				    sizeof(atom_ctx->vbios_pn)) ||
-			    strnstr(atom_ctx->vbios_pn, "D163",
-				    sizeof(atom_ctx->vbios_pn))) {
+			if (atom_ctx && (strnstr(atom_ctx->vbios_pn, "D161",
+						 sizeof(atom_ctx->vbios_pn)) ||
+					 strnstr(atom_ctx->vbios_pn, "D163",
+						 sizeof(atom_ctx->vbios_pn)))) {
 				if (fru_addr)
 					*fru_addr = FRU_EEPROM_MADDR_6;
 				return true;
@@ -78,8 +79,8 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr)
 			return false;
 		}
 	case IP_VERSION(11, 0, 7):
-		if (strnstr(atom_ctx->vbios_pn, "D603",
-			    sizeof(atom_ctx->vbios_pn))) {
+		if (atom_ctx && strnstr(atom_ctx->vbios_pn, "D603",
+					sizeof(atom_ctx->vbios_pn))) {
 			if (strnstr(atom_ctx->vbios_pn, "D603GLXE",
 				    sizeof(atom_ctx->vbios_pn))) {
 				return false;
@@ -94,8 +95,8 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr)
 		}
 	case IP_VERSION(13, 0, 2):
 		/* All Aldebaran SKUs have an FRU */
-		if (!strnstr(atom_ctx->vbios_pn, "D673",
-			     sizeof(atom_ctx->vbios_pn)))
+		if (atom_ctx && !strnstr(atom_ctx->vbios_pn, "D673",
+					 sizeof(atom_ctx->vbios_pn)))
 			if (fru_addr)
 				*fru_addr = FRU_EEPROM_MADDR_6;
 		return true;
@@ -104,6 +105,10 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr)
 			if (fru_addr)
 				*fru_addr = FRU_EEPROM_MADDR_8;
 			return true;
+	case IP_VERSION(13, 0, 12):
+			if (fru_addr)
+				*fru_addr = FRU_EEPROM_MADDR_INV;
+			return true;
 	default:
 		return false;
 	}
@@ -120,6 +125,10 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 	if (!is_fru_eeprom_supported(adev, &fru_addr))
 		return 0;
 
+	/* FRU data avaialble, but no direct EEPROM access */
+	if (fru_addr == FRU_EEPROM_MADDR_INV)
+		return 0;
+
 	if (!adev->fru_info) {
 		adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL);
 		if (!adev->fru_info)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c1f35ded684e..72af5e5a894a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -771,18 +771,8 @@ int amdgpu_gfx_enable_kgq(struct amdgpu_device *adev, int xcc_id)
 	return r;
 }
 
-/* amdgpu_gfx_off_ctrl - Handle gfx off feature enable/disable
- *
- * @adev: amdgpu_device pointer
- * @bool enable true: enable gfx off feature, false: disable gfx off feature
- *
- * 1. gfx off feature will be enabled by gfx ip after gfx cg gp enabled.
- * 2. other client can send request to disable gfx off feature, the request should be honored.
- * 3. other client can cancel their request of disable gfx off feature
- * 4. other client should not send request to enable gfx off feature before disable gfx off feature.
- */
-
-void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
+static void amdgpu_gfx_do_off_ctrl(struct amdgpu_device *adev, bool enable,
+				   bool no_delay)
 {
 	unsigned long delay = GFX_OFF_DELAY_ENABLE;
 
@@ -804,7 +794,7 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
 			/* If going to s2idle, no need to wait */
-			if (adev->in_s0ix) {
+			if (no_delay) {
 				if (!amdgpu_dpm_set_powergating_by_smu(adev,
 						AMD_IP_BLOCK_TYPE_GFX, true, 0))
 					adev->gfx.gfx_off_state = true;
@@ -836,6 +826,43 @@ unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 
+/* amdgpu_gfx_off_ctrl - Handle gfx off feature enable/disable
+ *
+ * @adev: amdgpu_device pointer
+ * @bool enable true: enable gfx off feature, false: disable gfx off feature
+ *
+ * 1. gfx off feature will be enabled by gfx ip after gfx cg pg enabled.
+ * 2. other client can send request to disable gfx off feature, the request should be honored.
+ * 3. other client can cancel their request of disable gfx off feature
+ * 4. other client should not send request to enable gfx off feature before disable gfx off feature.
+ *
+ * gfx off allow will be delayed by GFX_OFF_DELAY_ENABLE ms.
+ */
+void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
+{
+	/* If going to s2idle, no need to wait */
+	bool no_delay = adev->in_s0ix ? true : false;
+
+	amdgpu_gfx_do_off_ctrl(adev, enable, no_delay);
+}
+
+/* amdgpu_gfx_off_ctrl_immediate - Handle gfx off feature enable/disable
+ *
+ * @adev: amdgpu_device pointer
+ * @bool enable true: enable gfx off feature, false: disable gfx off feature
+ *
+ * 1. gfx off feature will be enabled by gfx ip after gfx cg pg enabled.
+ * 2. other client can send request to disable gfx off feature, the request should be honored.
+ * 3. other client can cancel their request of disable gfx off feature
+ * 4. other client should not send request to enable gfx off feature before disable gfx off feature.
+ *
+ * gfx off allow will be issued immediately.
+ */
+void amdgpu_gfx_off_ctrl_immediate(struct amdgpu_device *adev, bool enable)
+{
+	amdgpu_gfx_do_off_ctrl(adev, enable, true);
+}
+
 int amdgpu_set_gfx_off_residency(struct amdgpu_device *adev, bool value)
 {
 	int r = 0;
@@ -1638,15 +1665,8 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 	}
 
 	mutex_lock(&adev->enforce_isolation_mutex);
-	for (i = 0; i < num_partitions; i++) {
-		if (adev->enforce_isolation[i] && !partition_values[i])
-			/* Going from enabled to disabled */
-			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-		else if (!adev->enforce_isolation[i] && partition_values[i])
-			/* Going from disabled to enabled */
-			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
+	for (i = 0; i < num_partitions; i++)
 		adev->enforce_isolation[i] = partition_values[i];
-	}
 	mutex_unlock(&adev->enforce_isolation_mutex);
 
 	amdgpu_mes_update_enforce_isolation(adev);
@@ -1975,8 +1995,8 @@ void amdgpu_gfx_enforce_isolation_handler(struct work_struct *work)
 		if (adev->kfd.init_complete) {
 			WARN_ON_ONCE(!adev->gfx.kfd_sch_inactive[idx]);
 			WARN_ON_ONCE(adev->gfx.kfd_sch_req_count[idx]);
-				amdgpu_amdkfd_start_sched(adev, idx);
-				adev->gfx.kfd_sch_inactive[idx] = false;
+			amdgpu_amdkfd_start_sched(adev, idx);
+			adev->gfx.kfd_sch_inactive[idx] = false;
 		}
 	}
 	mutex_unlock(&adev->enforce_isolation_mutex);
@@ -2115,6 +2135,80 @@ void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring)
 		amdgpu_gfx_kfd_sch_ctrl(adev, idx, true);
 }
 
+void amdgpu_gfx_profile_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device, gfx.idle_work.work);
+	enum PP_SMC_POWER_PROFILE profile;
+	u32 i, fences = 0;
+	int r;
+
+	if (adev->gfx.num_gfx_rings)
+		profile = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
+	else
+		profile = PP_SMC_POWER_PROFILE_COMPUTE;
+
+	for (i = 0; i < AMDGPU_MAX_GFX_RINGS; ++i)
+		fences += amdgpu_fence_count_emitted(&adev->gfx.gfx_ring[i]);
+	for (i = 0; i < (AMDGPU_MAX_COMPUTE_RINGS * AMDGPU_MAX_GC_INSTANCES); ++i)
+		fences += amdgpu_fence_count_emitted(&adev->gfx.compute_ring[i]);
+	if (!fences && !atomic_read(&adev->gfx.total_submission_cnt)) {
+		mutex_lock(&adev->gfx.workload_profile_mutex);
+		if (adev->gfx.workload_profile_active) {
+			r = amdgpu_dpm_switch_power_profile(adev, profile, false);
+			if (r)
+				dev_warn(adev->dev, "(%d) failed to disable %s power profile mode\n", r,
+					 profile == PP_SMC_POWER_PROFILE_FULLSCREEN3D ?
+					 "fullscreen 3D" : "compute");
+			adev->gfx.workload_profile_active = false;
+		}
+		mutex_unlock(&adev->gfx.workload_profile_mutex);
+	} else {
+		schedule_delayed_work(&adev->gfx.idle_work, GFX_PROFILE_IDLE_TIMEOUT);
+	}
+}
+
+void amdgpu_gfx_profile_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	enum PP_SMC_POWER_PROFILE profile;
+	int r;
+
+	if (adev->gfx.num_gfx_rings)
+		profile = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
+	else
+		profile = PP_SMC_POWER_PROFILE_COMPUTE;
+
+	atomic_inc(&adev->gfx.total_submission_cnt);
+
+	cancel_delayed_work_sync(&adev->gfx.idle_work);
+
+	/* We can safely return early here because we've cancelled the
+	 * the delayed work so there is no one else to set it to false
+	 * and we don't care if someone else sets it to true.
+	 */
+	if (adev->gfx.workload_profile_active)
+		return;
+
+	mutex_lock(&adev->gfx.workload_profile_mutex);
+	if (!adev->gfx.workload_profile_active) {
+		r = amdgpu_dpm_switch_power_profile(adev, profile, true);
+		if (r)
+			dev_warn(adev->dev, "(%d) failed to disable %s power profile mode\n", r,
+				 profile == PP_SMC_POWER_PROFILE_FULLSCREEN3D ?
+				 "fullscreen 3D" : "compute");
+		adev->gfx.workload_profile_active = true;
+	}
+	mutex_unlock(&adev->gfx.workload_profile_mutex);
+}
+
+void amdgpu_gfx_profile_ring_end_use(struct amdgpu_ring *ring)
+{
+	atomic_dec(&ring->adev->gfx.total_submission_cnt);
+
+	schedule_delayed_work(&ring->adev->gfx.idle_work, GFX_PROFILE_IDLE_TIMEOUT);
+}
+
 /*
  * debugfs for to enable/disable gfx job submission to specific core.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 8b5bd63b5773..87e862188766 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -57,6 +57,9 @@ enum amdgpu_gfx_pipe_priority {
 #define AMDGPU_GFX_QUEUE_PRIORITY_MINIMUM  0
 #define AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM  15
 
+/* 1 second timeout */
+#define GFX_PROFILE_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
 enum amdgpu_gfx_partition {
 	AMDGPU_SPX_PARTITION_MODE = 0,
 	AMDGPU_DPX_PARTITION_MODE = 1,
@@ -476,6 +479,11 @@ struct amdgpu_gfx {
 	bool				kfd_sch_inactive[MAX_XCP];
 	unsigned long			enforce_isolation_jiffies[MAX_XCP];
 	unsigned long			enforce_isolation_time[MAX_XCP];
+
+	atomic_t			total_submission_cnt;
+	struct delayed_work		idle_work;
+	bool				workload_profile_active;
+	struct mutex                    workload_profile_mutex;
 };
 
 struct amdgpu_gfx_ras_reg_entry {
@@ -547,6 +555,7 @@ int amdgpu_gfx_me_queue_to_bit(struct amdgpu_device *adev, int me,
 bool amdgpu_gfx_is_me_queue_enabled(struct amdgpu_device *adev, int me,
 				    int pipe, int queue);
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable);
+void amdgpu_gfx_off_ctrl_immediate(struct amdgpu_device *adev, bool enable);
 int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value);
 int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block);
 void amdgpu_gfx_ras_fini(struct amdgpu_device *adev);
@@ -584,6 +593,11 @@ void amdgpu_gfx_cleaner_shader_init(struct amdgpu_device *adev,
 void amdgpu_gfx_enforce_isolation_handler(struct work_struct *work);
 void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring);
 void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring);
+
+void amdgpu_gfx_profile_idle_work_handler(struct work_struct *work);
+void amdgpu_gfx_profile_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_gfx_profile_ring_end_use(struct amdgpu_ring *ring);
+
 void amdgpu_debugfs_gfx_sched_mask_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_compute_sched_mask_init(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 1c19a65e6553..464625282872 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -269,7 +269,7 @@ void amdgpu_gmc_sysvm_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc
  * @mc: memory controller structure holding memory information
  * @gart_placement: GART placement policy with respect to VRAM
  *
- * Function will place try to place GART before or after VRAM.
+ * Function will try to place GART before or after VRAM.
  * If GART size is bigger than space left then we ajust GART size.
  * Thus function will never fails.
  */
@@ -573,6 +573,7 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] = {0};
 	unsigned i;
 	unsigned vmhub, inv_eng;
+	struct amdgpu_ring *shared_ring;
 
 	/* init the vm inv eng for all vmhubs */
 	for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS) {
@@ -591,7 +592,12 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 
 		if (ring == &adev->mes.ring[0] ||
 		    ring == &adev->mes.ring[1] ||
-		    ring == &adev->umsch_mm.ring)
+		    ring == &adev->umsch_mm.ring ||
+		    ring == &adev->cper.ring_buf)
+			continue;
+
+		/* Skip if the ring is a shared ring */
+		if (amdgpu_sdma_is_shared_inv_eng(adev, ring))
 			continue;
 
 		inv_eng = ffs(vm_inv_engs[vmhub]);
@@ -606,6 +612,21 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 
 		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
 			 ring->name, ring->vm_inv_eng, ring->vm_hub);
+		/* SDMA has a special packet which allows it to use the same
+		 * invalidation engine for all the rings in one instance.
+		 * Therefore, we do not allocate a separate VM invalidation engine
+		 * for SDMA page rings. Instead, they share the VM invalidation
+		 * engine with the SDMA gfx ring. This change ensures efficient
+		 * resource management and avoids the issue of insufficient VM
+		 * invalidation engines.
+		 */
+		shared_ring = amdgpu_sdma_get_shared_ring(adev, ring);
+		if (shared_ring) {
+			shared_ring->vm_inv_eng = ring->vm_inv_eng;
+			dev_info(adev->dev, "ring %s shares VM invalidation engine %u with ring %s on hub %u\n",
+					ring->name, ring->vm_inv_eng, shared_ring->name, ring->vm_hub);
+			continue;
+		}
 	}
 
 	return 0;
@@ -851,6 +872,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		/* Don't enable it by default yet.
 		 */
 		if (amdgpu_tmz < 1) {
@@ -888,6 +910,7 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
 				gc_ver == IP_VERSION(9, 4, 2) ||
 				gc_ver == IP_VERSION(9, 4, 3) ||
 				gc_ver == IP_VERSION(9, 4, 4) ||
+				gc_ver == IP_VERSION(9, 5, 0) ||
 				gc_ver >= IP_VERSION(10, 3, 0));
 
 	if (!amdgpu_sriov_xnack_support(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 459a30fe239f..bd7fc123b8f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -29,6 +29,7 @@
 #include <linux/types.h>
 
 #include "amdgpu_irq.h"
+#include "amdgpu_xgmi.h"
 #include "amdgpu_ras.h"
 
 /* VA hole for 48bit addresses on Vega10 */
@@ -174,28 +175,6 @@ struct amdgpu_gmc_funcs {
 	bool (*need_reset_on_init)(struct amdgpu_device *adev);
 };
 
-struct amdgpu_xgmi_ras {
-	struct amdgpu_ras_block_object ras_block;
-};
-
-struct amdgpu_xgmi {
-	/* from psp */
-	u64 node_id;
-	u64 hive_id;
-	/* fixed per family */
-	u64 node_segment_size;
-	/* physical node (0-3) */
-	unsigned physical_node_id;
-	/* number of nodes (0-4) */
-	unsigned num_physical_nodes;
-	/* gpu list in the same hive */
-	struct list_head head;
-	bool supported;
-	struct ras_common_if *ras_if;
-	bool connected_to_cpu;
-	struct amdgpu_xgmi_ras *ras;
-};
-
 struct amdgpu_mem_partition_info {
 	union {
 		struct {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index f0765ccde668..8179d0814db9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -225,6 +225,25 @@ void amdgpu_i2c_destroy(struct amdgpu_i2c_chan *i2c)
 	kfree(i2c);
 }
 
+void amdgpu_i2c_init(struct amdgpu_device *adev)
+{
+	if (!adev->is_atom_fw) {
+		if (!amdgpu_device_has_dc_support(adev)) {
+			amdgpu_atombios_i2c_init(adev);
+		} else {
+			switch (adev->asic_type) {
+			case CHIP_POLARIS10:
+			case CHIP_POLARIS11:
+			case CHIP_POLARIS12:
+				amdgpu_atombios_oem_i2c_init(adev, 0x97);
+				break;
+			default:
+				break;
+			}
+		}
+	}
+}
+
 /* remove all the buses */
 void amdgpu_i2c_fini(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.h
index 21e3d1dad0a1..1d3d3806e0dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.h
@@ -28,6 +28,7 @@ struct amdgpu_i2c_chan *amdgpu_i2c_create(struct drm_device *dev,
 					  const struct amdgpu_i2c_bus_rec *rec,
 					  const char *name);
 void amdgpu_i2c_destroy(struct amdgpu_i2c_chan *i2c);
+void amdgpu_i2c_init(struct amdgpu_device *adev);
 void amdgpu_i2c_fini(struct amdgpu_device *adev);
 struct amdgpu_i2c_chan *
 amdgpu_i2c_lookup(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 8e712a11aba5..4c4e087230ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -209,7 +209,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_ring *ring,
 		return 0;
 	}
 
-	fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_KERNEL);
+	fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_NOWAIT);
 	if (!fences)
 		return -ENOMEM;
 
@@ -287,46 +287,34 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 	    (*id)->flushed_updates < updates ||
 	    !(*id)->last_flush ||
 	    ((*id)->last_flush->context != fence_context &&
-	     !dma_fence_is_signaled((*id)->last_flush))) {
+	     !dma_fence_is_signaled((*id)->last_flush)))
+		needs_flush = true;
+
+	if ((*id)->owner != vm->immediate.fence_context ||
+	    (!adev->vm_manager.concurrent_flush && needs_flush)) {
 		struct dma_fence *tmp;
 
-		/* Wait for the gang to be assembled before using a
-		 * reserved VMID or otherwise the gang could deadlock.
+		/* Don't use per engine and per process VMID at the
+		 * same time
 		 */
-		tmp = amdgpu_device_get_gang(adev);
-		if (!dma_fence_is_signaled(tmp) && tmp != job->gang_submit) {
+		if (adev->vm_manager.concurrent_flush)
+			ring = NULL;
+
+		/* to prevent one context starved by another context */
+		(*id)->pd_gpu_addr = 0;
+		tmp = amdgpu_sync_peek_fence(&(*id)->active, ring);
+		if (tmp) {
 			*id = NULL;
-			*fence = tmp;
+			*fence = dma_fence_get(tmp);
 			return 0;
 		}
-		dma_fence_put(tmp);
-
-		/* Make sure the id is owned by the gang before proceeding */
-		if (!job->gang_submit ||
-		    (*id)->owner != vm->immediate.fence_context) {
-
-			/* Don't use per engine and per process VMID at the
-			 * same time
-			 */
-			if (adev->vm_manager.concurrent_flush)
-				ring = NULL;
-
-			/* to prevent one context starved by another context */
-			(*id)->pd_gpu_addr = 0;
-			tmp = amdgpu_sync_peek_fence(&(*id)->active, ring);
-			if (tmp) {
-				*id = NULL;
-				*fence = dma_fence_get(tmp);
-				return 0;
-			}
-		}
-		needs_flush = true;
 	}
 
 	/* Good we can use this VMID. Remember this submission as
 	* user of the VMID.
 	*/
-	r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished);
+	r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished,
+			      GFP_NOWAIT);
 	if (r)
 		return r;
 
@@ -385,7 +373,8 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
 		 * user of the VMID.
 		 */
 		r = amdgpu_sync_fence(&(*id)->active,
-				      &job->base.s_fence->finished);
+				      &job->base.s_fence->finished,
+				      GFP_NOWAIT);
 		if (r)
 			return r;
 
@@ -422,7 +411,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	if (r || !idle)
 		goto error;
 
-	if (amdgpu_vmid_uses_reserved(adev, vm, vmhub)) {
+	if (amdgpu_vmid_uses_reserved(vm, vmhub)) {
 		r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence);
 		if (r || !id)
 			goto error;
@@ -437,7 +426,8 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 
 			/* Remember this submission as user of the VMID */
 			r = amdgpu_sync_fence(&id->active,
-					      &job->base.s_fence->finished);
+					      &job->base.s_fence->finished,
+					      GFP_NOWAIT);
 			if (r)
 				goto error;
 
@@ -474,19 +464,14 @@ error:
 
 /*
  * amdgpu_vmid_uses_reserved - check if a VM will use a reserved VMID
- * @adev: amdgpu_device pointer
  * @vm: the VM to check
  * @vmhub: the VMHUB which will be used
  *
  * Returns: True if the VM will use a reserved VMID.
  */
-bool amdgpu_vmid_uses_reserved(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm, unsigned int vmhub)
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub)
 {
-	return vm->reserved_vmid[vmhub] ||
-		(adev->enforce_isolation[(vm->root.bo->xcp_id != AMDGPU_XCP_NO_PARTITION) ?
-					 vm->root.bo->xcp_id : 0] &&
-		 AMDGPU_IS_GFXHUB(vmhub));
+	return vm->reserved_vmid[vmhub];
 }
 
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 4012fb2dd08a..240fa6751260 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -78,8 +78,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
-bool amdgpu_vmid_uses_reserved(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm, unsigned int vmhub);
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub);
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
 				unsigned vmhub);
 void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index 7d4395a5d8ac..b0a88f92cd82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -78,6 +78,9 @@ struct amdgpu_ih_ring {
 #define amdgpu_ih_ts_after(t1, t2) \
 		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL)
 
+#define amdgpu_ih_ts_after_or_equal(t1, t2) \
+		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL)
+
 /* provided by the ih block */
 struct amdgpu_ih_funcs {
 	/* ring read/write ptr handling, called from interrupt context */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
index 732744488b03..43fc941dfa57 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
@@ -124,7 +124,7 @@ static int isp_early_init(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool isp_is_idle(void *handle)
+static bool isp_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h
index b03664c66dd6..4f3b7b5d9c1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h
@@ -50,6 +50,7 @@ struct amdgpu_isp {
 	struct mfd_cell *isp_cell;
 	struct resource *isp_res;
 	struct resource *isp_i2c_res;
+	struct resource *isp_gpio_res;
 	struct isp_platform_data *isp_pdata;
 	unsigned int harvest_config;
 	const struct firmware	*fw;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 100f04475943..acb21fc8b3ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -130,29 +130,48 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		amdgpu_vm_put_task_info(ti);
 	}
 
-	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
-
 	/* attempt a per ring reset */
-	if (amdgpu_gpu_recovery &&
-	    ring->funcs->reset) {
+	if (unlikely(adev->debug_disable_gpu_ring_reset)) {
+		dev_err(adev->dev, "Ring reset disabled by debug mask\n");
+	} else if (amdgpu_gpu_recovery && ring->funcs->reset) {
+		bool is_guilty;
+
 		dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name);
 		/* stop the scheduler, but don't mess with the
 		 * bad job yet because if ring reset fails
 		 * we'll fall back to full GPU reset.
 		 */
 		drm_sched_wqueue_stop(&ring->sched);
+
+		/* for engine resets, we need to reset the engine,
+		 * but individual queues may be unaffected.
+		 * check here to make sure the accounting is correct.
+		 */
+		if (ring->funcs->is_guilty)
+			is_guilty = ring->funcs->is_guilty(ring);
+		else
+			is_guilty = true;
+
+		if (is_guilty)
+			dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
+
 		r = amdgpu_ring_reset(ring, job->vmid);
 		if (!r) {
 			if (amdgpu_ring_sched_ready(ring))
 				drm_sched_stop(&ring->sched, s_job);
-			atomic_inc(&ring->adev->gpu_reset_counter);
-			amdgpu_fence_driver_force_completion(ring);
+			if (is_guilty) {
+				atomic_inc(&ring->adev->gpu_reset_counter);
+				amdgpu_fence_driver_force_completion(ring);
+			}
 			if (amdgpu_ring_sched_ready(ring))
 				drm_sched_start(&ring->sched, 0);
+			dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
+			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
 			goto exit;
 		}
 		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
 	}
+	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
 		struct amdgpu_reset_context reset_context;
@@ -342,17 +361,24 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
-	struct dma_fence *fence = NULL;
+	struct dma_fence *fence;
 	int r;
 
 	r = drm_sched_entity_error(s_entity);
 	if (r)
 		goto error;
 
-	if (job->gang_submit)
+	if (job->gang_submit) {
 		fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit);
+		if (fence)
+			return fence;
+	}
 
-	if (!fence && job->vm && !job->vmid) {
+	fence = amdgpu_device_enforce_isolation(ring->adev, ring, job);
+	if (fence)
+		return fence;
+
+	if (job->vm && !job->vmid) {
 		r = amdgpu_vmid_grab(job->vm, ring, job, &fence);
 		if (r) {
 			dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", r);
@@ -365,9 +391,10 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
 		 */
 		if (!fence)
 			job->vm = NULL;
+		return fence;
 	}
 
-	return fence;
+	return NULL;
 
 error:
 	dma_fence_set_error(&job->base.s_fence->finished, r);
@@ -411,8 +438,24 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	return fence;
 }
 
-#define to_drm_sched_job(sched_job)		\
-		container_of((sched_job), struct drm_sched_job, queue_node)
+/*
+ * This is a duplicate function from DRM scheduler sched_internal.h.
+ * Plan is to remove it when amdgpu_job_stop_all_jobs_on_sched is removed, due
+ * latter being incorrect and racy.
+ *
+ * See https://lore.kernel.org/amd-gfx/44edde63-7181-44fb-a4f7-94e50514f539@amd.com/
+ */
+static struct drm_sched_job *
+drm_sched_entity_queue_pop(struct drm_sched_entity *entity)
+{
+	struct spsc_node *node;
+
+	node = spsc_queue_pop(&entity->job_queue);
+	if (!node)
+		return NULL;
+
+	return container_of(node, struct drm_sched_job, queue_node);
+}
 
 void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 {
@@ -425,7 +468,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 		struct drm_sched_rq *rq = sched->sched_rq[i];
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {
-			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
+			while ((s_job = drm_sched_entity_queue_pop(s_entity))) {
 				struct drm_sched_fence *s_fence = s_job->s_fence;
 
 				dma_fence_signal(&s_fence->scheduled);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index b6d2eb049f54..dda29132dfb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -33,6 +33,7 @@
 #define JPEG_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
 static void amdgpu_jpeg_idle_work_handler(struct work_struct *work);
+static void amdgpu_jpeg_reg_dump_fini(struct amdgpu_device *adev);
 
 int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
 {
@@ -85,6 +86,9 @@ int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
 			amdgpu_ring_fini(&adev->jpeg.inst[i].ring_dec[j]);
 	}
 
+	if (adev->jpeg.reg_list)
+		amdgpu_jpeg_reg_dump_fini(adev);
+
 	mutex_destroy(&adev->jpeg.jpeg_pg_lock);
 
 	return 0;
@@ -452,3 +456,83 @@ void amdgpu_jpeg_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 			device_remove_file(adev->dev, &dev_attr_jpeg_reset_mask);
 	}
 }
+
+int amdgpu_jpeg_reg_dump_init(struct amdgpu_device *adev,
+			       const struct amdgpu_hwip_reg_entry *reg, u32 count)
+{
+	adev->jpeg.ip_dump = kcalloc(adev->jpeg.num_jpeg_inst * count,
+				     sizeof(uint32_t), GFP_KERNEL);
+	if (!adev->jpeg.ip_dump) {
+		DRM_ERROR("Failed to allocate memory for JPEG IP Dump\n");
+		return -ENOMEM;
+	}
+	adev->jpeg.reg_list = reg;
+	adev->jpeg.reg_count = count;
+
+	return 0;
+}
+
+static void amdgpu_jpeg_reg_dump_fini(struct amdgpu_device *adev)
+{
+	kfree(adev->jpeg.ip_dump);
+	adev->jpeg.reg_list = NULL;
+	adev->jpeg.reg_count = 0;
+}
+
+void amdgpu_jpeg_dump_ip_state(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	u32 inst_off, inst_id, is_powered;
+	int i, j;
+
+	if (!adev->jpeg.ip_dump)
+		return;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		inst_id = GET_INST(JPEG, i);
+		inst_off = i * adev->jpeg.reg_count;
+		/* check power status from UVD_JPEG_POWER_STATUS */
+		adev->jpeg.ip_dump[inst_off] =
+			RREG32(SOC15_REG_ENTRY_OFFSET_INST(adev->jpeg.reg_list[0],
+							   inst_id));
+		is_powered = ((adev->jpeg.ip_dump[inst_off] & 0x1) != 1);
+
+		if (is_powered)
+			for (j = 1; j < adev->jpeg.reg_count; j++)
+				adev->jpeg.ip_dump[inst_off + j] =
+					RREG32(SOC15_REG_ENTRY_OFFSET_INST(adev->jpeg.reg_list[j],
+									   inst_id));
+	}
+}
+
+void amdgpu_jpeg_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	u32 inst_off, is_powered;
+	int i, j;
+
+	if (!adev->jpeg.ip_dump)
+		return;
+
+	drm_printf(p, "num_instances:%d\n", adev->jpeg.num_jpeg_inst);
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+		if (adev->jpeg.harvest_config & (1 << i)) {
+			drm_printf(p, "\nHarvested Instance:JPEG%d Skipping dump\n", i);
+			continue;
+		}
+
+		inst_off = i * adev->jpeg.reg_count;
+		is_powered = ((adev->jpeg.ip_dump[inst_off] & 0x1) != 1);
+
+		if (is_powered) {
+			drm_printf(p, "Active Instance:JPEG%d\n", i);
+			for (j = 0; j < adev->jpeg.reg_count; j++)
+				drm_printf(p, "%-50s \t 0x%08x\n", adev->jpeg.reg_list[j].reg_name,
+					   adev->jpeg.ip_dump[inst_off + j]);
+		} else
+			drm_printf(p, "\nInactive Instance:JPEG%d\n", i);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
index d9cb343a8708..4f0775e39b54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
@@ -92,6 +92,14 @@
 		*adev->jpeg.inst[inst_idx].dpg_sram_curr_addr++ = value;	\
 	} while (0)
 
+struct amdgpu_hwip_reg_entry;
+
+enum amdgpu_jpeg_caps {
+	AMDGPU_JPEG_RRMT_ENABLED,
+};
+
+#define AMDGPU_JPEG_CAPS(caps) BIT(AMDGPU_JPEG_##caps)
+
 struct amdgpu_jpeg_reg{
 	unsigned jpeg_pitch[AMDGPU_MAX_JPEG_RINGS];
 };
@@ -130,6 +138,10 @@ struct amdgpu_jpeg {
 	uint8_t num_inst_per_aid;
 	bool	indirect_sram;
 	uint32_t supported_reset;
+	uint32_t caps;
+	u32 *ip_dump;
+	u32 reg_count;
+	const struct amdgpu_hwip_reg_entry *reg_list;
 };
 
 int amdgpu_jpeg_sw_init(struct amdgpu_device *adev);
@@ -154,5 +166,9 @@ int amdgpu_jpeg_psp_update_sram(struct amdgpu_device *adev, int inst_idx,
 void amdgpu_debugfs_jpeg_sched_mask_init(struct amdgpu_device *adev);
 int amdgpu_jpeg_sysfs_reset_mask_init(struct amdgpu_device *adev);
 void amdgpu_jpeg_sysfs_reset_mask_fini(struct amdgpu_device *adev);
+int amdgpu_jpeg_reg_dump_init(struct amdgpu_device *adev,
+			       const struct amdgpu_hwip_reg_entry *reg, u32 count);
+void amdgpu_jpeg_dump_ip_state(struct amdgpu_ip_block *ip_block);
+void amdgpu_jpeg_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p);
 
 #endif /*__AMDGPU_JPEG_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 98528ee94c15..27bfe9c8af06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -459,7 +459,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
 			if (adev->vcn.harvest_config & (1 << i))
 				continue;
 
-			for (j = 0; j < adev->vcn.num_enc_rings; j++)
+			for (j = 0; j < adev->vcn.inst[i].num_enc_rings; j++)
 				if (adev->vcn.inst[i].ring_enc[j].sched.ready)
 					++num_rings;
 		}
@@ -888,6 +888,15 @@ out:
 		if (adev->gfx.config.ta_cntl2_truncate_coord_mode)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD;
 
+		if (amdgpu_passthrough(adev))
+			dev_info->ids_flags |= (AMDGPU_IDS_FLAGS_MODE_PT <<
+						AMDGPU_IDS_FLAGS_MODE_SHIFT) &
+						AMDGPU_IDS_FLAGS_MODE_MASK;
+		else if (amdgpu_sriov_vf(adev))
+			dev_info->ids_flags |= (AMDGPU_IDS_FLAGS_MODE_VF <<
+						AMDGPU_IDS_FLAGS_MODE_SHIFT) &
+						AMDGPU_IDS_FLAGS_MODE_MASK;
+
 		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		vm_size -= AMDGPU_VA_RESERVED_TOP;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 709c11cbeabd..85f774063f9b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -145,9 +145,8 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 	adev->mes.vmid_mask_gfxhub = 0xffffff00;
 
 	for (i = 0; i < AMDGPU_MES_MAX_COMPUTE_PIPES; i++) {
-		/* use only 1st MEC pipes */
-		if (i >= adev->gfx.mec.num_pipe_per_mec)
-			continue;
+		if (i >= (adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_mec))
+			break;
 		adev->mes.compute_hqd_mask[i] = 0xc;
 	}
 
@@ -155,14 +154,9 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 		adev->mes.gfx_hqd_mask[i] = i ? 0 : 0xfffffffe;
 
 	for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) {
-		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) <
-		    IP_VERSION(6, 0, 0))
-			adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc;
-		/* zero sdma_hqd_mask for non-existent engine */
-		else if (adev->sdma.num_instances == 1)
-			adev->mes.sdma_hqd_mask[i] = i ? 0 : 0xfc;
-		else
-			adev->mes.sdma_hqd_mask[i] = 0xfc;
+		if (i >= adev->sdma.num_instances)
+			break;
+		adev->mes.sdma_hqd_mask[i] = 0xfc;
 	}
 
 	for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) {
@@ -1336,14 +1330,14 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
 		DRM_ERROR("failed to do vm_bo_update on meta data\n");
 		goto error_del_bo_va;
 	}
-	amdgpu_sync_fence(&sync, bo_va->last_pt_update);
+	amdgpu_sync_fence(&sync, bo_va->last_pt_update, GFP_KERNEL);
 
 	r = amdgpu_vm_update_pdes(adev, vm, false);
 	if (r) {
 		DRM_ERROR("failed to update pdes on meta data\n");
 		goto error_del_bo_va;
 	}
-	amdgpu_sync_fence(&sync, vm->last_update);
+	amdgpu_sync_fence(&sync, vm->last_update, GFP_KERNEL);
 
 	amdgpu_sync_wait(&sync, false);
 	drm_exec_fini(&exec);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index e98ea7ede1ba..da2c9a8cb3e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -56,7 +56,7 @@ enum amdgpu_mes_priority_level {
 
 struct amdgpu_mes_funcs;
 
-enum admgpu_mes_pipe {
+enum amdgpu_mes_pipe {
 	AMDGPU_MES_SCHED_PIPE = 0,
 	AMDGPU_MES_KIQ_PIPE,
 	AMDGPU_MAX_MES_PIPES = 2,
@@ -143,9 +143,9 @@ struct amdgpu_mes {
 	const struct amdgpu_mes_funcs   *funcs;
 
 	/* mes resource_1 bo*/
-	struct amdgpu_bo    *resource_1;
-	uint64_t            resource_1_gpu_addr;
-	void                *resource_1_addr;
+	struct amdgpu_bo    *resource_1[AMDGPU_MAX_MES_PIPES];
+	uint64_t            resource_1_gpu_addr[AMDGPU_MAX_MES_PIPES];
+	void                *resource_1_addr[AMDGPU_MAX_MES_PIPES];
 
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 5e3faefc5510..6da4f946cac0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -609,6 +609,7 @@ struct amdgpu_i2c_adapter {
 	struct i2c_adapter base;
 
 	struct ddc_service *ddc_service;
+	bool oem;
 };
 
 #define TO_DM_AUX(x) container_of((x), struct amdgpu_dm_dp_aux, aux)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 96f4b8904e9a..80cd6f5273db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1295,28 +1295,36 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	if (abo->kfd_bo)
 		amdgpu_amdkfd_release_notify(abo);
 
-	/* We only remove the fence if the resv has individualized. */
-	WARN_ON_ONCE(bo->type == ttm_bo_type_kernel
-			&& bo->base.resv != &bo->base._resv);
-	if (bo->base.resv == &bo->base._resv)
-		amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo);
+	/*
+	 * We lock the private dma_resv object here and since the BO is about to
+	 * be released nobody else should have a pointer to it.
+	 * So when this locking here fails something is wrong with the reference
+	 * counting.
+	 */
+	if (WARN_ON_ONCE(!dma_resv_trylock(&bo->base._resv)))
+		return;
+
+	amdgpu_amdkfd_remove_all_eviction_fences(abo);
 
 	if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM ||
 	    !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) ||
 	    adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev)))
-		return;
+		goto out;
 
-	if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))
-		return;
+	r = dma_resv_reserve_fences(&bo->base._resv, 1);
+	if (r)
+		goto out;
 
-	r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true);
-	if (!WARN_ON(r)) {
-		amdgpu_vram_mgr_set_cleared(bo->resource);
-		amdgpu_bo_fence(abo, fence, false);
-		dma_fence_put(fence);
-	}
+	r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true);
+	if (WARN_ON(r))
+		goto out;
+
+	amdgpu_vram_mgr_set_cleared(bo->resource);
+	dma_resv_add_fence(&bo->base._resv, fence, DMA_RESV_USAGE_KERNEL);
+	dma_fence_put(fence);
 
-	dma_resv_unlock(bo->base.resv);
+out:
+	dma_resv_unlock(&bo->base._resv);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e5fc80ed06ea..d54bb1377262 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -44,7 +44,7 @@
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_atomfirmware.h"
 
-#define AMD_VBIOS_FILE_MAX_SIZE_B      (1024*1024*3)
+#define AMD_VBIOS_FILE_MAX_SIZE_B      (1024*1024*16)
 
 static int psp_load_smu_fw(struct psp_context *psp);
 static int psp_rap_terminate(struct psp_context *psp);
@@ -153,6 +153,9 @@ static int psp_init_sriov_microcode(struct psp_context *psp)
 		adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MES1_DATA;
 		ret = psp_init_cap_microcode(psp, ucode_prefix);
 		break;
+	case IP_VERSION(13, 0, 12):
+		ret = psp_init_ta_microcode(psp, ucode_prefix);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -193,6 +196,7 @@ static int psp_early_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 0, 9):
 	case IP_VERSION(11, 0, 11):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 	case IP_VERSION(11, 0, 12):
 	case IP_VERSION(11, 0, 13):
 		psp_v11_0_set_psp_funcs(psp);
@@ -208,11 +212,15 @@ static int psp_early_init(struct amdgpu_ip_block *ip_block)
 		psp->boot_time_tmr = false;
 		fallthrough;
 	case IP_VERSION(13, 0, 6):
-	case IP_VERSION(13, 0, 12):
 	case IP_VERSION(13, 0, 14):
 		psp_v13_0_set_psp_funcs(psp);
 		psp->autoload_supported = false;
 		break;
+	case IP_VERSION(13, 0, 12):
+		psp_v13_0_set_psp_funcs(psp);
+		psp->autoload_supported = false;
+		adev->psp.sup_ifwi_up = !amdgpu_sriov_vf(adev);
+		break;
 	case IP_VERSION(13, 0, 1):
 	case IP_VERSION(13, 0, 3):
 	case IP_VERSION(13, 0, 5):
@@ -246,6 +254,10 @@ static int psp_early_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(14, 0, 3):
 		psp_v14_0_set_psp_funcs(psp);
 		break;
+	case IP_VERSION(14, 0, 5):
+		psp_v14_0_set_psp_funcs(psp);
+		psp->boot_time_tmr = false;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -533,7 +545,6 @@ static int psp_sw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
 
 	psp_memory_training_fini(psp);
 
@@ -543,8 +554,8 @@ static int psp_sw_fini(struct amdgpu_ip_block *ip_block)
 	amdgpu_ucode_release(&psp->cap_fw);
 	amdgpu_ucode_release(&psp->toc_fw);
 
-	kfree(cmd);
-	cmd = NULL;
+	kfree(psp->cmd);
+	psp->cmd = NULL;
 
 	psp_free_shared_bufs(psp);
 
@@ -1786,34 +1797,47 @@ int psp_ras_initialize(struct psp_context *psp)
 		if (ret)
 			dev_warn(adev->dev, "PSP get boot config failed\n");
 
-		if (!amdgpu_ras_is_supported(psp->adev, AMDGPU_RAS_BLOCK__UMC)) {
-			if (!boot_cfg) {
-				dev_info(adev->dev, "GECC is disabled\n");
-			} else {
-				/* disable GECC in next boot cycle if ras is
-				 * disabled by module parameter amdgpu_ras_enable
-				 * and/or amdgpu_ras_mask, or boot_config_get call
-				 * is failed
-				 */
-				ret = psp_boot_config_set(adev, 0);
-				if (ret)
-					dev_warn(adev->dev, "PSP set boot config failed\n");
-				else
-					dev_warn(adev->dev, "GECC will be disabled in next boot cycle if set amdgpu_ras_enable and/or amdgpu_ras_mask to 0x0\n");
-			}
+		if (boot_cfg == 1 && !adev->ras_default_ecc_enabled &&
+		    amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) {
+			dev_warn(adev->dev, "GECC is currently enabled, which may affect performance\n");
+			dev_warn(adev->dev,
+				"To disable GECC, please reboot the system and load the amdgpu driver with the parameter amdgpu_ras_enable=0\n");
 		} else {
-			if (boot_cfg == 1) {
-				dev_info(adev->dev, "GECC is enabled\n");
+			if ((adev->ras_default_ecc_enabled || amdgpu_ras_enable == 1) &&
+				amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) {
+				if (boot_cfg == 1) {
+					dev_info(adev->dev, "GECC is enabled\n");
+				} else {
+					/* enable GECC in next boot cycle if it is disabled
+					 * in boot config, or force enable GECC if failed to
+					 * get boot configuration
+					 */
+					ret = psp_boot_config_set(adev, BOOT_CONFIG_GECC);
+					if (ret)
+						dev_warn(adev->dev, "PSP set boot config failed\n");
+					else
+						dev_warn(adev->dev, "GECC will be enabled in next boot cycle\n");
+				}
 			} else {
-				/* enable GECC in next boot cycle if it is disabled
-				 * in boot config, or force enable GECC if failed to
-				 * get boot configuration
-				 */
-				ret = psp_boot_config_set(adev, BOOT_CONFIG_GECC);
-				if (ret)
-					dev_warn(adev->dev, "PSP set boot config failed\n");
-				else
-					dev_warn(adev->dev, "GECC will be enabled in next boot cycle\n");
+				if (!boot_cfg) {
+					if (!adev->ras_default_ecc_enabled &&
+					    amdgpu_ras_enable != 1 &&
+					    amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+						dev_warn(adev->dev, "GECC is disabled, set amdgpu_ras_enable=1 to enable GECC in next boot cycle if needed\n");
+					else
+						dev_info(adev->dev, "GECC is disabled\n");
+				} else {
+					/* disable GECC in next boot cycle if ras is
+					 * disabled by module parameter amdgpu_ras_enable
+					 * and/or amdgpu_ras_mask, or boot_config_get call
+					 * is failed
+					 */
+					ret = psp_boot_config_set(adev, 0);
+					if (ret)
+						dev_warn(adev->dev, "PSP set boot config failed\n");
+					else
+						dev_warn(adev->dev, "GECC will be disabled in next boot cycle if set amdgpu_ras_enable and/or amdgpu_ras_mask to 0x0\n");
+				}
 			}
 		}
 	}
@@ -1840,6 +1864,7 @@ int psp_ras_initialize(struct psp_context *psp)
 	if (adev->gmc.gmc_funcs->query_mem_partition_mode)
 		ras_cmd->ras_in_message.init_flags.nps_mode =
 			adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
+	ras_cmd->ras_in_message.init_flags.active_umc_mask = adev->umc.active_mask;
 
 	ret = psp_ta_load(psp, &psp->ras_context.context);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f0924aa3f4e4..bed2603ae4c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1864,6 +1864,9 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev,
 	if (!obj || obj->attr_inuse)
 		return -EINVAL;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_virt_ras_telemetry_block_en(adev, head->block))
+		return 0;
+
 	get_obj(obj);
 
 	snprintf(obj->fs_data.sysfs_name, sizeof(obj->fs_data.sysfs_name),
@@ -2796,20 +2799,108 @@ static int amdgpu_ras_mca2pa(struct amdgpu_device *adev,
 		return  -EINVAL;
 }
 
+static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev,
+					struct eeprom_table_record *bps, int count)
+{
+	int j;
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_err_handler_data *data = con->eh_data;
+
+	for (j = 0; j < count; j++) {
+		if (amdgpu_ras_check_bad_page_unlock(con,
+			bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+			continue;
+
+		if (!data->space_left &&
+		    amdgpu_ras_realloc_eh_data_space(adev, data, 256)) {
+			return -ENOMEM;
+		}
+
+		amdgpu_ras_reserve_page(adev, bps[j].retired_page);
+
+		memcpy(&data->bps[data->count], &(bps[j]),
+				sizeof(struct eeprom_table_record));
+		data->count++;
+		data->space_left--;
+	}
+
+	return 0;
+}
+
+static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev,
+				struct eeprom_table_record *bps, struct ras_err_data *err_data,
+				enum amdgpu_memory_partition nps)
+{
+	int i = 0;
+	enum amdgpu_memory_partition save_nps;
+
+	save_nps = (bps[0].retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK;
+
+	/*old asics just have pa in eeprom*/
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12) {
+		memcpy(err_data->err_addr, bps,
+			sizeof(struct eeprom_table_record) * adev->umc.retire_unit);
+		goto out;
+	}
+
+	for (i = 0; i < adev->umc.retire_unit; i++)
+		bps[i].retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT);
+
+	if (save_nps) {
+		if (save_nps == nps) {
+			if (amdgpu_umc_pages_in_a_row(adev, err_data,
+					bps[0].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+				return -EINVAL;
+		} else {
+			if (amdgpu_ras_mca2pa_by_idx(adev, &bps[0], err_data))
+				return -EINVAL;
+		}
+	} else {
+		if (amdgpu_ras_mca2pa(adev, &bps[0], err_data)) {
+			if (nps == AMDGPU_NPS1_PARTITION_MODE)
+				memcpy(err_data->err_addr, bps,
+					sizeof(struct eeprom_table_record) * adev->umc.retire_unit);
+			else
+				return -EOPNOTSUPP;
+		}
+	}
+
+out:
+	return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, adev->umc.retire_unit);
+}
+
+static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev,
+				struct eeprom_table_record *bps, struct ras_err_data *err_data,
+				enum amdgpu_memory_partition nps)
+{
+	enum amdgpu_memory_partition save_nps;
+
+	save_nps = (bps->retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK;
+	bps->retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT);
+
+	if (save_nps == nps) {
+		if (amdgpu_umc_pages_in_a_row(adev, err_data,
+				bps->retired_page << AMDGPU_GPU_PAGE_SHIFT))
+			return -EINVAL;
+	} else {
+		if (amdgpu_ras_mca2pa_by_idx(adev, bps, err_data))
+			return -EINVAL;
+	}
+	return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr,
+									adev->umc.retire_unit);
+}
+
 /* it deal with vram only. */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 		struct eeprom_table_record *bps, int pages, bool from_rom)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	struct ras_err_handler_data *data;
 	struct ras_err_data err_data;
-	struct eeprom_table_record *err_rec;
 	struct amdgpu_ras_eeprom_control *control =
 			&adev->psp.ras_context.ras->eeprom_control;
 	enum amdgpu_memory_partition nps = AMDGPU_NPS1_PARTITION_MODE;
 	int ret = 0;
-	uint32_t i, j, loop_cnt = 1;
-	bool find_pages_per_pa = false;
+	uint32_t i;
 
 	if (!con || !con->eh_data || !bps || pages <= 0)
 		return 0;
@@ -2820,114 +2911,46 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 				sizeof(struct eeprom_table_record), GFP_KERNEL);
 		if (!err_data.err_addr) {
 			dev_warn(adev->dev, "Failed to alloc UMC error address record in mca2pa conversion!\n");
-			ret = -ENOMEM;
-			goto out;
+			return -ENOMEM;
 		}
 
-		err_rec = err_data.err_addr;
-		loop_cnt = adev->umc.retire_unit;
 		if (adev->gmc.gmc_funcs->query_mem_partition_mode)
 			nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
 	}
 
 	mutex_lock(&con->recovery_lock);
-	data = con->eh_data;
-	if (!data) {
-		/* Returning 0 as the absence of eh_data is acceptable */
-		goto free;
-	}
-
-	for (i = 0; i < pages; i++) {
-		if (from_rom &&
-		    control->rec_type == AMDGPU_RAS_EEPROM_REC_MCA) {
-			if (!find_pages_per_pa) {
-				if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) {
-					if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) {
-						/* may use old RAS TA, use PA to find pages in
-						 * one row
-						 */
-						if (amdgpu_umc_pages_in_a_row(adev, &err_data,
-									      bps[i].retired_page <<
-									      AMDGPU_GPU_PAGE_SHIFT)) {
-							ret = -EINVAL;
-							goto free;
-						} else {
-							find_pages_per_pa = true;
-						}
-					} else {
-						/* unsupported cases */
-						ret = -EOPNOTSUPP;
-						goto free;
-					}
-				}
-			} else {
-				if (amdgpu_umc_pages_in_a_row(adev, &err_data,
-						bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) {
-					ret = -EINVAL;
-					goto free;
-				}
-			}
-		} else {
-			if (from_rom && !find_pages_per_pa) {
-				if (bps[i].retired_page & UMC_CHANNEL_IDX_V2) {
-					/* bad page in any NPS mode in eeprom */
-					if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) {
-						ret = -EINVAL;
+
+	if (from_rom) {
+		for (i = 0; i < pages; i++) {
+			if (control->ras_num_recs - i >= adev->umc.retire_unit) {
+				if ((bps[i].address == bps[i + 1].address) &&
+				    (bps[i].mem_channel == bps[i + 1].mem_channel)) {
+					//deal with retire_unit records a time
+					ret = __amdgpu_ras_convert_rec_array_from_rom(adev,
+									&bps[i], &err_data, nps);
+					if (ret)
 						goto free;
-					}
+					i += (adev->umc.retire_unit - 1);
 				} else {
-					/* legacy bad page in eeprom, generated only in
-					 * NPS1 mode
-					 */
-					if (amdgpu_ras_mca2pa(adev, &bps[i], &err_data)) {
-						/* old RAS TA or ASICs which don't support to
-						 * convert addrss via mca address
-						 */
-						if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) {
-							find_pages_per_pa = true;
-							err_rec = &bps[i];
-							loop_cnt = 1;
-						} else {
-							/* non-nps1 mode, old RAS TA
-							 * can't support it
-							 */
-							ret = -EOPNOTSUPP;
-							goto free;
-						}
-					}
+					break;
 				}
-
-				if (!find_pages_per_pa)
-					i += (adev->umc.retire_unit - 1);
 			} else {
-				err_rec = &bps[i];
+				break;
 			}
 		}
-
-		for (j = 0; j < loop_cnt; j++) {
-			if (amdgpu_ras_check_bad_page_unlock(con,
-				err_rec[j].retired_page << AMDGPU_GPU_PAGE_SHIFT))
-				continue;
-
-			if (!data->space_left &&
-			    amdgpu_ras_realloc_eh_data_space(adev, data, 256)) {
-				ret = -ENOMEM;
+		for (; i < pages; i++) {
+			ret = __amdgpu_ras_convert_rec_from_rom(adev,
+				&bps[i], &err_data, nps);
+			if (ret)
 				goto free;
-			}
-
-			amdgpu_ras_reserve_page(adev, err_rec[j].retired_page);
-
-			memcpy(&data->bps[data->count], &(err_rec[j]),
-					sizeof(struct eeprom_table_record));
-			data->count++;
-			data->space_left--;
 		}
+	} else {
+		ret = __amdgpu_ras_restore_bad_pages(adev, bps, pages);
 	}
 
 free:
 	if (from_rom)
 		kfree(err_data.err_addr);
-out:
 	mutex_unlock(&con->recovery_lock);
 
 	return ret;
@@ -2966,18 +2989,18 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 
 	/* only new entries are saved */
 	if (save_count > 0) {
-		if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) {
+		/*old asics only save pa to eeprom like before*/
+		if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12) {
 			if (amdgpu_ras_eeprom_append(control,
-						     &data->bps[control->ras_num_recs],
-						     save_count)) {
+					&data->bps[bad_page_num], save_count)) {
 				dev_err(adev->dev, "Failed to save EEPROM table data!");
 				return -EIO;
 			}
 		} else {
 			for (i = 0; i < unit_num; i++) {
 				if (amdgpu_ras_eeprom_append(control,
-						&data->bps[bad_page_num + i * adev->umc.retire_unit],
-						1)) {
+						&data->bps[bad_page_num +
+						i * adev->umc.retire_unit], 1)) {
 					dev_err(adev->dev, "Failed to save EEPROM table data!");
 					return -EIO;
 				}
@@ -2999,7 +3022,7 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 	struct amdgpu_ras_eeprom_control *control =
 		&adev->psp.ras_context.ras->eeprom_control;
 	struct eeprom_table_record *bps;
-	int ret;
+	int ret, i = 0;
 
 	/* no bad page record, skip eeprom access */
 	if (control->ras_num_recs == 0 || amdgpu_bad_page_threshold == 0)
@@ -3013,13 +3036,23 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 	if (ret) {
 		dev_err(adev->dev, "Failed to load EEPROM table records!");
 	} else {
-		if (control->ras_num_recs > 1 &&
-		    adev->umc.ras && adev->umc.ras->convert_ras_err_addr) {
-			if ((bps[0].address == bps[1].address) &&
-			    (bps[0].mem_channel == bps[1].mem_channel))
-				control->rec_type = AMDGPU_RAS_EEPROM_REC_PA;
-			else
-				control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA;
+		if (adev->umc.ras && adev->umc.ras->convert_ras_err_addr) {
+			for (i = 0; i < control->ras_num_recs; i++) {
+				if ((control->ras_num_recs - i) >= adev->umc.retire_unit) {
+					if ((bps[i].address == bps[i + 1].address) &&
+						(bps[i].mem_channel == bps[i + 1].mem_channel)) {
+						control->ras_num_pa_recs += adev->umc.retire_unit;
+						i += (adev->umc.retire_unit - 1);
+					} else {
+						control->ras_num_mca_recs +=
+									(control->ras_num_recs - i);
+						break;
+					}
+				} else {
+					control->ras_num_mca_recs += (control->ras_num_recs - i);
+					break;
+				}
+			}
 		}
 
 		ret = amdgpu_ras_eeprom_check(control);
@@ -3080,31 +3113,29 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
 	/*
-	 * Justification of value bad_page_cnt_threshold in ras structure
-	 *
-	 * Generally, 0 <= amdgpu_bad_page_threshold <= max record length
-	 * in eeprom or amdgpu_bad_page_threshold == -2, introduce two
-	 * scenarios accordingly.
-	 *
-	 * Bad page retirement enablement:
-	 *    - If amdgpu_bad_page_threshold = -2,
-	 *      bad_page_cnt_threshold = typical value by formula.
-	 *
-	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <
-	 *      max record length in eeprom, use it directly.
-	 *
-	 * Bad page retirement disablement:
-	 *    - If amdgpu_bad_page_threshold = 0, bad page retirement
-	 *      functionality is disabled, and bad_page_cnt_threshold will
-	 *      take no effect.
+	 * amdgpu_bad_page_threshold is used to config
+	 * the threshold for the number of bad pages.
+	 * -1:  Threshold is set to default value
+	 *      Driver will issue a warning message when threshold is reached
+	 *      and continue runtime services.
+	 * 0:   Disable bad page retirement
+	 *      Driver will not retire bad pages
+	 *      which is intended for debugging purpose.
+	 * -2:  Threshold is determined by a formula
+	 *      that assumes 1 bad page per 100M of local memory.
+	 *      Driver will continue runtime services when threhold is reached.
+	 * 0 < threshold < max number of bad page records in EEPROM,
+	 *      A user-defined threshold is set
+	 *      Driver will halt runtime services when this custom threshold is reached.
 	 */
-
-	if (amdgpu_bad_page_threshold < 0) {
+	if (amdgpu_bad_page_threshold == -2) {
 		u64 val = adev->gmc.mc_vram_size;
 
 		do_div(val, RAS_BAD_PAGE_COVER);
 		con->bad_page_cnt_threshold = min(lower_32_bits(val),
 						  max_count);
+	} else if (amdgpu_bad_page_threshold == -1) {
+		con->bad_page_cnt_threshold = ((con->reserved_pages_in_bytes) >> 21) << 4;
 	} else {
 		con->bad_page_cnt_threshold = min_t(int, max_count,
 						    amdgpu_bad_page_threshold);
@@ -3427,12 +3458,7 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 		return ret;
 
 	if (!adev->umc.ras || !adev->umc.ras->convert_ras_err_addr)
-		control->rec_type = AMDGPU_RAS_EEPROM_REC_PA;
-
-	/* default status is MCA storage */
-	if (control->ras_num_recs <= 1 &&
-	    adev->umc.ras && adev->umc.ras->convert_ras_err_addr)
-		control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA;
+		control->ras_num_pa_recs = control->ras_num_recs;
 
 	if (control->ras_num_recs) {
 		ret = amdgpu_ras_load_bad_pages(adev);
@@ -3447,6 +3473,13 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 				adev, control->bad_channel_bitmap);
 			con->update_channel_flag = false;
 		}
+
+		/* The format action is only applied to new ASICs */
+		if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) >= 12 &&
+		    control->tbl_hdr.version < RAS_TABLE_VER_V3)
+			if (!amdgpu_ras_eeprom_reset_table(control))
+				if (amdgpu_ras_save_bad_pages(adev, NULL))
+					dev_warn(adev->dev, "Failed to format RAS EEPROM data in V3 version!\n");
 	}
 
 	return ret;
@@ -3759,8 +3792,11 @@ init_ras_enabled_flag:
 	adev->ras_enabled = amdgpu_ras_enable == 0 ? 0 :
 		adev->ras_hw_enabled & amdgpu_ras_mask;
 
-	/* aca is disabled by default */
-	adev->aca.is_enabled = false;
+	/* aca is disabled by default except for psp v13_0_6/v13_0_12/v13_0_14 */
+	adev->aca.is_enabled =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6) ||
+		 amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12) ||
+		 amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 14));
 
 	/* bad page feature is not applicable to specific app platform */
 	if (adev->gmc.is_app_apu &&
@@ -3848,8 +3884,10 @@ static void amdgpu_ras_init_reserved_vram_size(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 2):
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 12):
+		con->reserved_pages_in_bytes = AMDGPU_RAS_RESERVED_VRAM_SIZE_DEFAULT;
+		break;
 	case IP_VERSION(13, 0, 14):
-		con->reserved_pages_in_bytes = AMDGPU_RAS_RESERVED_VRAM_SIZE;
+		con->reserved_pages_in_bytes = (AMDGPU_RAS_RESERVED_VRAM_SIZE_DEFAULT << 1);
 		break;
 	default:
 		break;
@@ -5127,9 +5165,9 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev,
 			 "socket: %d, aid: %d, fw_status: 0x%x, data abort exception\n",
 			 socket_id, aid_id, fw_status);
 
-	if (AMDGPU_RAS_GPU_ERR_UNKNOWN(boot_error))
+	if (AMDGPU_RAS_GPU_ERR_GENERIC(boot_error))
 		dev_info(adev->dev,
-			 "socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n",
+			 "socket: %d, aid: %d, fw_status: 0x%x, Boot Controller Generic Error\n",
 			 socket_id, aid_id, fw_status);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 82db986c36a0..764e9fa0a914 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -47,7 +47,7 @@ struct amdgpu_iv_entry;
 #define AMDGPU_RAS_GPU_ERR_AID_ID(x)			AMDGPU_GET_REG_FIELD(x, 12, 11)
 #define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 14, 13)
 #define AMDGPU_RAS_GPU_ERR_DATA_ABORT(x)		AMDGPU_GET_REG_FIELD(x, 29, 29)
-#define AMDGPU_RAS_GPU_ERR_UNKNOWN(x)			AMDGPU_GET_REG_FIELD(x, 30, 30)
+#define AMDGPU_RAS_GPU_ERR_GENERIC(x)			AMDGPU_GET_REG_FIELD(x, 30, 30)
 
 #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT	100
 #define AMDGPU_RAS_BOOT_STEADY_STATUS		0xBA
@@ -65,7 +65,7 @@ struct amdgpu_iv_entry;
 
 /* Reserve 8 physical dram row for possible retirement.
  * In worst cases, it will lose 8 * 2MB memory in vram domain */
-#define AMDGPU_RAS_RESERVED_VRAM_SIZE	(16ULL << 20)
+#define AMDGPU_RAS_RESERVED_VRAM_SIZE_DEFAULT	(16ULL << 20)
 /* The high three bits indicates socketid */
 #define AMDGPU_RAS_GET_FEATURES(val)  ((val) & ~AMDGPU_RAS_FEATURES_SOCKETID_MASK)
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 52c16bfeccaa..0ea7cfaf3587 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -161,6 +161,7 @@ static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 10):
 		return true;
 	case IP_VERSION(13, 0, 6):
+	case IP_VERSION(13, 0, 12):
 	case IP_VERSION(13, 0, 14):
 		return (adev->gmc.is_app_apu) ? false : true;
 	default:
@@ -177,7 +178,7 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 	if (!control)
 		return false;
 
-	if (amdgpu_atomfirmware_ras_rom_addr(adev, &i2c_addr)) {
+	if (adev->bios && amdgpu_atomfirmware_ras_rom_addr(adev, &i2c_addr)) {
 		/* The address given by VBIOS is an 8-bit, wire-format
 		 * address, i.e. the most significant byte.
 		 *
@@ -223,6 +224,7 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 		return true;
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
+	case IP_VERSION(13, 0, 12):
 	case IP_VERSION(13, 0, 14):
 		control->i2c_address = EEPROM_I2C_MADDR_4;
 		return true;
@@ -413,9 +415,11 @@ static void amdgpu_ras_set_eeprom_table_version(struct amdgpu_ras_eeprom_control
 
 	switch (amdgpu_ip_version(adev, UMC_HWIP, 0)) {
 	case IP_VERSION(8, 10, 0):
-	case IP_VERSION(12, 0, 0):
 		hdr->version = RAS_TABLE_VER_V2_1;
 		return;
+	case IP_VERSION(12, 0, 0):
+		hdr->version = RAS_TABLE_VER_V3;
+		return;
 	default:
 		hdr->version = RAS_TABLE_VER_V1;
 		return;
@@ -443,7 +447,7 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 	hdr->header = RAS_TABLE_HDR_VAL;
 	amdgpu_ras_set_eeprom_table_version(control);
 
-	if (hdr->version == RAS_TABLE_VER_V2_1) {
+	if (hdr->version >= RAS_TABLE_VER_V2_1) {
 		hdr->first_rec_offset = RAS_RECORD_START_V2_1;
 		hdr->tbl_size = RAS_TABLE_HEADER_SIZE +
 				RAS_TABLE_V2_1_INFO_SIZE;
@@ -461,7 +465,7 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 	}
 
 	csum = __calc_hdr_byte_sum(control);
-	if (hdr->version == RAS_TABLE_VER_V2_1)
+	if (hdr->version >= RAS_TABLE_VER_V2_1)
 		csum += __calc_ras_info_byte_sum(control);
 	csum = -csum;
 	hdr->checksum = csum;
@@ -558,16 +562,17 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev)
 			return false;
 
 	if (con->eeprom_control.tbl_hdr.header == RAS_TABLE_HDR_BAD) {
-		if (amdgpu_bad_page_threshold == -1) {
+		if (con->eeprom_control.ras_num_bad_pages > con->bad_page_cnt_threshold)
 			dev_warn(adev->dev, "RAS records:%d exceed threshold:%d",
-				con->eeprom_control.ras_num_bad_pages, con->bad_page_cnt_threshold);
+				 con->eeprom_control.ras_num_bad_pages, con->bad_page_cnt_threshold);
+		if ((amdgpu_bad_page_threshold == -1) ||
+		    (amdgpu_bad_page_threshold == -2)) {
 			dev_warn(adev->dev,
-				"But GPU can be operated due to bad_page_threshold = -1.\n");
+				 "Please consult AMD Service Action Guide (SAG) for appropriate service procedures.\n");
 			return false;
 		} else {
-			dev_warn(adev->dev, "This GPU is in BAD status.");
-			dev_warn(adev->dev, "Please retire it or set a larger "
-				 "threshold value when reloading driver.\n");
+			dev_warn(adev->dev,
+				 "Please consider adjusting the customized threshold.\n");
 			return true;
 		}
 	}
@@ -726,11 +731,14 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
 				     - control->ras_fri)
 		% control->ras_max_record_count;
 
-	if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA)
-		control->ras_num_bad_pages = control->ras_num_recs;
+	/*old asics only save pa to eeprom like before*/
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12)
+		control->ras_num_pa_recs += num;
 	else
-		control->ras_num_bad_pages =
-			control->ras_num_recs * adev->umc.retire_unit;
+		control->ras_num_mca_recs += num;
+
+	control->ras_num_bad_pages = control->ras_num_pa_recs +
+				control->ras_num_mca_recs * adev->umc.retire_unit;
 Out:
 	kfree(buf);
 	return res;
@@ -748,24 +756,25 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 	/* Modify the header if it exceeds.
 	 */
 	if (amdgpu_bad_page_threshold != 0 &&
-	    control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) {
+	    control->ras_num_bad_pages > ras->bad_page_cnt_threshold) {
 		dev_warn(adev->dev,
 			"Saved bad pages %d reaches threshold value %d\n",
 			control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
 		control->tbl_hdr.header = RAS_TABLE_HDR_BAD;
-		if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1) {
+		if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1) {
 			control->tbl_rai.rma_status = GPU_RETIRED__ECC_REACH_THRESHOLD;
 			control->tbl_rai.health_percent = 0;
 		}
 
-		if (amdgpu_bad_page_threshold != -1)
+		if ((amdgpu_bad_page_threshold != -1) &&
+		    (amdgpu_bad_page_threshold != -2))
 			ras->is_rma = true;
 
 		/* ignore the -ENOTSUPP return value */
 		amdgpu_dpm_send_rma_reason(adev);
 	}
 
-	if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1)
+	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)
 		control->tbl_hdr.tbl_size = RAS_TABLE_HEADER_SIZE +
 					    RAS_TABLE_V2_1_INFO_SIZE +
 					    control->ras_num_recs * RAS_TABLE_RECORD_SIZE;
@@ -805,8 +814,8 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 	 * now calculate gpu health percent
 	 */
 	if (amdgpu_bad_page_threshold != 0 &&
-	    control->tbl_hdr.version == RAS_TABLE_VER_V2_1 &&
-	    control->ras_num_bad_pages < ras->bad_page_cnt_threshold)
+	    control->tbl_hdr.version >= RAS_TABLE_VER_V2_1 &&
+	    control->ras_num_bad_pages <= ras->bad_page_cnt_threshold)
 		control->tbl_rai.health_percent = ((ras->bad_page_cnt_threshold -
 						   control->ras_num_bad_pages) * 100) /
 						   ras->bad_page_cnt_threshold;
@@ -818,7 +827,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 		csum += *pp;
 
 	csum += __calc_hdr_byte_sum(control);
-	if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1)
+	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)
 		csum += __calc_ras_info_byte_sum(control);
 	/* avoid sign extension when assigning to "checksum" */
 	csum = -csum;
@@ -850,6 +859,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res, i;
+	uint64_t nps = AMDGPU_NPS1_PARTITION_MODE;
 
 	if (!__is_ras_eeprom_supported(adev))
 		return 0;
@@ -863,9 +873,12 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 		return -EINVAL;
 	}
 
+	if (adev->gmc.gmc_funcs->query_mem_partition_mode)
+		nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
+
 	/* set the new channel index flag */
 	for (i = 0; i < num; i++)
-		record[i].retired_page |= UMC_CHANNEL_IDX_V2;
+		record[i].retired_page |= (nps << UMC_NPS_SHIFT);
 
 	mutex_lock(&control->ras_tbl_mutex);
 
@@ -879,7 +892,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 
 	/* clear channel index flag, the flag is only saved on eeprom */
 	for (i = 0; i < num; i++)
-		record[i].retired_page &= ~UMC_CHANNEL_IDX_V2;
+		record[i].retired_page &= ~(nps << UMC_NPS_SHIFT);
 
 	return res;
 }
@@ -1031,7 +1044,7 @@ uint32_t amdgpu_ras_eeprom_max_record_count(struct amdgpu_ras_eeprom_control *co
 	/* get available eeprom table version first before eeprom table init */
 	amdgpu_ras_set_eeprom_table_version(control);
 
-	if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1)
+	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)
 		return RAS_MAX_RECORD_COUNT_V2_1;
 	else
 		return RAS_MAX_RECORD_COUNT;
@@ -1276,7 +1289,7 @@ static int __verify_ras_table_checksum(struct amdgpu_ras_eeprom_control *control
 	int buf_size, res;
 	u8  csum, *buf, *pp;
 
-	if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1)
+	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)
 		buf_size = RAS_TABLE_HEADER_SIZE +
 			   RAS_TABLE_V2_1_INFO_SIZE +
 			   control->ras_num_recs * RAS_TABLE_RECORD_SIZE;
@@ -1379,7 +1392,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 
 	__decode_table_header_from_buf(hdr, buf);
 
-	if (hdr->version == RAS_TABLE_VER_V2_1) {
+	if (hdr->version >= RAS_TABLE_VER_V2_1) {
 		control->ras_num_recs = RAS_NUM_RECS_V2_1(hdr);
 		control->ras_record_offset = RAS_RECORD_START_V2_1;
 		control->ras_max_record_count = RAS_MAX_RECORD_COUNT_V2_1;
@@ -1390,6 +1403,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	}
 	control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset);
 
+	control->ras_num_mca_recs = 0;
+	control->ras_num_pa_recs = 0;
 	return 0;
 }
 
@@ -1410,17 +1425,14 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 	if (!__get_eeprom_i2c_addr(adev, control))
 		return -EINVAL;
 
-	if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA)
-		control->ras_num_bad_pages = control->ras_num_recs;
-	else
-		control->ras_num_bad_pages =
-			control->ras_num_recs * adev->umc.retire_unit;
+	control->ras_num_bad_pages = control->ras_num_pa_recs +
+			control->ras_num_mca_recs * adev->umc.retire_unit;
 
 	if (hdr->header == RAS_TABLE_HDR_VAL) {
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->ras_num_bad_pages);
 
-		if (hdr->version == RAS_TABLE_VER_V2_1) {
+		if (hdr->version >= RAS_TABLE_VER_V2_1) {
 			res = __read_table_ras_info(control);
 			if (res)
 				return res;
@@ -1428,8 +1440,9 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 
 		res = __verify_ras_table_checksum(control);
 		if (res)
-			DRM_ERROR("RAS table incorrect checksum or error:%d\n",
-				  res);
+			dev_err(adev->dev,
+				"RAS table incorrect checksum or error:%d\n",
+				res);
 
 		/* Warn if we are at 90% of the threshold or above
 		 */
@@ -1439,7 +1452,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 					ras->bad_page_cnt_threshold);
 	} else if (hdr->header == RAS_TABLE_HDR_BAD &&
 		   amdgpu_bad_page_threshold != 0) {
-		if (hdr->version == RAS_TABLE_VER_V2_1) {
+		if (hdr->version >= RAS_TABLE_VER_V2_1) {
 			res = __read_table_ras_info(control);
 			if (res)
 				return res;
@@ -1447,11 +1460,12 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 
 		res = __verify_ras_table_checksum(control);
 		if (res) {
-			dev_err(adev->dev, "RAS Table incorrect checksum or error:%d\n",
-				  res);
+			dev_err(adev->dev,
+				"RAS Table incorrect checksum or error:%d\n",
+				res);
 			return -EINVAL;
 		}
-		if (ras->bad_page_cnt_threshold > control->ras_num_bad_pages) {
+		if (ras->bad_page_cnt_threshold >= control->ras_num_bad_pages) {
 			/* This means that, the threshold was increased since
 			 * the last time the system was booted, and now,
 			 * ras->bad_page_cnt_threshold - control->num_recs > 0,
@@ -1466,17 +1480,18 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 			res = amdgpu_ras_eeprom_correct_header_tag(control,
 								   RAS_TABLE_HDR_VAL);
 		} else {
-			dev_err(adev->dev, "RAS records:%d exceed threshold:%d",
+			dev_warn(adev->dev,
+				"RAS records:%d exceed threshold:%d\n",
 				control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
-			if (amdgpu_bad_page_threshold == -1) {
-				dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -1.");
+			if ((amdgpu_bad_page_threshold == -1) ||
+			    (amdgpu_bad_page_threshold == -2)) {
 				res = 0;
+				dev_warn(adev->dev,
+					 "Please consult AMD Service Action Guide (SAG) for appropriate service procedures\n");
 			} else {
 				ras->is_rma = true;
-				dev_err(adev->dev,
-					"RAS records:%d exceed threshold:%d, "
-					"GPU will not be initialized. Replace this GPU or increase the threshold",
-					control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
+				dev_warn(adev->dev,
+					 "User defined threshold is set, runtime service will be halt when threshold is reached\n");
 			}
 		}
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index 81d55cb7b397..ec6d7ea37ad0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -28,6 +28,7 @@
 
 #define RAS_TABLE_VER_V1           0x00010000
 #define RAS_TABLE_VER_V2_1         0x00021000
+#define RAS_TABLE_VER_V3           0x00030000
 
 struct amdgpu_device;
 
@@ -43,19 +44,6 @@ enum amdgpu_ras_eeprom_err_type {
 	AMDGPU_RAS_EEPROM_ERR_COUNT,
 };
 
-/*
- * one UMC MCA address could map to multiply physical address (PA),
- * such as 1:16, we use eeprom_table_record.address to store MCA
- * address and use eeprom_table_record.retired_page to save PA.
- *
- * AMDGPU_RAS_EEPROM_REC_PA: one record store one PA
- * AMDGPU_RAS_EEPROM_REC_MCA: one record store one MCA address
- */
-enum amdgpu_ras_eeprom_rec_type {
-	AMDGPU_RAS_EEPROM_REC_PA,
-	AMDGPU_RAS_EEPROM_REC_MCA,
-};
-
 struct amdgpu_ras_eeprom_table_header {
 	uint32_t header;
 	uint32_t version;
@@ -100,6 +88,12 @@ struct amdgpu_ras_eeprom_control {
 	 */
 	u32 ras_num_bad_pages;
 
+	/* Number of records store mca address */
+	u32 ras_num_mca_recs;
+
+	/* Number of records store physical address */
+	u32 ras_num_pa_recs;
+
 	/* First record index to read, 0-based.
 	 * Range is [0, num_recs-1]. This is
 	 * an absolute index, starting right after
@@ -120,7 +114,6 @@ struct amdgpu_ras_eeprom_control {
 	/* Record channel info which occurred bad pages
 	 */
 	u32 bad_channel_bitmap;
-	enum amdgpu_ras_eeprom_rec_type rec_type;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index a6e28fe3f8d6..d55c8b7fdb59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -324,24 +324,33 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	/* always set cond_exec_polling to CONTINUE */
 	*ring->cond_exe_cpu_addr = 1;
 
-	r = amdgpu_fence_driver_start_ring(ring, irq_src, irq_type);
-	if (r) {
-		dev_err(adev->dev, "failed initializing fences (%d).\n", r);
-		return r;
-	}
+	if (ring->funcs->type != AMDGPU_RING_TYPE_CPER) {
+		r = amdgpu_fence_driver_start_ring(ring, irq_src, irq_type);
+		if (r) {
+			dev_err(adev->dev, "failed initializing fences (%d).\n", r);
+			return r;
+		}
 
-	max_ibs_dw = ring->funcs->emit_frame_size +
-		     amdgpu_ring_max_ibs(ring->funcs->type) * ring->funcs->emit_ib_size;
-	max_ibs_dw = (max_ibs_dw + ring->funcs->align_mask) & ~ring->funcs->align_mask;
+		max_ibs_dw = ring->funcs->emit_frame_size +
+			     amdgpu_ring_max_ibs(ring->funcs->type) * ring->funcs->emit_ib_size;
+		max_ibs_dw = (max_ibs_dw + ring->funcs->align_mask) & ~ring->funcs->align_mask;
 
-	if (WARN_ON(max_ibs_dw > max_dw))
-		max_dw = max_ibs_dw;
+		if (WARN_ON(max_ibs_dw > max_dw))
+			max_dw = max_ibs_dw;
 
-	ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission);
+		ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission);
+	} else {
+		ring->ring_size = roundup_pow_of_two(max_dw * 4);
+		ring->count_dw = (ring->ring_size - 4) >> 2;
+		/* ring buffer is empty now */
+		ring->wptr = *ring->rptr_cpu_addr = 0;
+	}
 
 	ring->buf_mask = (ring->ring_size / 4) - 1;
 	ring->ptr_mask = ring->funcs->support_64bit_ptrs ?
 		0xffffffffffffffff : ring->buf_mask;
+	/*  Initialize cached_rptr to 0 */
+	ring->cached_rptr = 0;
 
 	/* Allocate ring buffer */
 	if (ring->is_mes_queue) {
@@ -493,6 +502,7 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
 {
 	struct amdgpu_ring *ring = file_inode(f)->i_private;
 	uint32_t value, result, early[3];
+	uint64_t p;
 	loff_t i;
 	int r;
 
@@ -502,13 +512,18 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
 	result = 0;
 
 	if (*pos < 12) {
+		if (ring->funcs->type == AMDGPU_RING_TYPE_CPER)
+			mutex_lock(&ring->adev->cper.ring_lock);
+
 		early[0] = amdgpu_ring_get_rptr(ring) & ring->buf_mask;
 		early[1] = amdgpu_ring_get_wptr(ring) & ring->buf_mask;
 		early[2] = ring->wptr & ring->buf_mask;
 		for (i = *pos / 4; i < 3 && size; i++) {
 			r = put_user(early[i], (uint32_t *)buf);
-			if (r)
-				return r;
+			if (r) {
+				result = r;
+				goto out;
+			}
 			buf += 4;
 			result += 4;
 			size -= 4;
@@ -516,29 +531,79 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
 		}
 	}
 
-	while (size) {
-		if (*pos >= (ring->ring_size + 12))
-			return result;
+	if (ring->funcs->type != AMDGPU_RING_TYPE_CPER) {
+		while (size) {
+			if (*pos >= (ring->ring_size + 12))
+				return result;
 
-		value = ring->ring[(*pos - 12)/4];
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-		buf += 4;
-		result += 4;
-		size -= 4;
-		*pos += 4;
+			value = ring->ring[(*pos - 12)/4];
+			r = put_user(value, (uint32_t *)buf);
+			if (r)
+				return r;
+			buf += 4;
+			result += 4;
+			size -= 4;
+			*pos += 4;
+		}
+	} else {
+		p = early[0];
+		if (early[0] <= early[1])
+			size = (early[1] - early[0]);
+		else
+			size = ring->ring_size - (early[0] - early[1]);
+
+		while (size) {
+			if (p == early[1])
+				goto out;
+
+			value = ring->ring[p];
+			r = put_user(value, (uint32_t *)buf);
+			if (r) {
+				result = r;
+				goto out;
+			}
+
+			buf += 4;
+			result += 4;
+			size--;
+			p++;
+			p &= ring->ptr_mask;
+		}
 	}
 
+out:
+	if (ring->funcs->type == AMDGPU_RING_TYPE_CPER)
+		mutex_unlock(&ring->adev->cper.ring_lock);
+
 	return result;
 }
 
+static ssize_t amdgpu_debugfs_virt_ring_read(struct file *f, char __user *buf,
+	size_t size, loff_t *pos)
+{
+	struct amdgpu_ring *ring = file_inode(f)->i_private;
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	if (ring->funcs->type == AMDGPU_RING_TYPE_CPER)
+		amdgpu_virt_req_ras_cper_dump(ring->adev, false);
+
+	return amdgpu_debugfs_ring_read(f, buf, size, pos);
+}
+
 static const struct file_operations amdgpu_debugfs_ring_fops = {
 	.owner = THIS_MODULE,
 	.read = amdgpu_debugfs_ring_read,
 	.llseek = default_llseek
 };
 
+static const struct file_operations amdgpu_debugfs_virt_ring_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_virt_ring_read,
+	.llseek = default_llseek
+};
+
 static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf,
 				       size_t size, loff_t *pos)
 {
@@ -626,9 +691,14 @@ void amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	char name[32];
 
 	sprintf(name, "amdgpu_ring_%s", ring->name);
-	debugfs_create_file_size(name, S_IFREG | 0444, root, ring,
-				 &amdgpu_debugfs_ring_fops,
-				 ring->ring_size + 12);
+	if (amdgpu_sriov_vf(adev))
+		debugfs_create_file_size(name, S_IFREG | 0444, root, ring,
+					 &amdgpu_debugfs_virt_ring_fops,
+					 ring->ring_size + 12);
+	else
+		debugfs_create_file_size(name, S_IFREG | 0444, root, ring,
+					 &amdgpu_debugfs_ring_fops,
+					 ring->ring_size + 12);
 
 	if (ring->mqd_obj) {
 		sprintf(name, "amdgpu_mqd_%s", ring->name);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index dee5a1b4e572..bb2b66385223 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -37,7 +37,7 @@ struct amdgpu_job;
 struct amdgpu_vm;
 
 /* max number of rings */
-#define AMDGPU_MAX_RINGS		124
+#define AMDGPU_MAX_RINGS		149
 #define AMDGPU_MAX_HWIP_RINGS		64
 #define AMDGPU_MAX_GFX_RINGS		2
 #define AMDGPU_MAX_SW_GFX_RINGS         2
@@ -82,6 +82,7 @@ enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_KIQ,
 	AMDGPU_RING_TYPE_MES,
 	AMDGPU_RING_TYPE_UMSCH_MM,
+	AMDGPU_RING_TYPE_CPER,
 };
 
 enum amdgpu_ib_pool_type {
@@ -237,6 +238,7 @@ struct amdgpu_ring_funcs {
 	void (*patch_de)(struct amdgpu_ring *ring, unsigned offset);
 	int (*reset)(struct amdgpu_ring *ring, unsigned int vmid);
 	void (*emit_cleaner_shader)(struct amdgpu_ring *ring);
+	bool (*is_guilty)(struct amdgpu_ring *ring);
 };
 
 struct amdgpu_ring {
@@ -306,6 +308,8 @@ struct amdgpu_ring {
 
 	bool            is_sw_ring;
 	unsigned int    entry_index;
+	/* store the cached rptr to restore after reset */
+	uint64_t cached_rptr;
 
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 174badca27e7..529c9696c2f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_sdma.h"
 #include "amdgpu_ras.h"
+#include "amdgpu_reset.h"
 
 #define AMDGPU_CSA_SDMA_SIZE 64
 /* SDMA CSA reside in the 3rd page of CSA */
@@ -355,23 +356,44 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev)
 static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)data;
-	u32 i;
+	u64 i, num_ring;
 	u64 mask = 0;
-	struct amdgpu_ring *ring;
+	struct amdgpu_ring *ring, *page = NULL;
 
 	if (!adev)
 		return -ENODEV;
 
-	mask = BIT_ULL(adev->sdma.num_instances) - 1;
+	/* Determine the number of rings per SDMA instance
+	 * (1 for sdma gfx ring, 2 if page queue exists)
+	 */
+	if (adev->sdma.has_page_queue)
+		num_ring = 2;
+	else
+		num_ring = 1;
+
+	/* Calculate the maximum possible mask value
+	 * based on the number of SDMA instances and rings
+	*/
+	mask = BIT_ULL(adev->sdma.num_instances * num_ring) - 1;
+
 	if ((val & mask) == 0)
 		return -EINVAL;
 
 	for (i = 0; i < adev->sdma.num_instances; ++i) {
 		ring = &adev->sdma.instance[i].ring;
-		if (val & BIT_ULL(i))
+		if (adev->sdma.has_page_queue)
+			page = &adev->sdma.instance[i].page;
+		if (val & BIT_ULL(i * num_ring))
 			ring->sched.ready = true;
 		else
 			ring->sched.ready = false;
+
+		if (page) {
+			if (val & BIT_ULL(i * num_ring + 1))
+				page->sched.ready = true;
+			else
+				page->sched.ready = false;
+		}
 	}
 	/* publish sched.ready flag update effective immediately across smp */
 	smp_rmb();
@@ -381,16 +403,37 @@ static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val)
 static int amdgpu_debugfs_sdma_sched_mask_get(void *data, u64 *val)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)data;
-	u32 i;
+	u64 i, num_ring;
 	u64 mask = 0;
-	struct amdgpu_ring *ring;
+	struct amdgpu_ring *ring, *page = NULL;
 
 	if (!adev)
 		return -ENODEV;
+
+	/* Determine the number of rings per SDMA instance
+	 * (1 for sdma gfx ring, 2 if page queue exists)
+	 */
+	if (adev->sdma.has_page_queue)
+		num_ring = 2;
+	else
+		num_ring = 1;
+
 	for (i = 0; i < adev->sdma.num_instances; ++i) {
 		ring = &adev->sdma.instance[i].ring;
+		if (adev->sdma.has_page_queue)
+			page = &adev->sdma.instance[i].page;
+
 		if (ring->sched.ready)
-			mask |= 1 << i;
+			mask |= BIT_ULL(i * num_ring);
+		else
+			mask &= ~BIT_ULL(i * num_ring);
+
+		if (page) {
+			if (page->sched.ready)
+				mask |= BIT_ULL(i * num_ring + 1);
+			else
+				mask &= ~BIT_ULL(i * num_ring + 1);
+		}
 	}
 
 	*val = mask;
@@ -460,3 +503,147 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 			device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
 	}
 }
+
+struct amdgpu_ring *amdgpu_sdma_get_shared_ring(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	if (adev->sdma.has_page_queue &&
+	    (ring->me < adev->sdma.num_instances) &&
+	    (ring == &adev->sdma.instance[ring->me].ring))
+		return &adev->sdma.instance[ring->me].page;
+	else
+		return NULL;
+}
+
+/**
+* amdgpu_sdma_is_shared_inv_eng - Check if a ring is an SDMA ring that shares a VM invalidation engine
+* @adev: Pointer to the AMDGPU device structure
+* @ring: Pointer to the ring structure to check
+*
+* This function checks if the given ring is an SDMA ring that shares a VM invalidation engine.
+* It returns true if the ring is such an SDMA ring, false otherwise.
+*/
+bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	int i = ring->me;
+
+	if (!adev->sdma.has_page_queue || i >= adev->sdma.num_instances)
+		return false;
+
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+		return (ring == &adev->sdma.instance[i].page);
+	else
+		return false;
+}
+
+/**
+ * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks
+ * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions
+ *
+ * This function allows KFD and AMDGPU to register their own callbacks for handling
+ * pre-reset and post-reset operations for engine reset. These are needed because engine
+ * reset will stop all queues on that engine.
+ */
+void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs)
+{
+	if (!funcs)
+		return;
+
+	/* Ensure the reset_callback_list is initialized */
+	if (!adev->sdma.reset_callback_list.next) {
+		INIT_LIST_HEAD(&adev->sdma.reset_callback_list);
+	}
+	/* Initialize the list node in the callback structure */
+	INIT_LIST_HEAD(&funcs->list);
+
+	/* Add the callback structure to the global list */
+	list_add_tail(&funcs->list, &adev->sdma.reset_callback_list);
+}
+
+/**
+ * amdgpu_sdma_reset_engine - Reset a specific SDMA engine
+ * @adev: Pointer to the AMDGPU device
+ * @instance_id: ID of the SDMA engine instance to reset
+ *
+ * This function performs the following steps:
+ * 1. Calls all registered pre_reset callbacks to allow KFD and AMDGPU to save their state.
+ * 2. Resets the specified SDMA engine instance.
+ * 3. Calls all registered post_reset callbacks to allow KFD and AMDGPU to restore their state.
+ *
+ * Returns: 0 on success, or a negative error code on failure.
+ */
+int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
+{
+	struct sdma_on_reset_funcs *funcs;
+	int ret = 0;
+	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
+	struct amdgpu_ring *gfx_ring = &sdma_instance->ring;
+	struct amdgpu_ring *page_ring = &sdma_instance->page;
+	bool gfx_sched_stopped = false, page_sched_stopped = false;
+
+	mutex_lock(&sdma_instance->engine_reset_mutex);
+	/* Stop the scheduler's work queue for the GFX and page rings if they are running.
+	* This ensures that no new tasks are submitted to the queues while
+	* the reset is in progress.
+	*/
+	if (!amdgpu_ring_sched_ready(gfx_ring)) {
+		drm_sched_wqueue_stop(&gfx_ring->sched);
+		gfx_sched_stopped = true;
+	}
+
+	if (adev->sdma.has_page_queue && !amdgpu_ring_sched_ready(page_ring)) {
+		drm_sched_wqueue_stop(&page_ring->sched);
+		page_sched_stopped = true;
+	}
+
+	/* Invoke all registered pre_reset callbacks */
+	list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) {
+		if (funcs->pre_reset) {
+			ret = funcs->pre_reset(adev, instance_id);
+			if (ret) {
+				dev_err(adev->dev,
+				"beforeReset callback failed for instance %u: %d\n",
+					instance_id, ret);
+				goto exit;
+			}
+		}
+	}
+
+	/* Perform the SDMA reset for the specified instance */
+	ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+	if (ret) {
+		dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
+		goto exit;
+	}
+
+	/* Invoke all registered post_reset callbacks */
+	list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) {
+		if (funcs->post_reset) {
+			ret = funcs->post_reset(adev, instance_id);
+			if (ret) {
+				dev_err(adev->dev,
+				"afterReset callback failed for instance %u: %d\n",
+					instance_id, ret);
+				goto exit;
+			}
+		}
+	}
+
+exit:
+	/* Restart the scheduler's work queue for the GFX and page rings
+	 * if they were stopped by this function. This allows new tasks
+	 * to be submitted to the queues after the reset is complete.
+	 */
+	if (!ret) {
+		if (gfx_sched_stopped && amdgpu_ring_sched_ready(gfx_ring)) {
+			drm_sched_wqueue_start(&gfx_ring->sched);
+		}
+		if (page_sched_stopped && amdgpu_ring_sched_ready(page_ring)) {
+			drm_sched_wqueue_start(&page_ring->sched);
+		}
+	}
+	mutex_unlock(&sdma_instance->engine_reset_mutex);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 5f60736051d1..47d56fd0589f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -64,6 +64,11 @@ struct amdgpu_sdma_instance {
 	struct amdgpu_bo	*sdma_fw_obj;
 	uint64_t		sdma_fw_gpu_addr;
 	uint32_t		*sdma_fw_ptr;
+	struct mutex		engine_reset_mutex;
+	/* track guilty state of GFX and PAGE queues */
+	bool			gfx_guilty;
+	bool			page_guilty;
+
 };
 
 enum amdgpu_sdma_ras_memory_id {
@@ -98,6 +103,13 @@ struct amdgpu_sdma_ras {
 	struct amdgpu_ras_block_object ras_block;
 };
 
+struct sdma_on_reset_funcs {
+	int (*pre_reset)(struct amdgpu_device *adev, uint32_t instance_id);
+	int (*post_reset)(struct amdgpu_device *adev, uint32_t instance_id);
+	/* Linked list node to store this structure in a list; */
+	struct list_head list;
+};
+
 struct amdgpu_sdma {
 	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
 	struct amdgpu_irq_src	trap_irq;
@@ -118,6 +130,7 @@ struct amdgpu_sdma {
 	struct amdgpu_sdma_ras	*ras;
 	uint32_t		*ip_dump;
 	uint32_t 		supported_reset;
+	struct list_head	reset_callback_list;
 };
 
 /*
@@ -157,6 +170,9 @@ struct amdgpu_buffer_funcs {
 				 uint32_t byte_count);
 };
 
+void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs);
+int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id);
+
 #define amdgpu_emit_copy_buffer(adev, ib, s, d, b, t) (adev)->mman.buffer_funcs->emit_copy_buffer((ib),  (s), (d), (b), (t))
 #define amdgpu_emit_fill_buffer(adev, ib, s, d, b) (adev)->mman.buffer_funcs->emit_fill_buffer((ib), (s), (d), (b))
 
@@ -180,4 +196,7 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev);
 int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
 void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
+bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_ring *ring);
+struct amdgpu_ring *amdgpu_sdma_get_shared_ring(struct amdgpu_device *adev,
+	struct amdgpu_ring *ring);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index c586ab4c911b..5576ed0b508f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -135,11 +135,16 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
 	struct amdgpu_sync_entry *e;
 
 	hash_for_each_possible(sync->fences, e, node, f->context) {
-		if (unlikely(e->fence->context != f->context))
-			continue;
+		if (dma_fence_is_signaled(e->fence)) {
+			dma_fence_put(e->fence);
+			e->fence = dma_fence_get(f);
+			return true;
+		}
 
-		amdgpu_sync_keep_later(&e->fence, f);
-		return true;
+		if (likely(e->fence->context == f->context)) {
+			amdgpu_sync_keep_later(&e->fence, f);
+			return true;
+		}
 	}
 	return false;
 }
@@ -149,10 +154,12 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
  *
  * @sync: sync object to add fence to
  * @f: fence to sync to
+ * @flags: memory allocation flags to use when allocating sync entry
  *
  * Add the fence to the sync object.
  */
-int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f)
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      gfp_t flags)
 {
 	struct amdgpu_sync_entry *e;
 
@@ -162,7 +169,7 @@ int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f)
 	if (amdgpu_sync_add_later(sync, f))
 		return 0;
 
-	e = kmem_cache_alloc(amdgpu_sync_slab, GFP_KERNEL);
+	e = kmem_cache_alloc(amdgpu_sync_slab, flags);
 	if (!e)
 		return -ENOMEM;
 
@@ -249,7 +256,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
 			struct dma_fence *tmp = dma_fence_chain_contained(f);
 
 			if (amdgpu_sync_test_fence(adev, mode, owner, tmp)) {
-				r = amdgpu_sync_fence(sync, f);
+				r = amdgpu_sync_fence(sync, f, GFP_KERNEL);
 				dma_fence_put(f);
 				if (r)
 					return r;
@@ -281,7 +288,7 @@ int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv)
 		if (fence_owner != AMDGPU_FENCE_OWNER_KFD)
 			continue;
 
-		r = amdgpu_sync_fence(sync, f);
+		r = amdgpu_sync_fence(sync, f, GFP_KERNEL);
 		if (r)
 			break;
 	}
@@ -388,7 +395,7 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone)
 	hash_for_each_safe(source->fences, i, tmp, e, node) {
 		f = e->fence;
 		if (!dma_fence_is_signaled(f)) {
-			r = amdgpu_sync_fence(clone, f);
+			r = amdgpu_sync_fence(clone, f, GFP_KERNEL);
 			if (r)
 				return r;
 		} else {
@@ -400,6 +407,25 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone)
 }
 
 /**
+ * amdgpu_sync_move - move all fences from src to dst
+ *
+ * @src: source of the fences, empty after function
+ * @dst: destination for the fences
+ *
+ * Moves all fences from source to destination. All fences in destination are
+ * freed and source is empty after the function call.
+ */
+void amdgpu_sync_move(struct amdgpu_sync *src, struct amdgpu_sync *dst)
+{
+	unsigned int i;
+
+	amdgpu_sync_free(dst);
+
+	for (i = 0; i < HASH_SIZE(src->fences); ++i)
+		hlist_move_list(&src->fences[i], &dst->fences[i]);
+}
+
+/**
  * amdgpu_sync_push_to_job - push fences into job
  * @sync: sync object to get the fences from
  * @job: job to push the fences into
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index e3272dce798d..51eb4382c91e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -47,7 +47,8 @@ struct amdgpu_sync {
 };
 
 void amdgpu_sync_create(struct amdgpu_sync *sync);
-int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f);
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      gfp_t flags);
 int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
 		     struct dma_resv *resv, enum amdgpu_sync_mode mode,
 		     void *owner);
@@ -56,6 +57,7 @@ struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
 				     struct amdgpu_ring *ring);
 struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync);
 int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone);
+void amdgpu_sync_move(struct amdgpu_sync *src, struct amdgpu_sync *dst);
 int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job);
 int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr);
 void amdgpu_sync_free(struct amdgpu_sync *sync);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 383fce40d4dd..11dd2e0f7979 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -457,6 +457,38 @@ DEFINE_EVENT(amdgpu_pasid, amdgpu_pasid_freed,
 	    TP_ARGS(pasid)
 );
 
+TRACE_EVENT(amdgpu_isolation,
+	    TP_PROTO(void *prev, void *next),
+	    TP_ARGS(prev, next),
+	    TP_STRUCT__entry(
+			     __field(void *, prev)
+			     __field(void *, next)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->prev = prev;
+			   __entry->next = next;
+			   ),
+	    TP_printk("prev=%p, next=%p",
+		      __entry->prev,
+		      __entry->next)
+);
+
+TRACE_EVENT(amdgpu_cleaner_shader,
+	    TP_PROTO(struct amdgpu_ring *ring, struct dma_fence *fence),
+	    TP_ARGS(ring, fence),
+	    TP_STRUCT__entry(
+			     __string(ring, ring->name)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __assign_str(ring);
+			   __entry->seqno = fence->seqno;
+			   ),
+	    TP_printk("ring=%s, seqno=%Lu", __get_str(ring), __entry->seqno)
+);
+
 TRACE_EVENT(amdgpu_bo_list_set,
 	    TP_PROTO(struct amdgpu_bo_list *list, struct amdgpu_bo *bo),
 	    TP_ARGS(list, bo),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 262bd010a283..53b71e9d8076 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1964,10 +1964,19 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	/* Compute GTT size, either based on TTM limit
 	 * or whatever the user passed on module init.
 	 */
-	if (amdgpu_gtt_size == -1)
-		gtt_size = ttm_tt_pages_limit() << PAGE_SHIFT;
-	else
-		gtt_size = (uint64_t)amdgpu_gtt_size << 20;
+	gtt_size = ttm_tt_pages_limit() << PAGE_SHIFT;
+	if (amdgpu_gtt_size != -1) {
+		uint64_t configured_size = (uint64_t)amdgpu_gtt_size << 20;
+
+		drm_warn(&adev->ddev,
+			"Configuring gttsize via module parameter is deprecated, please use ttm.pages_limit\n");
+		if (gtt_size != configured_size)
+			drm_warn(&adev->ddev,
+				"GTT size has been set as %llu but TTM size has been set as %llu, this is unusual\n",
+				configured_size, gtt_size);
+
+		gtt_size = configured_size;
+	}
 
 	/* Initialize GTT memory pool */
 	r = amdgpu_gtt_mgr_init(adev, gtt_size);
@@ -1978,6 +1987,11 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	DRM_INFO("amdgpu: %uM of GTT memory ready.\n",
 		 (unsigned int)(gtt_size / (1024 * 1024)));
 
+	if (adev->flags & AMD_IS_APU) {
+		if (adev->gmc.real_vram_size < gtt_size)
+			adev->apu_prefer_gtt = true;
+	}
+
 	/* Initialize doorbell pool on PCI BAR */
 	r = amdgpu_ttm_init_on_chip(adev, AMDGPU_PL_DOORBELL, adev->doorbell.size / PAGE_SIZE);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index cf700824b960..3d9e9fdc10b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1216,6 +1216,7 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 		case IP_VERSION(11, 0, 13):
 			return "beige_goby";
 		case IP_VERSION(11, 5, 0):
+		case IP_VERSION(11, 5, 2):
 			return "vangogh";
 		case IP_VERSION(12, 0, 1):
 			return "green_sardine";
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index eafe20d8fe0b..0a1ef95b2866 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -387,6 +387,45 @@ int amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
 	return 0;
 }
 
+static int amdgpu_umc_loop_all_aid(struct amdgpu_device *adev, umc_func func,
+				   void *data)
+{
+	uint32_t umc_node_inst;
+	uint32_t node_inst;
+	uint32_t umc_inst;
+	uint32_t ch_inst;
+	int ret;
+
+	/*
+	 * This loop is done based on the following -
+	 * umc.active mask = mask of active umc instances across all nodes
+	 * umc.umc_inst_num = maximum number of umc instancess per node
+	 * umc.node_inst_num = maximum number of node instances
+	 * Channel instances are not assumed to be harvested.
+	 */
+	dev_dbg(adev->dev, "active umcs :%lx umc_inst per node: %d",
+		adev->umc.active_mask, adev->umc.umc_inst_num);
+	for_each_set_bit(umc_node_inst, &(adev->umc.active_mask),
+			 adev->umc.node_inst_num * adev->umc.umc_inst_num) {
+		node_inst = umc_node_inst / adev->umc.umc_inst_num;
+		umc_inst = umc_node_inst % adev->umc.umc_inst_num;
+		LOOP_UMC_CH_INST(ch_inst) {
+			dev_dbg(adev->dev,
+				"node_inst :%d umc_inst: %d ch_inst: %d",
+				node_inst, umc_inst, ch_inst);
+			ret = func(adev, node_inst, umc_inst, ch_inst, data);
+			if (ret) {
+				dev_err(adev->dev,
+					"Node %d umc %d ch %d func returns %d\n",
+					node_inst, umc_inst, ch_inst, ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
 int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 			umc_func func, void *data)
 {
@@ -395,6 +434,9 @@ int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 	uint32_t ch_inst         = 0;
 	int ret = 0;
 
+	if (adev->aid_mask)
+		return amdgpu_umc_loop_all_aid(adev, func, data);
+
 	if (adev->umc.node_inst_num) {
 		LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) {
 			ret = func(adev, node_inst, umc_inst, ch_inst, data);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index a4a7e61817aa..857693bcd8d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -71,6 +71,13 @@
  */
 #define UMC_CHANNEL_IDX_V2	BIT_ULL(47)
 
+/*
+ * save nps value to eeprom_table_record.retired_page[47:40],
+ * the channel index flag above will be retired.
+ */
+#define UMC_NPS_SHIFT 40
+#define UMC_NPS_MASK 0xffULL
+
 typedef int (*umc_func)(struct amdgpu_device *adev, uint32_t node_inst,
 			uint32_t umc_inst, uint32_t ch_inst, void *data);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index dde15c6a96e1..cd707d70a0bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -32,462 +32,7 @@
 #include "amdgpu_umsch_mm.h"
 #include "umsch_mm_v4_0.h"
 
-struct umsch_mm_test_ctx_data {
-	uint8_t process_csa[PAGE_SIZE];
-	uint8_t vpe_ctx_csa[PAGE_SIZE];
-	uint8_t vcn_ctx_csa[PAGE_SIZE];
-};
-
-struct umsch_mm_test_mqd_data {
-	uint8_t vpe_mqd[PAGE_SIZE];
-	uint8_t vcn_mqd[PAGE_SIZE];
-};
-
-struct umsch_mm_test_ring_data {
-	uint8_t vpe_ring[PAGE_SIZE];
-	uint8_t vpe_ib[PAGE_SIZE];
-	uint8_t vcn_ring[PAGE_SIZE];
-	uint8_t vcn_ib[PAGE_SIZE];
-};
-
-struct umsch_mm_test_queue_info {
-	uint64_t mqd_addr;
-	uint64_t csa_addr;
-	uint32_t doorbell_offset_0;
-	uint32_t doorbell_offset_1;
-	enum UMSCH_SWIP_ENGINE_TYPE engine;
-};
-
-struct umsch_mm_test {
-	struct amdgpu_bo	*ctx_data_obj;
-	uint64_t		ctx_data_gpu_addr;
-	uint32_t		*ctx_data_cpu_addr;
-
-	struct amdgpu_bo	*mqd_data_obj;
-	uint64_t		mqd_data_gpu_addr;
-	uint32_t		*mqd_data_cpu_addr;
-
-	struct amdgpu_bo	*ring_data_obj;
-	uint64_t		ring_data_gpu_addr;
-	uint32_t		*ring_data_cpu_addr;
-
-
-	struct amdgpu_vm	*vm;
-	struct amdgpu_bo_va	*bo_va;
-	uint32_t		pasid;
-	uint32_t		vm_cntx_cntl;
-	uint32_t		num_queues;
-};
-
-static int map_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			  struct amdgpu_bo *bo, struct amdgpu_bo_va **bo_va,
-			  uint64_t addr, uint32_t size)
-{
-	struct amdgpu_sync sync;
-	struct drm_exec exec;
-	int r;
-
-	amdgpu_sync_create(&sync);
-
-	drm_exec_init(&exec, 0, 0);
-	drm_exec_until_all_locked(&exec) {
-		r = drm_exec_lock_obj(&exec, &bo->tbo.base);
-		drm_exec_retry_on_contention(&exec);
-		if (unlikely(r))
-			goto error_fini_exec;
-
-		r = amdgpu_vm_lock_pd(vm, &exec, 0);
-		drm_exec_retry_on_contention(&exec);
-		if (unlikely(r))
-			goto error_fini_exec;
-	}
-
-	*bo_va = amdgpu_vm_bo_add(adev, vm, bo);
-	if (!*bo_va) {
-		r = -ENOMEM;
-		goto error_fini_exec;
-	}
-
-	r = amdgpu_vm_bo_map(adev, *bo_va, addr, 0, size,
-			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
-			     AMDGPU_PTE_EXECUTABLE);
-
-	if (r)
-		goto error_del_bo_va;
-
-
-	r = amdgpu_vm_bo_update(adev, *bo_va, false);
-	if (r)
-		goto error_del_bo_va;
-
-	amdgpu_sync_fence(&sync, (*bo_va)->last_pt_update);
-
-	r = amdgpu_vm_update_pdes(adev, vm, false);
-	if (r)
-		goto error_del_bo_va;
-
-	amdgpu_sync_fence(&sync, vm->last_update);
-
-	amdgpu_sync_wait(&sync, false);
-	drm_exec_fini(&exec);
-
-	amdgpu_sync_free(&sync);
-
-	return 0;
-
-error_del_bo_va:
-	amdgpu_vm_bo_del(adev, *bo_va);
-	amdgpu_sync_free(&sync);
-
-error_fini_exec:
-	drm_exec_fini(&exec);
-	amdgpu_sync_free(&sync);
-	return r;
-}
-
-static int unmap_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			    struct amdgpu_bo *bo, struct amdgpu_bo_va *bo_va,
-			    uint64_t addr)
-{
-	struct drm_exec exec;
-	long r;
-
-	drm_exec_init(&exec, 0, 0);
-	drm_exec_until_all_locked(&exec) {
-		r = drm_exec_lock_obj(&exec, &bo->tbo.base);
-		drm_exec_retry_on_contention(&exec);
-		if (unlikely(r))
-			goto out_unlock;
-
-		r = amdgpu_vm_lock_pd(vm, &exec, 0);
-		drm_exec_retry_on_contention(&exec);
-		if (unlikely(r))
-			goto out_unlock;
-	}
-
-
-	r = amdgpu_vm_bo_unmap(adev, bo_va, addr);
-	if (r)
-		goto out_unlock;
-
-	amdgpu_vm_bo_del(adev, bo_va);
-
-out_unlock:
-	drm_exec_fini(&exec);
-
-	return r;
-}
-
-static void setup_vpe_queue(struct amdgpu_device *adev,
-			    struct umsch_mm_test *test,
-			    struct umsch_mm_test_queue_info *qinfo)
-{
-	struct MQD_INFO *mqd = (struct MQD_INFO *)test->mqd_data_cpu_addr;
-	uint64_t ring_gpu_addr = test->ring_data_gpu_addr;
-
-	mqd->rb_base_lo = (ring_gpu_addr >> 8);
-	mqd->rb_base_hi = (ring_gpu_addr >> 40);
-	mqd->rb_size = PAGE_SIZE / 4;
-	mqd->wptr_val = 0;
-	mqd->rptr_val = 0;
-	mqd->unmapped = 1;
-
-	if (adev->vpe.collaborate_mode)
-		memcpy(++mqd, test->mqd_data_cpu_addr, sizeof(struct MQD_INFO));
-
-	qinfo->mqd_addr = test->mqd_data_gpu_addr;
-	qinfo->csa_addr = test->ctx_data_gpu_addr +
-		offsetof(struct umsch_mm_test_ctx_data, vpe_ctx_csa);
-	qinfo->doorbell_offset_0 = 0;
-	qinfo->doorbell_offset_1 = 0;
-}
-
-static void setup_vcn_queue(struct amdgpu_device *adev,
-			    struct umsch_mm_test *test,
-			    struct umsch_mm_test_queue_info *qinfo)
-{
-}
-
-static int add_test_queue(struct amdgpu_device *adev,
-			  struct umsch_mm_test *test,
-			  struct umsch_mm_test_queue_info *qinfo)
-{
-	struct umsch_mm_add_queue_input queue_input = {};
-	int r;
-
-	queue_input.process_id = test->pasid;
-	queue_input.page_table_base_addr = amdgpu_gmc_pd_addr(test->vm->root.bo);
-
-	queue_input.process_va_start = 0;
-	queue_input.process_va_end = (adev->vm_manager.max_pfn - 1) << AMDGPU_GPU_PAGE_SHIFT;
-
-	queue_input.process_quantum = 100000; /* 10ms */
-	queue_input.process_csa_addr = test->ctx_data_gpu_addr +
-				       offsetof(struct umsch_mm_test_ctx_data, process_csa);
-
-	queue_input.context_quantum = 10000; /* 1ms */
-	queue_input.context_csa_addr = qinfo->csa_addr;
-
-	queue_input.inprocess_context_priority = CONTEXT_PRIORITY_LEVEL_NORMAL;
-	queue_input.context_global_priority_level = CONTEXT_PRIORITY_LEVEL_NORMAL;
-	queue_input.doorbell_offset_0 = qinfo->doorbell_offset_0;
-	queue_input.doorbell_offset_1 = qinfo->doorbell_offset_1;
-
-	queue_input.engine_type = qinfo->engine;
-	queue_input.mqd_addr = qinfo->mqd_addr;
-	queue_input.vm_context_cntl = test->vm_cntx_cntl;
-
-	amdgpu_umsch_mm_lock(&adev->umsch_mm);
-	r = adev->umsch_mm.funcs->add_queue(&adev->umsch_mm, &queue_input);
-	amdgpu_umsch_mm_unlock(&adev->umsch_mm);
-	if (r)
-		return r;
-
-	return 0;
-}
-
-static int remove_test_queue(struct amdgpu_device *adev,
-			     struct umsch_mm_test *test,
-			     struct umsch_mm_test_queue_info *qinfo)
-{
-	struct umsch_mm_remove_queue_input queue_input = {};
-	int r;
-
-	queue_input.doorbell_offset_0 = qinfo->doorbell_offset_0;
-	queue_input.doorbell_offset_1 = qinfo->doorbell_offset_1;
-	queue_input.context_csa_addr = qinfo->csa_addr;
-
-	amdgpu_umsch_mm_lock(&adev->umsch_mm);
-	r = adev->umsch_mm.funcs->remove_queue(&adev->umsch_mm, &queue_input);
-	amdgpu_umsch_mm_unlock(&adev->umsch_mm);
-	if (r)
-		return r;
-
-	return 0;
-}
-
-static int submit_vpe_queue(struct amdgpu_device *adev, struct umsch_mm_test *test)
-{
-	struct MQD_INFO *mqd = (struct MQD_INFO *)test->mqd_data_cpu_addr;
-	uint32_t *ring = test->ring_data_cpu_addr +
-		offsetof(struct umsch_mm_test_ring_data, vpe_ring) / 4;
-	uint32_t *ib = test->ring_data_cpu_addr +
-		offsetof(struct umsch_mm_test_ring_data, vpe_ib) / 4;
-	uint64_t ib_gpu_addr = test->ring_data_gpu_addr +
-		offsetof(struct umsch_mm_test_ring_data, vpe_ib);
-	uint32_t *fence = ib + 2048 / 4;
-	uint64_t fence_gpu_addr = ib_gpu_addr + 2048;
-	const uint32_t test_pattern = 0xdeadbeef;
-	int i;
-
-	ib[0] = VPE_CMD_HEADER(VPE_CMD_OPCODE_FENCE, 0);
-	ib[1] = lower_32_bits(fence_gpu_addr);
-	ib[2] = upper_32_bits(fence_gpu_addr);
-	ib[3] = test_pattern;
-
-	ring[0] = VPE_CMD_HEADER(VPE_CMD_OPCODE_INDIRECT, 0);
-	ring[1] = (ib_gpu_addr & 0xffffffe0);
-	ring[2] = upper_32_bits(ib_gpu_addr);
-	ring[3] = 4;
-	ring[4] = 0;
-	ring[5] = 0;
-
-	mqd->wptr_val = (6 << 2);
-	if (adev->vpe.collaborate_mode)
-		(++mqd)->wptr_val = (6 << 2);
-
-	WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		if (*fence == test_pattern)
-			return 0;
-		udelay(1);
-	}
-
-	dev_err(adev->dev, "vpe queue submission timeout\n");
-
-	return -ETIMEDOUT;
-}
-
-static int submit_vcn_queue(struct amdgpu_device *adev, struct umsch_mm_test *test)
-{
-	return 0;
-}
-
-static int setup_umsch_mm_test(struct amdgpu_device *adev,
-			  struct umsch_mm_test *test)
-{
-	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB0(0)];
-	int r;
-
-	test->vm_cntx_cntl = hub->vm_cntx_cntl;
-
-	test->vm = kzalloc(sizeof(*test->vm), GFP_KERNEL);
-	if (!test->vm) {
-		r = -ENOMEM;
-		return r;
-	}
-
-	r = amdgpu_vm_init(adev, test->vm, -1);
-	if (r)
-		goto error_free_vm;
-
-	r = amdgpu_pasid_alloc(16);
-	if (r < 0)
-		goto error_fini_vm;
-	test->pasid = r;
-
-	r = amdgpu_bo_create_kernel(adev, sizeof(struct umsch_mm_test_ctx_data),
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
-				    &test->ctx_data_obj,
-				    &test->ctx_data_gpu_addr,
-				    (void **)&test->ctx_data_cpu_addr);
-	if (r)
-		goto error_free_pasid;
-
-	memset(test->ctx_data_cpu_addr, 0, sizeof(struct umsch_mm_test_ctx_data));
-
-	r = amdgpu_bo_create_kernel(adev, PAGE_SIZE,
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
-				    &test->mqd_data_obj,
-				    &test->mqd_data_gpu_addr,
-				    (void **)&test->mqd_data_cpu_addr);
-	if (r)
-		goto error_free_ctx_data_obj;
-
-	memset(test->mqd_data_cpu_addr, 0, PAGE_SIZE);
-
-	r = amdgpu_bo_create_kernel(adev, sizeof(struct umsch_mm_test_ring_data),
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
-				    &test->ring_data_obj,
-				    NULL,
-				    (void **)&test->ring_data_cpu_addr);
-	if (r)
-		goto error_free_mqd_data_obj;
-
-	memset(test->ring_data_cpu_addr, 0, sizeof(struct umsch_mm_test_ring_data));
-
-	test->ring_data_gpu_addr = AMDGPU_VA_RESERVED_BOTTOM;
-	r = map_ring_data(adev, test->vm, test->ring_data_obj, &test->bo_va,
-			  test->ring_data_gpu_addr, sizeof(struct umsch_mm_test_ring_data));
-	if (r)
-		goto error_free_ring_data_obj;
-
-	return 0;
-
-error_free_ring_data_obj:
-	amdgpu_bo_free_kernel(&test->ring_data_obj, NULL,
-			      (void **)&test->ring_data_cpu_addr);
-error_free_mqd_data_obj:
-	amdgpu_bo_free_kernel(&test->mqd_data_obj, &test->mqd_data_gpu_addr,
-			      (void **)&test->mqd_data_cpu_addr);
-error_free_ctx_data_obj:
-	amdgpu_bo_free_kernel(&test->ctx_data_obj, &test->ctx_data_gpu_addr,
-			      (void **)&test->ctx_data_cpu_addr);
-error_free_pasid:
-	amdgpu_pasid_free(test->pasid);
-error_fini_vm:
-	amdgpu_vm_fini(adev, test->vm);
-error_free_vm:
-	kfree(test->vm);
-
-	return r;
-}
-
-static void cleanup_umsch_mm_test(struct amdgpu_device *adev,
-				  struct umsch_mm_test *test)
-{
-	unmap_ring_data(adev, test->vm, test->ring_data_obj,
-			test->bo_va, test->ring_data_gpu_addr);
-	amdgpu_bo_free_kernel(&test->mqd_data_obj, &test->mqd_data_gpu_addr,
-			      (void **)&test->mqd_data_cpu_addr);
-	amdgpu_bo_free_kernel(&test->ring_data_obj, NULL,
-			      (void **)&test->ring_data_cpu_addr);
-	amdgpu_bo_free_kernel(&test->ctx_data_obj, &test->ctx_data_gpu_addr,
-			       (void **)&test->ctx_data_cpu_addr);
-	amdgpu_pasid_free(test->pasid);
-	amdgpu_vm_fini(adev, test->vm);
-	kfree(test->vm);
-}
-
-static int setup_test_queues(struct amdgpu_device *adev,
-			     struct umsch_mm_test *test,
-			     struct umsch_mm_test_queue_info *qinfo)
-{
-	int i, r;
-
-	for (i = 0; i < test->num_queues; i++) {
-		if (qinfo[i].engine == UMSCH_SWIP_ENGINE_TYPE_VPE)
-			setup_vpe_queue(adev, test, &qinfo[i]);
-		else
-			setup_vcn_queue(adev, test, &qinfo[i]);
-
-		r = add_test_queue(adev, test, &qinfo[i]);
-		if (r)
-			return r;
-	}
-
-	return 0;
-}
-
-static int submit_test_queues(struct amdgpu_device *adev,
-			      struct umsch_mm_test *test,
-			      struct umsch_mm_test_queue_info *qinfo)
-{
-	int i, r;
-
-	for (i = 0; i < test->num_queues; i++) {
-		if (qinfo[i].engine == UMSCH_SWIP_ENGINE_TYPE_VPE)
-			r = submit_vpe_queue(adev, test);
-		else
-			r = submit_vcn_queue(adev, test);
-		if (r)
-			return r;
-	}
-
-	return 0;
-}
-
-static void cleanup_test_queues(struct amdgpu_device *adev,
-			      struct umsch_mm_test *test,
-			      struct umsch_mm_test_queue_info *qinfo)
-{
-	int i;
-
-	for (i = 0; i < test->num_queues; i++)
-		remove_test_queue(adev, test, &qinfo[i]);
-}
-
-static int umsch_mm_test(struct amdgpu_device *adev)
-{
-	struct umsch_mm_test_queue_info qinfo[] = {
-		{ .engine = UMSCH_SWIP_ENGINE_TYPE_VPE },
-	};
-	struct umsch_mm_test test = { .num_queues = ARRAY_SIZE(qinfo) };
-	int r;
-
-	r = setup_umsch_mm_test(adev, &test);
-	if (r)
-		return r;
-
-	r = setup_test_queues(adev, &test, qinfo);
-	if (r)
-		goto cleanup;
-
-	r = submit_test_queues(adev, &test, qinfo);
-	if (r)
-		goto cleanup;
-
-	cleanup_test_queues(adev, &test, qinfo);
-	cleanup_umsch_mm_test(adev, &test);
-
-	return 0;
-
-cleanup:
-	cleanup_test_queues(adev, &test, qinfo);
-	cleanup_umsch_mm_test(adev, &test);
-	return r;
-}
+MODULE_FIRMWARE("amdgpu/umsch_mm_4_0_0.bin");
 
 int amdgpu_umsch_mm_submit_pkt(struct amdgpu_umsch_mm *umsch, void *pkt, int ndws)
 {
@@ -581,14 +126,14 @@ int amdgpu_umsch_mm_init_microcode(struct amdgpu_umsch_mm *umsch)
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
 	case IP_VERSION(4, 0, 6):
-		fw_name = "amdgpu/umsch_mm_4_0_0.bin";
+		fw_name = "4_0_0";
 		break;
 	default:
-		break;
+		return -EINVAL;
 	}
 
 	r = amdgpu_ucode_request(adev, &adev->umsch_mm.fw, AMDGPU_UCODE_REQUIRED,
-				 "%s", fw_name);
+				 "amdgpu/umsch_mm_%s.bin", fw_name);
 	if (r) {
 		release_firmware(adev->umsch_mm.fw);
 		adev->umsch_mm.fw = NULL;
@@ -792,7 +337,7 @@ static int umsch_mm_late_init(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_in_reset(adev) || adev->in_s0ix || adev->in_suspend)
 		return 0;
 
-	return umsch_mm_test(adev);
+	return 0;
 }
 
 static int umsch_mm_sw_init(struct amdgpu_ip_block *ip_block)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 83faf6e6788a..1991dd3d1056 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -93,47 +93,53 @@ MODULE_FIRMWARE(FIRMWARE_VCN5_0_1);
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
 
-int amdgpu_vcn_early_init(struct amdgpu_device *adev)
+int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i)
 {
 	char ucode_prefix[25];
-	int r, i;
+	int r;
 
+	adev->vcn.inst[i].adev = adev;
+	adev->vcn.inst[i].inst = i;
 	amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (i == 1 && amdgpu_ip_version(adev, UVD_HWIP, 0) ==  IP_VERSION(4, 0, 6))
-			r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw,
-						 AMDGPU_UCODE_REQUIRED,
-						 "amdgpu/%s_%d.bin", ucode_prefix, i);
-		else
-			r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw,
+
+	if (i != 0 && adev->vcn.per_inst_fw) {
+		r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw,
+					 AMDGPU_UCODE_REQUIRED,
+					 "amdgpu/%s_%d.bin", ucode_prefix, i);
+		if (r)
+			amdgpu_ucode_release(&adev->vcn.inst[i].fw);
+	} else {
+		if (!adev->vcn.inst[0].fw) {
+			r = amdgpu_ucode_request(adev, &adev->vcn.inst[0].fw,
 						 AMDGPU_UCODE_REQUIRED,
 						 "amdgpu/%s.bin", ucode_prefix);
-		if (r) {
-			amdgpu_ucode_release(&adev->vcn.inst[i].fw);
-			return r;
+			if (r)
+				amdgpu_ucode_release(&adev->vcn.inst[0].fw);
+		} else {
+			r = 0;
 		}
+		adev->vcn.inst[i].fw = adev->vcn.inst[0].fw;
 	}
+
 	return r;
 }
 
-int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
+int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i)
 {
 	unsigned long bo_size;
 	const struct common_firmware_header *hdr;
 	unsigned char fw_check;
 	unsigned int fw_shared_size, log_offset;
-	int i, r;
-
-	INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
-	mutex_init(&adev->vcn.vcn_pg_lock);
-	mutex_init(&adev->vcn.vcn1_jpeg1_workaround);
-	atomic_set(&adev->vcn.total_submission_cnt, 0);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++)
-		atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
+	int r;
 
+	mutex_init(&adev->vcn.inst[i].vcn1_jpeg1_workaround);
+	mutex_init(&adev->vcn.inst[i].vcn_pg_lock);
+	atomic_set(&adev->vcn.inst[i].total_submission_cnt, 0);
+	INIT_DELAYED_WORK(&adev->vcn.inst[i].idle_work, amdgpu_vcn_idle_work_handler);
+	atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
 	if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
 	    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-		adev->vcn.indirect_sram = true;
+		adev->vcn.inst[i].indirect_sram = true;
 
 	/*
 	 * Some Steam Deck's BIOS versions are incompatible with the
@@ -146,18 +152,19 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION);
 
 		if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) ||
-		     !strncmp("F7A0114", bios_ver, 7))) {
-			adev->vcn.indirect_sram = false;
+				 !strncmp("F7A0114", bios_ver, 7))) {
+			adev->vcn.inst[i].indirect_sram = false;
 			dev_info(adev->dev,
-				"Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver);
+				 "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver);
 		}
 	}
 
 	/* from vcn4 and above, only unified queue is used */
-	adev->vcn.using_unified_queue =
+	adev->vcn.inst[i].using_unified_queue =
 		amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0);
 
-	hdr = (const struct common_firmware_header *)adev->vcn.inst[0].fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data;
+	adev->vcn.inst[i].fw_version = le32_to_cpu(hdr->ucode_version);
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
 	/* Bit 20-23, it is encode major and non-zero for new naming convention.
@@ -175,16 +182,17 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		enc_major = fw_check;
 		dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf;
 		vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf;
-		DRM_INFO("Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n",
-			enc_major, enc_minor, dec_ver, vep, fw_rev);
+		dev_info(adev->dev,
+			 "Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n",
+			 enc_major, enc_minor, dec_ver, vep, fw_rev);
 	} else {
 		unsigned int version_major, version_minor, family_id;
 
 		family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
 		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
 		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
-		DRM_INFO("Found VCN firmware Version: %u.%u Family ID: %u\n",
-			version_major, version_minor, family_id);
+		dev_info(adev->dev, "Found VCN firmware Version: %u.%u Family ID: %u\n",
+			 version_major, version_minor, family_id);
 	}
 
 	bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE;
@@ -207,80 +215,77 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	if (amdgpu_vcnfw_log)
 		bo_size += AMDGPU_VCNFW_LOG_SIZE;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM |
+				    AMDGPU_GEM_DOMAIN_GTT,
+				    &adev->vcn.inst[i].vcpu_bo,
+				    &adev->vcn.inst[i].gpu_addr,
+				    &adev->vcn.inst[i].cpu_addr);
+	if (r) {
+		dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
+		return r;
+	}
 
-		r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
+	adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr +
+		bo_size - fw_shared_size;
+	adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr +
+		bo_size - fw_shared_size;
+
+	adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size;
+
+	if (amdgpu_vcnfw_log) {
+		adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
+		adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
+		adev->vcn.inst[i].fw_shared.log_offset = log_offset;
+	}
+
+	if (adev->vcn.inst[i].indirect_sram) {
+		r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_VRAM |
 					    AMDGPU_GEM_DOMAIN_GTT,
-					    &adev->vcn.inst[i].vcpu_bo,
-					    &adev->vcn.inst[i].gpu_addr,
-					    &adev->vcn.inst[i].cpu_addr);
+					    &adev->vcn.inst[i].dpg_sram_bo,
+					    &adev->vcn.inst[i].dpg_sram_gpu_addr,
+					    &adev->vcn.inst[i].dpg_sram_cpu_addr);
 		if (r) {
-			dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
+			dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r);
 			return r;
 		}
-
-		adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr +
-				bo_size - fw_shared_size;
-		adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr +
-				bo_size - fw_shared_size;
-
-		adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size;
-
-		if (amdgpu_vcnfw_log) {
-			adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
-			adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE;
-			adev->vcn.inst[i].fw_shared.log_offset = log_offset;
-		}
-
-		if (adev->vcn.indirect_sram) {
-			r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
-					AMDGPU_GEM_DOMAIN_VRAM |
-					AMDGPU_GEM_DOMAIN_GTT,
-					&adev->vcn.inst[i].dpg_sram_bo,
-					&adev->vcn.inst[i].dpg_sram_gpu_addr,
-					&adev->vcn.inst[i].dpg_sram_cpu_addr);
-			if (r) {
-				dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r);
-				return r;
-			}
-		}
 	}
 
 	return 0;
 }
 
-int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
+int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i)
 {
-	int i, j;
+	int j;
 
-	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-		if (adev->vcn.harvest_config & (1 << j))
-			continue;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		amdgpu_bo_free_kernel(
-			&adev->vcn.inst[j].dpg_sram_bo,
-			&adev->vcn.inst[j].dpg_sram_gpu_addr,
-			(void **)&adev->vcn.inst[j].dpg_sram_cpu_addr);
+	amdgpu_bo_free_kernel(
+		&adev->vcn.inst[i].dpg_sram_bo,
+		&adev->vcn.inst[i].dpg_sram_gpu_addr,
+		(void **)&adev->vcn.inst[i].dpg_sram_cpu_addr);
 
-		kvfree(adev->vcn.inst[j].saved_bo);
+	kvfree(adev->vcn.inst[i].saved_bo);
 
-		amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo,
-					  &adev->vcn.inst[j].gpu_addr,
-					  (void **)&adev->vcn.inst[j].cpu_addr);
+	amdgpu_bo_free_kernel(&adev->vcn.inst[i].vcpu_bo,
+			      &adev->vcn.inst[i].gpu_addr,
+			      (void **)&adev->vcn.inst[i].cpu_addr);
 
-		amdgpu_ring_fini(&adev->vcn.inst[j].ring_dec);
+	amdgpu_ring_fini(&adev->vcn.inst[i].ring_dec);
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
-			amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]);
+	for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j)
+		amdgpu_ring_fini(&adev->vcn.inst[i].ring_enc[j]);
 
-		amdgpu_ucode_release(&adev->vcn.inst[j].fw);
+	if (adev->vcn.per_inst_fw) {
+		amdgpu_ucode_release(&adev->vcn.inst[i].fw);
+	} else {
+		amdgpu_ucode_release(&adev->vcn.inst[0].fw);
+		adev->vcn.inst[i].fw = NULL;
 	}
-
-	mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
-	mutex_destroy(&adev->vcn.vcn_pg_lock);
+	mutex_destroy(&adev->vcn.inst[i].vcn_pg_lock);
+	mutex_destroy(&adev->vcn.inst[i].vcn1_jpeg1_workaround);
 
 	return 0;
 }
@@ -300,179 +305,208 @@ bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type t
 	return ret;
 }
 
-int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev)
+static int amdgpu_vcn_save_vcpu_bo_inst(struct amdgpu_device *adev, int i)
 {
 	unsigned int size;
 	void *ptr;
-	int i, idx;
+	int idx;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->vcn.inst[i].vcpu_bo == NULL)
-			return 0;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
+	if (adev->vcn.inst[i].vcpu_bo == NULL)
+		return 0;
 
-		size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo);
-		ptr = adev->vcn.inst[i].cpu_addr;
+	size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo);
+	ptr = adev->vcn.inst[i].cpu_addr;
 
-		adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL);
-		if (!adev->vcn.inst[i].saved_bo)
-			return -ENOMEM;
+	adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL);
+	if (!adev->vcn.inst[i].saved_bo)
+		return -ENOMEM;
 
-		if (drm_dev_enter(adev_to_drm(adev), &idx)) {
-			memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size);
-			drm_dev_exit(idx);
-		}
+	if (drm_dev_enter(adev_to_drm(adev), &idx)) {
+		memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size);
+		drm_dev_exit(idx);
+	}
+
+	return 0;
+}
+
+int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev)
+{
+	int ret, i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		ret = amdgpu_vcn_save_vcpu_bo_inst(adev, i);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
 
-int amdgpu_vcn_suspend(struct amdgpu_device *adev)
+int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i)
 {
 	bool in_ras_intr = amdgpu_ras_intr_triggered();
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
+
+	cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work);
 
 	/* err_event_athub will corrupt VCPU buffer, so we need to
 	 * restore fw data and clear buffer in amdgpu_vcn_resume() */
 	if (in_ras_intr)
 		return 0;
 
-	return amdgpu_vcn_save_vcpu_bo(adev);
+	return amdgpu_vcn_save_vcpu_bo_inst(adev, i);
 }
 
-int amdgpu_vcn_resume(struct amdgpu_device *adev)
+int amdgpu_vcn_resume(struct amdgpu_device *adev, int i)
 {
 	unsigned int size;
 	void *ptr;
-	int i, idx;
+	int idx;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->vcn.inst[i].vcpu_bo == NULL)
-			return -EINVAL;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
+	if (adev->vcn.inst[i].vcpu_bo == NULL)
+		return -EINVAL;
 
-		size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo);
-		ptr = adev->vcn.inst[i].cpu_addr;
+	size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo);
+	ptr = adev->vcn.inst[i].cpu_addr;
 
-		if (adev->vcn.inst[i].saved_bo != NULL) {
+	if (adev->vcn.inst[i].saved_bo != NULL) {
+		if (drm_dev_enter(adev_to_drm(adev), &idx)) {
+			memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size);
+			drm_dev_exit(idx);
+		}
+		kvfree(adev->vcn.inst[i].saved_bo);
+		adev->vcn.inst[i].saved_bo = NULL;
+	} else {
+		const struct common_firmware_header *hdr;
+		unsigned int offset;
+
+		hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data;
+		if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+			offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
 			if (drm_dev_enter(adev_to_drm(adev), &idx)) {
-				memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size);
+				memcpy_toio(adev->vcn.inst[i].cpu_addr,
+					    adev->vcn.inst[i].fw->data + offset,
+					    le32_to_cpu(hdr->ucode_size_bytes));
 				drm_dev_exit(idx);
 			}
-			kvfree(adev->vcn.inst[i].saved_bo);
-			adev->vcn.inst[i].saved_bo = NULL;
-		} else {
-			const struct common_firmware_header *hdr;
-			unsigned int offset;
-
-			hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data;
-			if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
-				offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
-				if (drm_dev_enter(adev_to_drm(adev), &idx)) {
-					memcpy_toio(adev->vcn.inst[i].cpu_addr,
-						    adev->vcn.inst[i].fw->data + offset,
-						    le32_to_cpu(hdr->ucode_size_bytes));
-					drm_dev_exit(idx);
-				}
-				size -= le32_to_cpu(hdr->ucode_size_bytes);
-				ptr += le32_to_cpu(hdr->ucode_size_bytes);
-			}
-			memset_io(ptr, 0, size);
+			size -= le32_to_cpu(hdr->ucode_size_bytes);
+			ptr += le32_to_cpu(hdr->ucode_size_bytes);
 		}
+		memset_io(ptr, 0, size);
 	}
+
 	return 0;
 }
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 {
-	struct amdgpu_device *adev =
-		container_of(work, struct amdgpu_device, vcn.idle_work.work);
+	struct amdgpu_vcn_inst *vcn_inst =
+		container_of(work, struct amdgpu_vcn_inst, idle_work.work);
+	struct amdgpu_device *adev = vcn_inst->adev;
 	unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0};
-	unsigned int i, j;
+	unsigned int i = vcn_inst->inst, j;
 	int r = 0;
 
-	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-		if (adev->vcn.harvest_config & (1 << j))
-			continue;
-
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
-			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
 
-		/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
-		    !adev->vcn.using_unified_queue) {
-			struct dpg_pause_state new_state;
+	for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j)
+		fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[j]);
 
-			if (fence[j] ||
-				unlikely(atomic_read(&adev->vcn.inst[j].dpg_enc_submission_cnt)))
-				new_state.fw_based = VCN_DPG_STATE__PAUSE;
-			else
-				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    !adev->vcn.inst[i].using_unified_queue) {
+		struct dpg_pause_state new_state;
 
-			adev->vcn.pause_dpg_mode(adev, j, &new_state);
-		}
+		if (fence[i] ||
+		    unlikely(atomic_read(&vcn_inst->dpg_enc_submission_cnt)))
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 
-		fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_dec);
-		fences += fence[j];
+		adev->vcn.inst[i].pause_dpg_mode(vcn_inst, &new_state);
 	}
 
-	if (!fences && !atomic_read(&adev->vcn.total_submission_cnt)) {
-		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-		       AMD_PG_STATE_GATE);
-		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-				false);
-		if (r)
-			dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
+	fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_dec);
+	fences += fence[i];
+
+	if (!fences && !atomic_read(&vcn_inst->total_submission_cnt)) {
+		vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_GATE);
+		mutex_lock(&adev->vcn.workload_profile_mutex);
+		if (adev->vcn.workload_profile_active) {
+			r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+							    false);
+			if (r)
+				dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
+			adev->vcn.workload_profile_active = false;
+		}
+		mutex_unlock(&adev->vcn.workload_profile_mutex);
 	} else {
-		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+		schedule_delayed_work(&vcn_inst->idle_work, VCN_IDLE_TIMEOUT);
 	}
 }
 
 void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_vcn_inst *vcn_inst = &adev->vcn.inst[ring->me];
 	int r = 0;
 
-	atomic_inc(&adev->vcn.total_submission_cnt);
+	atomic_inc(&vcn_inst->total_submission_cnt);
+
+	cancel_delayed_work_sync(&vcn_inst->idle_work);
 
-	if (!cancel_delayed_work_sync(&adev->vcn.idle_work)) {
+	/* We can safely return early here because we've cancelled the
+	 * the delayed work so there is no one else to set it to false
+	 * and we don't care if someone else sets it to true.
+	 */
+	if (adev->vcn.workload_profile_active)
+		goto pg_lock;
+
+	mutex_lock(&adev->vcn.workload_profile_mutex);
+	if (!adev->vcn.workload_profile_active) {
 		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-				true);
+						    true);
 		if (r)
 			dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r);
+		adev->vcn.workload_profile_active = true;
 	}
+	mutex_unlock(&adev->vcn.workload_profile_mutex);
 
-	mutex_lock(&adev->vcn.vcn_pg_lock);
-	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-	       AMD_PG_STATE_UNGATE);
+pg_lock:
+	mutex_lock(&vcn_inst->vcn_pg_lock);
+	vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_UNGATE);
 
 	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
-	    !adev->vcn.using_unified_queue) {
+	    !vcn_inst->using_unified_queue) {
 		struct dpg_pause_state new_state;
 
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
-			atomic_inc(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
+			atomic_inc(&vcn_inst->dpg_enc_submission_cnt);
 			new_state.fw_based = VCN_DPG_STATE__PAUSE;
 		} else {
 			unsigned int fences = 0;
 			unsigned int i;
 
-			for (i = 0; i < adev->vcn.num_enc_rings; ++i)
-				fences += amdgpu_fence_count_emitted(&adev->vcn.inst[ring->me].ring_enc[i]);
+			for (i = 0; i < vcn_inst->num_enc_rings; ++i)
+				fences += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[i]);
 
-			if (fences || atomic_read(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt))
+			if (fences || atomic_read(&vcn_inst->dpg_enc_submission_cnt))
 				new_state.fw_based = VCN_DPG_STATE__PAUSE;
 			else
 				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 		}
 
-		adev->vcn.pause_dpg_mode(adev, ring->me, &new_state);
+		vcn_inst->pause_dpg_mode(vcn_inst, &new_state);
 	}
-	mutex_unlock(&adev->vcn.vcn_pg_lock);
+	mutex_unlock(&vcn_inst->vcn_pg_lock);
 }
 
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
@@ -482,12 +516,13 @@ void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
 	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
 	if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
 	    ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
-	    !adev->vcn.using_unified_queue)
+	    !adev->vcn.inst[ring->me].using_unified_queue)
 		atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
-	atomic_dec(&ring->adev->vcn.total_submission_cnt);
+	atomic_dec(&ring->adev->vcn.inst[ring->me].total_submission_cnt);
 
-	schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+	schedule_delayed_work(&ring->adev->vcn.inst[ring->me].idle_work,
+			      VCN_IDLE_TIMEOUT);
 }
 
 int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
@@ -505,7 +540,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 3);
 	if (r)
 		return r;
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0));
 	amdgpu_ring_write(ring, 0xDEADBEEF);
 	amdgpu_ring_commit(ring);
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -570,14 +605,14 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 		goto err;
 
 	ib = &job->ibs[0];
-	ib->ptr[0] = PACKET0(adev->vcn.internal.data0, 0);
+	ib->ptr[0] = PACKET0(adev->vcn.inst[ring->me].internal.data0, 0);
 	ib->ptr[1] = addr;
-	ib->ptr[2] = PACKET0(adev->vcn.internal.data1, 0);
+	ib->ptr[2] = PACKET0(adev->vcn.inst[ring->me].internal.data1, 0);
 	ib->ptr[3] = addr >> 32;
-	ib->ptr[4] = PACKET0(adev->vcn.internal.cmd, 0);
+	ib->ptr[4] = PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0);
 	ib->ptr[5] = 0;
 	for (i = 6; i < 16; i += 2) {
-		ib->ptr[i] = PACKET0(adev->vcn.internal.nop, 0);
+		ib->ptr[i] = PACKET0(adev->vcn.inst[ring->me].internal.nop, 0);
 		ib->ptr[i+1] = 0;
 	}
 	ib->length_dw = 16;
@@ -740,7 +775,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	uint32_t ib_pack_in_dw;
 	int i, r;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -753,7 +788,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	ib->length_dw = 0;
 
 	/* single queue headers */
-	if (adev->vcn.using_unified_queue) {
+	if (adev->vcn.inst[ring->me].using_unified_queue) {
 		ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
 						+ 4 + 2; /* engine info + decoding ib in dw */
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
@@ -772,7 +807,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -870,7 +905,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	uint64_t addr;
 	int i, r;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -884,7 +919,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 
 	ib->length_dw = 0;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -906,7 +941,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -937,7 +972,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	uint64_t addr;
 	int i, r;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -951,7 +986,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
 	ib->length_dw = 0;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -973,7 +1008,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (adev->vcn.using_unified_queue)
+	if (adev->vcn.inst[ring->me].using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -1058,36 +1093,32 @@ enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring)
 	}
 }
 
-void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev)
+void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i)
 {
-	int i;
 	unsigned int idx;
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		const struct common_firmware_header *hdr;
 
-		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			if (adev->vcn.harvest_config & (1 << i))
-				continue;
-
-			hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data;
-			/* currently only support 2 FW instances */
-			if (i >= 2) {
-				dev_info(adev->dev, "More then 2 VCN FW instances!\n");
-				break;
-			}
-			idx = AMDGPU_UCODE_ID_VCN + i;
-			adev->firmware.ucode[idx].ucode_id = idx;
-			adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw;
-			adev->firmware.fw_size +=
-				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-
-			if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
-			    IP_VERSION(4, 0, 3) ||
-			    amdgpu_ip_version(adev, UVD_HWIP, 0) ==
-			    IP_VERSION(5, 0, 1))
-				break;
+		if (adev->vcn.harvest_config & (1 << i))
+			return;
+
+		if ((amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 3) ||
+		     amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(5, 0, 1))
+		    && (i > 0))
+			return;
+
+		hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data;
+		/* currently only support 2 FW instances */
+		if (i >= 2) {
+			dev_info(adev->dev, "More then 2 VCN FW instances!\n");
+			return;
 		}
+		idx = AMDGPU_UCODE_ID_VCN + i;
+		adev->firmware.ucode[idx].ucode_id = idx;
+		adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw;
+		adev->firmware.fw_size +=
+			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 	}
 }
 
@@ -1390,10 +1421,33 @@ void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev)
 	struct dentry *root = minor->debugfs_root;
 	char name[32];
 
-	if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.using_unified_queue)
+	if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.inst[0].using_unified_queue)
 		return;
 	sprintf(name, "amdgpu_vcn_sched_mask");
 	debugfs_create_file(name, 0600, root, adev,
 			    &amdgpu_debugfs_vcn_sched_mask_fops);
 #endif
 }
+
+/**
+ * vcn_set_powergating_state - set VCN block powergating state
+ *
+ * @ip_block: amdgpu_ip_block pointer
+ * @state: power gating state
+ *
+ * Set VCN block powergating state
+ */
+int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,
+			      enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int ret = 0, i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		ret |= vinst->set_pg_state(vinst, state);
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index adaf4388ad28..cdcdae7f71ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -238,6 +238,12 @@
 
 #define AMDGPU_DRM_KEY_INJECT_WORKAROUND_VCNFW_ASD_HANDSHAKING 2
 
+enum amdgpu_vcn_caps {
+	AMDGPU_VCN_RRMT_ENABLED,
+};
+
+#define AMDGPU_VCN_CAPS(caps) BIT(AMDGPU_VCN_##caps)
+
 enum fw_queue_mode {
 	FW_QUEUE_RING_RESET = 1,
 	FW_QUEUE_DPG_HOLD_OFF = 2,
@@ -289,6 +295,8 @@ struct amdgpu_vcn_fw_shared {
 };
 
 struct amdgpu_vcn_inst {
+	struct amdgpu_device	*adev;
+	int			inst;
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
@@ -310,6 +318,20 @@ struct amdgpu_vcn_inst {
 	const struct firmware	*fw; /* VCN firmware */
 	uint8_t			vcn_config;
 	uint32_t		vcn_codec_disable_mask;
+	atomic_t		total_submission_cnt;
+	struct mutex		vcn_pg_lock;
+	enum amd_powergating_state cur_state;
+	struct delayed_work	idle_work;
+	unsigned		fw_version;
+	unsigned		num_enc_rings;
+	bool			indirect_sram;
+	struct amdgpu_vcn_reg	 internal;
+	struct mutex		vcn1_jpeg1_workaround;
+	int (*pause_dpg_mode)(struct amdgpu_vcn_inst *vinst,
+			      struct dpg_pause_state *new_state);
+	int (*set_pg_state)(struct amdgpu_vcn_inst *vinst,
+			    enum amd_powergating_state state);
+	bool using_unified_queue;
 };
 
 struct amdgpu_vcn_ras {
@@ -317,34 +339,28 @@ struct amdgpu_vcn_ras {
 };
 
 struct amdgpu_vcn {
-	unsigned		fw_version;
-	struct delayed_work	idle_work;
-	unsigned		num_enc_rings;
-	enum amd_powergating_state cur_state;
-	bool			indirect_sram;
-
 	uint8_t	num_vcn_inst;
 	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
-	struct amdgpu_vcn_reg	 internal;
-	struct mutex		 vcn_pg_lock;
-	struct mutex		vcn1_jpeg1_workaround;
-	atomic_t		 total_submission_cnt;
 
 	unsigned	harvest_config;
-	int (*pause_dpg_mode)(struct amdgpu_device *adev,
-		int inst_idx, struct dpg_pause_state *new_state);
 
 	struct ras_common_if    *ras_if;
 	struct amdgpu_vcn_ras   *ras;
 
 	uint16_t inst_mask;
 	uint8_t	num_inst_per_aid;
-	bool using_unified_queue;
 
 	/* IP reg dump */
 	uint32_t		*ip_dump;
 
 	uint32_t		supported_reset;
+	uint32_t		caps;
+
+	bool			per_inst_fw;
+	unsigned		fw_version;
+
+	bool			workload_profile_active;
+	struct mutex            workload_profile_mutex;
 };
 
 struct amdgpu_fw_shared_rb_ptrs_struct {
@@ -493,11 +509,11 @@ enum vcn_ring_type {
 	VCN_UNIFIED_RING,
 };
 
-int amdgpu_vcn_early_init(struct amdgpu_device *adev);
-int amdgpu_vcn_sw_init(struct amdgpu_device *adev);
-int amdgpu_vcn_sw_fini(struct amdgpu_device *adev);
-int amdgpu_vcn_suspend(struct amdgpu_device *adev);
-int amdgpu_vcn_resume(struct amdgpu_device *adev);
+int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i);
+int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i);
+int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i);
+int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i);
+int amdgpu_vcn_resume(struct amdgpu_device *adev, int i);
 void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring);
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring);
 
@@ -515,7 +531,7 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
 enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring);
 
-void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev);
+void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i);
 
 void amdgpu_vcn_fwlog_init(struct amdgpu_vcn_inst *vcn);
 void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev,
@@ -535,4 +551,7 @@ int amdgpu_vcn_sysfs_reset_mask_init(struct amdgpu_device *adev);
 void amdgpu_vcn_sysfs_reset_mask_fini(struct amdgpu_device *adev);
 void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev);
 
+int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,
+			      enum amd_powergating_state state);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 0af469ec6fcc..0bb8cbe0dcc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -614,10 +614,11 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev)
 	vf2pf_info->decode_usage = 0;
 
 	vf2pf_info->dummy_page_addr = (uint64_t)adev->dummy_page_addr;
-	vf2pf_info->mes_info_addr = (uint64_t)adev->mes.resource_1_gpu_addr;
-
-	if (adev->mes.resource_1) {
-		vf2pf_info->mes_info_size = adev->mes.resource_1->tbo.base.size;
+	if (amdgpu_sriov_is_mes_info_enable(adev)) {
+		vf2pf_info->mes_info_addr =
+			(uint64_t)(adev->mes.resource_1_gpu_addr[0] + AMDGPU_GPU_PAGE_SIZE);
+		vf2pf_info->mes_info_size =
+			adev->mes.resource_1[0]->tbo.base.size - AMDGPU_GPU_PAGE_SIZE;
 	}
 	vf2pf_info->checksum =
 		amd_sriov_msg_checksum(
@@ -739,7 +740,7 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 	}
 }
 
-void amdgpu_detect_virtualization(struct amdgpu_device *adev)
+static u32 amdgpu_virt_init_detect_asic(struct amdgpu_device *adev)
 {
 	uint32_t reg;
 
@@ -775,8 +776,17 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev)
 			adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE;
 	}
 
+	return reg;
+}
+
+static bool amdgpu_virt_init_req_data(struct amdgpu_device *adev, u32 reg)
+{
+	bool is_sriov = false;
+
 	/* we have the ability to check now */
 	if (amdgpu_sriov_vf(adev)) {
+		is_sriov = true;
+
 		switch (adev->asic_type) {
 		case CHIP_TONGA:
 		case CHIP_FIJI:
@@ -805,10 +815,39 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev)
 			amdgpu_virt_request_init_data(adev);
 			break;
 		default: /* other chip doesn't support SRIOV */
+			is_sriov = false;
 			DRM_ERROR("Unknown asic type: %d!\n", adev->asic_type);
 			break;
 		}
 	}
+
+	return is_sriov;
+}
+
+static void amdgpu_virt_init_ras(struct amdgpu_device *adev)
+{
+	ratelimit_state_init(&adev->virt.ras.ras_error_cnt_rs, 5 * HZ, 1);
+	ratelimit_state_init(&adev->virt.ras.ras_cper_dump_rs, 5 * HZ, 1);
+
+	ratelimit_set_flags(&adev->virt.ras.ras_error_cnt_rs,
+			    RATELIMIT_MSG_ON_RELEASE);
+	ratelimit_set_flags(&adev->virt.ras.ras_cper_dump_rs,
+			    RATELIMIT_MSG_ON_RELEASE);
+
+	mutex_init(&adev->virt.ras.ras_telemetry_mutex);
+
+	adev->virt.ras.cper_rptr = 0;
+}
+
+void amdgpu_virt_init(struct amdgpu_device *adev)
+{
+	bool is_sriov = false;
+	uint32_t reg = amdgpu_virt_init_detect_asic(adev);
+
+	is_sriov = amdgpu_virt_init_req_data(adev, reg);
+
+	if (is_sriov)
+		amdgpu_virt_init_ras(adev);
 }
 
 static bool amdgpu_virt_access_debugfs_is_mmio(struct amdgpu_device *adev)
@@ -1017,6 +1056,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	void *scratch_reg2;
 	void *scratch_reg3;
 	void *spare_int;
+	unsigned long flags;
 
 	if (!adev->gfx.rlc.rlcg_reg_access_supported) {
 		dev_err(adev->dev,
@@ -1038,7 +1078,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2;
 	scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3;
 
-	mutex_lock(&adev->virt.rlcg_reg_lock);
+	spin_lock_irqsave(&adev->virt.rlcg_reg_lock, flags);
 
 	if (reg_access_ctrl->spare_int)
 		spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int;
@@ -1097,7 +1137,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 
 	ret = readl(scratch_reg0);
 
-	mutex_unlock(&adev->virt.rlcg_reg_lock);
+	spin_unlock_irqrestore(&adev->virt.rlcg_reg_lock, flags);
 
 	return ret;
 }
@@ -1246,7 +1286,8 @@ amdgpu_ras_block_to_sriov(struct amdgpu_device *adev, enum amdgpu_ras_block bloc
 	case AMDGPU_RAS_BLOCK__MPIO:
 		return RAS_TELEMETRY_GPU_BLOCK_MPIO;
 	default:
-		dev_err(adev->dev, "Unsupported SRIOV RAS telemetry block 0x%x\n", block);
+		DRM_WARN_ONCE("Unsupported SRIOV RAS telemetry block 0x%x\n",
+			      block);
 		return RAS_TELEMETRY_GPU_BLOCK_COUNT;
 	}
 }
@@ -1286,10 +1327,12 @@ static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bo
 	 * will ignore incoming guest messages. Ratelimit the guest messages to
 	 * prevent guest self DOS.
 	 */
-	if (__ratelimit(&adev->virt.ras_telemetry_rs) || force_update) {
+	if (__ratelimit(&virt->ras.ras_error_cnt_rs) || force_update) {
+		mutex_lock(&virt->ras.ras_telemetry_mutex);
 		if (!virt->ops->req_ras_err_count(adev))
 			amdgpu_virt_cache_host_error_counts(adev,
-				adev->virt.fw_reserve.ras_telemetry);
+				virt->fw_reserve.ras_telemetry);
+		mutex_unlock(&virt->ras.ras_telemetry_mutex);
 	}
 
 	return 0;
@@ -1320,6 +1363,98 @@ int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_bl
 	return 0;
 }
 
+static int
+amdgpu_virt_write_cpers_to_ring(struct amdgpu_device *adev,
+				struct amdsriov_ras_telemetry *host_telemetry,
+				u32 *more)
+{
+	struct amd_sriov_ras_cper_dump *cper_dump = NULL;
+	struct cper_hdr *entry = NULL;
+	struct amdgpu_ring *ring = &adev->cper.ring_buf;
+	uint32_t checksum, used_size, i;
+	int ret = 0;
+
+	checksum = host_telemetry->header.checksum;
+	used_size = host_telemetry->header.used_size;
+
+	if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10))
+		return 0;
+
+	cper_dump = kmemdup(&host_telemetry->body.cper_dump, used_size, GFP_KERNEL);
+	if (!cper_dump)
+		return -ENOMEM;
+
+	if (checksum != amd_sriov_msg_checksum(cper_dump, used_size, 0, 0))
+		goto out;
+
+	*more = cper_dump->more;
+
+	if (cper_dump->wptr < adev->virt.ras.cper_rptr) {
+		dev_warn(
+			adev->dev,
+			"guest specified rptr that was too high! guest rptr: 0x%llx, host rptr: 0x%llx\n",
+			adev->virt.ras.cper_rptr, cper_dump->wptr);
+
+		adev->virt.ras.cper_rptr = cper_dump->wptr;
+		goto out;
+	}
+
+	entry = (struct cper_hdr *)&cper_dump->buf[0];
+
+	for (i = 0; i < cper_dump->count; i++) {
+		amdgpu_cper_ring_write(ring, entry, entry->record_length);
+		entry = (struct cper_hdr *)((char *)entry +
+					    entry->record_length);
+	}
+
+	if (cper_dump->overflow_count)
+		dev_warn(adev->dev,
+			 "host reported CPER overflow of 0x%llx entries!\n",
+			 cper_dump->overflow_count);
+
+	adev->virt.ras.cper_rptr = cper_dump->wptr;
+out:
+	kfree(cper_dump);
+
+	return ret;
+}
+
+static int amdgpu_virt_req_ras_cper_dump_internal(struct amdgpu_device *adev)
+{
+	struct amdgpu_virt *virt = &adev->virt;
+	int ret = 0;
+	uint32_t more = 0;
+
+	if (!amdgpu_sriov_ras_cper_en(adev))
+		return -EOPNOTSUPP;
+
+	do {
+		if (!virt->ops->req_ras_cper_dump(adev, virt->ras.cper_rptr))
+			ret = amdgpu_virt_write_cpers_to_ring(
+				adev, virt->fw_reserve.ras_telemetry, &more);
+		else
+			ret = 0;
+	} while (more);
+
+	return ret;
+}
+
+int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update)
+{
+	struct amdgpu_virt *virt = &adev->virt;
+	int ret = 0;
+
+	if ((__ratelimit(&virt->ras.ras_cper_dump_rs) || force_update) &&
+	    down_read_trylock(&adev->reset_domain->sem)) {
+		mutex_lock(&virt->ras.ras_telemetry_mutex);
+		ret = amdgpu_virt_req_ras_cper_dump_internal(adev);
+		mutex_unlock(&virt->ras.ras_telemetry_mutex);
+		up_read(&adev->reset_domain->sem);
+	}
+
+	return ret;
+}
+
 int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev)
 {
 	unsigned long ue_count, ce_count;
@@ -1331,3 +1466,17 @@ int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev,
+					enum amdgpu_ras_block block)
+{
+	enum amd_sriov_ras_telemetry_gpu_block sriov_block;
+
+	sriov_block = amdgpu_ras_block_to_sriov(adev, block);
+
+	if (sriov_block >= RAS_TELEMETRY_GPU_BLOCK_COUNT ||
+	    !amdgpu_sriov_ras_telemetry_block_en(adev, sriov_block))
+		return false;
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 5381b8d596e6..df03dba67ab8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -96,6 +96,7 @@ struct amdgpu_virt_ops {
 					enum amdgpu_ras_block block);
 	bool (*rcvd_ras_intr)(struct amdgpu_device *adev);
 	int (*req_ras_err_count)(struct amdgpu_device *adev);
+	int (*req_ras_cper_dump)(struct amdgpu_device *adev, u64 vf_rptr);
 };
 
 /*
@@ -140,6 +141,7 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8),
 	AMDGIM_FEATURE_RAS_CAPS = (1 << 9),
 	AMDGIM_FEATURE_RAS_TELEMETRY = (1 << 10),
+	AMDGIM_FEATURE_RAS_CPER = (1 << 11),
 };
 
 enum AMDGIM_REG_ACCESS_FLAG {
@@ -242,6 +244,13 @@ struct amdgpu_virt_ras_err_handler_data {
 	int last_reserved;
 };
 
+struct amdgpu_virt_ras {
+	struct ratelimit_state ras_error_cnt_rs;
+	struct ratelimit_state ras_cper_dump_rs;
+	struct mutex ras_telemetry_mutex;
+	uint64_t cper_rptr;
+};
+
 /* GPU virtualization */
 struct amdgpu_virt {
 	uint32_t			caps;
@@ -279,12 +288,12 @@ struct amdgpu_virt {
 	/* the ucode id to signal the autoload */
 	uint32_t autoload_ucode_id;
 
-	struct mutex rlcg_reg_lock;
+	/* Spinlock to protect access to the RLCG register interface */
+	spinlock_t rlcg_reg_lock;
 
 	union amd_sriov_ras_caps ras_en_caps;
 	union amd_sriov_ras_caps ras_telemetry_en_caps;
-
-	struct ratelimit_state ras_telemetry_rs;
+	struct amdgpu_virt_ras ras;
 	struct amd_sriov_ras_telemetry_error_count count_cache;
 };
 
@@ -339,6 +348,9 @@ struct amdgpu_video_codec_info;
 #define amdgpu_sriov_ras_telemetry_block_en(adev, sriov_blk) \
 (amdgpu_sriov_ras_telemetry_en((adev)) && (adev)->virt.ras_telemetry_en_caps.all & BIT(sriov_blk))
 
+#define amdgpu_sriov_ras_cper_en(adev) \
+((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CPER)
+
 static inline bool is_virtual_machine(void)
 {
 #if defined(CONFIG_X86)
@@ -352,6 +364,8 @@ static inline bool is_virtual_machine(void)
 
 #define amdgpu_sriov_is_pp_one_vf(adev) \
 	((adev)->virt.gim_feature & AMDGIM_FEATURE_PP_ONE_VF)
+#define amdgpu_sriov_multi_vf_mode(adev) \
+	(amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 #define amdgpu_sriov_is_debug(adev) \
 	((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug)
 #define amdgpu_sriov_is_normal(adev) \
@@ -377,7 +391,7 @@ void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
 void amdgpu_virt_exchange_data(struct amdgpu_device *adev);
 void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev);
-void amdgpu_detect_virtualization(struct amdgpu_device *adev);
+void amdgpu_virt_init(struct amdgpu_device *adev);
 
 bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev);
 int amdgpu_virt_enable_access_debugfs(struct amdgpu_device *adev);
@@ -405,5 +419,8 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev);
 int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block,
 				  struct ras_err_data *err_data);
+int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update);
 int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev);
+bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev,
+					enum amdgpu_ras_block block);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index 7507d9443028..155bb9891a17 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -627,7 +627,7 @@ static int amdgpu_vkms_resume(struct amdgpu_ip_block *ip_block)
 	return drm_mode_config_helper_resume(adev_to_drm(ip_block->adev));
 }
 
-static bool amdgpu_vkms_is_idle(void *handle)
+static bool amdgpu_vkms_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5c07777d3239..ce52b4d75e94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -754,6 +754,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 		    bool need_pipe_sync)
 {
 	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_isolation *isolation = &adev->isolation[ring->xcp_id];
 	unsigned vmhub = ring->vm_hub;
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 	struct amdgpu_vmid *id = &id_mgr->ids[job->vmid];
@@ -761,8 +762,9 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	bool gds_switch_needed = ring->funcs->emit_gds_switch &&
 		job->gds_switch_needed;
 	bool vm_flush_needed = job->vm_needs_flush;
-	struct dma_fence *fence = NULL;
+	bool cleaner_shader_needed = false;
 	bool pasid_mapping_needed = false;
+	struct dma_fence *fence = NULL;
 	unsigned int patch;
 	int r;
 
@@ -785,8 +787,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping &&
 		ring->funcs->emit_wreg;
 
+	cleaner_shader_needed = adev->gfx.enable_cleaner_shader &&
+		ring->funcs->emit_cleaner_shader && job->base.s_fence &&
+		&job->base.s_fence->scheduled == isolation->spearhead;
+
 	if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync &&
-	    !(job->enforce_isolation && !job->vmid))
+	    !cleaner_shader_needed)
 		return 0;
 
 	amdgpu_ring_ib_begin(ring);
@@ -797,9 +803,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	if (need_pipe_sync)
 		amdgpu_ring_emit_pipeline_sync(ring);
 
-	if (adev->gfx.enable_cleaner_shader &&
-	    ring->funcs->emit_cleaner_shader &&
-	    job->enforce_isolation)
+	if (cleaner_shader_needed)
 		ring->funcs->emit_cleaner_shader(ring);
 
 	if (vm_flush_needed) {
@@ -821,7 +825,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 					    job->oa_size);
 	}
 
-	if (vm_flush_needed || pasid_mapping_needed) {
+	if (vm_flush_needed || pasid_mapping_needed || cleaner_shader_needed) {
 		r = amdgpu_fence_emit(ring, &fence, NULL, 0);
 		if (r)
 			return r;
@@ -843,6 +847,18 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 		id->pasid_mapping = dma_fence_get(fence);
 		mutex_unlock(&id_mgr->lock);
 	}
+
+	/*
+	 * Make sure that all other submissions wait for the cleaner shader to
+	 * finish before we push them to the HW.
+	 */
+	if (cleaner_shader_needed) {
+		trace_amdgpu_cleaner_shader(ring, fence);
+		mutex_lock(&adev->enforce_isolation_mutex);
+		dma_fence_put(isolation->spearhead);
+		isolation->spearhead = dma_fence_get(fence);
+		mutex_unlock(&adev->enforce_isolation_mutex);
+	}
 	dma_fence_put(fence);
 
 	amdgpu_ring_patch_cond_exec(ring, patch);
@@ -2534,8 +2550,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->done);
-	INIT_LIST_HEAD(&vm->pt_freed);
-	INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work);
 	INIT_KFIFO(vm->faults);
 
 	r = amdgpu_vm_init_entities(adev, vm);
@@ -2674,20 +2688,6 @@ unreserve_bo:
 	return r;
 }
 
-/**
- * amdgpu_vm_release_compute - release a compute vm
- * @adev: amdgpu_device pointer
- * @vm: a vm turned into compute vm by calling amdgpu_vm_make_compute
- *
- * This is a correspondant of amdgpu_vm_make_compute. It decouples compute
- * pasid from vm. Compute should stop use of vm after this call.
- */
-void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
-{
-	amdgpu_vm_set_pasid(adev, vm, 0);
-	vm->is_compute_context = false;
-}
-
 static int amdgpu_vm_stats_is_zero(struct amdgpu_vm *vm)
 {
 	for (int i = 0; i < __AMDGPU_PL_NUM; ++i) {
@@ -2717,8 +2717,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
 
-	flush_work(&vm->pt_free_work);
-
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
 	amdgpu_vm_set_pasid(adev, vm, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index a3e128e373bc..f3ad687125ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -374,10 +374,6 @@ struct amdgpu_vm {
 	/* BOs which are invalidated, has been updated in the PTs */
 	struct list_head        done;
 
-	/* PT BOs scheduled to free and fill with zero if vm_resv is not hold */
-	struct list_head	pt_freed;
-	struct work_struct	pt_free_work;
-
 	/* contains the page directory */
 	struct amdgpu_vm_bo_base     root;
 	struct dma_fence	*last_update;
@@ -493,7 +489,6 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,
 		      unsigned int num_fences);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index b0bf21682115..30022123b0bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -547,27 +547,6 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 	amdgpu_bo_unref(&entry->bo);
 }
 
-void amdgpu_vm_pt_free_work(struct work_struct *work)
-{
-	struct amdgpu_vm_bo_base *entry, *next;
-	struct amdgpu_vm *vm;
-	LIST_HEAD(pt_freed);
-
-	vm = container_of(work, struct amdgpu_vm, pt_free_work);
-
-	spin_lock(&vm->status_lock);
-	list_splice_init(&vm->pt_freed, &pt_freed);
-	spin_unlock(&vm->status_lock);
-
-	/* flush_work in amdgpu_vm_fini ensure vm->root.bo is valid. */
-	amdgpu_bo_reserve(vm->root.bo, true);
-
-	list_for_each_entry_safe(entry, next, &pt_freed, vm_status)
-		amdgpu_vm_pt_free(entry);
-
-	amdgpu_bo_unreserve(vm->root.bo);
-}
-
 /**
  * amdgpu_vm_pt_free_list - free PD/PT levels
  *
@@ -580,19 +559,15 @@ void amdgpu_vm_pt_free_list(struct amdgpu_device *adev,
 			    struct amdgpu_vm_update_params *params)
 {
 	struct amdgpu_vm_bo_base *entry, *next;
-	struct amdgpu_vm *vm = params->vm;
 	bool unlocked = params->unlocked;
 
 	if (list_empty(&params->tlb_flush_waitlist))
 		return;
 
-	if (unlocked) {
-		spin_lock(&vm->status_lock);
-		list_splice_init(&params->tlb_flush_waitlist, &vm->pt_freed);
-		spin_unlock(&vm->status_lock);
-		schedule_work(&vm->pt_free_work);
-		return;
-	}
+	/*
+	 * unlocked unmap clear page table leaves, warning to free the page entry.
+	 */
+	WARN_ON(unlocked);
 
 	list_for_each_entry_safe(entry, next, &params->tlb_flush_waitlist, vm_status)
 		amdgpu_vm_pt_free(entry);
@@ -900,7 +875,15 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params,
 		incr = (uint64_t)AMDGPU_GPU_PAGE_SIZE << shift;
 		mask = amdgpu_vm_pt_entries_mask(adev, cursor.level);
 		pe_start = ((cursor.pfn >> shift) & mask) * 8;
-		entry_end = ((uint64_t)mask + 1) << shift;
+
+		if (cursor.level < AMDGPU_VM_PTB && params->unlocked)
+			/*
+			 * MMU notifier callback unlocked unmap huge page, leave is PDE entry,
+			 * only clear one entry. Next entry search again for PDE or PTE leave.
+			 */
+			entry_end = 1ULL << shift;
+		else
+			entry_end = ((uint64_t)mask + 1) << shift;
 		entry_end += cursor.pfn & ~(entry_end - 1);
 		entry_end = min(entry_end, end);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index ff5e52025266..6da8994e0469 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -28,7 +28,6 @@
 #include "amdgpu.h"
 #include "amdgpu_vm.h"
 #include "amdgpu_res_cursor.h"
-#include "amdgpu_atomfirmware.h"
 #include "atom.h"
 
 #define AMDGPU_MAX_SG_SEGMENT_SIZE	(2UL << 30)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 74b4349e345a..6029a799074d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -315,6 +315,7 @@ int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num)
 
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		xgmi_state_reg_val = xgmi_v6_4_get_link_status(adev, global_link_num);
 		break;
 	default:
@@ -818,28 +819,71 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
  * num_hops[2:0] = number of hops
  */
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
-		struct amdgpu_device *peer_adev)
+			       struct amdgpu_device *peer_adev)
 {
 	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
 	uint8_t num_hops_mask = 0x7;
 	int i;
 
+	if (!adev->gmc.xgmi.supported)
+		return 0;
+
 	for (i = 0 ; i < top->num_nodes; ++i)
 		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
 			return top->nodes[i].num_hops & num_hops_mask;
-	return	-EINVAL;
+
+	dev_err(adev->dev, "Failed to get xgmi hops count for peer %d.\n",
+		peer_adev->gmc.xgmi.physical_node_id);
+
+	return 0;
 }
 
-int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,
-		struct amdgpu_device *peer_adev)
+int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev,
+			      enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit,
+			      uint32_t *min_bw, uint32_t *max_bw)
 {
-	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
-	int i;
+	bool peer_mode = bw_mode == AMDGPU_XGMI_BW_MODE_PER_PEER;
+	int unit_scale = bw_unit == AMDGPU_XGMI_BW_UNIT_MBYTES ? 1000 : 1;
+	int num_lanes = adev->gmc.xgmi.max_width;
+	int speed = adev->gmc.xgmi.max_speed;
+	int num_links = !peer_mode ? 1 : -1;
 
-	for (i = 0 ; i < top->num_nodes; ++i)
-		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
-			return top->nodes[i].num_links;
-	return	-EINVAL;
+	if (!(min_bw && max_bw))
+		return -EINVAL;
+
+	*min_bw = 0;
+	*max_bw = 0;
+
+	if (!adev->gmc.xgmi.supported)
+		return -ENODATA;
+
+	if (peer_mode && !peer_adev)
+		return -EINVAL;
+
+	if (peer_mode) {
+		struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+		int i;
+
+		for (i = 0 ; i < top->num_nodes; ++i) {
+			if (top->nodes[i].node_id != peer_adev->gmc.xgmi.node_id)
+				continue;
+
+			num_links =  top->nodes[i].num_links;
+			break;
+		}
+	}
+
+	if (num_links == -1) {
+		dev_err(adev->dev, "Failed to get number of xgmi links for peer %d.\n",
+			peer_adev->gmc.xgmi.physical_node_id);
+	} else if (num_links) {
+		int per_link_bw = (speed * num_lanes * unit_scale)/BITS_PER_BYTE;
+
+		*min_bw = per_link_bw;
+		*max_bw = num_links * per_link_bw;
+	}
+
+	return 0;
 }
 
 bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev,
@@ -1123,11 +1167,13 @@ static int xgmi_v6_4_0_aca_bank_parser(struct aca_handle *handle, struct aca_ban
 		if (ext_error_code != 0 && ext_error_code != 9)
 			count = 0ULL;
 
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
 		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE, count);
 		break;
 	case ACA_SMU_TYPE_CE:
 		count = ext_error_code == 6 ? count : 0ULL;
-		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, count);
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, count);
 		break;
 	default:
 		return -EINVAL;
@@ -1162,6 +1208,7 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_comm
 
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL,
 					&xgmi_v6_4_0_aca_info, NULL);
 		if (r)
@@ -1221,6 +1268,7 @@ static void amdgpu_xgmi_legacy_reset_ras_error_count(struct amdgpu_device *adev)
 
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++)
 			pcs_clear_status(adev,
 					xgmi3x16_pcs_err_status_reg_v6_4[i]);
@@ -1255,6 +1303,7 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 {
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		xgmi_v6_4_0_reset_ras_error_count(adev);
 		break;
 	default:
@@ -1280,7 +1329,9 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
 		if (amdgpu_ip_version(adev, XGMI_HWIP, 0) ==
 		    IP_VERSION(6, 1, 0) ||
 		    amdgpu_ip_version(adev, XGMI_HWIP, 0) ==
-		    IP_VERSION(6, 4, 0)) {
+		    IP_VERSION(6, 4, 0) ||
+		    amdgpu_ip_version(adev, XGMI_HWIP, 0) ==
+		    IP_VERSION(6, 4, 1)) {
 			pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0];
 			field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields);
 		} else {
@@ -1388,6 +1439,7 @@ static void amdgpu_xgmi_legacy_query_ras_error_count(struct amdgpu_device *adev,
 
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		/* check xgmi3x16 pcs error */
 		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) {
 			data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_v6_4[i]);
@@ -1484,6 +1536,7 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 {
 	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
 	case IP_VERSION(6, 4, 0):
+	case IP_VERSION(6, 4, 1):
 		xgmi_v6_4_0_query_ras_error_count(adev, ras_error_status);
 		break;
 	default:
@@ -1671,3 +1724,34 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev,
 
 	return r;
 }
+
+bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
+			   struct amdgpu_device *bo_adev)
+{
+	return (amdgpu_use_xgmi_p2p && adev != bo_adev &&
+		adev->gmc.xgmi.hive_id &&
+		adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id);
+}
+
+void amdgpu_xgmi_early_init(struct amdgpu_device *adev)
+{
+	if (!adev->gmc.xgmi.supported)
+		return;
+
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 4, 1):
+	case IP_VERSION(9, 4, 2):
+		adev->gmc.xgmi.max_speed = XGMI_SPEED_25GT;
+		adev->gmc.xgmi.max_width = 16;
+		break;
+	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
+	case IP_VERSION(9, 5, 0):
+		adev->gmc.xgmi.max_speed = XGMI_SPEED_32GT;
+		adev->gmc.xgmi.max_width = 16;
+		break;
+	default:
+		break;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index d1282b4c6348..32dabba4062f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -23,9 +23,14 @@
 #define __AMDGPU_XGMI_H__
 
 #include <drm/task_barrier.h>
-#include "amdgpu_psp.h"
 #include "amdgpu_ras.h"
 
+enum amdgpu_xgmi_link_speed {
+	XGMI_SPEED_16GT = 16,
+	XGMI_SPEED_25GT = 25,
+	XGMI_SPEED_32GT = 32
+};
+
 struct amdgpu_hive_info {
 	struct kobject kobj;
 	uint64_t hive_id;
@@ -55,29 +60,63 @@ struct amdgpu_pcs_ras_field {
 	uint32_t pcs_err_shift;
 };
 
-extern struct amdgpu_xgmi_ras  xgmi_ras;
+/**
+ * Bandwidth range reporting comes in two modes.
+ *
+ * PER_LINK - range for any xgmi link
+ * PER_PEER - range of max of single xgmi link to max of multiple links based on source peer
+ */
+enum amdgpu_xgmi_bw_mode {
+	AMDGPU_XGMI_BW_MODE_PER_LINK = 0,
+	AMDGPU_XGMI_BW_MODE_PER_PEER
+};
+
+enum amdgpu_xgmi_bw_unit {
+	AMDGPU_XGMI_BW_UNIT_GBYTES = 0,
+	AMDGPU_XGMI_BW_UNIT_MBYTES
+};
+
+struct amdgpu_xgmi_ras {
+	struct amdgpu_ras_block_object ras_block;
+};
+extern struct amdgpu_xgmi_ras xgmi_ras;
+
+struct amdgpu_xgmi {
+	/* from psp */
+	u64 node_id;
+	u64 hive_id;
+	/* fixed per family */
+	u64 node_segment_size;
+	/* physical node (0-3) */
+	unsigned physical_node_id;
+	/* number of nodes (0-4) */
+	unsigned num_physical_nodes;
+	/* gpu list in the same hive */
+	struct list_head head;
+	bool supported;
+	struct ras_common_if *ras_if;
+	bool connected_to_cpu;
+	struct amdgpu_xgmi_ras *ras;
+	enum amdgpu_xgmi_link_speed max_speed;
+	uint8_t max_width;
+};
+
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev);
 void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive);
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
 int amdgpu_xgmi_add_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
-int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
-		struct amdgpu_device *peer_adev);
-int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,
-		struct amdgpu_device *peer_adev);
+int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, struct amdgpu_device *peer_adev);
+int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev,
+			      enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit,
+			      uint32_t *min_bw, uint32_t *max_bw);
 bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev,
 					struct amdgpu_device *peer_adev);
 uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev,
 					   uint64_t addr);
-static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
-		struct amdgpu_device *bo_adev)
-{
-	return (amdgpu_use_xgmi_p2p &&
-		adev != bo_adev &&
-		adev->gmc.xgmi.hive_id &&
-		adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id);
-}
+bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
+			   struct amdgpu_device *bo_adev);
 int amdgpu_xgmi_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_xgmi_reset_on_init(struct amdgpu_device *adev);
 
@@ -87,4 +126,7 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev,
 int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev,
 				int global_link_num);
 
+void amdgpu_xgmi_early_init(struct amdgpu_device *adev);
+uint32_t amdgpu_xgmi_get_max_bandwidth(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
index b4f9c2f4e92c..d6ac2652f0ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -97,11 +97,12 @@ union amd_sriov_msg_feature_flags {
 		uint32_t pp_one_vf_mode		: 1;
 		uint32_t reg_indirect_acc	: 1;
 		uint32_t av1_support		: 1;
-		uint32_t vcn_rb_decouple 	: 1;
+		uint32_t vcn_rb_decouple	: 1;
 		uint32_t mes_info_dump_enable	: 1;
 		uint32_t ras_caps		: 1;
 		uint32_t ras_telemetry		: 1;
-		uint32_t reserved		: 21;
+		uint32_t ras_cper		: 1;
+		uint32_t reserved		: 20;
 	} flags;
 	uint32_t all;
 };
@@ -328,21 +329,25 @@ enum amd_sriov_mailbox_request_message {
 	MB_REQ_MSG_READY_TO_RESET = 201,
 	MB_REQ_MSG_RAS_POISON = 202,
 	MB_REQ_RAS_ERROR_COUNT = 203,
+	MB_REQ_RAS_CPER_DUMP = 204,
 };
 
 /* mailbox message send from host to guest  */
 enum amd_sriov_mailbox_response_message {
-	MB_RES_MSG_CLR_MSG_BUF = 0,
-	MB_RES_MSG_READY_TO_ACCESS_GPU = 1,
-	MB_RES_MSG_FLR_NOTIFICATION,
-	MB_RES_MSG_FLR_NOTIFICATION_COMPLETION,
-	MB_RES_MSG_SUCCESS,
-	MB_RES_MSG_FAIL,
-	MB_RES_MSG_QUERY_ALIVE,
-	MB_RES_MSG_GPU_INIT_DATA_READY,
-	MB_RES_MSG_RAS_ERROR_COUNT_READY = 11,
-
-	MB_RES_MSG_TEXT_MESSAGE = 255
+	MB_RES_MSG_CLR_MSG_BUF			= 0,
+	MB_RES_MSG_READY_TO_ACCESS_GPU		= 1,
+	MB_RES_MSG_FLR_NOTIFICATION		= 2,
+	MB_RES_MSG_FLR_NOTIFICATION_COMPLETION  = 3,
+	MB_RES_MSG_SUCCESS			= 4,
+	MB_RES_MSG_FAIL				= 5,
+	MB_RES_MSG_QUERY_ALIVE			= 6,
+	MB_RES_MSG_GPU_INIT_DATA_READY		= 7,
+	MB_RES_MSG_RAS_POISON_READY		= 8,
+	MB_RES_MSG_PF_SOFT_FLR_NOTIFICATION	= 9,
+	MB_RES_MSG_GPU_RMA			= 10,
+	MB_RES_MSG_RAS_ERROR_COUNT_READY	= 11,
+	MB_REQ_RAS_CPER_DUMP_READY		= 14,
+	MB_RES_MSG_TEXT_MESSAGE			= 255
 };
 
 enum amd_sriov_ras_telemetry_gpu_block {
@@ -386,11 +391,20 @@ struct amd_sriov_ras_telemetry_error_count {
 	} block[RAS_TELEMETRY_GPU_BLOCK_COUNT];
 };
 
+struct amd_sriov_ras_cper_dump {
+	uint32_t more;
+	uint64_t overflow_count;
+	uint64_t count;
+	uint64_t wptr;
+	uint32_t buf[];
+};
+
 struct amdsriov_ras_telemetry {
 	struct amd_sriov_ras_telemetry_header header;
 
 	union {
 		struct amd_sriov_ras_telemetry_error_count error_count;
+		struct amd_sriov_ras_cper_dump cper_dump;
 	} body;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index e157d6d857b6..3c07517be09a 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -77,7 +77,8 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
 	ring->xcp_id = AMDGPU_XCP_NO_PARTITION;
 	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)
 		adev->gfx.enforce_isolation[0].xcp_id = ring->xcp_id;
-	if (adev->xcp_mgr->mode == AMDGPU_XCP_MODE_NONE)
+	if ((adev->xcp_mgr->mode == AMDGPU_XCP_MODE_NONE) ||
+	    (ring->funcs->type == AMDGPU_RING_TYPE_CPER))
 		return;
 
 	inst_mask = 1 << inst_idx;
@@ -559,8 +560,11 @@ static bool __aqua_vanjaram_is_valid_mode(struct amdgpu_xcp_mgr *xcp_mgr,
 			adev->gmc.num_mem_partitions == 4) &&
 		       (num_xccs_per_xcp >= 2);
 	case AMDGPU_CPX_PARTITION_MODE:
+		/* (num_xcc > 1) because 1 XCC is considered SPX, not CPX.
+		 * (num_xcc % adev->gmc.num_mem_partitions) == 0 because
+		 * num_compute_partitions can't be less than num_mem_partitions
+		 */
 		return ((num_xcc > 1) &&
-		       (adev->gmc.num_mem_partitions == 1 || adev->gmc.num_mem_partitions == 4) &&
 		       (num_xcc % adev->gmc.num_mem_partitions) == 0);
 	default:
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 622634c08c7b..521b9faab180 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -430,7 +430,7 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 }
 
 int amdgpu_atombios_dp_mode_valid_helper(struct drm_connector *connector,
-				  struct drm_display_mode *mode)
+				  const struct drm_display_mode *mode)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *dig_connector;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.h b/drivers/gpu/drm/amd/amdgpu/atombios_dp.h
index f59d85eaddf0..3e24acf8133f 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.h
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.h
@@ -32,7 +32,7 @@ int amdgpu_atombios_dp_get_panel_mode(struct drm_encoder *encoder,
 void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 				 const struct drm_display_mode *mode);
 int amdgpu_atombios_dp_mode_valid_helper(struct drm_connector *connector,
-				  struct drm_display_mode *mode);
+				  const struct drm_display_mode *mode);
 bool amdgpu_atombios_dp_needs_link_train(struct amdgpu_connector *amdgpu_connector);
 void amdgpu_atombios_dp_set_rx_power_state(struct drm_connector *connector,
 				    u8 power_state);
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 08d6787893b3..9cd63b4177bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -2148,7 +2148,7 @@ static int cik_common_resume(struct amdgpu_ip_block *ip_block)
 	return cik_common_hw_init(ip_block);
 }
 
-static bool cik_common_is_idle(void *handle)
+static bool cik_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 444563486769..41f4705bdbbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -345,9 +345,9 @@ static int cik_ih_resume(struct amdgpu_ip_block *ip_block)
 	return cik_ih_hw_init(ip_block);
 }
 
-static bool cik_ih_is_idle(void *handle)
+static bool cik_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (tmp & SRBM_STATUS__IH_BUSY_MASK)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index d9bd8f3f17e2..508cea965983 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1025,9 +1025,9 @@ static int cik_sdma_resume(struct amdgpu_ip_block *ip_block)
 	return cik_sdma_hw_init(ip_block);
 }
 
-static bool cik_sdma_is_idle(void *handle)
+static bool cik_sdma_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS2);
 
 	if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK |
diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h
index 06088d52d81c..279288365940 100644
--- a/drivers/gpu/drm/amd/amdgpu/cikd.h
+++ b/drivers/gpu/drm/amd/amdgpu/cikd.h
@@ -51,6 +51,15 @@
 #define HPD4_REGISTER_OFFSET                 (0x1813 - 0x1807)
 #define HPD5_REGISTER_OFFSET                 (0x1816 - 0x1807)
 
+/* audio endpt instance offsets */
+#define AUD0_REGISTER_OFFSET                 (0x1780 - 0x1780)
+#define AUD1_REGISTER_OFFSET                 (0x1786 - 0x1780)
+#define AUD2_REGISTER_OFFSET                 (0x178c - 0x1780)
+#define AUD3_REGISTER_OFFSET                 (0x1792 - 0x1780)
+#define AUD4_REGISTER_OFFSET                 (0x1798 - 0x1780)
+#define AUD5_REGISTER_OFFSET                 (0x179d - 0x1780)
+#define AUD6_REGISTER_OFFSET                 (0x17a4 - 0x1780)
+
 #define BONAIRE_GB_ADDR_CONFIG_GOLDEN        0x12010001
 #define HAWAII_GB_ADDR_CONFIG_GOLDEN         0x12011003
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 82586b76aeda..2f891fb846d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -341,9 +341,9 @@ static int cz_ih_resume(struct amdgpu_ip_block *ip_block)
 	return cz_ih_hw_init(ip_block);
 }
 
-static bool cz_ih_is_idle(void *handle)
+static bool cz_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY))
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index c5e3d2251b18..df401aded662 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2970,7 +2970,7 @@ static int dce_v10_0_resume(struct amdgpu_ip_block *ip_block)
 	return amdgpu_display_resume_helper(adev);
 }
 
-static bool dce_v10_0_is_idle(void *handle)
+static bool dce_v10_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index ea42a4472bf6..80f01c3989cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3108,7 +3108,7 @@ static int dce_v11_0_resume(struct amdgpu_ip_block *ip_block)
 	return amdgpu_display_resume_helper(adev);
 }
 
-static bool dce_v11_0_is_idle(void *handle)
+static bool dce_v11_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 915804a6a1d7..255c70959343 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -40,18 +40,25 @@
 #include "amdgpu_connectors.h"
 #include "amdgpu_display.h"
 
+#include "dce_v6_0.h"
+#include "sid.h"
+
 #include "bif/bif_3_0_d.h"
 #include "bif/bif_3_0_sh_mask.h"
+
 #include "oss/oss_1_0_d.h"
 #include "oss/oss_1_0_sh_mask.h"
+
 #include "gca/gfx_6_0_d.h"
 #include "gca/gfx_6_0_sh_mask.h"
+#include "gca/gfx_7_2_enum.h"
+
 #include "gmc/gmc_6_0_d.h"
 #include "gmc/gmc_6_0_sh_mask.h"
+
 #include "dce/dce_6_0_d.h"
 #include "dce/dce_6_0_sh_mask.h"
-#include "gca/gfx_7_2_enum.h"
-#include "dce_v6_0.h"
+
 #include "si_enums.h"
 
 static void dce_v6_0_set_display_funcs(struct amdgpu_device *adev);
@@ -59,31 +66,31 @@ static void dce_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 
 static const u32 crtc_offsets[6] =
 {
-	SI_CRTC0_REGISTER_OFFSET,
-	SI_CRTC1_REGISTER_OFFSET,
-	SI_CRTC2_REGISTER_OFFSET,
-	SI_CRTC3_REGISTER_OFFSET,
-	SI_CRTC4_REGISTER_OFFSET,
-	SI_CRTC5_REGISTER_OFFSET
+	CRTC0_REGISTER_OFFSET,
+	CRTC1_REGISTER_OFFSET,
+	CRTC2_REGISTER_OFFSET,
+	CRTC3_REGISTER_OFFSET,
+	CRTC4_REGISTER_OFFSET,
+	CRTC5_REGISTER_OFFSET
 };
 
 static const u32 hpd_offsets[] =
 {
-	mmDC_HPD1_INT_STATUS - mmDC_HPD1_INT_STATUS,
-	mmDC_HPD2_INT_STATUS - mmDC_HPD1_INT_STATUS,
-	mmDC_HPD3_INT_STATUS - mmDC_HPD1_INT_STATUS,
-	mmDC_HPD4_INT_STATUS - mmDC_HPD1_INT_STATUS,
-	mmDC_HPD5_INT_STATUS - mmDC_HPD1_INT_STATUS,
-	mmDC_HPD6_INT_STATUS - mmDC_HPD1_INT_STATUS,
+	HPD0_REGISTER_OFFSET,
+	HPD1_REGISTER_OFFSET,
+	HPD2_REGISTER_OFFSET,
+	HPD3_REGISTER_OFFSET,
+	HPD4_REGISTER_OFFSET,
+	HPD5_REGISTER_OFFSET
 };
 
 static const uint32_t dig_offsets[] = {
-	SI_CRTC0_REGISTER_OFFSET,
-	SI_CRTC1_REGISTER_OFFSET,
-	SI_CRTC2_REGISTER_OFFSET,
-	SI_CRTC3_REGISTER_OFFSET,
-	SI_CRTC4_REGISTER_OFFSET,
-	SI_CRTC5_REGISTER_OFFSET,
+	CRTC0_REGISTER_OFFSET,
+	CRTC1_REGISTER_OFFSET,
+	CRTC2_REGISTER_OFFSET,
+	CRTC3_REGISTER_OFFSET,
+	CRTC4_REGISTER_OFFSET,
+	CRTC5_REGISTER_OFFSET,
 	(0x13830 - 0x7030) >> 2,
 };
 
@@ -206,9 +213,9 @@ static void dce_v6_0_page_flip(struct amdgpu_device *adev,
 	/* update the scanout addresses */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
+	/* writing to the low address triggers the update */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
 	       (u32)crtc_base);
-
 	/* post the write */
 	RREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset);
 }
@@ -218,11 +225,11 @@ static int dce_v6_0_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 {
 	if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc))
 		return -EINVAL;
+
 	*vbl = RREG32(mmCRTC_V_BLANK_START_END + crtc_offsets[crtc]);
 	*position = RREG32(mmCRTC_STATUS_POSITION + crtc_offsets[crtc]);
 
 	return 0;
-
 }
 
 /**
@@ -242,7 +249,8 @@ static bool dce_v6_0_hpd_sense(struct amdgpu_device *adev,
 	if (hpd >= adev->mode_info.num_hpd)
 		return connected;
 
-	if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) & DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK)
+	if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) &
+	    DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK)
 		connected = true;
 
 	return connected;
@@ -370,13 +378,41 @@ static u32 dce_v6_0_hpd_get_gpio_reg(struct amdgpu_device *adev)
 	return mmDC_GPIO_HPD_A;
 }
 
+static bool dce_v6_0_is_display_hung(struct amdgpu_device *adev)
+{
+	u32 crtc_hung = 0;
+	u32 crtc_status[6];
+	u32 i, j, tmp;
+
+	for (i = 0; i < adev->mode_info.num_crtc; i++) {
+		if (RREG32(mmCRTC_CONTROL + crtc_offsets[i]) & CRTC_CONTROL__CRTC_MASTER_EN_MASK) {
+			crtc_status[i] = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+			crtc_hung |= (1 << i);
+		}
+	}
+
+	for (j = 0; j < 10; j++) {
+		for (i = 0; i < adev->mode_info.num_crtc; i++) {
+			if (crtc_hung & (1 << i)) {
+				tmp = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+				if (tmp != crtc_status[i])
+					crtc_hung &= ~(1 << i);
+			}
+		}
+		if (crtc_hung == 0)
+			return false;
+		udelay(100);
+	}
+
+	return true;
+}
+
 static void dce_v6_0_set_vga_render_state(struct amdgpu_device *adev,
 					  bool render)
 {
 	if (!render)
 		WREG32(mmVGA_RENDER_CONTROL,
 			RREG32(mmVGA_RENDER_CONTROL) & VGA_VSTATUS_CNTL);
-
 }
 
 static int dce_v6_0_get_num_crtc(struct amdgpu_device *adev)
@@ -419,7 +455,6 @@ void dce_v6_0_disable_dce(struct amdgpu_device *adev)
 
 static void dce_v6_0_program_fmt(struct drm_encoder *encoder)
 {
-
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
@@ -895,8 +930,8 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev,
 		wm_high.dram_channels = dram_channels;
 		wm_high.num_heads = num_heads;
 
-		if (adev->pm.dpm_enabled) {
 		/* watermark for low clocks */
+		if (adev->pm.dpm_enabled) {
 			wm_low.yclk =
 				amdgpu_dpm_get_mclk(adev, true) * 10;
 			wm_low.sclk =
@@ -1006,6 +1041,20 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev,
 }
 
 /* watermark setup */
+/**
+ * dce_v6_0_line_buffer_adjust - Set up the line buffer
+ *
+ * @adev: amdgpu_device pointer
+ * @amdgpu_crtc: the selected display controller
+ * @mode: the current display mode on the selected display
+ * controller
+ * @other_mode: the display mode of another display controller
+ *              that may be sharing the line buffer
+ *
+ * Setup up the line buffer allocation for
+ * the selected display controller (CIK).
+ * Returns the line buffer size in pixels.
+ */
 static u32 dce_v6_0_line_buffer_adjust(struct amdgpu_device *adev,
 				   struct amdgpu_crtc *amdgpu_crtc,
 				   struct drm_display_mode *mode,
@@ -1347,13 +1396,13 @@ static void dce_v6_0_audio_enable(struct amdgpu_device *adev,
 
 static const u32 pin_offsets[7] =
 {
-	(0x1780 - 0x1780),
-	(0x1786 - 0x1780),
-	(0x178c - 0x1780),
-	(0x1792 - 0x1780),
-	(0x1798 - 0x1780),
-	(0x179d - 0x1780),
-	(0x17a4 - 0x1780),
+	AUD0_REGISTER_OFFSET,
+	AUD1_REGISTER_OFFSET,
+	AUD2_REGISTER_OFFSET,
+	AUD3_REGISTER_OFFSET,
+	AUD4_REGISTER_OFFSET,
+	AUD5_REGISTER_OFFSET,
+	AUD6_REGISTER_OFFSET,
 };
 
 static int dce_v6_0_audio_init(struct amdgpu_device *adev)
@@ -1386,6 +1435,8 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev)
 		adev->mode_info.audio.pin[i].connected = false;
 		adev->mode_info.audio.pin[i].offset = pin_offsets[i];
 		adev->mode_info.audio.pin[i].id = i;
+		/* disable audio.  it will be set up later */
+		/* XXX remove once we switch to ip funcs */
 		dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
 	}
 
@@ -2865,14 +2916,35 @@ static int dce_v6_0_resume(struct amdgpu_ip_block *ip_block)
 	return amdgpu_display_resume_helper(adev);
 }
 
-static bool dce_v6_0_is_idle(void *handle)
+static bool dce_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
 
 static int dce_v6_0_soft_reset(struct amdgpu_ip_block *ip_block)
 {
-	DRM_INFO("xxxx: dce_v6_0_soft_reset --- no impl!!\n");
+	u32 srbm_soft_reset = 0, tmp;
+	struct amdgpu_device *adev = ip_block->adev;
+
+	if (dce_v6_0_is_display_hung(adev))
+		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_DC_MASK;
+
+	if (srbm_soft_reset) {
+		tmp = RREG32(mmSRBM_SOFT_RESET);
+		tmp |= srbm_soft_reset;
+		dev_info(adev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(mmSRBM_SOFT_RESET, tmp);
+		tmp = RREG32(mmSRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~srbm_soft_reset;
+		WREG32(mmSRBM_SOFT_RESET, tmp);
+		tmp = RREG32(mmSRBM_SOFT_RESET);
+
+		/* Wait a little for things to settle down */
+		udelay(50);
+	}
 	return 0;
 }
 
@@ -2889,22 +2961,22 @@ static void dce_v6_0_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
 
 	switch (crtc) {
 	case 0:
-		reg_block = SI_CRTC0_REGISTER_OFFSET;
+		reg_block = CRTC0_REGISTER_OFFSET;
 		break;
 	case 1:
-		reg_block = SI_CRTC1_REGISTER_OFFSET;
+		reg_block = CRTC1_REGISTER_OFFSET;
 		break;
 	case 2:
-		reg_block = SI_CRTC2_REGISTER_OFFSET;
+		reg_block = CRTC2_REGISTER_OFFSET;
 		break;
 	case 3:
-		reg_block = SI_CRTC3_REGISTER_OFFSET;
+		reg_block = CRTC3_REGISTER_OFFSET;
 		break;
 	case 4:
-		reg_block = SI_CRTC4_REGISTER_OFFSET;
+		reg_block = CRTC4_REGISTER_OFFSET;
 		break;
 	case 5:
-		reg_block = SI_CRTC5_REGISTER_OFFSET;
+		reg_block = CRTC5_REGISTER_OFFSET;
 		break;
 	default:
 		DRM_DEBUG("invalid crtc %d\n", crtc);
@@ -3148,7 +3220,6 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev,
 	}
 
 	return 0;
-
 }
 
 static int dce_v6_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
@@ -3281,8 +3352,7 @@ static void dce_v6_0_ext_commit(struct drm_encoder *encoder)
 
 }
 
-static void
-dce_v6_0_ext_mode_set(struct drm_encoder *encoder,
+static void dce_v6_0_ext_mode_set(struct drm_encoder *encoder,
 		      struct drm_display_mode *mode,
 		      struct drm_display_mode *adjusted_mode)
 {
@@ -3294,8 +3364,7 @@ static void dce_v6_0_ext_disable(struct drm_encoder *encoder)
 
 }
 
-static void
-dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode)
+static void dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode)
 {
 
 }
@@ -3366,7 +3435,6 @@ static void dce_v6_0_encoder_add(struct amdgpu_device *adev,
 			amdgpu_encoder->devices |= supported_device;
 			return;
 		}
-
 	}
 
 	/* add a new one */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index f2edc0fece5b..07358546581f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1395,13 +1395,13 @@ static void dce_v8_0_audio_enable(struct amdgpu_device *adev,
 }
 
 static const u32 pin_offsets[7] = {
-	(0x1780 - 0x1780),
-	(0x1786 - 0x1780),
-	(0x178c - 0x1780),
-	(0x1792 - 0x1780),
-	(0x1798 - 0x1780),
-	(0x179d - 0x1780),
-	(0x17a4 - 0x1780),
+	AUD0_REGISTER_OFFSET,
+	AUD1_REGISTER_OFFSET,
+	AUD2_REGISTER_OFFSET,
+	AUD3_REGISTER_OFFSET,
+	AUD4_REGISTER_OFFSET,
+	AUD5_REGISTER_OFFSET,
+	AUD6_REGISTER_OFFSET,
 };
 
 static int dce_v8_0_audio_init(struct amdgpu_device *adev)
@@ -2887,7 +2887,7 @@ static int dce_v8_0_resume(struct amdgpu_ip_block *ip_block)
 	return amdgpu_display_resume_helper(adev);
 }
 
-static bool dce_v8_0_is_idle(void *handle)
+static bool dce_v8_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 5ba263fe5512..6d514efb0a6d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -40,7 +40,6 @@
 #include "ivsrcid/gfx/irqsrcs_gfx_10_1.h"
 
 #include "soc15.h"
-#include "soc15d.h"
 #include "soc15_common.h"
 #include "clearstate_gfx10.h"
 #include "v10_structs.h"
@@ -3790,12 +3789,65 @@ static void gfx10_kiq_invalidate_tlbs(struct amdgpu_ring *kiq_ring,
 	gfx_v10_0_ring_invalidate_tlbs(kiq_ring, pasid, flush_type, all_hub, 1);
 }
 
+static void gfx_v10_0_kiq_reset_hw_queue(struct amdgpu_ring *kiq_ring, uint32_t queue_type,
+					uint32_t me_id, uint32_t pipe_id, uint32_t queue_id,
+					uint32_t xcc_id, uint32_t vmid)
+{
+	struct amdgpu_device *adev = kiq_ring->adev;
+	unsigned i;
+	uint32_t tmp;
+
+	/* enter save mode */
+	amdgpu_gfx_rlc_enter_safe_mode(adev, xcc_id);
+	mutex_lock(&adev->srbm_mutex);
+	nv_grbm_select(adev, me_id, pipe_id, queue_id, 0);
+
+	if (queue_type == AMDGPU_RING_TYPE_COMPUTE) {
+		WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 0x2);
+		WREG32_SOC15(GC, 0, mmSPI_COMPUTE_QUEUE_RESET, 0x1);
+		/* wait till dequeue take effects */
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+		if (i >= adev->usec_timeout)
+			dev_err(adev->dev, "fail to wait on hqd deactive\n");
+	} else if (queue_type == AMDGPU_RING_TYPE_GFX) {
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX,
+			     (uint32_t)(0x1 << GRBM_GFX_INDEX__SE_BROADCAST_WRITES__SHIFT));
+		tmp = REG_SET_FIELD(0, CP_VMID_RESET, RESET_REQUEST, 1 << vmid);
+		if (pipe_id == 0)
+			tmp = REG_SET_FIELD(tmp, CP_VMID_RESET, PIPE0_QUEUES, 1 << queue_id);
+		else
+			tmp = REG_SET_FIELD(tmp, CP_VMID_RESET, PIPE1_QUEUES, 1 << queue_id);
+		WREG32_SOC15(GC, 0, mmCP_VMID_RESET, tmp);
+
+		/* wait till dequeue take effects */
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32_SOC15(GC, 0, mmCP_GFX_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+		if (i >= adev->usec_timeout)
+			dev_err(adev->dev, "failed to wait on gfx hqd deactivate\n");
+	} else {
+		dev_err(adev->dev, "reset queue_type(%d) not supported\n", queue_type);
+	}
+
+	nv_grbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+	/* exit safe mode */
+	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
+}
+
 static const struct kiq_pm4_funcs gfx_v10_0_kiq_pm4_funcs = {
 	.kiq_set_resources = gfx10_kiq_set_resources,
 	.kiq_map_queues = gfx10_kiq_map_queues,
 	.kiq_unmap_queues = gfx10_kiq_unmap_queues,
 	.kiq_query_status = gfx10_kiq_query_status,
 	.kiq_invalidate_tlbs = gfx10_kiq_invalidate_tlbs,
+	.kiq_reset_hw_queue = gfx_v10_0_kiq_reset_hw_queue,
 	.set_resources_size = 8,
 	.map_queues_size = 7,
 	.unmap_queues_size = 6,
@@ -4701,6 +4753,8 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
 	int xcc_id = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
+	INIT_DELAYED_WORK(&adev->gfx.idle_work, amdgpu_gfx_profile_idle_work_handler);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(10, 1, 10):
 	case IP_VERSION(10, 1, 1):
@@ -4739,6 +4793,22 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
 		break;
 	}
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 2):
+		adev->gfx.cleaner_shader_ptr = gfx_10_1_10_cleaner_shader_hex;
+		adev->gfx.cleaner_shader_size = sizeof(gfx_10_1_10_cleaner_shader_hex);
+		if (adev->gfx.me_fw_version >= 101 &&
+		    adev->gfx.pfp_fw_version  >= 158 &&
+		    adev->gfx.mec_fw_version >= 152) {
+			adev->gfx.enable_cleaner_shader = true;
+			r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+			if (r) {
+				adev->gfx.enable_cleaner_shader = false;
+				dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+			}
+		}
+		break;
 	case IP_VERSION(10, 3, 0):
 	case IP_VERSION(10, 3, 2):
 	case IP_VERSION(10, 3, 4):
@@ -7467,6 +7537,8 @@ static int gfx_v10_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_delayed_work_sync(&adev->gfx.idle_work);
+
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.bad_op_irq, 0);
@@ -7511,9 +7583,9 @@ static int gfx_v10_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v10_0_hw_init(ip_block);
 }
 
-static bool gfx_v10_0_is_idle(void *handle)
+static bool gfx_v10_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS),
 				GRBM_STATUS, GUI_ACTIVE))
@@ -8431,9 +8503,9 @@ static int gfx_v10_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gfx_v10_0_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v10_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	/* AMD_CG_SUPPORT_GFX_FGCG */
@@ -9748,6 +9820,20 @@ static void gfx_v10_0_ring_emit_cleaner_shader(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0);  /* RESERVED field, programmed to zero */
 }
 
+static void gfx_v10_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_begin_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_begin_use(ring);
+}
+
+static void gfx_v10_0_ring_end_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_end_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_end_use(ring);
+}
+
 static const struct amd_ip_funcs gfx_v10_0_ip_funcs = {
 	.name = "gfx_v10_0",
 	.early_init = gfx_v10_0_early_init,
@@ -9823,8 +9909,8 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_mem_sync = gfx_v10_0_emit_mem_sync,
 	.reset = gfx_v10_0_reset_kgq,
 	.emit_cleaner_shader = gfx_v10_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v10_0_ring_begin_use,
+	.end_use = gfx_v10_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
@@ -9864,8 +9950,8 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
 	.emit_mem_sync = gfx_v10_0_emit_mem_sync,
 	.reset = gfx_v10_0_reset_kcq,
 	.emit_cleaner_shader = gfx_v10_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v10_0_ring_begin_use,
+	.end_use = gfx_v10_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h
index 663c2572d440..5255378af53c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h
@@ -21,6 +21,41 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+/* Define the cleaner shader gfx_10_1_10 */
+static const u32 gfx_10_1_10_cleaner_shader_hex[] = {
+	0xb0804004, 0xbf8a0000,
+	0xbf068100, 0xbf840023,
+	0xbe8203b8, 0xbefc0380,
+	0x7e008480, 0x7e028480,
+	0x7e048480, 0x7e068480,
+	0x7e088480, 0x7e0a8480,
+	0x7e0c8480, 0x7e0e8480,
+	0xbefc0302, 0x80828802,
+	0xbf84fff5, 0xbe8203ff,
+	0x80000000, 0x87020102,
+	0xbf840012, 0xbefe03c1,
+	0xbeff03c1, 0xd7650001,
+	0x0001007f, 0xd7660001,
+	0x0002027e, 0x16020288,
+	0xbe8203bf, 0xbefc03c1,
+	0xd9382000, 0x00020201,
+	0xd9386040, 0x00040401,
+	0xd70f6a01, 0x000202ff,
+	0x00000400, 0x80828102,
+	0xbf84fff7, 0xbefc03ff,
+	0x00000068, 0xbe803080,
+	0xbe813080, 0xbe823080,
+	0xbe833080, 0x80fc847c,
+	0xbf84fffa, 0xbeea0480,
+	0xbeec0480, 0xbeee0480,
+	0xbef00480, 0xbef20480,
+	0xbef40480, 0xbef60480,
+	0xbef80480, 0xbefa0480,
+	0xbf810000, 0xbf9f0000,
+	0xbf9f0000, 0xbf9f0000,
+	0xbf9f0000, 0xbf9f0000,
+};
+
 /* Define the cleaner shader gfx_10_3_0 */
 static const u32 gfx_10_3_0_cleaner_shader_hex[] = {
 	0xb0804004, 0xbf8a0000,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_1_10_cleaner_shader.asm b/drivers/gpu/drm/amd/amdgpu/gfx_v10_1_10_cleaner_shader.asm
new file mode 100644
index 000000000000..9ba3359253c9
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_1_10_cleaner_shader.asm
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2025 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.
+ */
+
+// This shader is to clean LDS, SGPRs and VGPRs. It is  first 64 Dwords or 256 bytes of 256 Dwords cleaner shader.
+
+// GFX10.1 : Clear SGPRs, VGPRs and LDS
+//   Launch 32 waves per CU (16 per SIMD) as a workgroup (threadgroup) to fill every wave slot
+//   Waves are "wave32" and have 64 VGPRs each, which uses all 1024 VGPRs per SIMD
+//   Waves are launched in "CU" mode, and the workgroup shares 64KB of LDS (half of the WGP's LDS)
+//      It takes 2 workgroups to use all of LDS: one on each CU of the WGP
+//   Each wave clears SGPRs 0 - 107
+//   Each wave clears VGPRs 0 - 63
+//   The first wave of the workgroup clears its 64KB of LDS
+//   The shader starts with "S_BARRIER" to ensure SPI has launched all waves of the workgroup
+//       before any wave in the workgroup could end.  Without this, it is possible not all SGPRs get cleared.
+
+
+shader main
+  asic(GFX10.1)
+  type(CS)
+  wave_size(32)
+// Note: original source code from SQ team
+
+//
+// Create 32 waves in a threadgroup (CS waves)
+// Each allocates 64 VGPRs
+// The workgroup allocates all of LDS (64kbytes)
+//
+// Takes about 2500 clocks to run.
+//   (theorhetical fastest = 1024clks vgpr + 640lds = 1660 clks)
+//
+  S_BARRIER
+  s_cmp_eq_u32 s0, 1                                // Bit0 is set, sgpr0 is set then clear VGPRS and LDS as FW set COMPUTE_USER_DATA_0
+  s_cbranch_scc0  label_0023                        // Clean VGPRs and LDS if sgpr0 of wave is set, scc = (s0 == 1)
+
+  s_mov_b32     s2, 0x00000038  // Loop 64/8=8 times  (loop unrolled for performance)
+  s_mov_b32     m0, 0
+  //
+  // CLEAR VGPRs
+  //
+label_0005:
+  v_movreld_b32     v0, 0
+  v_movreld_b32     v1, 0
+  v_movreld_b32     v2, 0
+  v_movreld_b32     v3, 0
+  v_movreld_b32     v4, 0
+  v_movreld_b32     v5, 0
+  v_movreld_b32     v6, 0
+  v_movreld_b32     v7, 0
+  s_mov_b32         m0, s2
+  s_sub_u32     s2, s2, 8
+  s_cbranch_scc0  label_0005
+  //
+  s_mov_b32     s2, 0x80000000                     // Bit31 is first_wave
+  s_and_b32     s2, s2, s0                                  // sgpr0 has tg_size (first_wave) term as in ucode only COMPUTE_PGM_RSRC2.tg_size_en is set
+  s_cbranch_scc0  label_0023                         // Clean LDS if its first wave of ThreadGroup/WorkGroup
+  // CLEAR LDS
+  //
+  s_mov_b32 exec_lo, 0xffffffff
+  s_mov_b32 exec_hi, 0xffffffff
+  v_mbcnt_lo_u32_b32  v1, exec_hi, 0          // Set V1 to thread-ID (0..63)
+  v_mbcnt_hi_u32_b32  v1, exec_lo, v1        // Set V1 to thread-ID (0..63)
+  v_mul_u32_u24  v1, 0x00000008, v1          // * 8, so each thread is a double-dword address (8byte)
+  s_mov_b32     s2, 0x00000003f                    // 64 loop iterations
+  s_mov_b32     m0, 0xffffffff
+  // Clear all of LDS space
+  // Each FirstWave of WorkGroup clears 64kbyte block
+
+label_001F:
+  ds_write2_b64  v1, v[2:3], v[2:3] offset1:32
+  ds_write2_b64  v1, v[4:5], v[4:5] offset0:64 offset1:96
+  v_add_co_u32     v1, vcc, 0x00000400, v1
+  s_sub_u32     s2, s2, 1
+  s_cbranch_scc0  label_001F
+
+  //
+  // CLEAR SGPRs
+  //
+label_0023:
+  s_mov_b32     m0, 0x00000068  // Loop 108/4=27 times  (loop unrolled for performance)
+label_sgpr_loop:
+  s_movreld_b32     s0, 0
+  s_movreld_b32     s1, 0
+  s_movreld_b32     s2, 0
+  s_movreld_b32     s3, 0
+  s_sub_u32         m0, m0, 4
+  s_cbranch_scc0  label_sgpr_loop
+
+  //clear vcc
+  s_mov_b64 vcc, 0          //clear vcc
+  //s_setreg_imm32_b32 hw_reg_shader_flat_scratch_lo, 0   //clear  flat scratch lo SGPR
+  //s_setreg_imm32_b32 hw_reg_shader_flat_scratch_hi, 0    //clear  flat scratch hi SGPR
+  s_mov_b64 ttmp0, 0        //Clear ttmp0 and ttmp1
+  s_mov_b64 ttmp2, 0        //Clear ttmp2 and ttmp3
+  s_mov_b64 ttmp4, 0        //Clear ttmp4 and ttmp5
+  s_mov_b64 ttmp6, 0        //Clear ttmp6 and ttmp7
+  s_mov_b64 ttmp8, 0        //Clear ttmp8 and ttmp9
+  s_mov_b64 ttmp10, 0       //Clear ttmp10 and ttmp11
+  s_mov_b64 ttmp12, 0       //Clear ttmp12 and ttmp13
+  s_mov_b64 ttmp14, 0       //Clear ttmp14 and ttmp15
+
+ s_endpgm
+
+end
+
+
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 56c06b72a70a..d8772cd6db63 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -29,7 +29,6 @@
 #include "amdgpu_gfx.h"
 #include "amdgpu_psp.h"
 #include "amdgpu_smu.h"
-#include "amdgpu_atomfirmware.h"
 #include "imu_v11_0.h"
 #include "soc21.h"
 #include "nvd.h"
@@ -42,7 +41,6 @@
 #include "ivsrcid/gfx/irqsrcs_gfx_11_0_0.h"
 
 #include "soc15.h"
-#include "soc15d.h"
 #include "clearstate_gfx11.h"
 #include "v11_structs.h"
 #include "gfx_v11_0.h"
@@ -64,6 +62,23 @@
 #define regPC_CONFIG_CNTL_1		0x194d
 #define regPC_CONFIG_CNTL_1_BASE_IDX	1
 
+#define regCP_GFX_MQD_CONTROL_DEFAULT                                             0x00000100
+#define regCP_GFX_HQD_VMID_DEFAULT                                                0x00000000
+#define regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT                                      0x00000000
+#define regCP_GFX_HQD_QUANTUM_DEFAULT                                             0x00000a01
+#define regCP_GFX_HQD_CNTL_DEFAULT                                                0x00a00000
+#define regCP_RB_DOORBELL_CONTROL_DEFAULT                                         0x00000000
+#define regCP_GFX_HQD_RPTR_DEFAULT                                                0x00000000
+
+#define regCP_HQD_EOP_CONTROL_DEFAULT                                             0x00000006
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_MQD_CONTROL_DEFAULT                                                 0x00000100
+#define regCP_HQD_PQ_CONTROL_DEFAULT                                              0x00308509
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_HQD_PQ_RPTR_DEFAULT                                                 0x00000000
+#define regCP_HQD_PERSISTENT_STATE_DEFAULT                                        0x0be05501
+#define regCP_HQD_IB_CONTROL_DEFAULT                                              0x00300000
+
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
@@ -98,6 +113,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_2_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_rlc.bin");
 
 static const struct amdgpu_hwip_reg_entry gc_reg_list_11_0[] = {
 	SOC15_REG_ENTRY_STR(GC, 0, regGRBM_STATUS),
@@ -1087,6 +1106,7 @@ static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -1552,6 +1572,8 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	int xcc_id = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
+	INIT_DELAYED_WORK(&adev->gfx.idle_work, amdgpu_gfx_profile_idle_work_handler);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 2):
@@ -1568,6 +1590,7 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
@@ -1603,6 +1626,20 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 			}
 		}
 		break;
+	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
+		adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex;
+		adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex);
+		if (adev->gfx.mec_fw_version >= 26 &&
+		    adev->mes.fw_version[0] >= 114) {
+			adev->gfx.enable_cleaner_shader = true;
+			r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+			if (r) {
+				adev->gfx.enable_cleaner_shader = false;
+				dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+			}
+		}
+		break;
 	default:
 		adev->gfx.enable_cleaner_shader = false;
 		break;
@@ -2926,7 +2963,8 @@ static int gfx_v11_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev)
 			    IP_VERSION(11, 0, 4) ||
 		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 0) ||
 		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 1) ||
-		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 2))
+		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 2) ||
+		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 3))
 			bootload_status = RREG32_SOC15(GC, 0,
 					regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1);
 		else
@@ -3958,7 +3996,7 @@ static void gfx_v11_0_gfx_mqd_set_priority(struct amdgpu_device *adev,
 	if (prop->hqd_pipe_priority == AMDGPU_GFX_PIPE_PRIO_HIGH)
 		priority = 1;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUEUE_PRIORITY);
+	tmp = regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUEUE_PRIORITY, PRIORITY_LEVEL, priority);
 	mqd->cp_gfx_hqd_queue_priority = tmp;
 }
@@ -3980,14 +4018,14 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set up mqd control */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_MQD_CONTROL);
+	tmp = regCP_GFX_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, VMID, 0);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, PRIV_STATE, 1);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, CACHE_POLICY, 0);
 	mqd->cp_gfx_mqd_control = tmp;
 
 	/* set up gfx_hqd_vimd with 0x0 to indicate the ring buffer's vmid */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_VMID);
+	tmp = regCP_GFX_HQD_VMID_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_VMID, VMID, 0);
 	mqd->cp_gfx_hqd_vmid = 0;
 
@@ -3995,7 +4033,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	gfx_v11_0_gfx_mqd_set_priority(adev, mqd, prop);
 
 	/* set up time quantum */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUANTUM);
+	tmp = regCP_GFX_HQD_QUANTUM_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUANTUM, QUANTUM_EN, 1);
 	mqd->cp_gfx_hqd_quantum = tmp;
 
@@ -4017,7 +4055,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 
 	/* set up the gfx_hqd_control, similar as CP_RB0_CNTL */
 	rb_bufsz = order_base_2(prop->queue_size / 4) - 1;
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_CNTL);
+	tmp = regCP_GFX_HQD_CNTL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BUFSZ, rb_bufsz);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BLKSZ, rb_bufsz - 2);
 #ifdef __BIG_ENDIAN
@@ -4026,7 +4064,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
-	tmp = RREG32_SOC15(GC, 0, regCP_RB_DOORBELL_CONTROL);
+	tmp = regCP_RB_DOORBELL_CONTROL_DEFAULT;
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_RB_DOORBELL_CONTROL,
 				    DOORBELL_OFFSET, prop->doorbell_index);
@@ -4038,7 +4076,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_rb_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_gfx_hqd_rptr = RREG32_SOC15(GC, 0, regCP_GFX_HQD_RPTR);
+	mqd->cp_gfx_hqd_rptr = regCP_GFX_HQD_RPTR_DEFAULT;
 
 	/* active the queue */
 	mqd->cp_gfx_hqd_active = 1;
@@ -4124,14 +4162,14 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
 	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_EOP_CONTROL);
+	tmp = regCP_HQD_EOP_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
 			(order_base_2(GFX11_MEC_HPD_SIZE / 4) - 1));
 
 	mqd->cp_hqd_eop_control = tmp;
 
 	/* enable doorbell? */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -4160,7 +4198,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	tmp = RREG32_SOC15(GC, 0, regCP_MQD_CONTROL);
+	tmp = regCP_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
 	mqd->cp_mqd_control = tmp;
 
@@ -4170,7 +4208,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_CONTROL);
+	tmp = regCP_HQD_PQ_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
@@ -4196,7 +4234,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = 0;
 	/* enable the doorbell if requested */
 	if (prop->use_doorbell) {
-		tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+		tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 				DOORBELL_OFFSET, prop->doorbell_index);
 
@@ -4211,17 +4249,17 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_rptr = regCP_HQD_PQ_RPTR_DEFAULT;
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PERSISTENT_STATE);
+	tmp = regCP_HQD_PERSISTENT_STATE_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x55);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* set MIN_IB_AVAIL_SIZE */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_IB_CONTROL);
+	tmp = regCP_HQD_IB_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
@@ -4734,6 +4772,8 @@ static int gfx_v11_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_delayed_work_sync(&adev->gfx.idle_work);
+
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.bad_op_irq, 0);
@@ -4778,9 +4818,9 @@ static int gfx_v11_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v11_0_hw_init(ip_block);
 }
 
-static bool gfx_v11_0_is_idle(void *handle)
+static bool gfx_v11_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS),
 				GRBM_STATUS, GUI_ACTIVE))
@@ -5448,6 +5488,7 @@ static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable)
 		case IP_VERSION(11, 5, 0):
 		case IP_VERSION(11, 5, 1):
 		case IP_VERSION(11, 5, 2):
+		case IP_VERSION(11, 5, 3):
 			WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1);
 			break;
 		default:
@@ -5485,6 +5526,7 @@ static int gfx_v11_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
 
@@ -5518,6 +5560,7 @@ static int gfx_v11_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);
 	        break;
@@ -5528,9 +5571,9 @@ static int gfx_v11_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gfx_v11_0_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v11_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	/* AMD_CG_SUPPORT_GFX_MGCG */
@@ -6826,6 +6869,20 @@ static void gfx_v11_0_ring_emit_cleaner_shader(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0);  /* RESERVED field, programmed to zero */
 }
 
+static void gfx_v11_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_begin_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_begin_use(ring);
+}
+
+static void gfx_v11_0_ring_end_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_end_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_end_use(ring);
+}
+
 static const struct amd_ip_funcs gfx_v11_0_ip_funcs = {
 	.name = "gfx_v11_0",
 	.early_init = gfx_v11_0_early_init,
@@ -6900,8 +6957,8 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = {
 	.emit_mem_sync = gfx_v11_0_emit_mem_sync,
 	.reset = gfx_v11_0_reset_kgq,
 	.emit_cleaner_shader = gfx_v11_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v11_0_ring_begin_use,
+	.end_use = gfx_v11_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_compute = {
@@ -6942,8 +6999,8 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_compute = {
 	.emit_mem_sync = gfx_v11_0_emit_mem_sync,
 	.reset = gfx_v11_0_reset_kcq,
 	.emit_cleaner_shader = gfx_v11_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v11_0_ring_begin_use,
+	.end_use = gfx_v11_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 48ff00427882..dceb5ad38862 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -29,7 +29,6 @@
 #include "amdgpu_gfx.h"
 #include "amdgpu_psp.h"
 #include "amdgpu_smu.h"
-#include "amdgpu_atomfirmware.h"
 #include "imu_v12_0.h"
 #include "soc24.h"
 #include "nvd.h"
@@ -40,7 +39,6 @@
 #include "ivsrcid/gfx/irqsrcs_gfx_11_0_0.h"
 
 #include "soc15.h"
-#include "soc15d.h"
 #include "clearstate_gfx12.h"
 #include "v12_structs.h"
 #include "gfx_v12_0.h"
@@ -52,6 +50,24 @@
 
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
 
+#define regCP_GFX_MQD_CONTROL_DEFAULT                                             0x00000100
+#define regCP_GFX_HQD_VMID_DEFAULT                                                0x00000000
+#define regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT                                      0x00000000
+#define regCP_GFX_HQD_QUANTUM_DEFAULT                                             0x00000a01
+#define regCP_GFX_HQD_CNTL_DEFAULT                                                0x00f00000
+#define regCP_RB_DOORBELL_CONTROL_DEFAULT                                         0x00000000
+#define regCP_GFX_HQD_RPTR_DEFAULT                                                0x00000000
+
+#define regCP_HQD_EOP_CONTROL_DEFAULT                                             0x00000006
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_MQD_CONTROL_DEFAULT                                                 0x00000100
+#define regCP_HQD_PQ_CONTROL_DEFAULT                                              0x00308509
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_HQD_PQ_RPTR_DEFAULT                                                 0x00000000
+#define regCP_HQD_PERSISTENT_STATE_DEFAULT                                        0x0be05501
+#define regCP_HQD_IB_CONTROL_DEFAULT                                              0x00300000
+
+
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_mec.bin");
@@ -1331,6 +1347,8 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 	int xcc_id = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
+	INIT_DELAYED_WORK(&adev->gfx.idle_work, amdgpu_gfx_profile_idle_work_handler);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
@@ -2619,7 +2637,6 @@ static int gfx_v12_0_cp_gfx_resume(struct amdgpu_device *adev)
 	u32 tmp;
 	u32 rb_bufsz;
 	u64 rb_addr, rptr_addr, wptr_gpu_addr;
-	u32 i;
 
 	/* Set the write pointer delay */
 	WREG32_SOC15(GC, 0, regCP_RB_WPTR_DELAY, 0);
@@ -2674,12 +2691,6 @@ static int gfx_v12_0_cp_gfx_resume(struct amdgpu_device *adev)
 
 	/* start the ring */
 	gfx_v12_0_cp_gfx_start(adev);
-
-	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
-		ring = &adev->gfx.gfx_ring[i];
-		ring->sched.ready = true;
-	}
-
 	return 0;
 }
 
@@ -2891,25 +2902,25 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set up mqd control */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_MQD_CONTROL);
+	tmp = regCP_GFX_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, VMID, 0);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, PRIV_STATE, 1);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, CACHE_POLICY, 0);
 	mqd->cp_gfx_mqd_control = tmp;
 
 	/* set up gfx_hqd_vimd with 0x0 to indicate the ring buffer's vmid */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_VMID);
+	tmp = regCP_GFX_HQD_VMID_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_VMID, VMID, 0);
 	mqd->cp_gfx_hqd_vmid = 0;
 
 	/* set up default queue priority level
 	 * 0x0 = low priority, 0x1 = high priority */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUEUE_PRIORITY);
+	tmp = regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUEUE_PRIORITY, PRIORITY_LEVEL, 0);
 	mqd->cp_gfx_hqd_queue_priority = tmp;
 
 	/* set up time quantum */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUANTUM);
+	tmp = regCP_GFX_HQD_QUANTUM_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUANTUM, QUANTUM_EN, 1);
 	mqd->cp_gfx_hqd_quantum = tmp;
 
@@ -2931,7 +2942,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 
 	/* set up the gfx_hqd_control, similar as CP_RB0_CNTL */
 	rb_bufsz = order_base_2(prop->queue_size / 4) - 1;
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_CNTL);
+	tmp = regCP_GFX_HQD_CNTL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BUFSZ, rb_bufsz);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BLKSZ, rb_bufsz - 2);
 #ifdef __BIG_ENDIAN
@@ -2940,7 +2951,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
-	tmp = RREG32_SOC15(GC, 0, regCP_RB_DOORBELL_CONTROL);
+	tmp = regCP_RB_DOORBELL_CONTROL_DEFAULT;
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_RB_DOORBELL_CONTROL,
 				    DOORBELL_OFFSET, prop->doorbell_index);
@@ -2952,7 +2963,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_rb_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_gfx_hqd_rptr = RREG32_SOC15(GC, 0, regCP_GFX_HQD_RPTR);
+	mqd->cp_gfx_hqd_rptr = regCP_GFX_HQD_RPTR_DEFAULT;
 
 	/* active the queue */
 	mqd->cp_gfx_hqd_active = 1;
@@ -3019,10 +3030,6 @@ static int gfx_v12_0_cp_async_gfx_ring_resume(struct amdgpu_device *adev)
 	if (r)
 		goto done;
 
-	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
-		ring = &adev->gfx.gfx_ring[i];
-		ring->sched.ready = true;
-	}
 done:
 	return r;
 }
@@ -3047,14 +3054,14 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
 	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_EOP_CONTROL);
+	tmp = regCP_HQD_EOP_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
 			(order_base_2(GFX12_MEC_HPD_SIZE / 4) - 1));
 
 	mqd->cp_hqd_eop_control = tmp;
 
 	/* enable doorbell? */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -3083,7 +3090,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	tmp = RREG32_SOC15(GC, 0, regCP_MQD_CONTROL);
+	tmp = regCP_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
 	mqd->cp_mqd_control = tmp;
 
@@ -3093,7 +3100,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_CONTROL);
+	tmp = regCP_HQD_PQ_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
@@ -3118,7 +3125,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = 0;
 	/* enable the doorbell if requested */
 	if (prop->use_doorbell) {
-		tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+		tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 				DOORBELL_OFFSET, prop->doorbell_index);
 
@@ -3133,17 +3140,17 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_rptr = regCP_HQD_PQ_RPTR_DEFAULT;
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PERSISTENT_STATE);
+	tmp = regCP_HQD_PERSISTENT_STATE_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x55);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* set MIN_IB_AVAIL_SIZE */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_IB_CONTROL);
+	tmp = regCP_HQD_IB_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
@@ -3648,6 +3655,8 @@ static int gfx_v12_0_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	uint32_t tmp;
 
+	cancel_delayed_work_sync(&adev->gfx.idle_work);
+
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.bad_op_irq, 0);
@@ -3693,9 +3702,9 @@ static int gfx_v12_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v12_0_hw_init(ip_block);
 }
 
-static bool gfx_v12_0_is_idle(void *handle)
+static bool gfx_v12_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS),
 				GRBM_STATUS, GUI_ACTIVE))
@@ -4147,9 +4156,9 @@ static int gfx_v12_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gfx_v12_0_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v12_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	/* AMD_CG_SUPPORT_GFX_MGCG */
@@ -5280,6 +5289,20 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring, unsigned int vmid)
 	return amdgpu_ring_test_ring(ring);
 }
 
+static void gfx_v12_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_begin_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_begin_use(ring);
+}
+
+static void gfx_v12_0_ring_end_use(struct amdgpu_ring *ring)
+{
+	amdgpu_gfx_profile_ring_end_use(ring);
+
+	amdgpu_gfx_enforce_isolation_ring_end_use(ring);
+}
+
 static const struct amd_ip_funcs gfx_v12_0_ip_funcs = {
 	.name = "gfx_v12_0",
 	.early_init = gfx_v12_0_early_init,
@@ -5345,8 +5368,8 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = {
 	.emit_mem_sync = gfx_v12_0_emit_mem_sync,
 	.reset = gfx_v12_0_reset_kgq,
 	.emit_cleaner_shader = gfx_v12_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v12_0_ring_begin_use,
+	.end_use = gfx_v12_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_compute = {
@@ -5384,8 +5407,8 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_compute = {
 	.emit_mem_sync = gfx_v12_0_emit_mem_sync,
 	.reset = gfx_v12_0_reset_kcq,
 	.emit_cleaner_shader = gfx_v12_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v12_0_ring_begin_use,
+	.end_use = gfx_v12_0_ring_end_use,
 };
 
 static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_kiq = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index f26e2cdec07a..13fbee46417a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -28,19 +28,30 @@
 #include "amdgpu_gfx.h"
 #include "amdgpu_ucode.h"
 #include "clearstate_si.h"
+#include "si.h"
+#include "sid.h"
+
 #include "bif/bif_3_0_d.h"
 #include "bif/bif_3_0_sh_mask.h"
+
 #include "oss/oss_1_0_d.h"
 #include "oss/oss_1_0_sh_mask.h"
+
 #include "gca/gfx_6_0_d.h"
 #include "gca/gfx_6_0_sh_mask.h"
+#include "gca/gfx_7_2_enum.h"
+
 #include "gmc/gmc_6_0_d.h"
 #include "gmc/gmc_6_0_sh_mask.h"
+
 #include "dce/dce_6_0_d.h"
 #include "dce/dce_6_0_sh_mask.h"
-#include "gca/gfx_7_2_enum.h"
+
 #include "si_enums.h"
-#include "si.h"
+
+#define TAHITI_GB_ADDR_CONFIG_GOLDEN        0x12011003
+#define VERDE_GB_ADDR_CONFIG_GOLDEN         0x12010002
+#define HAINAN_GB_ADDR_CONFIG_GOLDEN        0x02010001
 
 static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -3167,9 +3178,9 @@ static int gfx_v6_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v6_0_hw_init(ip_block);
 }
 
-static bool gfx_v6_0_is_idle(void *handle)
+static bool gfx_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK)
 		return false;
@@ -3183,7 +3194,7 @@ static int gfx_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (gfx_v6_0_is_idle(adev))
+		if (gfx_v6_0_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 84745b2453ab..8181bd0e4f18 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4515,9 +4515,9 @@ static int gfx_v7_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v7_0_hw_init(ip_block);
 }
 
-static bool gfx_v7_0_is_idle(void *handle)
+static bool gfx_v7_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK)
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6a025438f9d0..d116a2e2f469 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4851,9 +4851,9 @@ static int gfx_v8_0_kcq_disable(struct amdgpu_device *adev)
 	return r;
 }
 
-static bool gfx_v8_0_is_idle(void *handle)
+static bool gfx_v8_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (REG_GET_FIELD(RREG32(mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)
 		|| RREG32(mmGRBM_STATUS2) != 0x8)
@@ -4892,7 +4892,7 @@ static int gfx_v8_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (gfx_v8_0_is_idle(adev))
+		if (gfx_v8_0_is_idle(ip_block))
 			return 0;
 
 		udelay(1);
@@ -5452,9 +5452,9 @@ static int gfx_v8_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gfx_v8_0_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v8_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 0dce4421418c..d345285ea885 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2637,7 +2637,10 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 	u32 tmp;
 	int i;
 
-	WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
+	if (!amdgpu_sriov_vf(adev) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 2)) {
+		WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
+	}
 
 	gfx_v9_0_tiling_mode_table_init(adev);
 
@@ -4042,7 +4045,8 @@ static int gfx_v9_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2))
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) &&
+	    !amdgpu_sriov_vf(adev))
 		gfx_v9_4_2_set_power_brake_sequence(adev);
 
 	return r;
@@ -4110,9 +4114,9 @@ static int gfx_v9_0_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v9_0_hw_init(ip_block);
 }
 
-static bool gfx_v9_0_is_idle(void *handle)
+static bool gfx_v9_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS),
 				GRBM_STATUS, GUI_ACTIVE))
@@ -4127,7 +4131,7 @@ static int gfx_v9_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (gfx_v9_0_is_idle(adev))
+		if (gfx_v9_0_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
@@ -5241,7 +5245,7 @@ static int gfx_v9_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	case IP_VERSION(9, 1, 0):
 	case IP_VERSION(9, 3, 0):
 		if (!enable)
-			amdgpu_gfx_off_ctrl(adev, false);
+			amdgpu_gfx_off_ctrl_immediate(adev, false);
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
 			gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
@@ -5263,10 +5267,10 @@ static int gfx_v9_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 		gfx_v9_0_update_gfx_mg_power_gating(adev, enable);
 
 		if (enable)
-			amdgpu_gfx_off_ctrl(adev, true);
+			amdgpu_gfx_off_ctrl_immediate(adev, true);
 		break;
 	case IP_VERSION(9, 2, 1):
-		amdgpu_gfx_off_ctrl(adev, enable);
+		amdgpu_gfx_off_ctrl_immediate(adev, enable);
 		break;
 	default:
 		break;
@@ -5301,9 +5305,9 @@ static int gfx_v9_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gfx_v9_0_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v9_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
index f53b379d8971..6028afd81690 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
@@ -27,7 +27,6 @@
 #include "amdgpu_gfx.h"
 #include "soc15.h"
 #include "soc15d.h"
-#include "amdgpu_atomfirmware.h"
 #include "amdgpu_pm.h"
 
 #include "gc/gc_9_4_1_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 2ba185875baa..736398b0d16d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -349,18 +349,7 @@ static void gfx_v9_4_3_init_golden_registers(struct amdgpu_device *adev)
 
 		WREG32_SOC15(GC, dev_inst, regGB_ADDR_CONFIG,
 			     GOLDEN_GB_ADDR_CONFIG);
-		if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) {
-			WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1);
-		} else {
-			/* Golden settings applied by driver for ASIC with rev_id 0 */
-			if (adev->rev_id == 0) {
-				WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL1,
-						      REDUCE_FIFO_DEPTH_BY_2, 2);
-			} else {
-				WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2,
-						      SPARE, 0x1);
-			}
-		}
+		WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1);
 	}
 }
 
@@ -563,17 +552,6 @@ out:
 	return err;
 }
 
-static bool gfx_v9_4_3_should_disable_gfxoff(struct pci_dev *pdev)
-{
-	return true;
-}
-
-static void gfx_v9_4_3_check_if_need_gfxoff(struct amdgpu_device *adev)
-{
-	if (gfx_v9_4_3_should_disable_gfxoff(adev->pdev))
-		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
-}
-
 static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev,
 					  const char *chip_name)
 {
@@ -600,8 +578,6 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev,
 	adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version;
 	adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version;
 
-	gfx_v9_4_3_check_if_need_gfxoff(adev);
-
 out:
 	if (err)
 		amdgpu_ucode_release(&adev->gfx.mec_fw);
@@ -891,12 +867,14 @@ static int gfx_v9_4_3_aca_bank_parser(struct aca_handle *handle,
 
 	switch (type) {
 	case ACA_SMU_TYPE_UE:
-		ret = aca_error_cache_log_bank_error(handle, &info,
-						     ACA_ERROR_TYPE_UE, 1ULL);
+		bank->aca_err_type = ACA_BANK_ERR_UE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, 1ULL);
 		break;
 	case ACA_SMU_TYPE_CE:
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
 		ret = aca_error_cache_log_bank_error(handle, &info,
-						     ACA_ERROR_TYPE_CE, ACA_REG__MISC0__ERRCNT(misc0));
+						     bank->aca_err_type,
+						     ACA_REG__MISC0__ERRCNT(misc0));
 		break;
 	default:
 		return -EINVAL;
@@ -937,28 +915,15 @@ static const struct aca_info gfx_v9_4_3_aca_info = {
 
 static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev)
 {
-	u32 gb_addr_config;
-
 	adev->gfx.funcs = &gfx_v9_4_3_gfx_funcs;
 	adev->gfx.ras = &gfx_v9_4_3_ras;
 
-	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-	case IP_VERSION(9, 4, 3):
-	case IP_VERSION(9, 4, 4):
-	case IP_VERSION(9, 5, 0):
-		adev->gfx.config.max_hw_contexts = 8;
-		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
-		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
-		adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
-		adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0;
-		gb_addr_config = RREG32_SOC15(GC, GET_INST(GC, 0), regGB_ADDR_CONFIG);
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	adev->gfx.config.gb_addr_config = gb_addr_config;
+	adev->gfx.config.max_hw_contexts = 8;
+	adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+	adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+	adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+	adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0;
+	adev->gfx.config.gb_addr_config = GOLDEN_GB_ADDR_CONFIG;
 
 	adev->gfx.config.gb_addr_config_fields.num_pipes = 1 <<
 			REG_GET_FIELD(
@@ -1369,10 +1334,8 @@ static void gfx_v9_4_3_xcc_init_pg(struct amdgpu_device *adev, int xcc_id)
 {
 	/*
 	 * Rlc save restore list is workable since v2_1.
-	 * And it's needed by gfxoff feature.
 	 */
-	if (adev->gfx.rlc.is_rlc_v2_1)
-		gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id);
+	gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id);
 }
 
 static void gfx_v9_4_3_xcc_disable_gpa_mode(struct amdgpu_device *adev, int xcc_id)
@@ -1857,7 +1820,7 @@ static int gfx_v9_4_3_xcc_mqd_init(struct amdgpu_ring *ring, int xcc_id)
 				    DOORBELL_SOURCE, 0);
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 				    DOORBELL_HIT, 0);
-		if (amdgpu_sriov_vf(adev))
+		if (amdgpu_sriov_multi_vf_mode(adev))
 			tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 					    DOORBELL_MODE, 1);
 	} else {
@@ -2415,9 +2378,9 @@ static int gfx_v9_4_3_resume(struct amdgpu_ip_block *ip_block)
 	return gfx_v9_4_3_hw_init(ip_block);
 }
 
-static bool gfx_v9_4_3_is_idle(void *handle)
+static bool gfx_v9_4_3_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, num_xcc;
 
 	num_xcc = NUM_XCC(adev->gfx.xcc_mask);
@@ -2435,7 +2398,7 @@ static int gfx_v9_4_3_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (gfx_v9_4_3_is_idle(adev))
+		if (gfx_v9_4_3_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
@@ -2795,22 +2758,16 @@ static int gfx_v9_4_3_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 		return 0;
 
 	num_xcc = NUM_XCC(adev->gfx.xcc_mask);
-	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-	case IP_VERSION(9, 4, 3):
-	case IP_VERSION(9, 4, 4):
-		for (i = 0; i < num_xcc; i++)
-			gfx_v9_4_3_xcc_update_gfx_clock_gating(
-				adev, state == AMD_CG_STATE_GATE, i);
-		break;
-	default:
-		break;
-	}
+	for (i = 0; i < num_xcc; i++)
+		gfx_v9_4_3_xcc_update_gfx_clock_gating(
+			adev, state == AMD_CG_STATE_GATE, i);
+
 	return 0;
 }
 
-static void gfx_v9_4_3_get_clockgating_state(void *handle, u64 *flags)
+static void gfx_v9_4_3_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
@@ -4867,34 +4824,13 @@ static void gfx_v9_4_3_set_rlc_funcs(struct amdgpu_device *adev)
 
 static void gfx_v9_4_3_set_gds_init(struct amdgpu_device *adev)
 {
-	/* init asci gds info */
-	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-	case IP_VERSION(9, 4, 3):
-	case IP_VERSION(9, 4, 4):
-	case IP_VERSION(9, 5, 0):
-		/* 9.4.3 removed all the GDS internal memory,
-		 * only support GWS opcode in kernel, like barrier
-		 * semaphore.etc */
-		adev->gds.gds_size = 0;
-		break;
-	default:
-		adev->gds.gds_size = 0x10000;
-		break;
-	}
-
-	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-	case IP_VERSION(9, 4, 3):
-	case IP_VERSION(9, 4, 4):
-	case IP_VERSION(9, 5, 0):
-		/* deprecated for 9.4.3, no usage at all */
-		adev->gds.gds_compute_max_wave_id = 0;
-		break;
-	default:
-		/* this really depends on the chip */
-		adev->gds.gds_compute_max_wave_id = 0x7ff;
-		break;
-	}
+	/* 9.4.3 variants removed all the GDS internal memory,
+	 * only support GWS opcode in kernel, like barrier
+	 * semaphore.etc */
 
+	/* init asic gds info */
+	adev->gds.gds_size = 0;
+	adev->gds.gds_compute_max_wave_id = 0;
 	adev->gds.gws_size = 64;
 	adev->gds.oa_size = 16;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 0e3ddea7b8e0..a7bfc9f41d0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -92,12 +92,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 {
 	uint64_t value;
 
-	/* Program the AGP BAR */
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0);
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
-
 	if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) {
+		/* Program the AGP BAR */
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0);
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
+
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 5470cef7e9bd..cb25f7f0dfc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -313,6 +313,16 @@ gfxhub_v1_2_xcc_disable_identity_aperture(struct amdgpu_device *adev,
 	}
 }
 
+static inline bool
+gfxhub_v1_2_per_process_xnack_support(struct amdgpu_device *adev)
+{
+	/*
+	 * TODO: Check if this function is really needed, so far only 9.4.3
+	 * variants use GFXHUB 1.2
+	 */
+	return !!adev->aid_mask;
+}
+
 static void gfxhub_v1_2_xcc_setup_vmid_config(struct amdgpu_device *adev,
 					      uint32_t xcc_mask)
 {
@@ -355,7 +365,7 @@ static void gfxhub_v1_2_xcc_setup_vmid_config(struct amdgpu_device *adev,
 					    PAGE_TABLE_BLOCK_SIZE,
 					    block_size);
 			/* Send no-retry XNACK on fault to suppress VM fault storm.
-			 * On 9.4.2 and 9.4.3, XNACK can be enabled in
+			 * On 9.4.3 variants, XNACK can be enabled in
 			 * the SQ per-process.
 			 * Retry faults need to be enabled for that to work.
 			 */
@@ -363,14 +373,8 @@ static void gfxhub_v1_2_xcc_setup_vmid_config(struct amdgpu_device *adev,
 				tmp, VM_CONTEXT1_CNTL,
 				RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
 				!adev->gmc.noretry ||
-					amdgpu_ip_version(adev, GC_HWIP, 0) ==
-						IP_VERSION(9, 4, 2) ||
-					amdgpu_ip_version(adev, GC_HWIP, 0) ==
-						IP_VERSION(9, 4, 3) ||
-					amdgpu_ip_version(adev, GC_HWIP, 0) ==
-						IP_VERSION(9, 4, 4) ||
-					amdgpu_ip_version(adev, GC_HWIP, 0) ==
-						IP_VERSION(9, 5, 0));
+					gfxhub_v1_2_per_process_xnack_support(
+						adev));
 			WREG32_SOC15_OFFSET(GC, GET_INST(GC, j), regVM_CONTEXT1_CNTL,
 					    i * hub->ctx_distance, tmp);
 			WREG32_SOC15_OFFSET(GC, GET_INST(GC, j),
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index 17509f32f61a..deb95fab02df 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -505,42 +505,6 @@ static void gfxhub_v2_1_init(struct amdgpu_device *adev)
 	hub->vmhub_funcs = &gfxhub_v2_1_vmhub_funcs;
 }
 
-static int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev)
-{
-	u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmGCMC_VM_XGMI_LFB_CNTL);
-	u32 max_region =
-		REG_GET_FIELD(xgmi_lfb_cntl, GCMC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
-	u32 max_num_physical_nodes   = 0;
-	u32 max_physical_node_id     = 0;
-
-	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
-	case IP_VERSION(4, 8, 0):
-		max_num_physical_nodes   = 4;
-		max_physical_node_id     = 3;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* PF_MAX_REGION=0 means xgmi is disabled */
-	if (max_region) {
-		adev->gmc.xgmi.num_physical_nodes = max_region + 1;
-		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
-			return -EINVAL;
-
-		adev->gmc.xgmi.physical_node_id =
-			REG_GET_FIELD(xgmi_lfb_cntl, GCMC_VM_XGMI_LFB_CNTL, PF_LFB_REGION);
-		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
-			return -EINVAL;
-
-		adev->gmc.xgmi.node_segment_size = REG_GET_FIELD(
-			RREG32_SOC15(GC, 0, mmGCMC_VM_XGMI_LFB_SIZE),
-			GCMC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
-	}
-
-	return 0;
-}
-
 static void gfxhub_v2_1_utcl2_harvest(struct amdgpu_device *adev)
 {
 	int i;
@@ -696,7 +660,6 @@ const struct amdgpu_gfxhub_funcs gfxhub_v2_1_funcs = {
 	.gart_disable = gfxhub_v2_1_gart_disable,
 	.set_fault_enable_default = gfxhub_v2_1_set_fault_enable_default,
 	.init = gfxhub_v2_1_init,
-	.get_xgmi_info = gfxhub_v2_1_get_xgmi_info,
 	.utcl2_harvest = gfxhub_v2_1_utcl2_harvest,
 	.mode2_save_regs = gfxhub_v2_1_save_regs,
 	.mode2_restore_regs = gfxhub_v2_1_restore_regs,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 9bedca9a79c6..95d894a231fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1076,7 +1076,7 @@ static int gmc_v10_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v10_0_is_idle(void *handle)
+static bool gmc_v10_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* MC is always ready in GMC v10.*/
 	return true;
@@ -1115,9 +1115,9 @@ static int gmc_v10_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 		return athub_v2_0_set_clockgating(adev, state);
 }
 
-static void gmc_v10_0_get_clockgating_state(void *handle, u64 *flags)
+static void gmc_v10_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(10, 1, 3) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(10, 1, 4))
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 72751ab4c766..ad099f136f84 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -579,6 +579,7 @@ static void gmc_v11_0_set_mmhub_funcs(struct amdgpu_device *adev)
 		break;
 	case IP_VERSION(3, 3, 0):
 	case IP_VERSION(3, 3, 1):
+	case IP_VERSION(3, 3, 2):
 		adev->mmhub.funcs = &mmhub_v3_3_funcs;
 		break;
 	default:
@@ -596,6 +597,7 @@ static void gmc_v11_0_set_gfxhub_funcs(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		adev->gfxhub.funcs = &gfxhub_v11_5_0_funcs;
 		break;
 	default:
@@ -759,6 +761,7 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 5, 0):
 	case IP_VERSION(11, 5, 1):
 	case IP_VERSION(11, 5, 2):
+	case IP_VERSION(11, 5, 3):
 		set_bit(AMDGPU_GFXHUB(0), adev->vmhubs_mask);
 		set_bit(AMDGPU_MMHUB0(0), adev->vmhubs_mask);
 		/*
@@ -984,7 +987,7 @@ static int gmc_v11_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v11_0_is_idle(void *handle)
+static bool gmc_v11_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* MC is always ready in GMC v11.*/
 	return true;
@@ -1009,9 +1012,9 @@ static int gmc_v11_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return athub_v3_0_set_clockgating(adev, state);
 }
 
-static void gmc_v11_0_get_clockgating_state(void *handle, u64 *flags)
+static void gmc_v11_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	adev->mmhub.funcs->get_clockgating(adev, flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index c3c144a4f45e..05c026d0b0d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -967,7 +967,7 @@ static int gmc_v12_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v12_0_is_idle(void *handle)
+static bool gmc_v12_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* MC is always ready in GMC v11.*/
 	return true;
@@ -992,9 +992,9 @@ static int gmc_v12_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return athub_v4_1_0_set_clockgating(adev, state);
 }
 
-static void gmc_v12_0_get_clockgating_state(void *handle, u64 *flags)
+static void gmc_v12_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	adev->mmhub.funcs->get_clockgating(adev, flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 2245dda92021..a992e79d9581 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -957,9 +957,9 @@ static int gmc_v6_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v6_0_is_idle(void *handle)
+static bool gmc_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
@@ -976,7 +976,7 @@ static int gmc_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (gmc_v6_0_is_idle(adev))
+		if (gmc_v6_0_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 9aac4b1101e3..83e39f16044a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1142,9 +1142,9 @@ static int gmc_v7_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v7_0_is_idle(void *handle)
+static bool gmc_v7_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK |
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index d06585207c33..99ca08e9bdb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1263,9 +1263,9 @@ static int gmc_v8_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v8_0_is_idle(void *handle)
+static bool gmc_v8_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK |
@@ -1686,9 +1686,9 @@ static int gmc_v8_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gmc_v8_0_get_clockgating_state(void *handle, u64 *flags)
+static void gmc_v8_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 291549765c38..783e0c3b86b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -411,6 +411,11 @@ static const uint32_t ecc_umc_mcumc_ctrl_mask_addrs[] = {
 	(0x001d43e0 + 0x00001800),
 };
 
+static inline bool gmc_v9_0_is_multi_chiplet(struct amdgpu_device *adev)
+{
+	return !!adev->aid_mask;
+}
+
 static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev,
 		struct amdgpu_irq_src *src,
 		unsigned int type,
@@ -647,9 +652,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 		addr, entry->client_id,
 		soc15_ih_clientid_name[entry->client_id]);
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	if (gmc_v9_0_is_multi_chiplet(adev))
 		dev_err(adev->dev, "  cookie node_id %d fault from die %s%d%s\n",
 			node_id, node_id % 4 == 3 ? "RSV" : "AID", node_id / 4,
 			node_id % 4 == 1 ? ".XCD0" : node_id % 4 == 2 ? ".XCD1" : "");
@@ -798,9 +801,7 @@ static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev,
 				       uint32_t vmhub)
 {
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	    gmc_v9_0_is_multi_chiplet(adev))
 		return false;
 
 	return ((vmhub == AMDGPU_MMHUB0(0) ||
@@ -1278,9 +1279,8 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 	/* Only GFX 9.4.3 APUs associate GPUs with NUMA nodes. Local system
 	 * memory can use more efficient MTYPEs.
 	 */
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 3) &&
-	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 4) &&
-	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 5, 0))
+	if (!(adev->flags & AMD_IS_APU) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 3))
 		return;
 
 	/* Only direct-mapped memory allows us to determine the NUMA node from
@@ -1498,13 +1498,13 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 			adev->umc.channel_idx_tbl = &umc_v6_7_channel_idx_tbl_second[0][0];
 		break;
 	case IP_VERSION(12, 0, 0):
+	case IP_VERSION(12, 5, 0):
 		adev->umc.max_ras_err_cnt_per_query =
 			UMC_V12_0_TOTAL_CHANNEL_NUM(adev) * UMC_V12_0_BAD_PAGE_NUM_PER_CHANNEL;
 		adev->umc.channel_inst_num = UMC_V12_0_CHANNEL_INSTANCE_NUM;
 		adev->umc.umc_inst_num = UMC_V12_0_UMC_INSTANCE_NUM;
 		adev->umc.node_inst_num /= UMC_V12_0_UMC_INSTANCE_NUM;
 		adev->umc.channel_offs = UMC_V12_0_PER_CHANNEL_OFFSET;
-		adev->umc.active_mask = adev->aid_mask;
 		adev->umc.retire_unit = UMC_V12_0_BAD_PAGE_NUM_PER_CHANNEL;
 		if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu)
 			adev->umc.ras = &umc_v12_0_ras;
@@ -1524,6 +1524,7 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 		adev->mmhub.funcs = &mmhub_v1_7_funcs;
 		break;
 	case IP_VERSION(1, 8, 0):
+	case IP_VERSION(1, 8, 1):
 		adev->mmhub.funcs = &mmhub_v1_8_funcs;
 		break;
 	default:
@@ -1556,9 +1557,7 @@ static void gmc_v9_0_set_mmhub_ras_funcs(struct amdgpu_device *adev)
 
 static void gmc_v9_0_set_gfxhub_funcs(struct amdgpu_device *adev)
 {
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	if (gmc_v9_0_is_multi_chiplet(adev))
 		adev->gfxhub.funcs = &gfxhub_v1_2_funcs;
 	else
 		adev->gfxhub.funcs = &gfxhub_v1_0_funcs;
@@ -1595,23 +1594,38 @@ static void gmc_v9_0_set_xgmi_ras_funcs(struct amdgpu_device *adev)
 
 static void gmc_v9_0_init_nps_details(struct amdgpu_device *adev)
 {
+	enum amdgpu_memory_partition mode;
+	uint32_t supp_modes;
+	int i;
+
 	adev->gmc.supported_nps_modes = 0;
 
 	if (amdgpu_sriov_vf(adev) || (adev->flags & AMD_IS_APU))
 		return;
 
-	/*TODO: Check PSP version also which supports NPS switch. Otherwise keep
+	mode = gmc_v9_0_get_memory_partition(adev, &supp_modes);
+
+	/* Mode detected by hardware and supported modes available */
+	if ((mode != UNKNOWN_MEMORY_PARTITION_MODE) && supp_modes) {
+		while ((i = ffs(supp_modes))) {
+			if (AMDGPU_ALL_NPS_MASK & BIT(i))
+				adev->gmc.supported_nps_modes |= BIT(i);
+			supp_modes &= supp_modes - 1;
+		}
+	} else {
+		/*TODO: Check PSP version also which supports NPS switch. Otherwise keep
 	 * supported modes as 0.
 	 */
-	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-	case IP_VERSION(9, 4, 3):
-	case IP_VERSION(9, 4, 4):
-		adev->gmc.supported_nps_modes =
-			BIT(AMDGPU_NPS1_PARTITION_MODE) |
-			BIT(AMDGPU_NPS4_PARTITION_MODE);
-		break;
-	default:
-		break;
+		switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+		case IP_VERSION(9, 4, 3):
+		case IP_VERSION(9, 4, 4):
+			adev->gmc.supported_nps_modes =
+				BIT(AMDGPU_NPS1_PARTITION_MODE) |
+				BIT(AMDGPU_NPS4_PARTITION_MODE);
+			break;
+		default:
+			break;
+		}
 	}
 }
 
@@ -1625,9 +1639,7 @@ static int gmc_v9_0_early_init(struct amdgpu_ip_block *ip_block)
 	 */
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 0) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 1) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	    gmc_v9_0_is_multi_chiplet(adev))
 		adev->gmc.xgmi.supported = true;
 
 	if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(6, 1, 0)) {
@@ -1636,8 +1648,7 @@ static int gmc_v9_0_early_init(struct amdgpu_ip_block *ip_block)
 			adev->smuio.funcs->is_host_gpu_xgmi_supported(adev);
 	}
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) {
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) {
 		enum amdgpu_pkg_type pkg_type =
 			adev->smuio.funcs->get_pkg_type(adev);
 		/* On GFXIP 9.4.3. APU, there is no physical VRAM domain present
@@ -2078,9 +2089,7 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) {
+	if (gmc_v9_0_is_multi_chiplet(adev)) {
 		gmc_v9_4_3_init_vram_info(adev);
 	} else if (!adev->bios) {
 		if (adev->flags & AMD_IS_APU) {
@@ -2230,9 +2239,7 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	amdgpu_gmc_get_vbios_allocations(adev);
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) {
+	if (gmc_v9_0_is_multi_chiplet(adev)) {
 		r = gmc_v9_0_init_mem_ranges(adev);
 		if (r)
 			return r;
@@ -2261,9 +2268,7 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->vm_manager.first_kfd_vmid =
 		(amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 1) ||
 		 amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) ||
-		 amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-		 amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-		 amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) ?
+		 gmc_v9_0_is_multi_chiplet(adev)) ?
 			3 :
 			8;
 
@@ -2275,9 +2280,7 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	if (gmc_v9_0_is_multi_chiplet(adev))
 		amdgpu_gmc_sysfs_init(adev);
 
 	return 0;
@@ -2287,9 +2290,7 @@ static int gmc_v9_0_sw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+	if (gmc_v9_0_is_multi_chiplet(adev))
 		amdgpu_gmc_sysfs_fini(adev);
 
 	amdgpu_gmc_ras_fini(adev);
@@ -2541,7 +2542,7 @@ static int gmc_v9_0_resume(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-static bool gmc_v9_0_is_idle(void *handle)
+static bool gmc_v9_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* MC is always ready in GMC v9.*/
 	return true;
@@ -2571,9 +2572,9 @@ static int gmc_v9_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void gmc_v9_0_get_clockgating_state(void *handle, u64 *flags)
+static void gmc_v9_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	adev->mmhub.funcs->get_clockgating(adev, flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 194026e9be33..f1dc13b3ab38 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "hdp_v4_0.h"
 #include "amdgpu_ras.h"
 
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index d3962d469088..43195c079748 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "hdp_v5_0.h"
 
 #include "hdp/hdp_5_0_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index f52552c5fa27..fcb8dd2876bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "hdp_v5_2.h"
 
 #include "hdp/hdp_5_2_1_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
index 6948fe9956ce..a88d25a06c29 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "hdp_v6_0.h"
 
 #include "hdp/hdp_6_0_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
index 63820329f67e..49f7eb4fbd11 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "hdp_v7_0.h"
 
 #include "hdp/hdp_7_0_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index 8ac3d3282268..1317ede131b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -335,9 +335,9 @@ static int iceland_ih_resume(struct amdgpu_ip_block *ip_block)
 	return iceland_ih_hw_init(ip_block);
 }
 
-static bool iceland_ih_is_idle(void *handle)
+static bool iceland_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY))
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index f8a485164437..eb4185dcbd1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -652,7 +652,7 @@ static int ih_v6_0_resume(struct amdgpu_ip_block *ip_block)
 	return ih_v6_0_hw_init(ip_block);
 }
 
-static bool ih_v6_0_is_idle(void *handle)
+static bool ih_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
@@ -768,9 +768,9 @@ static int ih_v6_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void ih_v6_0_get_clockgating_state(void *handle, u64 *flags)
+static void ih_v6_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (!RREG32_SOC15(OSSSYS, 0, regIH_CLK_CTRL))
 		*flags |= AMD_CG_SUPPORT_IH_CG;
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index dd0042efceec..068ed849dbad 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -631,7 +631,7 @@ static int ih_v6_1_resume(struct amdgpu_ip_block *ip_block)
 	return ih_v6_1_hw_init(ip_block);
 }
 
-static bool ih_v6_1_is_idle(void *handle)
+static bool ih_v6_1_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
@@ -749,9 +749,9 @@ static int ih_v6_1_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void ih_v6_1_get_clockgating_state(void *handle, u64 *flags)
+static void ih_v6_1_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (!RREG32_SOC15(OSSSYS, 0, regIH_CLK_CTRL))
 		*flags |= AMD_CG_SUPPORT_IH_CG;
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
index 8f9b15c171f3..40a3530e0453 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
@@ -621,7 +621,7 @@ static int ih_v7_0_resume(struct amdgpu_ip_block *ip_block)
 	return ih_v7_0_hw_init(ip_block);
 }
 
-static bool ih_v7_0_is_idle(void *handle)
+static bool ih_v7_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
@@ -739,9 +739,9 @@ static int ih_v7_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void ih_v7_0_get_clockgating_state(void *handle, u64 *flags)
+static void ih_v7_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (!RREG32_SOC15(OSSSYS, 0, regIH_CLK_CTRL))
 		*flags |= AMD_CG_SUPPORT_IH_CG;
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index aeca5c08ea2f..cfa91d709d49 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -39,6 +39,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_1_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_imu.bin");
 
 static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c
index 964c29ef25dc..0027a639c7e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c
@@ -50,26 +50,29 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp)
 
 	isp_base = adev->rmmio_base;
 
-	isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL);
+	isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL);
 	if (!isp->isp_cell) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd cell alloc failed\n", __func__);
 		goto failure;
 	}
 
-	num_res = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES + MAX_ISP410_INT_SRC;
+	num_res = MAX_ISP410_MEM_RES + MAX_ISP410_INT_SRC;
 	isp->isp_res = kcalloc(num_res, sizeof(struct resource),
 			       GFP_KERNEL);
 	if (!isp->isp_res) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd res alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd res alloc failed\n", __func__);
 		goto failure;
 	}
 
 	isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL);
 	if (!isp->isp_pdata) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp platform data alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp platform data alloc failed\n", __func__);
 		goto failure;
 	}
 
@@ -88,14 +91,7 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp)
 	isp->isp_res[1].start = isp_base + ISP410_PHY0_OFFSET;
 	isp->isp_res[1].end = isp_base + ISP410_PHY0_OFFSET + ISP410_PHY0_SIZE;
 
-	isp->isp_res[2].name = "isp_gpio_sensor0_reg";
-	isp->isp_res[2].flags = IORESOURCE_MEM;
-	isp->isp_res[2].start = isp_base + ISP410_GPIO_SENSOR0_OFFSET;
-	isp->isp_res[2].end = isp_base + ISP410_GPIO_SENSOR0_OFFSET +
-			      ISP410_GPIO_SENSOR0_SIZE;
-
-	for (idx = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES, int_idx = 0;
-	     idx < num_res; idx++, int_idx++) {
+	for (idx = MAX_ISP410_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) {
 		isp->isp_res[idx].name = "isp_4_1_0_irq";
 		isp->isp_res[idx].flags = IORESOURCE_IRQ;
 		isp->isp_res[idx].start =
@@ -110,11 +106,12 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp)
 	isp->isp_cell[0].platform_data = isp->isp_pdata;
 	isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data);
 
-	isp->isp_i2c_res = kcalloc(1, sizeof(struct resource),
-				   GFP_KERNEL);
+	/* initialize isp i2c platform data */
+	isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL);
 	if (!isp->isp_i2c_res) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd res alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd res alloc failed\n", __func__);
 		goto failure;
 	}
 
@@ -129,9 +126,31 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp)
 	isp->isp_cell[1].platform_data = isp->isp_pdata;
 	isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data);
 
-	r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2);
+	/* initialize isp gpiochip platform data */
+	isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL);
+	if (!isp->isp_gpio_res) {
+		r = -ENOMEM;
+		drm_err(&adev->ddev,
+			"%s: isp gpio res alloc failed\n", __func__);
+		goto failure;
+	}
+
+	isp->isp_gpio_res[0].name = "isp_gpio_reg";
+	isp->isp_gpio_res[0].flags = IORESOURCE_MEM;
+	isp->isp_gpio_res[0].start = isp_base + ISP410_GPIO_SENSOR_OFFSET;
+	isp->isp_gpio_res[0].end = isp_base + ISP410_GPIO_SENSOR_OFFSET +
+				   ISP410_GPIO_SENSOR_SIZE;
+
+	isp->isp_cell[2].name = "amdisp-pinctrl";
+	isp->isp_cell[2].num_resources = 1;
+	isp->isp_cell[2].resources = &isp->isp_gpio_res[0];
+	isp->isp_cell[2].platform_data = isp->isp_pdata;
+	isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data);
+
+	r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3);
 	if (r) {
-		DRM_ERROR("%s: add mfd hotplug device failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: add mfd hotplug device failed\n", __func__);
 		goto failure;
 	}
 
@@ -143,6 +162,7 @@ failure:
 	kfree(isp->isp_res);
 	kfree(isp->isp_cell);
 	kfree(isp->isp_i2c_res);
+	kfree(isp->isp_gpio_res);
 
 	return r;
 }
@@ -155,6 +175,7 @@ static int isp_v4_1_0_hw_fini(struct amdgpu_isp *isp)
 	kfree(isp->isp_cell);
 	kfree(isp->isp_pdata);
 	kfree(isp->isp_i2c_res);
+	kfree(isp->isp_gpio_res);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h
index 7db24c0f1080..4d239198edd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h
@@ -42,8 +42,8 @@
 #define ISP410_I2C0_OFFSET 0x66400
 #define ISP410_I2C0_SIZE 0x100
 
-#define ISP410_GPIO_SENSOR0_OFFSET 0x6613C
-#define ISP410_GPIO_SENSOR0_SIZE 0x4
+#define ISP410_GPIO_SENSOR_OFFSET 0x6613C
+#define ISP410_GPIO_SENSOR_SIZE 0x54
 
 void isp_v4_1_0_set_isp_funcs(struct amdgpu_isp *isp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
index b56f27295468..69dd92f6e86d 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
@@ -50,27 +50,30 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp)
 
 	isp_base = adev->rmmio_base;
 
-	isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL);
+	isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL);
 	if (!isp->isp_cell) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd cell alloc failed\n", __func__);
 		goto failure;
 	}
 
-	num_res = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES + MAX_ISP411_INT_SRC;
+	num_res = MAX_ISP411_MEM_RES + MAX_ISP411_INT_SRC;
 
 	isp->isp_res = kcalloc(num_res, sizeof(struct resource),
 			       GFP_KERNEL);
 	if (!isp->isp_res) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd res alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd res alloc failed\n", __func__);
 		goto failure;
 	}
 
 	isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL);
 	if (!isp->isp_pdata) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp platform data alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp platform data alloc failed\n", __func__);
 		goto failure;
 	}
 
@@ -89,14 +92,7 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp)
 	isp->isp_res[1].start = isp_base + ISP411_PHY0_OFFSET;
 	isp->isp_res[1].end = isp_base + ISP411_PHY0_OFFSET + ISP411_PHY0_SIZE;
 
-	isp->isp_res[2].name = "isp_4_1_1_sensor0_reg";
-	isp->isp_res[2].flags = IORESOURCE_MEM;
-	isp->isp_res[2].start = isp_base + ISP411_GPIO_SENSOR0_OFFSET;
-	isp->isp_res[2].end = isp_base + ISP411_GPIO_SENSOR0_OFFSET +
-			      ISP411_GPIO_SENSOR0_SIZE;
-
-	for (idx = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES, int_idx = 0;
-	     idx < num_res; idx++, int_idx++) {
+	for (idx = MAX_ISP411_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) {
 		isp->isp_res[idx].name = "isp_4_1_1_irq";
 		isp->isp_res[idx].flags = IORESOURCE_IRQ;
 		isp->isp_res[idx].start =
@@ -111,10 +107,12 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp)
 	isp->isp_cell[0].platform_data = isp->isp_pdata;
 	isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data);
 
+	/* initialize isp i2c platform data */
 	isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL);
 	if (!isp->isp_i2c_res) {
 		r = -ENOMEM;
-		DRM_ERROR("%s: isp mfd res alloc failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: isp mfd res alloc failed\n", __func__);
 		goto failure;
 	}
 
@@ -129,9 +127,31 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp)
 	isp->isp_cell[1].platform_data = isp->isp_pdata;
 	isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data);
 
-	r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2);
+	/* initialize isp gpiochip platform data */
+	isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL);
+	if (!isp->isp_gpio_res) {
+		r = -ENOMEM;
+		drm_err(&adev->ddev,
+			"%s: isp gpio res alloc failed\n", __func__);
+		goto failure;
+	}
+
+	isp->isp_gpio_res[0].name = "isp_gpio_reg";
+	isp->isp_gpio_res[0].flags = IORESOURCE_MEM;
+	isp->isp_gpio_res[0].start = isp_base + ISP411_GPIO_SENSOR_OFFSET;
+	isp->isp_gpio_res[0].end = isp_base + ISP411_GPIO_SENSOR_OFFSET +
+				   ISP411_GPIO_SENSOR_SIZE;
+
+	isp->isp_cell[2].name = "amdisp-pinctrl";
+	isp->isp_cell[2].num_resources = 1;
+	isp->isp_cell[2].resources = &isp->isp_gpio_res[0];
+	isp->isp_cell[2].platform_data = isp->isp_pdata;
+	isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data);
+
+	r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3);
 	if (r) {
-		DRM_ERROR("%s: add mfd hotplug device failed\n", __func__);
+		drm_err(&adev->ddev,
+			"%s: add mfd hotplug device failed\n", __func__);
 		goto failure;
 	}
 
@@ -143,6 +163,7 @@ failure:
 	kfree(isp->isp_res);
 	kfree(isp->isp_cell);
 	kfree(isp->isp_i2c_res);
+	kfree(isp->isp_gpio_res);
 
 	return r;
 }
@@ -155,6 +176,7 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp)
 	kfree(isp->isp_cell);
 	kfree(isp->isp_pdata);
 	kfree(isp->isp_i2c_res);
+	kfree(isp->isp_gpio_res);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h
index 40887ddeb08c..fe45d70d87f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h
@@ -33,7 +33,6 @@
 #include "ivsrcid/isp/irqsrcs_isp_4_1.h"
 
 #define MAX_ISP411_MEM_RES 2
-#define MAX_ISP411_SENSOR_RES 1
 #define MAX_ISP411_INT_SRC 8
 
 #define ISP411_PHY0_OFFSET 0x66700
@@ -42,8 +41,8 @@
 #define ISP411_I2C0_OFFSET 0x66400
 #define ISP411_I2C0_SIZE 0x100
 
-#define ISP411_GPIO_SENSOR0_OFFSET 0x6613C
-#define ISP411_GPIO_SENSOR0_SIZE 0x4
+#define ISP411_GPIO_SENSOR_OFFSET 0x6613C
+#define ISP411_GPIO_SENSOR_SIZE 0x54
 
 void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
index 03b8b7cd5229..9e428e669ada 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -604,15 +604,15 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct	amdgpu_device *adev = ring->adev;
-	bool	set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+	bool	set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
 	int		cnt = 0;
 
-	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+	mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround);
 
 	if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec))
 		DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n");
 
-	for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) {
+	for (cnt = 0; cnt < adev->vcn.inst[0].num_enc_rings; cnt++) {
 		if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt]))
 			DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index 7c9251c03815..4cde8a8bcc83 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -33,6 +33,22 @@
 #include "vcn/vcn_2_0_0_sh_mask.h"
 #include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_2_0[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_UV_PITCH),
+};
+
 static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v2_0_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
@@ -98,7 +114,14 @@ static int jpeg_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->jpeg.internal.jpeg_pitch[0] = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
 	adev->jpeg.inst->external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
 
-	return 0;
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_2_0, ARRAY_SIZE(jpeg_reg_list_2_0));
+	if (r)
+		return r;
+
+	adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+
+	return r;
 }
 
 /**
@@ -117,6 +140,8 @@ static int jpeg_v2_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
@@ -655,9 +680,9 @@ void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count)
 	}
 }
 
-static bool jpeg_v2_0_is_idle(void *handle)
+static bool jpeg_v2_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return ((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) &
 		UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
@@ -682,7 +707,7 @@ static int jpeg_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	bool enable = (state == AMD_CG_STATE_GATE);
 
 	if (enable) {
-		if (!jpeg_v2_0_is_idle(adev))
+		if (!jpeg_v2_0_is_idle(ip_block))
 			return -EBUSY;
 		jpeg_v2_0_enable_clock_gating(adev);
 	} else {
@@ -739,6 +764,13 @@ static int jpeg_v2_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	jpeg_v2_0_stop(ring->adev);
+	jpeg_v2_0_start(ring->adev);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
 	.name = "jpeg_v2_0",
 	.early_init = jpeg_v2_0_early_init,
@@ -752,6 +784,8 @@ static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
 	.wait_for_idle = jpeg_v2_0_wait_for_idle,
 	.set_clockgating_state = jpeg_v2_0_set_clockgating_state,
 	.set_powergating_state = jpeg_v2_0_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
@@ -782,6 +816,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v2_0_ring_reset,
 };
 
 static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 11f6af2646e7..8b39e114f3be 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -36,6 +36,22 @@
 
 #define JPEG25_MAX_HW_INSTANCES_ARCTURUS			2
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_2_5[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_UV_PITCH),
+};
+
 static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
@@ -147,7 +163,14 @@ static int jpeg_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	return 0;
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_2_5, ARRAY_SIZE(jpeg_reg_list_2_5));
+	if (r)
+		return r;
+
+	adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+
+	return r;
 }
 
 /**
@@ -166,6 +189,8 @@ static int jpeg_v2_5_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
@@ -310,6 +335,44 @@ static void jpeg_v2_5_enable_clock_gating(struct amdgpu_device *adev, int inst)
 	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE, data);
 }
 
+static void jpeg_v2_5_start_inst(struct amdgpu_device *adev, int i)
+{
+	struct amdgpu_ring *ring = adev->jpeg.inst[i].ring_dec;
+	/* disable anti hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS), 0,
+		~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+
+	/* JPEG disable CGC */
+	jpeg_v2_5_disable_clock_gating(adev, i);
+
+	/* MJPEG global tiling registers */
+	WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
+		adev->gfx.config.gb_addr_config);
+	WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
+		adev->gfx.config.gb_addr_config);
+
+	/* enable JMI channel */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL), 0,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	/* enable System Interrupt for JRBC */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmJPEG_SYS_INT_EN),
+		JPEG_SYS_INT_EN__DJRBC_MASK,
+		~JPEG_SYS_INT_EN__DJRBC_MASK);
+
+	WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_VMID, 0);
+	WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+		upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_RPTR, 0);
+	WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR, 0);
+	WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+	WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
+	ring->wptr = RREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR);
+}
+
 /**
  * jpeg_v2_5_start - start JPEG block
  *
@@ -319,52 +382,33 @@ static void jpeg_v2_5_enable_clock_gating(struct amdgpu_device *adev, int inst)
  */
 static int jpeg_v2_5_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring;
 	int i;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
 			continue;
+		jpeg_v2_5_start_inst(adev, i);
 
-		ring = adev->jpeg.inst[i].ring_dec;
-		/* disable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS), 0,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-
-		/* JPEG disable CGC */
-		jpeg_v2_5_disable_clock_gating(adev, i);
-
-		/* MJPEG global tiling registers */
-		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* enable JMI channel */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL), 0,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		/* enable System Interrupt for JRBC */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmJPEG_SYS_INT_EN),
-			JPEG_SYS_INT_EN__DJRBC_MASK,
-			~JPEG_SYS_INT_EN__DJRBC_MASK);
-
-		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_VMID, 0);
-		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
-		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_RPTR, 0);
-		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR, 0);
-		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
-		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
-		ring->wptr = RREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR);
 	}
 
 	return 0;
 }
 
+static void jpeg_v2_5_stop_inst(struct amdgpu_device *adev, int i)
+{
+	/* reset JMI */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL),
+		UVD_JMI_CNTL__SOFT_RESET_MASK,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	jpeg_v2_5_enable_clock_gating(adev, i);
+
+	/* enable anti hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS),
+		UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
+		~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+}
+
 /**
  * jpeg_v2_5_stop - stop JPEG block
  *
@@ -379,18 +423,7 @@ static int jpeg_v2_5_stop(struct amdgpu_device *adev)
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
 			continue;
-
-		/* reset JMI */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL),
-			UVD_JMI_CNTL__SOFT_RESET_MASK,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		jpeg_v2_5_enable_clock_gating(adev, i);
-
-		/* enable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS),
-			UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+		jpeg_v2_5_stop_inst(adev, i);
 	}
 
 	return 0;
@@ -482,9 +515,9 @@ static void jpeg_v2_6_dec_ring_insert_end(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, (1 << (ring->me * 2 + 14)));
 }
 
-static bool jpeg_v2_5_is_idle(void *handle)
+static bool jpeg_v2_5_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
@@ -530,7 +563,7 @@ static int jpeg_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 			continue;
 
 		if (enable) {
-			if (!jpeg_v2_5_is_idle(adev))
+			if (!jpeg_v2_5_is_idle(ip_block))
 				return -EBUSY;
 			jpeg_v2_5_enable_clock_gating(adev, i);
 		} else {
@@ -610,6 +643,13 @@ static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	jpeg_v2_5_stop_inst(ring->adev, ring->me);
+	jpeg_v2_5_start_inst(ring->adev, ring->me);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
 	.name = "jpeg_v2_5",
 	.early_init = jpeg_v2_5_early_init,
@@ -623,6 +663,8 @@ static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
 	.wait_for_idle = jpeg_v2_5_wait_for_idle,
 	.set_clockgating_state = jpeg_v2_5_set_clockgating_state,
 	.set_powergating_state = jpeg_v2_5_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = {
@@ -638,6 +680,8 @@ static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = {
 	.wait_for_idle = jpeg_v2_5_wait_for_idle,
 	.set_clockgating_state = jpeg_v2_5_set_clockgating_state,
 	.set_powergating_state = jpeg_v2_5_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
@@ -668,6 +712,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v2_5_ring_reset,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = {
@@ -698,6 +743,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v2_5_ring_reset,
 };
 
 static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index 4eca65ea9053..2f8510c2986b 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -34,6 +34,22 @@
 
 #define mmUVD_JPEG_PITCH_INTERNAL_OFFSET	0x401f
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_3_0[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, mmUVD_JPEG_UV_PITCH),
+};
+
 static void jpeg_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v3_0_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
@@ -112,7 +128,14 @@ static int jpeg_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->jpeg.internal.jpeg_pitch[0] = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
 	adev->jpeg.inst->external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
 
-	return 0;
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_3_0, ARRAY_SIZE(jpeg_reg_list_3_0));
+	if (r)
+		return r;
+
+	adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+
+	return r;
 }
 
 /**
@@ -131,6 +154,8 @@ static int jpeg_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
@@ -445,9 +470,9 @@ static void jpeg_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static bool jpeg_v3_0_is_idle(void *handle)
+static bool jpeg_v3_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int ret = 1;
 
 	ret &= (((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) &
@@ -473,7 +498,7 @@ static int jpeg_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	bool enable = state == AMD_CG_STATE_GATE;
 
 	if (enable) {
-		if (!jpeg_v3_0_is_idle(adev))
+		if (!jpeg_v3_0_is_idle(ip_block))
 			return -EBUSY;
 		jpeg_v3_0_enable_clock_gating(adev);
 	} else {
@@ -530,6 +555,13 @@ static int jpeg_v3_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	jpeg_v3_0_stop(ring->adev);
+	jpeg_v3_0_start(ring->adev);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = {
 	.name = "jpeg_v3_0",
 	.early_init = jpeg_v3_0_early_init,
@@ -543,6 +575,8 @@ static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = {
 	.wait_for_idle = jpeg_v3_0_wait_for_idle,
 	.set_clockgating_state = jpeg_v3_0_set_clockgating_state,
 	.set_powergating_state = jpeg_v3_0_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = {
@@ -573,6 +607,7 @@ static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v3_0_ring_reset,
 };
 
 static void jpeg_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index 0aef1f64afd0..f17ec5414fd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -36,13 +36,28 @@
 
 #define regUVD_JPEG_PITCH_INTERNAL_OFFSET                  0x401f
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_4_0[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_UV_PITCH),
+};
+
 static int jpeg_v4_0_start_sriov(struct amdgpu_device *adev);
 static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v4_0_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 				enum amd_powergating_state state);
 static void jpeg_v4_0_set_ras_funcs(struct amdgpu_device *adev);
-
 static void jpeg_v4_0_dec_ring_set_wptr(struct amdgpu_ring *ring);
 
 /**
@@ -123,14 +138,15 @@ static int jpeg_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 	r = amdgpu_jpeg_ras_sw_init(adev);
 	if (r)
 		return r;
-	/* TODO: Add queue reset mask when FW fully supports it */
-	adev->jpeg.supported_reset =
-		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
-	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_4_0, ARRAY_SIZE(jpeg_reg_list_4_0));
 	if (r)
 		return r;
 
-	return 0;
+	adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+
+	return r;
 }
 
 /**
@@ -614,9 +630,9 @@ static void jpeg_v4_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static bool jpeg_v4_0_is_idle(void *handle)
+static bool jpeg_v4_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int ret = 1;
 
 	ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) &
@@ -642,7 +658,7 @@ static int jpeg_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	bool enable = state == AMD_CG_STATE_GATE;
 
 	if (enable) {
-		if (!jpeg_v4_0_is_idle(adev))
+		if (!jpeg_v4_0_is_idle(ip_block))
 			return -EBUSY;
 		jpeg_v4_0_enable_clock_gating(adev);
 	} else {
@@ -704,6 +720,16 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	if (amdgpu_sriov_vf(ring->adev))
+		return -EINVAL;
+
+	jpeg_v4_0_stop(ring->adev);
+	jpeg_v4_0_start(ring->adev);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = {
 	.name = "jpeg_v4_0",
 	.early_init = jpeg_v4_0_early_init,
@@ -717,6 +743,8 @@ static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = {
 	.wait_for_idle = jpeg_v4_0_wait_for_idle,
 	.set_clockgating_state = jpeg_v4_0_set_clockgating_state,
 	.set_powergating_state = jpeg_v4_0_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = {
@@ -747,6 +775,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v4_0_ring_reset,
 };
 
 static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 88f9771c1686..5598a35f72af 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -59,10 +59,53 @@ static int amdgpu_ih_srcid_jpeg[] = {
 	VCN_4_0__SRCID__JPEG7_DECODE
 };
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_4_0_3[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_SYS_INT_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_UV_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_STATUS),
+};
+
 static inline bool jpeg_v4_0_3_normalizn_reqd(struct amdgpu_device *adev)
 {
-	return amdgpu_sriov_vf(adev) ||
-	       (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4));
+	return (adev->jpeg.caps & AMDGPU_JPEG_CAPS(RRMT_ENABLED)) == 0;
+}
+
+static inline int jpeg_v4_0_3_core_reg_offset(u32 pipe)
+{
+	if (pipe)
+		return ((0x40 * pipe) - 0xc80);
+	else
+		return 0;
 }
 
 /**
@@ -144,10 +187,8 @@ static int jpeg_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 			adev->jpeg.internal.jpeg_pitch[j] =
 				regUVD_JRBC0_UVD_JRBC_SCRATCH0_INTERNAL_OFFSET;
 			adev->jpeg.inst[i].external.jpeg_pitch[j] =
-				SOC15_REG_OFFSET1(
-					JPEG, jpeg_inst,
-					regUVD_JRBC0_UVD_JRBC_SCRATCH0,
-					(j ? (0x40 * j - 0xc80) : 0));
+				SOC15_REG_OFFSET1(JPEG, jpeg_inst, regUVD_JRBC0_UVD_JRBC_SCRATCH0,
+						  jpeg_v4_0_3_core_reg_offset(j));
 		}
 	}
 
@@ -159,13 +200,17 @@ static int jpeg_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
-	/* TODO: Add queue reset mask when FW fully supports it */
-	adev->jpeg.supported_reset =
-		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
-	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_4_0_3, ARRAY_SIZE(jpeg_reg_list_4_0_3));
 	if (r)
 		return r;
 
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+		r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -185,7 +230,9 @@ static int jpeg_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+	if (!amdgpu_sriov_vf(adev))
+		amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
@@ -331,6 +378,11 @@ static int jpeg_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
 			}
 		}
 	} else {
+		/* This flag is not set for VF, assumed to be disabled always */
+		if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) &
+		    0x100)
+			adev->jpeg.caps |= AMDGPU_JPEG_CAPS(RRMT_ENABLED);
+
 		for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 			jpeg_inst = GET_INST(JPEG, i);
 
@@ -475,6 +527,75 @@ static void jpeg_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst
 	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CGC_GATE, data);
 }
 
+static void jpeg_v4_0_3_start_inst(struct amdgpu_device *adev, int inst)
+{
+	int jpeg_inst = GET_INST(JPEG, inst);
+
+	WREG32_SOC15(JPEG, jpeg_inst, regUVD_PGFSM_CONFIG,
+		     1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT);
+	SOC15_WAIT_ON_RREG(JPEG, jpeg_inst, regUVD_PGFSM_STATUS,
+			   UVD_PGFSM_STATUS__UVDJ_PWR_ON <<
+			   UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT,
+			   UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK);
+
+	/* disable anti hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS),
+		 0, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+
+	/* JPEG disable CGC */
+	jpeg_v4_0_3_disable_clock_gating(adev, inst);
+
+	/* MJPEG global tiling registers */
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_DEC_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_DEC_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* enable JMI channel */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0,
+		 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
+}
+
+static void jpeg_v4_0_3_start_jrbc(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	int jpeg_inst = GET_INST(JPEG, ring->me);
+	int reg_offset = jpeg_v4_0_3_core_reg_offset(ring->pipe);
+
+	/* enable System Interrupt for JRBC */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN),
+		 JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe,
+		 ~(JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe));
+
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_LMI_JRBC_RB_VMID,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC0_UVD_JRBC_RB_CNTL,
+			    reg_offset,
+			    (0x00000001L | 0x00000002L));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+			    reg_offset, lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+			    reg_offset, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC0_UVD_JRBC_RB_RPTR,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC0_UVD_JRBC_RB_WPTR,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC0_UVD_JRBC_RB_CNTL,
+			    reg_offset, 0x00000002L);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC0_UVD_JRBC_RB_SIZE,
+			    reg_offset, ring->ring_size / 4);
+	ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC0_UVD_JRBC_RB_WPTR,
+					 reg_offset);
+}
+
 /**
  * jpeg_v4_0_3_start - start JPEG block
  *
@@ -485,84 +606,36 @@ static void jpeg_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst
 static int jpeg_v4_0_3_start(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	int i, j, jpeg_inst;
+	int i, j;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		jpeg_inst = GET_INST(JPEG, i);
-
-		WREG32_SOC15(JPEG, jpeg_inst, regUVD_PGFSM_CONFIG,
-			     1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT);
-		SOC15_WAIT_ON_RREG(
-			JPEG, jpeg_inst, regUVD_PGFSM_STATUS,
-			UVD_PGFSM_STATUS__UVDJ_PWR_ON
-				<< UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT,
-			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK);
-
-		/* disable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst,
-					  regUVD_JPEG_POWER_STATUS),
-			 0, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-
-		/* JPEG disable CGC */
-		jpeg_v4_0_3_disable_clock_gating(adev, i);
-
-		/* MJPEG global tiling registers */
-		WREG32_SOC15(JPEG, jpeg_inst, regJPEG_DEC_GFX8_ADDR_CONFIG,
-			     adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(JPEG, jpeg_inst, regJPEG_DEC_GFX10_ADDR_CONFIG,
-			     adev->gfx.config.gb_addr_config);
-
-		/* enable JMI channel */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0,
-			 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
+		jpeg_v4_0_3_start_inst(adev, i);
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
-			unsigned int reg_offset = (j?(0x40 * j - 0xc80):0);
-
 			ring = &adev->jpeg.inst[i].ring_dec[j];
-
-			/* enable System Interrupt for JRBC */
-			WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst,
-						  regJPEG_SYS_INT_EN),
-				 JPEG_SYS_INT_EN__DJRBC0_MASK << j,
-				 ~(JPEG_SYS_INT_EN__DJRBC0_MASK << j));
-
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JMI0_UVD_LMI_JRBC_RB_VMID,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC0_UVD_JRBC_RB_CNTL,
-					    reg_offset,
-					    (0x00000001L | 0x00000002L));
-			WREG32_SOC15_OFFSET(
-				JPEG, jpeg_inst,
-				regUVD_JMI0_UVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-				reg_offset, lower_32_bits(ring->gpu_addr));
-			WREG32_SOC15_OFFSET(
-				JPEG, jpeg_inst,
-				regUVD_JMI0_UVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-				reg_offset, upper_32_bits(ring->gpu_addr));
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC0_UVD_JRBC_RB_RPTR,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC0_UVD_JRBC_RB_WPTR,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC0_UVD_JRBC_RB_CNTL,
-					    reg_offset, 0x00000002L);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC0_UVD_JRBC_RB_SIZE,
-					    reg_offset, ring->ring_size / 4);
-			ring->wptr = RREG32_SOC15_OFFSET(
-				JPEG, jpeg_inst, regUVD_JRBC0_UVD_JRBC_RB_WPTR,
-				reg_offset);
+			jpeg_v4_0_3_start_jrbc(ring);
 		}
 	}
 
 	return 0;
 }
 
+static void jpeg_v4_0_3_stop_inst(struct amdgpu_device *adev, int inst)
+{
+	int jpeg_inst = GET_INST(JPEG, inst);
+	/* reset JMI */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL),
+		 UVD_JMI_CNTL__SOFT_RESET_MASK,
+		 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	jpeg_v4_0_3_enable_clock_gating(adev, inst);
+
+	/* enable anti hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS),
+		 UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
+		 ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+
+}
+
 /**
  * jpeg_v4_0_3_stop - stop JPEG block
  *
@@ -572,31 +645,10 @@ static int jpeg_v4_0_3_start(struct amdgpu_device *adev)
  */
 static int jpeg_v4_0_3_stop(struct amdgpu_device *adev)
 {
-	int i, jpeg_inst;
+	int i;
 
-	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		jpeg_inst = GET_INST(JPEG, i);
-		/* reset JMI */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL),
-			 UVD_JMI_CNTL__SOFT_RESET_MASK,
-			 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		jpeg_v4_0_3_enable_clock_gating(adev, i);
-
-		/* enable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst,
-					  regUVD_JPEG_POWER_STATUS),
-			 UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
-			 ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-
-		WREG32_SOC15(JPEG, jpeg_inst, regUVD_PGFSM_CONFIG,
-			     2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT);
-		SOC15_WAIT_ON_RREG(
-			JPEG, jpeg_inst, regUVD_PGFSM_STATUS,
-			UVD_PGFSM_STATUS__UVDJ_PWR_OFF
-				<< UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT,
-			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK);
-	}
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i)
+		jpeg_v4_0_3_stop_inst(adev, i);
 
 	return 0;
 }
@@ -612,9 +664,8 @@ static uint64_t jpeg_v4_0_3_dec_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	return RREG32_SOC15_OFFSET(
-		JPEG, GET_INST(JPEG, ring->me), regUVD_JRBC0_UVD_JRBC_RB_RPTR,
-		ring->pipe ? (0x40 * ring->pipe - 0xc80) : 0);
+	return RREG32_SOC15_OFFSET(JPEG, GET_INST(JPEG, ring->me), regUVD_JRBC0_UVD_JRBC_RB_RPTR,
+				   jpeg_v4_0_3_core_reg_offset(ring->pipe));
 }
 
 /**
@@ -630,14 +681,12 @@ static uint64_t jpeg_v4_0_3_dec_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell)
 		return adev->wb.wb[ring->wptr_offs];
-	else
-		return RREG32_SOC15_OFFSET(
-			JPEG, GET_INST(JPEG, ring->me),
-			regUVD_JRBC0_UVD_JRBC_RB_WPTR,
-			ring->pipe ? (0x40 * ring->pipe - 0xc80) : 0);
+
+	return RREG32_SOC15_OFFSET(JPEG, GET_INST(JPEG, ring->me), regUVD_JRBC0_UVD_JRBC_RB_WPTR,
+				   jpeg_v4_0_3_core_reg_offset(ring->pipe));
 }
 
-static void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	/* JPEG engine access for HDP flush doesn't work when RRMT is enabled.
 	 * This is a workaround to avoid any HDP flush through JPEG ring.
@@ -659,10 +708,8 @@ static void jpeg_v4_0_3_dec_ring_set_wptr(struct amdgpu_ring *ring)
 		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
-		WREG32_SOC15_OFFSET(JPEG, GET_INST(JPEG, ring->me),
-				    regUVD_JRBC0_UVD_JRBC_RB_WPTR,
-				    (ring->pipe ? (0x40 * ring->pipe - 0xc80) :
-						  0),
+		WREG32_SOC15_OFFSET(JPEG, GET_INST(JPEG, ring->me), regUVD_JRBC0_UVD_JRBC_RB_WPTR,
+				    jpeg_v4_0_3_core_reg_offset(ring->pipe),
 				    lower_32_bits(ring->wptr));
 	}
 }
@@ -907,21 +954,17 @@ void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count)
 	}
 }
 
-static bool jpeg_v4_0_3_is_idle(void *handle)
+static bool jpeg_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	bool ret = false;
 	int i, j;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
-			unsigned int reg_offset = (j?(0x40 * j - 0xc80):0);
-
-			ret &= ((RREG32_SOC15_OFFSET(
-					 JPEG, GET_INST(JPEG, i),
-					 regUVD_JRBC0_UVD_JRBC_STATUS,
-					 reg_offset) &
-				 UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+			ret &= ((RREG32_SOC15_OFFSET(JPEG, GET_INST(JPEG, i),
+				regUVD_JRBC0_UVD_JRBC_STATUS, jpeg_v4_0_3_core_reg_offset(j)) &
+				UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
 				UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
 		}
 	}
@@ -937,13 +980,10 @@ static int jpeg_v4_0_3_wait_for_idle(struct amdgpu_ip_block *ip_block)
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
-			unsigned int reg_offset = (j?(0x40 * j - 0xc80):0);
-
-			ret &= SOC15_WAIT_ON_RREG_OFFSET(
-				JPEG, GET_INST(JPEG, i),
-				regUVD_JRBC0_UVD_JRBC_STATUS, reg_offset,
+			ret &= (SOC15_WAIT_ON_RREG_OFFSET(JPEG, GET_INST(JPEG, i),
+				regUVD_JRBC0_UVD_JRBC_STATUS, jpeg_v4_0_3_core_reg_offset(j),
 				UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
-				UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
+				UVD_JRBC0_UVD_JRBC_STATUS__RB_JOB_DONE_MASK));
 		}
 	}
 	return ret;
@@ -958,7 +998,7 @@ static int jpeg_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (enable) {
-			if (!jpeg_v4_0_3_is_idle(adev))
+			if (!jpeg_v4_0_3_is_idle(ip_block))
 				return -EBUSY;
 			jpeg_v4_0_3_enable_clock_gating(adev, i);
 		} else {
@@ -1055,6 +1095,41 @@ static int jpeg_v4_0_3_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void jpeg_v4_0_3_core_stall_reset(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	int jpeg_inst = GET_INST(JPEG, ring->me);
+	int reg_offset = jpeg_v4_0_3_core_reg_offset(ring->pipe);
+
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_JMI_CLIENT_STALL,
+			    reg_offset, 0x1F);
+	SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst,
+				  regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS,
+				  reg_offset, 0x1F, 0x1F);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_JPEG_LMI_DROP,
+			    reg_offset, 0x1F);
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_JMI_CLIENT_STALL,
+			    reg_offset, 0x00);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_JPEG_LMI_DROP,
+			    reg_offset, 0x00);
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00);
+}
+
+static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	if (amdgpu_sriov_vf(ring->adev))
+		return -EOPNOTSUPP;
+
+	jpeg_v4_0_3_core_stall_reset(ring);
+	jpeg_v4_0_3_start_jrbc(ring);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = {
 	.name = "jpeg_v4_0_3",
 	.early_init = jpeg_v4_0_3_early_init,
@@ -1068,6 +1143,8 @@ static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = {
 	.wait_for_idle = jpeg_v4_0_3_wait_for_idle,
 	.set_clockgating_state = jpeg_v4_0_3_set_clockgating_state,
 	.set_powergating_state = jpeg_v4_0_3_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
@@ -1099,6 +1176,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v4_0_3_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v4_0_3_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v4_0_3_ring_reset,
 };
 
 static void jpeg_v4_0_3_set_dec_ring_funcs(struct amdgpu_device *adev)
@@ -1245,11 +1323,13 @@ static int jpeg_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_ban
 	misc0 = bank->regs[ACA_REG_IDX_MISC0];
 	switch (type) {
 	case ACA_SMU_TYPE_UE:
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
 		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE,
 						     1ULL);
 		break;
 	case ACA_SMU_TYPE_CE:
-		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE,
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type,
 						     ACA_REG__MISC0__ERRCNT(misc0));
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
index 747a3e5f6856..a90bf370a002 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
@@ -56,6 +56,7 @@ void jpeg_v4_0_3_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 				unsigned int flags);
 void jpeg_v4_0_3_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned int vmid, uint64_t pd_addr);
+void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring);
 void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count);
 void jpeg_v4_0_3_dec_ring_insert_start(struct amdgpu_ring *ring);
 void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6b3656984957..974030a5c03c 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -46,11 +46,26 @@
 #define regJPEG_CGC_GATE_INTERNAL_OFFSET		0x4160
 #define regUVD_NO_OP_INTERNAL_OFFSET			0x0029
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_4_0_5[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_UV_PITCH),
+};
+
 static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v4_0_5_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
 				enum amd_powergating_state state);
-
 static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring);
 
 static int amdgpu_ih_clientid_jpeg[] = {
@@ -58,6 +73,8 @@ static int amdgpu_ih_clientid_jpeg[] = {
 	SOC15_IH_CLIENTID_VCN1
 };
 
+
+
 /**
  * jpeg_v4_0_5_early_init - set function pointers
  *
@@ -153,6 +170,10 @@ static int jpeg_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->jpeg.inst[i].external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, i, regUVD_JPEG_PITCH);
 	}
 
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_4_0_5, ARRAY_SIZE(jpeg_reg_list_4_0_5));
+	if (r)
+		return r;
+
 	/* TODO: Add queue reset mask when FW fully supports it */
 	adev->jpeg.supported_reset =
 		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
@@ -627,9 +648,9 @@ static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static bool jpeg_v4_0_5_is_idle(void *handle)
+static bool jpeg_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
@@ -672,7 +693,7 @@ static int jpeg_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 			continue;
 
 		if (enable) {
-			if (!jpeg_v4_0_5_is_idle(adev))
+			if (!jpeg_v4_0_5_is_idle(ip_block))
 				return -EBUSY;
 
 			jpeg_v4_0_5_enable_clock_gating(adev, i);
@@ -759,6 +780,8 @@ static const struct amd_ip_funcs jpeg_v4_0_5_ip_funcs = {
 	.wait_for_idle = jpeg_v4_0_5_wait_for_idle,
 	.set_clockgating_state = jpeg_v4_0_5_set_clockgating_state,
 	.set_powergating_state = jpeg_v4_0_5_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
index d5cf0f2799d4..31d213ccbe0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
@@ -34,6 +34,22 @@
 #include "ivsrcid/vcn/irqsrcs_vcn_5_0.h"
 #include "jpeg_v5_0_0.h"
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_5_0[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_CNTL),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_RB_SIZE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_UV_PITCH),
+};
+
 static void jpeg_v5_0_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v5_0_0_set_irq_funcs(struct amdgpu_device *adev);
 static int jpeg_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
@@ -100,6 +116,10 @@ static int jpeg_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->jpeg.internal.jpeg_pitch[0] = regUVD_JPEG_PITCH_INTERNAL_OFFSET;
 	adev->jpeg.inst->external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, 0, regUVD_JPEG_PITCH);
 
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_5_0, ARRAY_SIZE(jpeg_reg_list_5_0));
+	if (r)
+		return r;
+
 	/* TODO: Add queue reset mask when FW fully supports it */
 	adev->jpeg.supported_reset =
 		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
@@ -539,9 +559,9 @@ static void jpeg_v5_0_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static bool jpeg_v5_0_0_is_idle(void *handle)
+static bool jpeg_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int ret = 1;
 
 	ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) &
@@ -567,7 +587,7 @@ static int jpeg_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
 	if (enable) {
-		if (!jpeg_v5_0_0_is_idle(adev))
+		if (!jpeg_v5_0_0_is_idle(ip_block))
 			return -EBUSY;
 		jpeg_v5_0_0_enable_clock_gating(adev);
 	} else {
@@ -637,6 +657,8 @@ static const struct amd_ip_funcs jpeg_v5_0_0_ip_funcs = {
 	.wait_for_idle = jpeg_v5_0_0_wait_for_idle,
 	.set_clockgating_state = jpeg_v5_0_0_set_clockgating_state,
 	.set_powergating_state = jpeg_v5_0_0_set_powergating_state,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 40d4c32a8c2a..218e16b68f1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -52,6 +52,47 @@ static int amdgpu_ih_srcid_jpeg[] = {
 	VCN_5_0__SRCID__JPEG9_DECODE,
 };
 
+static const struct amdgpu_hwip_reg_entry jpeg_reg_list_5_0_1[] = {
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_INT_STAT),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC0_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_ADDR_MODE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_Y_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regJPEG_DEC_UV_GFX10_TILING_SURFACE),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JPEG_UV_PITCH),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC1_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC2_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC3_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC4_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC5_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC6_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC7_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC8_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC8_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC8_UVD_JRBC_STATUS),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC9_UVD_JRBC_RB_RPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC9_UVD_JRBC_RB_WPTR),
+	SOC15_REG_ENTRY_STR(JPEG, 0, regUVD_JRBC9_UVD_JRBC_STATUS),
+};
+
 static int jpeg_v5_0_1_core_reg_offset(u32 pipe)
 {
 	if (pipe <= AMDGPU_MAX_JPEG_RINGS_4_0_3)
@@ -145,6 +186,17 @@ static int jpeg_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_5_0_1, ARRAY_SIZE(jpeg_reg_list_5_0_1));
+	if (r)
+		return r;
+
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+		r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -164,6 +216,9 @@ static int jpeg_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	if (!amdgpu_sriov_vf(adev))
+		amdgpu_jpeg_sysfs_reset_mask_fini(adev);
+
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
@@ -194,6 +249,9 @@ static int jpeg_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 		}
 		return 0;
 	}
+	if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100)
+		adev->jpeg.caps |= AMDGPU_JPEG_CAPS(RRMT_ENABLED);
+
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		jpeg_inst = GET_INST(JPEG, i);
 		ring = adev->jpeg.inst[i].ring_dec;
@@ -281,11 +339,10 @@ static int jpeg_v5_0_1_resume(struct amdgpu_ip_block *ip_block)
 	return r;
 }
 
-static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx)
+static void jpeg_v5_0_1_init_inst(struct amdgpu_device *adev, int i)
 {
-	int jpeg_inst;
+	int jpeg_inst = GET_INST(JPEG, i);
 
-	jpeg_inst = GET_INST(JPEG, inst_idx);
 	/* disable anti hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0,
 		 ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
@@ -294,20 +351,75 @@ static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx
 	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0,
 		 ~UVD_JPEG_POWER_STATUS__JPEG_PG_MODE_MASK);
 
-	return 0;
+	/* MJPEG global tiling registers */
+	WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* enable JMI channel */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0,
+		 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
 }
 
-static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx)
+static void jpeg_v5_0_1_deinit_inst(struct amdgpu_device *adev, int i)
 {
-	int jpeg_inst;
+	int jpeg_inst = GET_INST(JPEG, i);
+	/* reset JMI */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL),
+		 UVD_JMI_CNTL__SOFT_RESET_MASK,
+		 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
 
-	jpeg_inst = GET_INST(JPEG, inst_idx);
 	/* enable anti hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS),
 		 UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
-		~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+		 ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+}
 
-	return 0;
+static void jpeg_v5_0_1_init_jrbc(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	u32 reg, data, mask;
+	int jpeg_inst = GET_INST(JPEG, ring->me);
+	int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0;
+
+	/* enable System Interrupt for JRBC */
+	reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN);
+	if (ring->pipe < AMDGPU_MAX_JPEG_RINGS_4_0_3) {
+		data = JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe;
+		mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe);
+		WREG32_P(reg, data, mask);
+	} else {
+		data = JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12);
+		mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12));
+		WREG32_P(reg, data, mask);
+	}
+
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_LMI_JRBC_RB_VMID,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC_RB_CNTL,
+			    reg_offset,
+			    (0x00000001L | 0x00000002L));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+			    reg_offset, lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+			    reg_offset, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC_RB_RPTR,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC_RB_WPTR,
+			    reg_offset, 0);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC_RB_CNTL,
+			    reg_offset, 0x00000002L);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JRBC_RB_SIZE,
+			    reg_offset, ring->ring_size / 4);
+	ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR,
+					 reg_offset);
 }
 
 /**
@@ -320,69 +432,13 @@ static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx)
 static int jpeg_v5_0_1_start(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	int i, j, jpeg_inst, r;
+	int i, j;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		jpeg_inst = GET_INST(JPEG, i);
-
-		/* disable antihang */
-		r = jpeg_v5_0_1_disable_antihang(adev, i);
-		if (r)
-			return r;
-
-		/* MJPEG global tiling registers */
-		WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG,
-			     adev->gfx.config.gb_addr_config);
-
-		/* enable JMI channel */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0,
-			 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
+		jpeg_v5_0_1_init_inst(adev, i);
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
-			int reg_offset = (j ? jpeg_v5_0_1_core_reg_offset(j) : 0);
-			u32 reg, data, mask;
-
 			ring = &adev->jpeg.inst[i].ring_dec[j];
-
-			/* enable System Interrupt for JRBC */
-			reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN);
-			if (j < AMDGPU_MAX_JPEG_RINGS_4_0_3) {
-				data = JPEG_SYS_INT_EN__DJRBC0_MASK << j;
-				mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << j);
-				WREG32_P(reg, data, mask);
-			} else {
-				data = JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12);
-				mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12));
-				WREG32_P(reg, data, mask);
-			}
-
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_LMI_JRBC_RB_VMID,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC_RB_CNTL,
-					    reg_offset,
-					    (0x00000001L | 0x00000002L));
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-					    reg_offset, lower_32_bits(ring->gpu_addr));
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-					    reg_offset, upper_32_bits(ring->gpu_addr));
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC_RB_RPTR,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC_RB_WPTR,
-					    reg_offset, 0);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC_RB_CNTL,
-					    reg_offset, 0x00000002L);
-			WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
-					    regUVD_JRBC_RB_SIZE,
-					    reg_offset, ring->ring_size / 4);
-			ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR,
-							 reg_offset);
+			jpeg_v5_0_1_init_jrbc(ring);
 		}
 	}
 
@@ -398,20 +454,10 @@ static int jpeg_v5_0_1_start(struct amdgpu_device *adev)
  */
 static int jpeg_v5_0_1_stop(struct amdgpu_device *adev)
 {
-	int i, jpeg_inst, r;
-
-	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		jpeg_inst = GET_INST(JPEG, i);
-		/* reset JMI */
-		WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL),
-			 UVD_JMI_CNTL__SOFT_RESET_MASK,
-			 ~UVD_JMI_CNTL__SOFT_RESET_MASK);
+	int i;
 
-		/* enable antihang */
-		r = jpeg_v5_0_1_enable_antihang(adev, i);
-		if (r)
-			return r;
-	}
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i)
+		jpeg_v5_0_1_deinit_inst(adev, i);
 
 	return 0;
 }
@@ -471,9 +517,9 @@ static void jpeg_v5_0_1_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static bool jpeg_v5_0_1_is_idle(void *handle)
+static bool jpeg_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	bool ret = false;
 	int i, j;
 
@@ -522,7 +568,7 @@ static int jpeg_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 		return 0;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		if (!jpeg_v5_0_1_is_idle(adev))
+		if (!jpeg_v5_0_1_is_idle(ip_block))
 			return -EBUSY;
 	}
 
@@ -617,6 +663,41 @@ static int jpeg_v5_0_1_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void jpeg_v5_0_1_core_stall_reset(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	int jpeg_inst = GET_INST(JPEG, ring->me);
+	int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0;
+
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_JMI_CLIENT_STALL,
+			    reg_offset, 0x1F);
+	SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst,
+				  regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS,
+				  reg_offset, 0x1F, 0x1F);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_JPEG_LMI_DROP,
+			    reg_offset, 0x1F);
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_UVD_JMI_CLIENT_STALL,
+			    reg_offset, 0x00);
+	WREG32_SOC15_OFFSET(JPEG, jpeg_inst,
+			    regUVD_JMI0_JPEG_LMI_DROP,
+			    reg_offset, 0x00);
+	WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00);
+}
+
+static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	if (amdgpu_sriov_vf(ring->adev))
+		return -EOPNOTSUPP;
+
+	jpeg_v5_0_1_core_stall_reset(ring);
+	jpeg_v5_0_1_init_jrbc(ring);
+	return amdgpu_ring_test_helper(ring);
+}
+
 static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = {
 	.name = "jpeg_v5_0_1",
 	.early_init = jpeg_v5_0_1_early_init,
@@ -635,8 +716,8 @@ static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = {
 	.post_soft_reset = NULL,
 	.set_clockgating_state = jpeg_v5_0_1_set_clockgating_state,
 	.set_powergating_state = jpeg_v5_0_1_set_powergating_state,
-	.dump_ip_state = NULL,
-	.print_ip_state = NULL,
+	.dump_ip_state = amdgpu_jpeg_dump_ip_state,
+	.print_ip_state = amdgpu_jpeg_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = {
@@ -655,6 +736,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = {
 	.emit_ib = jpeg_v4_0_3_dec_ring_emit_ib,
 	.emit_fence = jpeg_v4_0_3_dec_ring_emit_fence,
 	.emit_vm_flush = jpeg_v4_0_3_dec_ring_emit_vm_flush,
+	.emit_hdp_flush = jpeg_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
 	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
 	.insert_nop = jpeg_v4_0_3_dec_ring_nop,
@@ -666,6 +748,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = {
 	.emit_wreg = jpeg_v4_0_3_dec_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v4_0_3_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = jpeg_v5_0_1_ring_reset,
 };
 
 static void jpeg_v5_0_1_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h
index 8ce146c00bb6..efdab57324e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h
@@ -26,4 +26,76 @@
 
 extern const struct amdgpu_ip_block_version jpeg_v5_0_1_ip_block;
 
-#endif /* __JPEG_V5_0_0_H__ */
+#define regUVD_JRBC0_UVD_JRBC_RB_WPTR                                                         0x0640
+#define regUVD_JRBC0_UVD_JRBC_RB_WPTR_BASE_IDX                                                1
+#define regUVD_JRBC0_UVD_JRBC_STATUS                                                          0x0649
+#define regUVD_JRBC0_UVD_JRBC_STATUS_BASE_IDX                                                 1
+#define regUVD_JRBC0_UVD_JRBC_RB_RPTR                                                         0x064a
+#define regUVD_JRBC0_UVD_JRBC_RB_RPTR_BASE_IDX                                                1
+#define regUVD_JRBC1_UVD_JRBC_RB_WPTR                                                         0x0000
+#define regUVD_JRBC1_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC1_UVD_JRBC_STATUS                                                          0x0009
+#define regUVD_JRBC1_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC1_UVD_JRBC_RB_RPTR                                                         0x000a
+#define regUVD_JRBC1_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC2_UVD_JRBC_RB_WPTR                                                         0x0040
+#define regUVD_JRBC2_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC2_UVD_JRBC_STATUS                                                          0x0049
+#define regUVD_JRBC2_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC2_UVD_JRBC_RB_RPTR                                                         0x004a
+#define regUVD_JRBC2_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC3_UVD_JRBC_RB_WPTR                                                         0x0080
+#define regUVD_JRBC3_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC3_UVD_JRBC_STATUS                                                          0x0089
+#define regUVD_JRBC3_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC3_UVD_JRBC_RB_RPTR                                                         0x008a
+#define regUVD_JRBC3_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC4_UVD_JRBC_RB_WPTR                                                         0x00c0
+#define regUVD_JRBC4_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC4_UVD_JRBC_STATUS                                                          0x00c9
+#define regUVD_JRBC4_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC4_UVD_JRBC_RB_RPTR                                                         0x00ca
+#define regUVD_JRBC4_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC5_UVD_JRBC_RB_WPTR                                                         0x0100
+#define regUVD_JRBC5_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC5_UVD_JRBC_STATUS                                                          0x0109
+#define regUVD_JRBC5_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC5_UVD_JRBC_RB_RPTR                                                         0x010a
+#define regUVD_JRBC5_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC6_UVD_JRBC_RB_WPTR                                                         0x0140
+#define regUVD_JRBC6_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC6_UVD_JRBC_STATUS                                                          0x0149
+#define regUVD_JRBC6_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC6_UVD_JRBC_RB_RPTR                                                         0x014a
+#define regUVD_JRBC6_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC7_UVD_JRBC_RB_WPTR                                                         0x0180
+#define regUVD_JRBC7_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC7_UVD_JRBC_STATUS                                                          0x0189
+#define regUVD_JRBC7_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC7_UVD_JRBC_RB_RPTR                                                         0x018a
+#define regUVD_JRBC7_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC8_UVD_JRBC_RB_WPTR                                                         0x01c0
+#define regUVD_JRBC8_UVD_JRBC_RB_WPTR_BASE_IDX                                                0
+#define regUVD_JRBC8_UVD_JRBC_STATUS                                                          0x01c9
+#define regUVD_JRBC8_UVD_JRBC_STATUS_BASE_IDX                                                 0
+#define regUVD_JRBC8_UVD_JRBC_RB_RPTR                                                         0x01ca
+#define regUVD_JRBC8_UVD_JRBC_RB_RPTR_BASE_IDX                                                0
+#define regUVD_JRBC9_UVD_JRBC_RB_WPTR                                                         0x0440
+#define regUVD_JRBC9_UVD_JRBC_RB_WPTR_BASE_IDX                                                1
+#define regUVD_JRBC9_UVD_JRBC_STATUS                                                          0x0449
+#define regUVD_JRBC9_UVD_JRBC_STATUS_BASE_IDX                                                 1
+#define regUVD_JRBC9_UVD_JRBC_RB_RPTR                                                         0x044a
+#define regUVD_JRBC9_UVD_JRBC_RB_RPTR_BASE_IDX                                                1
+#define regUVD_JMI0_JPEG_LMI_DROP                                                             0x0663
+#define regUVD_JMI0_JPEG_LMI_DROP_BASE_IDX                                                    1
+#define regUVD_JMI0_UVD_JMI_CLIENT_STALL                                                      0x067a
+#define regUVD_JMI0_UVD_JMI_CLIENT_STALL_BASE_IDX                                             1
+#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS                                               0x067b
+#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS_BASE_IDX                                      1
+#define regJPEG_CORE_RST_CTRL                                                                 0x072e
+#define regJPEG_CORE_RST_CTRL_BASE_IDX                                                        1
+
+#define regVCN_RRMT_CNTL                          0x0940
+#define regVCN_RRMT_CNTL_BASE_IDX                 1
+
+#endif /* __JPEG_V5_0_1_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index f9a4d08eef92..e65916ada23b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -54,6 +54,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_1_mes_2.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_1_mes1.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_mes_2.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_2_mes1.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_mes_2.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_3_mes1.bin");
 
 static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block);
 static int mes_v11_0_hw_fini(struct amdgpu_ip_block *ip_block);
@@ -62,6 +64,7 @@ static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev);
 
 #define MES_EOP_SIZE   2048
 #define GFX_MES_DRAM_SIZE	0x80000
+#define MES11_HW_RESOURCE_1_SIZE (128 * AMDGPU_GPU_PAGE_SIZE)
 
 static void mes_v11_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
@@ -730,9 +733,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 
 static int mes_v11_0_set_hw_resources_1(struct amdgpu_mes *mes)
 {
-	int size = 128 * PAGE_SIZE;
-	int ret = 0;
-	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES_1 mes_set_hw_res_pkt;
 	memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt));
 
@@ -741,18 +741,13 @@ static int mes_v11_0_set_hw_resources_1(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
 	mes_set_hw_res_pkt.enable_mes_info_ctx = 1;
 
-	ret = amdgpu_bo_create_kernel(adev, size, PAGE_SIZE,
-				AMDGPU_GEM_DOMAIN_VRAM,
-				&mes->resource_1,
-				&mes->resource_1_gpu_addr,
-				&mes->resource_1_addr);
-	if (ret) {
-		dev_err(adev->dev, "(%d) failed to create mes resource_1 bo\n", ret);
-		return ret;
+	mes_set_hw_res_pkt.cleaner_shader_fence_mc_addr = mes->resource_1_gpu_addr[0];
+	if (amdgpu_sriov_is_mes_info_enable(mes->adev)) {
+		mes_set_hw_res_pkt.mes_info_ctx_mc_addr =
+			mes->resource_1_gpu_addr[0] + AMDGPU_GPU_PAGE_SIZE;
+		mes_set_hw_res_pkt.mes_info_ctx_size = MES11_HW_RESOURCE_1_SIZE;
 	}
 
-	mes_set_hw_res_pkt.mes_info_ctx_mc_addr = mes->resource_1_gpu_addr;
-	mes_set_hw_res_pkt.mes_info_ctx_size = mes->resource_1->tbo.base.size;
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
 			offsetof(union MESAPI_SET_HW_RESOURCES_1, api_status));
@@ -808,7 +803,7 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = {
 };
 
 static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev,
-					   enum admgpu_mes_pipe pipe)
+					   enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	const struct mes_firmware_header_v1_0 *mes_hdr;
@@ -843,7 +838,7 @@ static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev,
 }
 
 static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev,
-						enum admgpu_mes_pipe pipe)
+						enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	const struct mes_firmware_header_v1_0 *mes_hdr;
@@ -884,7 +879,7 @@ static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev,
 }
 
 static void mes_v11_0_free_ucode_buffers(struct amdgpu_device *adev,
-					 enum admgpu_mes_pipe pipe)
+					 enum amdgpu_mes_pipe pipe)
 {
 	amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe],
 			      &adev->mes.data_fw_gpu_addr[pipe],
@@ -982,7 +977,7 @@ static void mes_v11_0_enable(struct amdgpu_device *adev, bool enable)
 
 /* This function is for backdoor MES firmware */
 static int mes_v11_0_load_microcode(struct amdgpu_device *adev,
-				    enum admgpu_mes_pipe pipe, bool prime_icache)
+				    enum amdgpu_mes_pipe pipe, bool prime_icache)
 {
 	int r;
 	uint32_t data;
@@ -1054,7 +1049,7 @@ static int mes_v11_0_load_microcode(struct amdgpu_device *adev,
 }
 
 static int mes_v11_0_allocate_eop_buf(struct amdgpu_device *adev,
-				      enum admgpu_mes_pipe pipe)
+				      enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	u32 *eop;
@@ -1265,7 +1260,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev)
 }
 
 static int mes_v11_0_queue_init(struct amdgpu_device *adev,
-				enum admgpu_mes_pipe pipe)
+				enum amdgpu_mes_pipe pipe)
 {
 	struct amdgpu_ring *ring;
 	int r;
@@ -1348,7 +1343,7 @@ static int mes_v11_0_kiq_ring_init(struct amdgpu_device *adev)
 }
 
 static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev,
-				 enum admgpu_mes_pipe pipe)
+				 enum amdgpu_mes_pipe pipe)
 {
 	int r, mqd_size = sizeof(struct v11_compute_mqd);
 	struct amdgpu_ring *ring;
@@ -1389,7 +1384,7 @@ static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev,
 static int mes_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	int pipe, r;
+	int pipe, r, bo_size;
 
 	adev->mes.funcs = &mes_v11_0_funcs;
 	adev->mes.kiq_hw_init = &mes_v11_0_kiq_hw_init;
@@ -1424,6 +1419,23 @@ static int mes_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	bo_size = AMDGPU_GPU_PAGE_SIZE;
+	if (amdgpu_sriov_is_mes_info_enable(adev))
+		bo_size += MES11_HW_RESOURCE_1_SIZE;
+
+	/* Only needed for AMDGPU_MES_SCHED_PIPE on MES 11*/
+	r = amdgpu_bo_create_kernel(adev,
+				    bo_size,
+				    PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM,
+				    &adev->mes.resource_1[0],
+				    &adev->mes.resource_1_gpu_addr[0],
+				    &adev->mes.resource_1_addr[0]);
+	if (r) {
+		dev_err(adev->dev, "(%d) failed to create mes resource_1 bo\n", r);
+		return r;
+	}
+
 	return 0;
 }
 
@@ -1432,6 +1444,9 @@ static int mes_v11_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int pipe;
 
+	amdgpu_bo_free_kernel(&adev->mes.resource_1[0], &adev->mes.resource_1_gpu_addr[0],
+			      &adev->mes.resource_1_addr[0]);
+
 	for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
 		kfree(adev->mes.mqd_backup[pipe]);
 
@@ -1619,12 +1634,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		goto failure;
 
-	if (amdgpu_sriov_is_mes_info_enable(adev)) {
-		r = mes_v11_0_set_hw_resources_1(&adev->mes);
-		if (r) {
-			DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r);
-			goto failure;
-		}
+	r = mes_v11_0_set_hw_resources_1(&adev->mes);
+	if (r) {
+		DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r);
+		goto failure;
 	}
 
 	r = mes_v11_0_query_sched_status(&adev->mes);
@@ -1655,34 +1668,17 @@ failure:
 
 static int mes_v11_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	if (amdgpu_sriov_is_mes_info_enable(adev)) {
-		amdgpu_bo_free_kernel(&adev->mes.resource_1, &adev->mes.resource_1_gpu_addr,
-					&adev->mes.resource_1_addr);
-	}
 	return 0;
 }
 
 static int mes_v11_0_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
-
-	r = amdgpu_mes_suspend(ip_block->adev);
-	if (r)
-		return r;
-
 	return mes_v11_0_hw_fini(ip_block);
 }
 
 static int mes_v11_0_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
-
-	r = mes_v11_0_hw_init(ip_block);
-	if (r)
-		return r;
-
-	return amdgpu_mes_resume(ip_block->adev);
+	return mes_v11_0_hw_init(ip_block);
 }
 
 static int mes_v11_0_early_init(struct amdgpu_ip_block *ip_block)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 0fd0fa6ed518..183dd3346da5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -686,6 +686,8 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_1_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC_1;
 	mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
 	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa;
+	mes_set_hw_res_1_pkt.cleaner_shader_fence_mc_addr =
+		mes->resource_1_gpu_addr[pipe];
 
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
 			&mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt),
@@ -899,7 +901,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = {
 };
 
 static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev,
-					   enum admgpu_mes_pipe pipe)
+					   enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	const struct mes_firmware_header_v1_0 *mes_hdr;
@@ -933,7 +935,7 @@ static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev,
 }
 
 static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev,
-						enum admgpu_mes_pipe pipe)
+						enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	const struct mes_firmware_header_v1_0 *mes_hdr;
@@ -967,7 +969,7 @@ static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev,
 }
 
 static void mes_v12_0_free_ucode_buffers(struct amdgpu_device *adev,
-					 enum admgpu_mes_pipe pipe)
+					 enum amdgpu_mes_pipe pipe)
 {
 	amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe],
 			      &adev->mes.data_fw_gpu_addr[pipe],
@@ -1073,7 +1075,7 @@ static void mes_v12_0_set_ucode_start_addr(struct amdgpu_device *adev)
 
 /* This function is for backdoor MES firmware */
 static int mes_v12_0_load_microcode(struct amdgpu_device *adev,
-				    enum admgpu_mes_pipe pipe, bool prime_icache)
+				    enum amdgpu_mes_pipe pipe, bool prime_icache)
 {
 	int r;
 	uint32_t data;
@@ -1137,7 +1139,7 @@ static int mes_v12_0_load_microcode(struct amdgpu_device *adev,
 }
 
 static int mes_v12_0_allocate_eop_buf(struct amdgpu_device *adev,
-				      enum admgpu_mes_pipe pipe)
+				      enum amdgpu_mes_pipe pipe)
 {
 	int r;
 	u32 *eop;
@@ -1358,7 +1360,7 @@ static int mes_v12_0_kiq_enable_queue(struct amdgpu_device *adev)
 }
 
 static int mes_v12_0_queue_init(struct amdgpu_device *adev,
-				enum admgpu_mes_pipe pipe)
+				enum amdgpu_mes_pipe pipe)
 {
 	struct amdgpu_ring *ring;
 	int r;
@@ -1458,7 +1460,7 @@ static int mes_v12_0_kiq_ring_init(struct amdgpu_device *adev)
 }
 
 static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev,
-				 enum admgpu_mes_pipe pipe)
+				 enum amdgpu_mes_pipe pipe)
 {
 	int r, mqd_size = sizeof(struct v12_compute_mqd);
 	struct amdgpu_ring *ring;
@@ -1517,12 +1519,23 @@ static int mes_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE)
+		if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE) {
 			r = mes_v12_0_kiq_ring_init(adev);
-		else
+		}
+		else {
 			r = mes_v12_0_ring_init(adev, pipe);
-		if (r)
-			return r;
+			if (r)
+				return r;
+			r = amdgpu_bo_create_kernel(adev, AMDGPU_GPU_PAGE_SIZE, PAGE_SIZE,
+						    AMDGPU_GEM_DOMAIN_VRAM,
+						    &adev->mes.resource_1[pipe],
+						    &adev->mes.resource_1_gpu_addr[pipe],
+						    &adev->mes.resource_1_addr[pipe]);
+			if (r) {
+				dev_err(adev->dev, "(%d) failed to create mes resource_1 bo pipe[%d]\n", r, pipe);
+				return r;
+			}
+		}
 	}
 
 	return 0;
@@ -1534,6 +1547,10 @@ static int mes_v12_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	int pipe;
 
 	for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
+		amdgpu_bo_free_kernel(&adev->mes.resource_1[pipe],
+				      &adev->mes.resource_1_gpu_addr[pipe],
+				      &adev->mes.resource_1_addr[pipe]);
+
 		kfree(adev->mes.mqd_backup[pipe]);
 
 		amdgpu_bo_free_kernel(&adev->mes.eop_gpu_obj[pipe],
@@ -1732,8 +1749,7 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		goto failure;
 
-	if (adev->enable_uni_mes)
-		mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE);
+	mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE);
 
 	mes_v12_0_init_aggregated_doorbell(&adev->mes);
 
@@ -1770,24 +1786,12 @@ static int mes_v12_0_hw_fini(struct amdgpu_ip_block *ip_block)
 
 static int mes_v12_0_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
-
-	r = amdgpu_mes_suspend(ip_block->adev);
-	if (r)
-		return r;
-
 	return mes_v12_0_hw_fini(ip_block);
 }
 
 static int mes_v12_0_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
-
-	r = mes_v12_0_hw_init(ip_block);
-	if (r)
-		return r;
-
-	return amdgpu_mes_resume(ip_block->adev);
+	return mes_v12_0_hw_init(ip_block);
 }
 
 static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
index 9689e2b5d4e5..2adee2b94c37 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
@@ -172,6 +172,30 @@ static void mmhub_v1_7_init_tlb_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, regMC_VM_MX_L1_TLB_CNTL, tmp);
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v1_7_init_snoop_override_regs(struct amdgpu_device *adev)
+{
+	uint32_t tmp;
+	int i;
+	uint32_t distance = regDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+
+	for (i = 0; i < 5; i++) { /* DAGB instances */
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, i * distance);
+		tmp |= (1 << 15); /* SDMA client is BIT15 */
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, i * distance, tmp);
+
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, i * distance);
+		tmp |= (1 << 15);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, i * distance, tmp);
+	}
+
+}
+
 static void mmhub_v1_7_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
@@ -337,6 +361,7 @@ static int mmhub_v1_7_gart_enable(struct amdgpu_device *adev)
 	mmhub_v1_7_init_system_aperture_regs(adev);
 	mmhub_v1_7_init_tlb_regs(adev);
 	mmhub_v1_7_init_cache_regs(adev);
+	mmhub_v1_7_init_snoop_override_regs(adev);
 
 	mmhub_v1_7_enable_system_domain(adev);
 	mmhub_v1_7_disable_identity_aperture(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
index e646e5cef0a2..a54e7b929295 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
@@ -213,6 +213,32 @@ static void mmhub_v1_8_init_tlb_regs(struct amdgpu_device *adev)
 	}
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v1_8_init_snoop_override_regs(struct amdgpu_device *adev)
+{
+	uint32_t tmp, inst_mask;
+	int i, j;
+	uint32_t distance = regDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+
+	inst_mask = adev->aid_mask;
+	for_each_inst(i, inst_mask) {
+		for (j = 0; j < 5; j++) { /* DAGB instances */
+			tmp = RREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, j * distance);
+			tmp |= (1 << 15); /* SDMA client is BIT15 */
+			WREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, j * distance, tmp);
+
+			tmp = RREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, j * distance);
+			tmp |= (1 << 15);
+			WREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, j * distance, tmp);
+		}
+	}
+}
+
 static void mmhub_v1_8_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp, inst_mask;
@@ -418,6 +444,7 @@ static int mmhub_v1_8_gart_enable(struct amdgpu_device *adev)
 	mmhub_v1_8_init_system_aperture_regs(adev);
 	mmhub_v1_8_init_tlb_regs(adev);
 	mmhub_v1_8_init_cache_regs(adev);
+	mmhub_v1_8_init_snoop_override_regs(adev);
 
 	mmhub_v1_8_enable_system_domain(adev);
 	mmhub_v1_8_disable_identity_aperture(adev);
@@ -719,11 +746,13 @@ static int mmhub_v1_8_aca_bank_parser(struct aca_handle *handle, struct aca_bank
 	misc0 = bank->regs[ACA_REG_IDX_MISC0];
 	switch (type) {
 	case ACA_SMU_TYPE_UE:
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
 		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE,
 						     1ULL);
 		break;
 	case ACA_SMU_TYPE_CE:
-		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE,
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type,
 						     ACA_REG__MISC0__ERRCNT(misc0));
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
index b4ce3375d3fd..bc3d6c2fc87a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
@@ -103,6 +103,7 @@ mmhub_v3_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(3, 3, 0):
 	case IP_VERSION(3, 3, 1):
+	case IP_VERSION(3, 3, 2):
 		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_3) ?
 			    mmhub_client_ids_v3_3[cid][rw] :
 			    cid == 0x140 ? "UMSCH" : NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index ff1b58e44689..fe0710b55c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -198,6 +198,36 @@ static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v9_4_init_snoop_override_regs(struct amdgpu_device *adev, int hubid)
+{
+	uint32_t tmp;
+	int i;
+	uint32_t distance = mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+	uint32_t huboffset = hubid * MMHUB_INSTANCE_REGISTER_OFFSET;
+
+	for (i = 0; i < 5 - (2 * hubid); i++) {
+		/* DAGB instances 0 to 4 are in hub0 and 5 to 7 are in hub1 */
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE,
+			huboffset + i * distance);
+		tmp |= (1 << 15); /* SDMA client is BIT15 */
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE,
+			huboffset + i * distance, tmp);
+
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE,
+			huboffset + i * distance);
+		tmp |= (1 << 15);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE,
+			huboffset + i * distance, tmp);
+	}
+
+}
+
 static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid)
 {
 	uint32_t tmp;
@@ -392,6 +422,7 @@ static int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 		if (!amdgpu_sriov_vf(adev))
 			mmhub_v9_4_init_cache_regs(adev, i);
 
+		mmhub_v9_4_init_snoop_override_regs(adev, i);
 		mmhub_v9_4_enable_system_domain(adev, i);
 		if (!amdgpu_sriov_vf(adev))
 			mmhub_v9_4_disable_identity_aperture(adev, i);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 4dcb72d1bdda..5aadf24cb202 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -184,6 +184,9 @@ send_request:
 	case IDH_REQ_RAS_ERROR_COUNT:
 		event = IDH_RAS_ERROR_COUNT_READY;
 		break;
+	case IDH_REQ_RAS_CPER_DUMP:
+		event = IDH_RAS_CPER_DUMP_READY;
+		break;
 	default:
 		break;
 	}
@@ -467,6 +470,16 @@ static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev)
 	return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_ERROR_COUNT);
 }
 
+static int xgpu_nv_req_ras_cper_dump(struct amdgpu_device *adev, u64 vf_rptr)
+{
+	uint32_t vf_rptr_hi, vf_rptr_lo;
+
+	vf_rptr_hi = (uint32_t)(vf_rptr >> 32);
+	vf_rptr_lo = (uint32_t)(vf_rptr & 0xFFFFFFFF);
+	return xgpu_nv_send_access_requests_with_param(
+		adev, IDH_REQ_RAS_CPER_DUMP, vf_rptr_hi, vf_rptr_lo, 0);
+}
+
 const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.req_full_gpu	= xgpu_nv_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_nv_release_full_gpu_access,
@@ -478,4 +491,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.ras_poison_handler = xgpu_nv_ras_poison_handler,
 	.rcvd_ras_intr = xgpu_nv_rcvd_ras_intr,
 	.req_ras_err_count = xgpu_nv_req_ras_err_count,
+	.req_ras_cper_dump = xgpu_nv_req_ras_cper_dump,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
index 9d61d76e1bf9..72c9fceb9d79 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
@@ -41,6 +41,7 @@ enum idh_request {
 	IDH_READY_TO_RESET 	= 201,
 	IDH_RAS_POISON	= 202,
 	IDH_REQ_RAS_ERROR_COUNT = 203,
+	IDH_REQ_RAS_CPER_DUMP = 204,
 };
 
 enum idh_event {
@@ -56,6 +57,7 @@ enum idh_event {
 	IDH_PF_SOFT_FLR_NOTIFICATION,
 	IDH_RAS_ERROR_DETECTED,
 	IDH_RAS_ERROR_COUNT_READY = 11,
+	IDH_RAS_CPER_DUMP_READY = 14,
 
 	IDH_TEXT_MESSAGE = 255,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 62cdfe10e6f4..4cd325149b63 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -625,7 +625,7 @@ static int navi10_ih_resume(struct amdgpu_ip_block *ip_block)
 	return navi10_ih_hw_init(ip_block);
 }
 
-static bool navi10_ih_is_idle(void *handle)
+static bool navi10_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
@@ -682,9 +682,9 @@ static int navi10_ih_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void navi10_ih_get_clockgating_state(void *handle, u64 *flags)
+static void navi10_ih_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (!RREG32_SOC15(OSSSYS, 0, mmIH_CLK_CTRL))
 		*flags |= AMD_CG_SUPPORT_IH_CG;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c
index c92875ceb31f..9b4025c39e44 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbif_v6_3_1.h"
 
 #include "nbif/nbif_6_3_1_offset.h"
@@ -474,52 +473,6 @@ const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs = {
 };
 
 
-static void nbif_v6_3_1_sriov_ih_doorbell_range(struct amdgpu_device *adev,
-						bool use_doorbell, int doorbell_index)
-{
-}
-
-static void nbif_v6_3_1_sriov_sdma_doorbell_range(struct amdgpu_device *adev,
-						  int instance, bool use_doorbell,
-						  int doorbell_index,
-						  int doorbell_size)
-{
-}
-
-static void nbif_v6_3_1_sriov_vcn_doorbell_range(struct amdgpu_device *adev,
-						 bool use_doorbell,
-						 int doorbell_index, int instance)
-{
-}
-
-static void nbif_v6_3_1_sriov_gc_doorbell_init(struct amdgpu_device *adev)
-{
-}
-
-const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs = {
-	.get_hdp_flush_req_offset = nbif_v6_3_1_get_hdp_flush_req_offset,
-	.get_hdp_flush_done_offset = nbif_v6_3_1_get_hdp_flush_done_offset,
-	.get_pcie_index_offset = nbif_v6_3_1_get_pcie_index_offset,
-	.get_pcie_data_offset = nbif_v6_3_1_get_pcie_data_offset,
-	.get_rev_id = nbif_v6_3_1_get_rev_id,
-	.mc_access_enable = nbif_v6_3_1_mc_access_enable,
-	.get_memsize = nbif_v6_3_1_get_memsize,
-	.sdma_doorbell_range = nbif_v6_3_1_sriov_sdma_doorbell_range,
-	.vcn_doorbell_range = nbif_v6_3_1_sriov_vcn_doorbell_range,
-	.gc_doorbell_init = nbif_v6_3_1_sriov_gc_doorbell_init,
-	.enable_doorbell_aperture = nbif_v6_3_1_enable_doorbell_aperture,
-	.enable_doorbell_selfring_aperture = nbif_v6_3_1_enable_doorbell_selfring_aperture,
-	.ih_doorbell_range = nbif_v6_3_1_sriov_ih_doorbell_range,
-	.update_medium_grain_clock_gating = nbif_v6_3_1_update_medium_grain_clock_gating,
-	.update_medium_grain_light_sleep = nbif_v6_3_1_update_medium_grain_light_sleep,
-	.get_clockgating_state = nbif_v6_3_1_get_clockgating_state,
-	.ih_control = nbif_v6_3_1_ih_control,
-	.init_registers = nbif_v6_3_1_init_registers,
-	.remap_hdp_registers = nbif_v6_3_1_remap_hdp_registers,
-	.get_rom_offset = nbif_v6_3_1_get_rom_offset,
-	.set_reg_remap = nbif_v6_3_1_set_reg_remap,
-};
-
 static int nbif_v6_3_1_set_ras_err_event_athub_irq_state(struct amdgpu_device *adev,
 						       struct amdgpu_irq_src *src,
 						       unsigned type,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h
index 9ac4831d39e1..3afec715a9fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h
@@ -28,7 +28,6 @@
 
 extern const struct nbio_hdp_flush_reg nbif_v6_3_1_hdp_flush_reg;
 extern const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs;
-extern const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs;
 extern struct amdgpu_nbio_ras nbif_v6_3_1_ras;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 739fce4fa8fd..04041b398781 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v2_3.h"
 
 #include "nbio/nbio_2_3_default.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
index a54052dea8bf..f89e5f40e1a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v4_3.h"
 
 #include "nbio/nbio_4_3_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 34180c6070dd..e911368c1aeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v6_1.h"
 
 #include "nbio/nbio_6_1_default.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index d1032e9992b4..1569a1e934ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_0.h"
 
 #include "nbio/nbio_7_0_default.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 41421da63a08..2ece3ae75ec1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_11.h"
 
 #include "nbio/nbio_7_11_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
index a766e2d90cd0..acc5f363684a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_2.h"
 
 #include "nbio/nbio_7_2_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index a26a9be58eac..d5002ff931d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_4.h"
 #include "amdgpu_ras.h"
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index 3fb6d2aa7e3b..2ee60b8746a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_7.h"
 
 #include "nbio/nbio_7_7_0_offset.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 8a0a63ac88d2..f23cb79110d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -21,7 +21,6 @@
  *
  */
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "nbio_v7_9.h"
 #include "amdgpu_ras.h"
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 95c609317a8d..50e77d9b30af 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -141,23 +141,23 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
@@ -454,6 +454,7 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 
 	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 	case IP_VERSION(13, 0, 1):
 	case IP_VERSION(13, 0, 3):
 	case IP_VERSION(13, 0, 5):
@@ -1034,7 +1035,7 @@ static int nv_common_resume(struct amdgpu_ip_block *ip_block)
 	return nv_common_hw_init(ip_block);
 }
 
-static bool nv_common_is_idle(void *handle)
+static bool nv_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
@@ -1077,9 +1078,9 @@ static int nv_common_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void nv_common_get_clockgating_state(void *handle, u64 *flags)
+static void nv_common_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/nvd.h b/drivers/gpu/drm/amd/amdgpu/nvd.h
index 631dafb92299..56f1bfac0b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/nvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/nvd.h
@@ -64,6 +64,24 @@
 #define	PACKET3_INDIRECT_BUFFER_CNST_END		0x19
 #define	PACKET3_ATOMIC_GDS				0x1D
 #define	PACKET3_ATOMIC_MEM				0x1E
+#define 	PACKET3_ATOMIC_MEM__ATOMIC(x) ((((unsigned)(x)) & 0x7F) << 0)
+#define 	PACKET3_ATOMIC_MEM__COMMAND(x) ((((unsigned)(x)) & 0xF) << 8)
+#define 	PACKET3_ATOMIC_MEM__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define 	PACKET3_ATOMIC_MEM__ADDR_LO(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__ADDR_HI(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__SRC_DATA_LO(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__SRC_DATA_HI(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__CMP_DATA_LO(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__CMP_DATA_HI(x) (((unsigned)(x)))
+#define 	PACKET3_ATOMIC_MEM__LOOP_INTERVAL(x) ((((unsigned)(x)) & 0x1FFF) << 0)
+#define 	PACKET3_ATOMIC_MEM__COMMAND__SINGLE_PASS_ATOMIC 0
+#define 	PACKET3_ATOMIC_MEM__COMMAND__LOOP_UNTIL_COMPARE_SATISFIED 1
+#define 	PACKET3_ATOMIC_MEM__COMMAND__WAIT_FOR_WRITE_CONFIRMATION 2
+#define 	PACKET3_ATOMIC_MEM__COMMAND__SEND_AND_CONTINUE 3
+#define 	PACKET3_ATOMIC_MEM__CACHE_POLICY__LRU 0
+#define 	PACKET3_ATOMIC_MEM__CACHE_POLICY__STREAM 1
+#define 	PACKET3_ATOMIC_MEM__CACHE_POLICY__NOA 2
+#define 	PACKET3_ATOMIC_MEM__CACHE_POLICY__BYPASS 3
 #define	PACKET3_OCCLUSION_QUERY				0x1F
 #define	PACKET3_SET_PREDICATION				0x20
 #define	PACKET3_REG_RMW					0x21
@@ -105,6 +123,38 @@
 		 * 1 - pfp
 		 * 2 - ce
 		 */
+#define 	PACKET3_WRITE_DATA__DST_SEL(x) ((((unsigned)(x)) & 0xF) << 8)
+#define 	PACKET3_WRITE_DATA__ADDR_INCR(x) ((((unsigned)(x)) & 0x1) << 16)
+#define 	PACKET3_WRITE_DATA__WR_CONFIRM(x) ((((unsigned)(x)) & 0x1) << 20)
+#define 	PACKET3_WRITE_DATA__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define 	PACKET3_WRITE_DATA__DST_MMREG_ADDR(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define 	PACKET3_WRITE_DATA__DST_GDS_ADDR(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_WRITE_DATA__DST_MEM_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define 	PACKET3_WRITE_DATA__DST_MEM_ADDR_HI(x) ((unsigned)(x))
+#define 	PACKET3_WRITE_DATA__MODE(x) ((((unsigned)(x)) & 0x1) << 21)
+#define 	PACKET3_WRITE_DATA__AID_ID(x) ((((unsigned)(x)) & 0x3) << 22)
+#define 	PACKET3_WRITE_DATA__TEMPORAL(x) ((((unsigned)(x)) & 0x3) << 24)
+#define 	PACKET3_WRITE_DATA__DST_MMREG_ADDR_LO(x) ((unsigned)(x))
+#define 	PACKET3_WRITE_DATA__DST_MMREG_ADDR_HI(x) ((((unsigned)(x)) & 0xFF) << 0)
+#define 	PACKET3_WRITE_DATA__DST_SEL__MEM_MAPPED_REGISTER 0
+#define 	PACKET3_WRITE_DATA__DST_SEL__TC_L2 2
+#define 	PACKET3_WRITE_DATA__DST_SEL__GDS 3
+#define 	PACKET3_WRITE_DATA__DST_SEL__MEMORY 5
+#define 	PACKET3_WRITE_DATA__DST_SEL__MEMORY_MAPPED_ADC_PERSISTENT_STATE 6
+#define 	PACKET3_WRITE_DATA__ADDR_INCR__INCREMENT_ADDRESS 0
+#define 	PACKET3_WRITE_DATA__ADDR_INCR__DO_NOT_INCREMENT_ADDRESS 1
+#define 	PACKET3_WRITE_DATA__WR_CONFIRM__DO_NOT_WAIT_FOR_WRITE_CONFIRMATION 0
+#define 	PACKET3_WRITE_DATA__WR_CONFIRM__WAIT_FOR_WRITE_CONFIRMATION 1
+#define 	PACKET3_WRITE_DATA__MODE__PF_VF_DISABLED 0
+#define 	PACKET3_WRITE_DATA__MODE__PF_VF_ENABLED 1
+#define 	PACKET3_WRITE_DATA__TEMPORAL__RT 0
+#define 	PACKET3_WRITE_DATA__TEMPORAL__NT 1
+#define 	PACKET3_WRITE_DATA__TEMPORAL__HT 2
+#define 	PACKET3_WRITE_DATA__TEMPORAL__LU 3
+#define 	PACKET3_WRITE_DATA__CACHE_POLICY__LRU 0
+#define 	PACKET3_WRITE_DATA__CACHE_POLICY__STREAM 1
+#define 	PACKET3_WRITE_DATA__CACHE_POLICY__NOA 2
+#define 	PACKET3_WRITE_DATA__CACHE_POLICY__BYPASS 3
 #define	PACKET3_DRAW_INDEX_INDIRECT_MULTI		0x38
 #define	PACKET3_MEM_SEMAPHORE				0x39
 #              define PACKET3_SEM_USE_MAILBOX       (0x1 << 16)
@@ -135,6 +185,42 @@
 		/* 0 - me
 		 * 1 - pfp
 		 */
+#define		PACKET3_WAIT_REG_MEM__FUNCTION(x) ((((unsigned)(x)) & 0x7) << 0)
+#define		PACKET3_WAIT_REG_MEM__MEM_SPACE(x) ((((unsigned)(x)) & 0x3) << 4)
+#define		PACKET3_WAIT_REG_MEM__OPERATION(x) ((((unsigned)(x)) & 0x3) << 6)
+#define		PACKET3_WAIT_REG_MEM__MES_INTR_PIPE(x) ((((unsigned)(x)) & 0x3) << 22)
+#define		PACKET3_WAIT_REG_MEM__MES_ACTION(x) ((((unsigned)(x)) & 0x1) << 24)
+#define		PACKET3_WAIT_REG_MEM__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_WAIT_REG_MEM__TEMPORAL(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_WAIT_REG_MEM__MEM_POLL_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_WAIT_REG_MEM__REG_POLL_ADDR(x) ((((unsigned)(x)) & 0X3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__REG_WRITE_ADDR1(x) ((((unsigned)(x)) & 0X3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__MEM_POLL_ADDR_HI(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__REG_WRITE_ADDR2(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__REFERENCE(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__MASK(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__POLL_INTERVAL(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__OPTIMIZE_ACE_OFFLOAD_MODE(x) ((((unsigned)(x)) & 0x1) << 31)
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__ALWAYS_PASS 0
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__LESS_THAN_REF_VALUE 1
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__LESS_THAN_EQUAL_TO_THE_REF_VALUE 2
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__EQUAL_TO_THE_REFERENCE_VALUE 3
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__NOT_EQUAL_REFERENCE_VALUE 4
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__GREATER_THAN_OR_EQUAL_REFERENCE_VALUE 5
+#define 	PACKET3_WAIT_REG_MEM__FUNCTION__GREATER_THAN_REFERENCE_VALUE 6
+#define 	PACKET3_WAIT_REG_MEM__MEM_SPACE__REGISTER_SPACE 0
+#define 	PACKET3_WAIT_REG_MEM__MEM_SPACE__MEMORY_SPACE 1
+#define 	PACKET3_WAIT_REG_MEM__OPERATION__WAIT_REG_MEM 0
+#define 	PACKET3_WAIT_REG_MEM__OPERATION__WR_WAIT_WR_REG 1
+#define 	PACKET3_WAIT_REG_MEM__OPERATION__WAIT_MEM_PREEMPTABLE 3
+#define 	PACKET3_WAIT_REG_MEM__CACHE_POLICY__LRU 0
+#define 	PACKET3_WAIT_REG_MEM__CACHE_POLICY__STREAM 1
+#define 	PACKET3_WAIT_REG_MEM__CACHE_POLICY__NOA 2
+#define 	PACKET3_WAIT_REG_MEM__CACHE_POLICY__BYPASS 3
+#define 	PACKET3_WAIT_REG_MEM__TEMPORAL__RT 0
+#define 	PACKET3_WAIT_REG_MEM__TEMPORAL__NT 1
+#define 	PACKET3_WAIT_REG_MEM__TEMPORAL__HT 2
+#define 	PACKET3_WAIT_REG_MEM__TEMPORAL__LU 3
 #define	PACKET3_INDIRECT_BUFFER				0x3F
 #define		INDIRECT_BUFFER_VALID                   (1 << 23)
 #define		INDIRECT_BUFFER_CACHE_POLICY(x)         ((x) << 28)
@@ -144,8 +230,94 @@
 		 */
 #define		INDIRECT_BUFFER_PRE_ENB(x)		((x) << 21)
 #define		INDIRECT_BUFFER_PRE_RESUME(x)           ((x) << 30)
+#define 	PACKET3_INDIRECT_BUFFER__IB_BASE_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define 	PACKET3_INDIRECT_BUFFER__IB_BASE_HI(x) ((unsigned)(x))
+#define 	PACKET3_INDIRECT_BUFFER__IB_SIZE(x) ((((unsigned)(x)) & 0xFFFFF) << 0)
+#define 	PACKET3_INDIRECT_BUFFER__CHAIN(x) ((((unsigned)(x)) & 0x1) << 20)
+#define 	PACKET3_INDIRECT_BUFFER__OFFLOAD_POLLING(x) ((((unsigned)(x)) & 0x1) << 21)
+#define 	PACKET3_INDIRECT_BUFFER__VALID(x) ((((unsigned)(x)) & 0x1) << 23)
+#define 	PACKET3_INDIRECT_BUFFER__VMID(x) ((((unsigned)(x)) & 0xF) << 24)
+#define 	PACKET3_INDIRECT_BUFFER__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 28)
+#define 	PACKET3_INDIRECT_BUFFER__TEMPORAL(x) ((((unsigned)(x)) & 0x3) << 28)
+#define 	PACKET3_INDIRECT_BUFFER__PRIV(x) ((((unsigned)(x)) & 0x1) << 31)
+#define 	PACKET3_INDIRECT_BUFFER__TEMPORAL__RT 0
+#define 	PACKET3_INDIRECT_BUFFER__TEMPORAL__NT 1
+#define 	PACKET3_INDIRECT_BUFFER__TEMPORAL__HT 2
+#define 	PACKET3_INDIRECT_BUFFER__TEMPORAL__LU 3
+#define 	PACKET3_INDIRECT_BUFFER__CACHE_POLICY__LRU 0
+#define 	PACKET3_INDIRECT_BUFFER__CACHE_POLICY__STREAM 1
+#define 	PACKET3_INDIRECT_BUFFER__CACHE_POLICY__NOA 2
+#define 	PACKET3_INDIRECT_BUFFER__CACHE_POLICY__BYPASS 3
 #define	PACKET3_COND_INDIRECT_BUFFER			0x3F
 #define	PACKET3_COPY_DATA				0x40
+#define 	PACKET3_COPY_DATA__SRC_SEL(x) ((((unsigned)(x)) & 0xF) << 0)
+#define 	PACKET3_COPY_DATA__DST_SEL(x) ((((unsigned)(x)) & 0xF) << 8)
+#define 	PACKET3_COPY_DATA__SRC_CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 13)
+#define 	PACKET3_COPY_DATA__SRC_TEMPORAL(x) ((((unsigned)(x)) & 0x3) << 13)
+#define 	PACKET3_COPY_DATA__COUNT_SEL(x) ((((unsigned)(x)) & 0x1) << 16)
+#define 	PACKET3_COPY_DATA__WR_CONFIRM(x) ((((unsigned)(x)) & 0x1) << 20)
+#define 	PACKET3_COPY_DATA__DST_CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define 	PACKET3_COPY_DATA__PQ_EXE_STATUS(x) ((((unsigned)(x)) & 0x1) << 29)
+#define 	PACKET3_COPY_DATA__SRC_REG_OFFSET(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define 	PACKET3_COPY_DATA__SRC_32B_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define 	PACKET3_COPY_DATA__SRC_64B_ADDR_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define 	PACKET3_COPY_DATA__SRC_GDS_ADDR_LO(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_COPY_DATA__IMM_DATA(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__SRC_MEMTC_ADDR_HI(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__SRC_IMM_DATA(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__DST_REG_OFFSET(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define 	PACKET3_COPY_DATA__DST_32B_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define 	PACKET3_COPY_DATA__DST_64B_ADDR_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define 	PACKET3_COPY_DATA__DST_GDS_ADDR_LO(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_COPY_DATA__DST_ADDR_HI(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__MODE(x) ((((unsigned)(x)) & 0x1) << 21)
+#define 	PACKET3_COPY_DATA__AID_ID(x) ((((unsigned)(x)) & 0x3) << 23)
+#define 	PACKET3_COPY_DATA__DST_TEMPORAL(x) ((((unsigned)(x)) & 0x3) << 25)
+#define 	PACKET3_COPY_DATA__SRC_REG_OFFSET_LO(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__SRC_REG_OFFSET_HI(x) ((((unsigned)(x)) & 0xFF) << 0)
+#define 	PACKET3_COPY_DATA__DST_REG_OFFSET_LO(x) ((unsigned)(x))
+#define 	PACKET3_COPY_DATA__DST_REG_OFFSET_HI(x) ((((unsigned)(x)) & 0xFF) << 0)
+#define 	PACKET3_COPY_DATA__SRC_SEL__MEM_MAPPED_REGISTER 0
+#define 	PACKET3_COPY_DATA__SRC_SEL__TC_L2_OBSOLETE 1
+#define 	PACKET3_COPY_DATA__SRC_SEL__TC_L2 2
+#define 	PACKET3_COPY_DATA__SRC_SEL__GDS 3
+#define 	PACKET3_COPY_DATA__SRC_SEL__PERFCOUNTERS 4
+#define 	PACKET3_COPY_DATA__SRC_SEL__IMMEDIATE_DATA 5
+#define 	PACKET3_COPY_DATA__SRC_SEL__ATOMIC_RETURN_DATA 6
+#define 	PACKET3_COPY_DATA__SRC_SEL__GDS_ATOMIC_RETURN_DATA0 7
+#define 	PACKET3_COPY_DATA__SRC_SEL__GDS_ATOMIC_RETURN_DATA1 8
+#define 	PACKET3_COPY_DATA__SRC_SEL__GPU_CLOCK_COUNT 9
+#define 	PACKET3_COPY_DATA__SRC_SEL__SYSTEM_CLOCK_COUNT 10
+#define 	PACKET3_COPY_DATA__DST_SEL__MEM_MAPPED_REGISTER 0
+#define 	PACKET3_COPY_DATA__DST_SEL__TC_L2 2
+#define 	PACKET3_COPY_DATA__DST_SEL__GDS 3
+#define 	PACKET3_COPY_DATA__DST_SEL__PERFCOUNTERS 4
+#define 	PACKET3_COPY_DATA__DST_SEL__TC_L2_OBSOLETE 5
+#define 	PACKET3_COPY_DATA__DST_SEL__MEM_MAPPED_REG_DC 6
+#define 	PACKET3_COPY_DATA__SRC_TEMPORAL__RT 0
+#define 	PACKET3_COPY_DATA__SRC_TEMPORAL__NT 1
+#define 	PACKET3_COPY_DATA__SRC_TEMPORAL__HT 2
+#define 	PACKET3_COPY_DATA__SRC_TEMPORAL__LU 3
+#define 	PACKET3_COPY_DATA__SRC_CACHE_POLICY__LRU 0
+#define 	PACKET3_COPY_DATA__SRC_CACHE_POLICY__STREAM 1
+#define 	PACKET3_COPY_DATA__SRC_CACHE_POLICY__NOA 2
+#define 	PACKET3_COPY_DATA__SRC_CACHE_POLICY__BYPASS 3
+#define 	PACKET3_COPY_DATA__COUNT_SEL__32_BITS_OF_DATA 0
+#define 	PACKET3_COPY_DATA__COUNT_SEL__64_BITS_OF_DATA 1
+#define 	PACKET3_COPY_DATA__WR_CONFIRM__DO_NOT_WAIT_FOR_CONFIRMATION 0
+#define 	PACKET3_COPY_DATA__WR_CONFIRM__WAIT_FOR_CONFIRMATION 1
+#define 	PACKET3_COPY_DATA__MODE__PF_VF_DISABLED 0
+#define 	PACKET3_COPY_DATA__MODE__PF_VF_ENABLED 1
+#define 	PACKET3_COPY_DATA__DST_TEMPORAL__RT 0
+#define 	PACKET3_COPY_DATA__DST_TEMPORAL__NT 1
+#define 	PACKET3_COPY_DATA__DST_TEMPORAL__HT 2
+#define 	PACKET3_COPY_DATA__DST_TEMPORAL__LU 3
+#define 	PACKET3_COPY_DATA__DST_CACHE_POLICY__LRU 0
+#define 	PACKET3_COPY_DATA__DST_CACHE_POLICY__STREAM 1
+#define 	PACKET3_COPY_DATA__DST_CACHE_POLICY__NOA 2
+#define 	PACKET3_COPY_DATA__DST_CACHE_POLICY__BYPASS 3
+#define 	PACKET3_COPY_DATA__PQ_EXE_STATUS__DEFAULT 0
+#define 	PACKET3_COPY_DATA__PQ_EXE_STATUS__PHASE_UPDATE 1
 #define	PACKET3_CP_DMA					0x41
 #define	PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_SURFACE_SYNC				0x43
@@ -160,6 +332,23 @@
 		 * 3 - SAMPLE_STREAMOUTSTAT*
 		 * 4 - *S_PARTIAL_FLUSH
 		 */
+#define		PACKET3_EVENT_WRITE__EVENT_TYPE(x) ((((unsigned)(x)) & 0x3F) << 0)
+#define		PACKET3_EVENT_WRITE__EVENT_INDEX(x) ((((unsigned)(x)) & 0xF) << 8)
+#define		PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE(x) ((((unsigned)(x)) & 0x3) << 29)
+#define		PACKET3_EVENT_WRITE__OFFLOAD_ENABLE(x) ((((unsigned)(x)) & 0x1) << 0)
+#define 	PACKET3_EVENT_WRITE__ADDRESS_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define 	PACKET3_EVENT_WRITE__ADDRESS_HI(x) ((unsigned)(x))
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__OTHER 0
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_PIPELINESTAT 2
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__CS_PARTIAL_FLUSH 4
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_STREAMOUTSTATS 8
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_STREAMOUTSTATS1 9
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_STREAMOUTSTATS2 10
+#define 	PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_STREAMOUTSTATS3 11
+#define 	PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE__LEGACY_MODE 0
+#define 	PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE__MIXED_MODE1 1
+#define 	PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE__NEW_MODE 2
+#define 	PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE__MIXED_MODE3 3
 #define	PACKET3_EVENT_WRITE_EOP				0x47
 #define	PACKET3_EVENT_WRITE_EOS				0x48
 #define	PACKET3_RELEASE_MEM				0x49
@@ -304,6 +493,12 @@
 		 * 2: REVERSE
 		 */
 #define 	PACKET3_ACQUIRE_MEM_GCR_RANGE_IS_PA  (1 << 18)
+#define 	PACKET3_ACQUIRE_MEM__COHER_SIZE(x) ((unsigned)(x))
+#define 	PACKET3_ACQUIRE_MEM__COHER_SIZE_HI(x) ((((unsigned)(x)) & 0xFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__COHER_BASE_LO(x) ((unsigned)(x))
+#define 	PACKET3_ACQUIRE_MEM__COHER_BASE_HI(x) ((((unsigned)(x)) & 0xFFFFFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__POLL_INTERVAL(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__GCR_CNTL(x) ((((unsigned)(x)) & 0x7FFFF) << 0)
 #define	PACKET3_REWIND					0x59
 #define	PACKET3_INTERRUPT				0x5A
 #define	PACKET3_GEN_PDEPTE				0x5B
@@ -330,11 +525,17 @@
 #define	PACKET3_SET_SH_REG				0x76
 #define		PACKET3_SET_SH_REG_START			0x00002c00
 #define		PACKET3_SET_SH_REG_END				0x00003000
+#define 	PACKET3_SET_SH_REG__REG_OFFSET(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_SET_SH_REG__VMID_SHIFT(x) ((((unsigned)(x)) & 0x1F) << 23)
+#define 	PACKET3_SET_SH_REG__INDEX(x) ((((unsigned)(x)) & 0xF) << 28)
+#define 	PACKET3_SET_SH_REG__INDEX__DEFAULT 0
+#define 	PACKET3_SET_SH_REG__INDEX__INSERT_VMID 1
 #define	PACKET3_SET_SH_REG_OFFSET			0x77
 #define	PACKET3_SET_QUEUE_REG				0x78
 #define	PACKET3_SET_UCONFIG_REG				0x79
 #define		PACKET3_SET_UCONFIG_REG_START			0x0000c000
 #define		PACKET3_SET_UCONFIG_REG_END			0x0000c400
+#define 	PACKET3_SET_UCONFIG_REG__REG_OFFSET(x) ((((unsigned)(x)) & 0xFFFF) << 0)
 #define	PACKET3_SET_UCONFIG_REG_INDEX			0x7A
 #define	PACKET3_FORWARD_HEADER				0x7C
 #define	PACKET3_SCRATCH_RAM_WRITE			0x7D
@@ -369,6 +570,7 @@
 #              define PACKET3_INVALIDATE_TLBS_DST_SEL(x)     ((x) << 0)
 #              define PACKET3_INVALIDATE_TLBS_ALL_HUB(x)     ((x) << 4)
 #              define PACKET3_INVALIDATE_TLBS_PASID(x)       ((x) << 5)
+#              define PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(x)  ((x) << 29)
 #define	PACKET3_AQL_PACKET				0x99
 #define	PACKET3_DMA_DATA_FILL_MULTI			0x9A
 #define	PACKET3_SET_SH_REG_INDEX			0x9B
@@ -462,6 +664,12 @@
 #              define PACKET3_QUERY_STATUS_ENG_SEL(x)          ((x) << 25)
 #define	PACKET3_RUN_LIST				0xA5
 #define	PACKET3_MAP_PROCESS_VM				0xA6
+
+#define PACKET3_RUN_CLEANER_SHADER                      0xD2
+/* 1. header
+ * 2. RESERVED [31:0]
+ */
+
 /* GFX11 */
 #define	PACKET3_SET_Q_PREEMPTION_MODE			0xF0
 #              define PACKET3_SET_Q_PREEMPTION_MODE_IB_VMID(x)  ((x) << 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 2395f1856962..bb5dfc410a66 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -129,6 +129,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 		err = psp_init_ta_microcode(psp, ucode_prefix);
 		break;
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 2):
 		err = psp_init_asd_microcode(psp, ucode_prefix);
 		if (err)
 			return err;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index 4d33c95a5116..7c49c3f3c388 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -35,6 +35,8 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_2_sos.bin");
 MODULE_FIRMWARE("amdgpu/psp_14_0_2_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_14_0_3_sos.bin");
 MODULE_FIRMWARE("amdgpu/psp_14_0_3_ta.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_5_toc.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_5_ta.bin");
 
 /* For large FW files the time to complete can be very long */
 #define USBC_PD_POLLING_LIMIT_S 240
@@ -72,6 +74,14 @@ static int psp_v14_0_init_microcode(struct psp_context *psp)
 		if (err)
 			return err;
 		break;
+	case IP_VERSION(14, 0, 5):
+		err = psp_init_toc_microcode(psp, ucode_prefix);
+		if (err)
+			return err;
+		err = psp_init_ta_microcode(psp, ucode_prefix);
+		if (err)
+			return err;
+		break;
 	default:
 		BUG();
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 135c5099bfb8..92ce580647cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -911,9 +911,9 @@ static int sdma_v2_4_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v2_4_hw_init(ip_block);
 }
 
-static bool sdma_v2_4_is_idle(void *handle)
+static bool sdma_v2_4_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS2);
 
 	if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK |
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index c611328671ed..1c076bd1cf73 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -1200,9 +1200,9 @@ static int sdma_v3_0_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v3_0_hw_init(ip_block);
 }
 
-static bool sdma_v3_0_is_idle(void *handle)
+static bool sdma_v3_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS2);
 
 	if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK |
@@ -1514,9 +1514,9 @@ static int sdma_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v3_0_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v3_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index b48d9c0b2e1c..33ed2b158fcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -2015,9 +2015,9 @@ static int sdma_v4_0_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v4_0_hw_init(ip_block);
 }
 
-static bool sdma_v4_0_is_idle(void *handle)
+static bool sdma_v4_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -2331,9 +2331,9 @@ static int sdma_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v4_0_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v4_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
@@ -2381,7 +2381,6 @@ static void sdma_v4_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
 	if (!adev->sdma.ip_dump)
 		return;
 
-	amdgpu_gfx_off_ctrl(adev, false);
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		instance_offset = i * reg_count;
 		for (j = 0; j < reg_count; j++)
@@ -2389,7 +2388,6 @@ static void sdma_v4_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
 				RREG32(sdma_v4_0_get_reg_offset(adev, i,
 				       sdma_reg_list_4_0[j].reg_offset));
 	}
-	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 const struct amd_ip_funcs sdma_v4_0_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 5e0066cd6c51..dc94d58d33a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -30,6 +30,8 @@
 #include "amdgpu_xcp.h"
 #include "amdgpu_ucode.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_reset.h"
+#include "gc/gc_9_0_sh_mask.h"
 
 #include "sdma/sdma_4_4_2_offset.h"
 #include "sdma/sdma_4_4_2_sh_mask.h"
@@ -105,6 +107,8 @@ static void sdma_v4_4_2_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev);
 static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev);
 static void sdma_v4_4_2_set_ras_funcs(struct amdgpu_device *adev);
+static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev);
+static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev);
 
 static u32 sdma_v4_4_2_get_reg_offset(struct amdgpu_device *adev,
 		u32 instance, u32 offset)
@@ -681,6 +685,7 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b
 	u32 doorbell;
 	u32 doorbell_offset;
 	u64 wptr_gpu_addr;
+	u64 rwptr;
 
 	wb_offset = (ring->rptr_offs * 4);
 
@@ -706,12 +711,20 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b
 	/* before programing wptr to a less value, need set minor_ptr_update first */
 	WREG32_SDMA(i, regSDMA_GFX_MINOR_PTR_UPDATE, 1);
 
+	/* For the guilty queue, set RPTR to the current wptr to skip bad commands,
+	 * It is not a guilty queue, restore cache_rptr and continue execution.
+	 */
+	if (adev->sdma.instance[i].gfx_guilty)
+		rwptr = ring->wptr;
+	else
+		rwptr = ring->cached_rptr;
+
 	/* Initialize the ring buffer's read and write pointers */
 	if (restore) {
-		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2));
+		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(rwptr << 2));
 	} else {
 		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, 0);
 		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, 0);
@@ -778,6 +791,7 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i,
 	u32 doorbell;
 	u32 doorbell_offset;
 	u64 wptr_gpu_addr;
+	u64 rwptr;
 
 	wb_offset = (ring->rptr_offs * 4);
 
@@ -785,12 +799,20 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i,
 	rb_cntl = sdma_v4_4_2_rb_cntl(ring, rb_cntl);
 	WREG32_SDMA(i, regSDMA_PAGE_RB_CNTL, rb_cntl);
 
+	/* For the guilty queue, set RPTR to the current wptr to skip bad commands,
+	 * It is not a guilty queue, restore cache_rptr and continue execution.
+	 */
+	if (adev->sdma.instance[i].page_guilty)
+		rwptr = ring->wptr;
+	else
+		rwptr = ring->cached_rptr;
+
 	/* Initialize the ring buffer's read and write pointers */
 	if (restore) {
-		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2));
-		WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2));
+		WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, lower_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, upper_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR, lower_32_bits(rwptr << 2));
+		WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR_HI, upper_32_bits(rwptr << 2));
 	} else {
 		WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, 0);
 		WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, 0);
@@ -1269,21 +1291,71 @@ static void sdma_v4_4_2_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 			       seq, 0xffffffff, 4);
 }
 
-
-/**
- * sdma_v4_4_2_ring_emit_vm_flush - vm flush using sDMA
+/*
+ * sdma_v4_4_2_get_invalidate_req - Construct the VM_INVALIDATE_ENG0_REQ register value
+ * @vmid: The VMID to invalidate
+ * @flush_type: The type of flush (0 = legacy, 1 = lightweight, 2 = heavyweight)
  *
- * @ring: amdgpu_ring pointer
- * @vmid: vmid number to use
- * @pd_addr: address
+ * This function constructs the VM_INVALIDATE_ENG0_REQ register value for the specified VMID
+ * and flush type. It ensures that all relevant page table cache levels (L1 PTEs, L2 PTEs, and
+ * L2 PDEs) are invalidated.
+ */
+static uint32_t sdma_v4_4_2_get_invalidate_req(unsigned int vmid,
+						uint32_t flush_type)
+{
+	u32 req = 0;
+
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ,
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ,
+			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
+
+	return req;
+}
+
+/*
+ * sdma_v4_4_2_ring_emit_vm_flush - Emit VM flush commands for SDMA
+ * @ring: The SDMA ring
+ * @vmid: The VMID to flush
+ * @pd_addr: The page directory address
  *
- * Update the page table base and flush the VM TLB
- * using sDMA.
+ * This function emits the necessary register writes and waits to perform a VM flush for the
+ * specified VMID. It updates the PTB address registers and issues a VM invalidation request
+ * using the specified VM invalidation engine.
  */
 static void sdma_v4_4_2_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vmid, uint64_t pd_addr)
+					    unsigned int vmid, uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t req = sdma_v4_4_2_get_invalidate_req(vmid, 0);
+	unsigned int eng = ring->vm_inv_eng;
+	struct amdgpu_vmhub *hub = &adev->vmhub[ring->vm_hub];
+
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 +
+				(hub->ctx_addr_distance * vmid),
+				lower_32_bits(pd_addr));
+
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 +
+				(hub->ctx_addr_distance * vmid),
+				upper_32_bits(pd_addr));
+	/*
+	 * Construct and emit the VM invalidation packet
+	 */
+	amdgpu_ring_write(ring,
+		SDMA_PKT_VM_INVALIDATION_HEADER_OP(SDMA_OP_VM_INVALIDATE) |
+		SDMA_PKT_VM_INVALIDATION_HEADER_SUB_OP(SDMA_SUBOP_VM_INVALIDATE) |
+		SDMA_PKT_VM_INVALIDATION_HEADER_XCC0_ENG_ID(0x1f) |
+		SDMA_PKT_VM_INVALIDATION_HEADER_XCC1_ENG_ID(0x1f) |
+		SDMA_PKT_VM_INVALIDATION_HEADER_MMHUB_ENG_ID(eng));
+	amdgpu_ring_write(ring, SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_INVALIDATEREQ(req));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_INVALIDATEACK(BIT(vmid)));
 }
 
 static void sdma_v4_4_2_ring_emit_wreg(struct amdgpu_ring *ring,
@@ -1330,6 +1402,7 @@ static int sdma_v4_4_2_early_init(struct amdgpu_ip_block *ip_block)
 	sdma_v4_4_2_set_vm_pte_funcs(adev);
 	sdma_v4_4_2_set_irq_funcs(adev);
 	sdma_v4_4_2_set_ras_funcs(adev);
+	sdma_v4_4_2_set_engine_reset_funcs(adev);
 
 	return 0;
 }
@@ -1351,6 +1424,12 @@ static int sdma_v4_4_2_late_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_persistent_edc_harvesting_supported(adev))
 		amdgpu_ras_reset_error_count(adev, AMDGPU_RAS_BLOCK__SDMA);
 
+	/* The initialization is done in the late_init stage to ensure that the SMU
+	 * initialization and capability setup are completed before we check the SDMA
+	 * reset capability
+	 */
+	sdma_v4_4_2_update_reset_mask(adev);
+
 	return 0;
 }
 
@@ -1415,6 +1494,11 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
+		mutex_init(&adev->sdma.instance[i].engine_reset_mutex);
+		/* Initialize guilty flags for GFX and PAGE queues */
+		adev->sdma.instance[i].gfx_guilty = false;
+		adev->sdma.instance[i].page_guilty = false;
+
 		ring = &adev->sdma.instance[i].ring;
 		ring->ring_obj = NULL;
 		ring->use_doorbell = true;
@@ -1458,7 +1542,6 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
-	/* TODO: Add queue reset mask when FW fully supports it */
 	adev->sdma.supported_reset =
 		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
 
@@ -1561,9 +1644,9 @@ static int sdma_v4_4_2_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v4_4_2_hw_init(ip_block);
 }
 
-static bool sdma_v4_4_2_is_idle(void *handle)
+static bool sdma_v4_4_2_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1602,25 +1685,94 @@ static int sdma_v4_4_2_soft_reset(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static bool sdma_v4_4_2_is_queue_selected(struct amdgpu_device *adev, uint32_t instance_id, bool is_page_queue)
+{
+	uint32_t reg_offset = is_page_queue ? regSDMA_PAGE_CONTEXT_STATUS : regSDMA_GFX_CONTEXT_STATUS;
+	uint32_t context_status = RREG32(sdma_v4_4_2_get_reg_offset(adev, instance_id, reg_offset));
+
+	/* Check if the SELECTED bit is set */
+	return (context_status & SDMA_GFX_CONTEXT_STATUS__SELECTED_MASK) != 0;
+}
+
+static bool sdma_v4_4_2_ring_is_guilty(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t instance_id = ring->me;
+
+	return sdma_v4_4_2_is_queue_selected(adev, instance_id, false);
+}
+
+static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t instance_id = ring->me;
+
+	if (!adev->sdma.has_page_queue)
+		return false;
+
+	return sdma_v4_4_2_is_queue_selected(adev, instance_id, true);
+}
+
 static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int i, r;
+	u32 id = GET_INST(SDMA0, ring->me);
+	int r;
+
+	if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
+		return -EOPNOTSUPP;
+
+	amdgpu_amdkfd_suspend(adev, false);
+	r = amdgpu_sdma_reset_engine(adev, id);
+	amdgpu_amdkfd_resume(adev, false);
+
+	return r;
+}
+
+static int sdma_v4_4_2_stop_queue(struct amdgpu_device *adev, uint32_t instance_id)
+{
 	u32 inst_mask;
+	uint64_t rptr;
+	struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring;
 
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	/* Check if this queue is the guilty one */
+	adev->sdma.instance[instance_id].gfx_guilty =
+		sdma_v4_4_2_is_queue_selected(adev, instance_id, false);
+	if (adev->sdma.has_page_queue)
+		adev->sdma.instance[instance_id].page_guilty =
+			sdma_v4_4_2_is_queue_selected(adev, instance_id, true);
+
+	/* Cache the rptr before reset, after the reset,
+	* all of the registers will be reset to 0
+	*/
+	rptr = amdgpu_ring_get_rptr(ring);
+	ring->cached_rptr = rptr;
+	/* Cache the rptr for the page queue if it exists */
+	if (adev->sdma.has_page_queue) {
+		struct amdgpu_ring *page_ring = &adev->sdma.instance[instance_id].page;
+		rptr = amdgpu_ring_get_rptr(page_ring);
+		page_ring->cached_rptr = rptr;
+	}
+
 	/* stop queue */
 	inst_mask = 1 << ring->me;
 	sdma_v4_4_2_inst_gfx_stop(adev, inst_mask);
 	if (adev->sdma.has_page_queue)
 		sdma_v4_4_2_inst_page_stop(adev, inst_mask);
 
-	r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, ring->me));
-	if (r)
-		return r;
+	return 0;
+}
+
+static int sdma_v4_4_2_restore_queue(struct amdgpu_device *adev, uint32_t instance_id)
+{
+	int i;
+	u32 inst_mask;
+	struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring;
 
+	inst_mask = 1 << ring->me;
 	udelay(50);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -1638,6 +1790,16 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 	return sdma_v4_4_2_inst_start(adev, inst_mask, true);
 }
 
+static struct sdma_on_reset_funcs sdma_v4_4_2_engine_reset_funcs = {
+	.pre_reset = sdma_v4_4_2_stop_queue,
+	.post_reset = sdma_v4_4_2_restore_queue,
+};
+
+static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev)
+{
+	amdgpu_sdma_register_on_reset_callbacks(adev, &sdma_v4_4_2_engine_reset_funcs);
+}
+
 static int sdma_v4_4_2_set_trap_irq_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -1683,6 +1845,9 @@ static int sdma_v4_4_2_process_trap_irq(struct amdgpu_device *adev,
 	case 0:
 		amdgpu_fence_process(&adev->sdma.instance[i].ring);
 		break;
+	case 1:
+		amdgpu_fence_process(&adev->sdma.instance[i].page);
+		break;
 	default:
 		break;
 	}
@@ -1920,9 +2085,9 @@ static int sdma_v4_4_2_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v4_4_2_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v4_4_2_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
@@ -2012,8 +2177,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = {
 		3 + /* hdp invalidate */
 		6 + /* sdma_v4_4_2_ring_emit_pipeline_sync */
 		/* sdma_v4_4_2_ring_emit_vm_flush */
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 +
+		4 + 2 * 3 +
 		10 + 10 + 10, /* sdma_v4_4_2_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 7 + 6, /* sdma_v4_4_2_ring_emit_ib */
 	.emit_ib = sdma_v4_4_2_ring_emit_ib,
@@ -2029,6 +2193,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = {
 	.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 	.reset = sdma_v4_4_2_reset_queue,
+	.is_guilty = sdma_v4_4_2_ring_is_guilty,
 };
 
 static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
@@ -2044,8 +2209,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
 		3 + /* hdp invalidate */
 		6 + /* sdma_v4_4_2_ring_emit_pipeline_sync */
 		/* sdma_v4_4_2_ring_emit_vm_flush */
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 +
+		4 + 2 * 3 +
 		10 + 10 + 10, /* sdma_v4_4_2_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 7 + 6, /* sdma_v4_4_2_ring_emit_ib */
 	.emit_ib = sdma_v4_4_2_ring_emit_ib,
@@ -2060,6 +2224,8 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
 	.emit_wreg = sdma_v4_4_2_ring_emit_wreg,
 	.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = sdma_v4_4_2_reset_queue,
+	.is_guilty = sdma_v4_4_2_page_ring_is_guilty,
 };
 
 static void sdma_v4_4_2_set_ring_funcs(struct amdgpu_device *adev)
@@ -2231,6 +2397,38 @@ static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev)
 	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
+/**
+ * sdma_v4_4_2_update_reset_mask - update  reset mask for SDMA
+ * @adev: Pointer to the AMDGPU device structure
+ *
+ * This function update reset mask for SDMA and sets the supported
+ * reset types based on the IP version and firmware versions.
+ *
+ */
+static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev)
+{
+	/* per queue reset not supported for SRIOV */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
+	/*
+	 * the user queue relies on MEC fw and pmfw when the sdma queue do reset.
+	 * it needs to check both of them at here to skip old mec and pmfw.
+	 */
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
+		if ((adev->gfx.mec_fw_version >= 0xb0) && amdgpu_dpm_reset_sdma_is_supported(adev))
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	case IP_VERSION(9, 5, 0):
+		/*TODO: enable the queue reset flag until fw supported */
+	default:
+		break;
+	}
+
+}
+
 const struct amdgpu_ip_block_version sdma_v4_4_2_ip_block = {
 	.type = AMD_IP_BLOCK_TYPE_SDMA,
 	.major = 4,
@@ -2392,11 +2590,13 @@ static int sdma_v4_4_2_aca_bank_parser(struct aca_handle *handle, struct aca_ban
 	misc0 = bank->regs[ACA_REG_IDX_MISC0];
 	switch (type) {
 	case ACA_SMU_TYPE_UE:
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
 		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE,
 						     1ULL);
 		break;
 	case ACA_SMU_TYPE_CE:
-		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE,
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type,
 						     ACA_REG__MISC0__ERRCNT(misc0));
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index b764550834a0..0dce59f4f6e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1530,9 +1530,9 @@ static int sdma_v5_0_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v5_0_hw_init(ip_block);
 }
 
-static bool sdma_v5_0_is_idle(void *handle)
+static bool sdma_v5_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1883,9 +1883,9 @@ static int sdma_v5_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v5_0_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v5_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index b1818e87889a..2b39a03ff0c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1435,9 +1435,9 @@ static int sdma_v5_2_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v5_2_hw_init(ip_block);
 }
 
-static bool sdma_v5_2_is_idle(void *handle)
+static bool sdma_v5_2_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1847,9 +1847,9 @@ static int sdma_v5_2_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v5_2_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 1a023b45f0be..c214c3d2149b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -51,6 +51,7 @@ MODULE_FIRMWARE("amdgpu/sdma_6_0_3.bin");
 MODULE_FIRMWARE("amdgpu/sdma_6_1_0.bin");
 MODULE_FIRMWARE("amdgpu/sdma_6_1_1.bin");
 MODULE_FIRMWARE("amdgpu/sdma_6_1_2.bin");
+MODULE_FIRMWARE("amdgpu/sdma_6_1_3.bin");
 
 #define SDMA1_REG_OFFSET 0x600
 #define SDMA0_HYP_DEC_REG_START 0x5880
@@ -1428,9 +1429,9 @@ static int sdma_v6_0_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v6_0_hw_init(ip_block);
 }
 
-static bool sdma_v6_0_is_idle(void *handle)
+static bool sdma_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1613,7 +1614,7 @@ static int sdma_v6_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v6_0_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v6_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index 7e10e94624e3..b2706221df99 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1430,9 +1430,9 @@ static int sdma_v7_0_resume(struct amdgpu_ip_block *ip_block)
 	return sdma_v7_0_hw_init(ip_block);
 }
 
-static bool sdma_v7_0_is_idle(void *handle)
+static bool sdma_v7_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1592,7 +1592,7 @@ static int sdma_v7_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void sdma_v7_0_get_clockgating_state(void *handle, u64 *flags)
+static void sdma_v7_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 77ef7da2e4fe..2247f6a94858 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -909,7 +909,7 @@ static const u32 hainan_mgcg_cgcg_init[] =
 
 /* XXX: update when we support VCE */
 #if 0
-/* tahiti, pitcarin, verde */
+/* tahiti, pitcairn, verde */
 static const struct amdgpu_video_codec_info tahiti_video_codecs_encode_array[] =
 {
 	{
@@ -940,7 +940,7 @@ static const struct amdgpu_video_codecs hainan_video_codecs_encode =
 	.codec_array = NULL,
 };
 
-/* tahiti, pitcarin, verde, oland */
+/* tahiti, pitcairn, verde, oland */
 static const struct amdgpu_video_codec_info tahiti_video_codecs_decode_array[] =
 {
 	{
@@ -1124,41 +1124,41 @@ static struct amdgpu_allowed_register_entry si_allowed_read_registers[] = {
 	{mmCP_STALLED_STAT3},
 	{GB_ADDR_CONFIG},
 	{MC_ARB_RAMCFG},
-	{GB_TILE_MODE0},
-	{GB_TILE_MODE1},
-	{GB_TILE_MODE2},
-	{GB_TILE_MODE3},
-	{GB_TILE_MODE4},
-	{GB_TILE_MODE5},
-	{GB_TILE_MODE6},
-	{GB_TILE_MODE7},
-	{GB_TILE_MODE8},
-	{GB_TILE_MODE9},
-	{GB_TILE_MODE10},
-	{GB_TILE_MODE11},
-	{GB_TILE_MODE12},
-	{GB_TILE_MODE13},
-	{GB_TILE_MODE14},
-	{GB_TILE_MODE15},
-	{GB_TILE_MODE16},
-	{GB_TILE_MODE17},
-	{GB_TILE_MODE18},
-	{GB_TILE_MODE19},
-	{GB_TILE_MODE20},
-	{GB_TILE_MODE21},
-	{GB_TILE_MODE22},
-	{GB_TILE_MODE23},
-	{GB_TILE_MODE24},
-	{GB_TILE_MODE25},
-	{GB_TILE_MODE26},
-	{GB_TILE_MODE27},
-	{GB_TILE_MODE28},
-	{GB_TILE_MODE29},
-	{GB_TILE_MODE30},
-	{GB_TILE_MODE31},
+	{mmGB_TILE_MODE0},
+	{mmGB_TILE_MODE1},
+	{mmGB_TILE_MODE2},
+	{mmGB_TILE_MODE3},
+	{mmGB_TILE_MODE4},
+	{mmGB_TILE_MODE5},
+	{mmGB_TILE_MODE6},
+	{mmGB_TILE_MODE7},
+	{mmGB_TILE_MODE8},
+	{mmGB_TILE_MODE9},
+	{mmGB_TILE_MODE10},
+	{mmGB_TILE_MODE11},
+	{mmGB_TILE_MODE12},
+	{mmGB_TILE_MODE13},
+	{mmGB_TILE_MODE14},
+	{mmGB_TILE_MODE15},
+	{mmGB_TILE_MODE16},
+	{mmGB_TILE_MODE17},
+	{mmGB_TILE_MODE18},
+	{mmGB_TILE_MODE19},
+	{mmGB_TILE_MODE20},
+	{mmGB_TILE_MODE21},
+	{mmGB_TILE_MODE22},
+	{mmGB_TILE_MODE23},
+	{mmGB_TILE_MODE24},
+	{mmGB_TILE_MODE25},
+	{mmGB_TILE_MODE26},
+	{mmGB_TILE_MODE27},
+	{mmGB_TILE_MODE28},
+	{mmGB_TILE_MODE29},
+	{mmGB_TILE_MODE30},
+	{mmGB_TILE_MODE31},
 	{CC_RB_BACKEND_DISABLE, true},
-	{GC_USER_RB_BACKEND_DISABLE, true},
-	{PA_SC_RASTER_CONFIG, true},
+	{mmGC_USER_RB_BACKEND_DISABLE, true},
+	{mmPA_SC_RASTER_CONFIG, true},
 };
 
 static uint32_t si_get_register_value(struct amdgpu_device *adev,
@@ -1888,7 +1888,7 @@ static int si_vce_send_vcepll_ctlreq(struct amdgpu_device *adev)
 	WREG32_SMC_P(CG_VCEPLL_FUNC_CNTL, 0, ~UPLL_CTLREQ_MASK);
 
 	if (i == SI_MAX_CTLACKS_ASSERTION_WAIT) {
-		DRM_ERROR("Timeout setting UVD clocks!\n");
+		DRM_ERROR("Timeout setting VCE clocks!\n");
 		return -ETIMEDOUT;
 	}
 
@@ -2644,7 +2644,7 @@ static int si_common_resume(struct amdgpu_ip_block *ip_block)
 	return si_common_hw_init(ip_block);
 }
 
-static bool si_common_is_idle(void *handle)
+static bool si_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index dbd78d5345a4..e2089c8da71b 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -541,9 +541,9 @@ static int si_dma_resume(struct amdgpu_ip_block *ip_block)
 	return si_dma_hw_init(ip_block);
 }
 
-static bool si_dma_is_idle(void *handle)
+static bool si_dma_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	u32 tmp = RREG32(SRBM_STATUS2);
 
@@ -559,7 +559,7 @@ static int si_dma_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (si_dma_is_idle(adev))
+		if (si_dma_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/si_enums.h b/drivers/gpu/drm/amd/amdgpu/si_enums.h
index 4e935baa7b91..d656ef1fa6e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_enums.h
+++ b/drivers/gpu/drm/amd/amdgpu/si_enums.h
@@ -121,15 +121,7 @@
 #define CURSOR_UPDATE_LOCK             (1 << 16)
 #define CURSOR_DISABLE_MULTIPLE_UPDATE (1 << 24)
 
-#define SI_CRTC0_REGISTER_OFFSET                0
-#define SI_CRTC1_REGISTER_OFFSET                0x300
-#define SI_CRTC2_REGISTER_OFFSET                0x2600
-#define SI_CRTC3_REGISTER_OFFSET                0x2900
-#define SI_CRTC4_REGISTER_OFFSET                0x2c00
-#define SI_CRTC5_REGISTER_OFFSET                0x2f00
 
-#define DMA0_REGISTER_OFFSET 0x000
-#define DMA1_REGISTER_OFFSET 0x200
 #define ES_AND_GS_AUTO       3
 #define RADEON_PACKET_TYPE3  3
 #define CE_PARTITION_BASE    3
@@ -161,10 +153,6 @@
 #define RLC_SAVE_AND_RESTORE_STARTING_OFFSET 0x90
 #define RLC_CLEAR_STATE_DESCRIPTOR_OFFSET    0x3D
 
-#define TAHITI_GB_ADDR_CONFIG_GOLDEN        0x12011003
-#define VERDE_GB_ADDR_CONFIG_GOLDEN         0x02010002
-#define HAINAN_GB_ADDR_CONFIG_GOLDEN        0x02011003
-
 #define PACKET3(op, n)  ((RADEON_PACKET_TYPE3 << 30) |                  \
                          (((op) & 0xFF) << 8) |                         \
                          ((n) & 0x3FFF) << 16)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index a32b6243c1f8..5c38e1fb1dca 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -210,9 +210,9 @@ static int si_ih_resume(struct amdgpu_ip_block *ip_block)
 	return si_ih_hw_init(ip_block);
 }
 
-static bool si_ih_is_idle(void *handle)
+static bool si_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(SRBM_STATUS);
 
 	if (tmp & SRBM_STATUS__IH_BUSY_MASK)
@@ -227,7 +227,7 @@ static int si_ih_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (si_ih_is_idle(adev))
+		if (si_ih_is_idle(ip_block))
 			return 0;
 		udelay(1);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/sid.h b/drivers/gpu/drm/amd/amdgpu/sid.h
index 9a39cbfe6db9..cbf232f5235b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sid.h
+++ b/drivers/gpu/drm/amd/amdgpu/sid.h
@@ -26,10 +26,6 @@
 
 #define TAHITI_RB_BITMAP_WIDTH_PER_SH  2
 
-#define TAHITI_GB_ADDR_CONFIG_GOLDEN        0x12011003
-#define VERDE_GB_ADDR_CONFIG_GOLDEN         0x12010002
-#define HAINAN_GB_ADDR_CONFIG_GOLDEN        0x02010001
-
 #define SI_MAX_SH_GPRS		 	256
 #define SI_MAX_TEMP_GPRS         	16
 #define SI_MAX_SH_THREADS        	256
@@ -696,18 +692,6 @@
 #define HDP_REG_COHERENCY_FLUSH_CNTL			0x1528
 
 /* DCE6 ELD audio interface */
-#define AZ_F0_CODEC_ENDPOINT_INDEX                       0x1780
-#       define AZ_ENDPOINT_REG_INDEX(x)                  (((x) & 0xff) << 0)
-#       define AZ_ENDPOINT_REG_WRITE_EN                  (1 << 8)
-#define AZ_F0_CODEC_ENDPOINT_DATA                        0x1781
-
-#define AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER          0x25
-#define		SPEAKER_ALLOCATION(x)			(((x) & 0x7f) << 0)
-#define		SPEAKER_ALLOCATION_MASK			(0x7f << 0)
-#define		SPEAKER_ALLOCATION_SHIFT		0
-#define		HDMI_CONNECTION				(1 << 16)
-#define		DP_CONNECTION				(1 << 17)
-
 #define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0        0x28 /* LPCM */
 #define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR1        0x29 /* AC3 */
 #define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR2        0x2A /* MPEG1 */
@@ -909,26 +893,11 @@
 #define CRTC_STATUS_FRAME_COUNT                         0x1BA6
 
 /* Audio clocks */
-#define DCCG_AUDIO_DTO_SOURCE                           0x05ac
-#       define DCCG_AUDIO_DTO0_SOURCE_SEL(x) ((x) << 0) /* crtc0 - crtc5 */
-#       define DCCG_AUDIO_DTO_SEL            (1 << 4)   /* 0=dto0 1=dto1 */
-
 #define DCCG_AUDIO_DTO0_PHASE                           0x05b0
 #define DCCG_AUDIO_DTO0_MODULE                          0x05b4
 #define DCCG_AUDIO_DTO1_PHASE                           0x05c0
 #define DCCG_AUDIO_DTO1_MODULE                          0x05c4
 
-#define AFMT_AUDIO_SRC_CONTROL                          0x1c4f
-#define		AFMT_AUDIO_SRC_SELECT(x)		(((x) & 7) << 0)
-/* AFMT_AUDIO_SRC_SELECT
- * 0 = stream0
- * 1 = stream1
- * 2 = stream2
- * 3 = stream3
- * 4 = stream4
- * 5 = stream5
- */
-
 #define	GRBM_CNTL					0x2000
 #define		GRBM_READ_TIMEOUT(x)				((x) << 0)
 
@@ -977,30 +946,6 @@
 #define		SE_DB_BUSY					(1 << 30)
 #define		SE_CB_BUSY					(1 << 31)
 
-#define	GRBM_SOFT_RESET					0x2008
-#define		SOFT_RESET_CP					(1 << 0)
-#define		SOFT_RESET_CB					(1 << 1)
-#define		SOFT_RESET_RLC					(1 << 2)
-#define		SOFT_RESET_DB					(1 << 3)
-#define		SOFT_RESET_GDS					(1 << 4)
-#define		SOFT_RESET_PA					(1 << 5)
-#define		SOFT_RESET_SC					(1 << 6)
-#define		SOFT_RESET_BCI					(1 << 7)
-#define		SOFT_RESET_SPI					(1 << 8)
-#define		SOFT_RESET_SX					(1 << 10)
-#define		SOFT_RESET_TC					(1 << 11)
-#define		SOFT_RESET_TA					(1 << 12)
-#define		SOFT_RESET_VGT					(1 << 14)
-#define		SOFT_RESET_IA					(1 << 15)
-
-#define GRBM_GFX_INDEX          			0x200B
-#define		INSTANCE_INDEX(x)			((x) << 0)
-#define		SH_INDEX(x)     			((x) << 8)
-#define		SE_INDEX(x)     			((x) << 16)
-#define		SH_BROADCAST_WRITES      		(1 << 29)
-#define		INSTANCE_BROADCAST_WRITES      		(1 << 30)
-#define		SE_BROADCAST_WRITES      		(1 << 31)
-
 #define GRBM_INT_CNTL                                   0x2018
 #       define RDERR_INT_ENABLE                         (1 << 0)
 #       define GUI_IDLE_INT_ENABLE                      (1 << 19)
@@ -1045,16 +990,6 @@
 
 #define	VGT_VTX_VECT_EJECT_REG				0x222C
 
-#define	VGT_CACHE_INVALIDATION				0x2231
-#define		CACHE_INVALIDATION(x)				((x) << 0)
-#define			VC_ONLY						0
-#define			TC_ONLY						1
-#define			VC_AND_TC					2
-#define		AUTO_INVLD_EN(x)				((x) << 6)
-#define			NO_AUTO						0
-#define			ES_AUTO						1
-#define			GS_AUTO						2
-#define			ES_AND_GS_AUTO					3
 #define	VGT_ESGS_RING_SIZE				0x2232
 #define	VGT_GSVS_RING_SIZE				0x2233
 
@@ -1072,11 +1007,6 @@
 
 #define	VGT_TF_MEMORY_BASE				0x226E
 
-#define CC_GC_SHADER_ARRAY_CONFIG			0x226F
-#define		INACTIVE_CUS_MASK			0xFFFF0000
-#define		INACTIVE_CUS_SHIFT			16
-#define GC_USER_SHADER_ARRAY_CONFIG			0x2270
-
 #define	PA_CL_ENHANCE					0x2285
 #define		CLIP_VTX_REORDER_ENA				(1 << 0)
 #define		NUM_CLIP_SEQ(x)					((x) << 1)
@@ -1169,89 +1099,6 @@
 #define		ROW_SIZE_MASK				0x30000000
 #define		ROW_SIZE_SHIFT				28
 
-#define	GB_TILE_MODE0					0x2644
-#       define MICRO_TILE_MODE(x)				((x) << 0)
-#              define	ADDR_SURF_DISPLAY_MICRO_TILING		0
-#              define	ADDR_SURF_THIN_MICRO_TILING		1
-#              define	ADDR_SURF_DEPTH_MICRO_TILING		2
-#       define ARRAY_MODE(x)					((x) << 2)
-#              define	ARRAY_LINEAR_GENERAL			0
-#              define	ARRAY_LINEAR_ALIGNED			1
-#              define	ARRAY_1D_TILED_THIN1			2
-#              define	ARRAY_2D_TILED_THIN1			4
-#       define PIPE_CONFIG(x)					((x) << 6)
-#              define	ADDR_SURF_P2				0
-#              define	ADDR_SURF_P4_8x16			4
-#              define	ADDR_SURF_P4_16x16			5
-#              define	ADDR_SURF_P4_16x32			6
-#              define	ADDR_SURF_P4_32x32			7
-#              define	ADDR_SURF_P8_16x16_8x16			8
-#              define	ADDR_SURF_P8_16x32_8x16			9
-#              define	ADDR_SURF_P8_32x32_8x16			10
-#              define	ADDR_SURF_P8_16x32_16x16		11
-#              define	ADDR_SURF_P8_32x32_16x16		12
-#              define	ADDR_SURF_P8_32x32_16x32		13
-#              define	ADDR_SURF_P8_32x64_32x32		14
-#       define TILE_SPLIT(x)					((x) << 11)
-#              define	ADDR_SURF_TILE_SPLIT_64B		0
-#              define	ADDR_SURF_TILE_SPLIT_128B		1
-#              define	ADDR_SURF_TILE_SPLIT_256B		2
-#              define	ADDR_SURF_TILE_SPLIT_512B		3
-#              define	ADDR_SURF_TILE_SPLIT_1KB		4
-#              define	ADDR_SURF_TILE_SPLIT_2KB		5
-#              define	ADDR_SURF_TILE_SPLIT_4KB		6
-#       define BANK_WIDTH(x)					((x) << 14)
-#              define	ADDR_SURF_BANK_WIDTH_1			0
-#              define	ADDR_SURF_BANK_WIDTH_2			1
-#              define	ADDR_SURF_BANK_WIDTH_4			2
-#              define	ADDR_SURF_BANK_WIDTH_8			3
-#       define BANK_HEIGHT(x)					((x) << 16)
-#              define	ADDR_SURF_BANK_HEIGHT_1			0
-#              define	ADDR_SURF_BANK_HEIGHT_2			1
-#              define	ADDR_SURF_BANK_HEIGHT_4			2
-#              define	ADDR_SURF_BANK_HEIGHT_8			3
-#       define MACRO_TILE_ASPECT(x)				((x) << 18)
-#              define	ADDR_SURF_MACRO_ASPECT_1		0
-#              define	ADDR_SURF_MACRO_ASPECT_2		1
-#              define	ADDR_SURF_MACRO_ASPECT_4		2
-#              define	ADDR_SURF_MACRO_ASPECT_8		3
-#       define NUM_BANKS(x)					((x) << 20)
-#              define	ADDR_SURF_2_BANK			0
-#              define	ADDR_SURF_4_BANK			1
-#              define	ADDR_SURF_8_BANK			2
-#              define	ADDR_SURF_16_BANK			3
-#define	GB_TILE_MODE1					0x2645
-#define	GB_TILE_MODE2					0x2646
-#define	GB_TILE_MODE3					0x2647
-#define	GB_TILE_MODE4					0x2648
-#define	GB_TILE_MODE5					0x2649
-#define	GB_TILE_MODE6					0x264a
-#define	GB_TILE_MODE7					0x264b
-#define	GB_TILE_MODE8					0x264c
-#define	GB_TILE_MODE9					0x264d
-#define	GB_TILE_MODE10					0x264e
-#define	GB_TILE_MODE11					0x264f
-#define	GB_TILE_MODE12					0x2650
-#define	GB_TILE_MODE13					0x2651
-#define	GB_TILE_MODE14					0x2652
-#define	GB_TILE_MODE15					0x2653
-#define	GB_TILE_MODE16					0x2654
-#define	GB_TILE_MODE17					0x2655
-#define	GB_TILE_MODE18					0x2656
-#define	GB_TILE_MODE19					0x2657
-#define	GB_TILE_MODE20					0x2658
-#define	GB_TILE_MODE21					0x2659
-#define	GB_TILE_MODE22					0x265a
-#define	GB_TILE_MODE23					0x265b
-#define	GB_TILE_MODE24					0x265c
-#define	GB_TILE_MODE25					0x265d
-#define	GB_TILE_MODE26					0x265e
-#define	GB_TILE_MODE27					0x265f
-#define	GB_TILE_MODE28					0x2660
-#define	GB_TILE_MODE29					0x2661
-#define	GB_TILE_MODE30					0x2662
-#define	GB_TILE_MODE31					0x2663
-
 #define	CB_PERFCOUNTER0_SELECT0				0x2688
 #define	CB_PERFCOUNTER0_SELECT1				0x2689
 #define	CB_PERFCOUNTER1_SELECT0				0x268A
@@ -1263,10 +1110,6 @@
 
 #define	CB_CGTT_SCLK_CTRL				0x2698
 
-#define	GC_USER_RB_BACKEND_DISABLE			0x26DF
-#define		BACKEND_DISABLE_MASK			0x00FF0000
-#define		BACKEND_DISABLE_SHIFT			16
-
 #define	TCP_CHAN_STEER_LO				0x2B03
 #define	TCP_CHAN_STEER_HI				0x2B94
 
@@ -1320,101 +1163,12 @@
 #       define CP_RINGID1_INT_STAT                      (1 << 30)
 #       define CP_RINGID0_INT_STAT                      (1 << 31)
 
-#define	CP_MEM_SLP_CNTL					0x3079
-#       define CP_MEM_LS_EN                             (1 << 0)
-
-#define	CP_DEBUG					0x307F
-
-#define RLC_CNTL                                          0x30C0
-#       define RLC_ENABLE                                 (1 << 0)
-#define RLC_RL_BASE                                       0x30C1
-#define RLC_RL_SIZE                                       0x30C2
-#define RLC_LB_CNTL                                       0x30C3
-#       define LOAD_BALANCE_ENABLE                        (1 << 0)
-#define RLC_SAVE_AND_RESTORE_BASE                         0x30C4
-#define RLC_LB_CNTR_MAX                                   0x30C5
-#define RLC_LB_CNTR_INIT                                  0x30C6
-
-#define RLC_CLEAR_STATE_RESTORE_BASE                      0x30C8
-
-#define RLC_UCODE_ADDR                                    0x30CB
-#define RLC_UCODE_DATA                                    0x30CC
-
-#define RLC_GPU_CLOCK_COUNT_LSB                           0x30CE
-#define RLC_GPU_CLOCK_COUNT_MSB                           0x30CF
-#define RLC_CAPTURE_GPU_CLOCK_COUNT                       0x30D0
-#define RLC_MC_CNTL                                       0x30D1
-#define RLC_UCODE_CNTL                                    0x30D2
-#define RLC_STAT                                          0x30D3
-#       define RLC_BUSY_STATUS                            (1 << 0)
-#       define GFX_POWER_STATUS                           (1 << 1)
-#       define GFX_CLOCK_STATUS                           (1 << 2)
-#       define GFX_LS_STATUS                              (1 << 3)
-
-#define	RLC_PG_CNTL					0x30D7
-#	define GFX_PG_ENABLE				(1 << 0)
-#	define GFX_PG_SRC				(1 << 1)
-
-#define	RLC_CGTT_MGCG_OVERRIDE				0x3100
-#define	RLC_CGCG_CGLS_CTRL				0x3101
-#	define CGCG_EN					(1 << 0)
-#	define CGLS_EN					(1 << 1)
-
-#define	RLC_TTOP_D					0x3105
-#	define RLC_PUD(x)				((x) << 0)
-#	define RLC_PUD_MASK				(0xff << 0)
-#	define RLC_PDD(x)				((x) << 8)
-#	define RLC_PDD_MASK				(0xff << 8)
-#	define RLC_TTPD(x)				((x) << 16)
-#	define RLC_TTPD_MASK				(0xff << 16)
-#	define RLC_MSD(x)				((x) << 24)
-#	define RLC_MSD_MASK				(0xff << 24)
-
-#define RLC_LB_INIT_CU_MASK                               0x3107
-
-#define	RLC_PG_AO_CU_MASK				0x310B
-#define	RLC_MAX_PG_CU					0x310C
-#	define MAX_PU_CU(x)				((x) << 0)
-#	define MAX_PU_CU_MASK				(0xff << 0)
-#define	RLC_AUTO_PG_CTRL				0x310C
-#	define AUTO_PG_EN				(1 << 0)
-#	define GRBM_REG_SGIT(x)				((x) << 3)
-#	define GRBM_REG_SGIT_MASK			(0xffff << 3)
-#	define PG_AFTER_GRBM_REG_ST(x)			((x) << 19)
-#	define PG_AFTER_GRBM_REG_ST_MASK		(0x1fff << 19)
-
-#define RLC_SERDES_WR_MASTER_MASK_0                       0x3115
-#define RLC_SERDES_WR_MASTER_MASK_1                       0x3116
-#define RLC_SERDES_WR_CTRL                                0x3117
-
-#define RLC_SERDES_MASTER_BUSY_0                          0x3119
-#define RLC_SERDES_MASTER_BUSY_1                          0x311A
-
-#define RLC_GCPM_GENERAL_3                                0x311E
-
-#define	DB_RENDER_CONTROL				0xA000
-
-#define DB_DEPTH_INFO                                   0xA00F
-
-#define PA_SC_RASTER_CONFIG                             0xA0D4
-#	define RB_MAP_PKR0(x)				((x) << 0)
-#	define RB_MAP_PKR0_MASK				(0x3 << 0)
-#	define RB_MAP_PKR1(x)				((x) << 2)
-#	define RB_MAP_PKR1_MASK				(0x3 << 2)
-#       define RASTER_CONFIG_RB_MAP_0                   0
-#       define RASTER_CONFIG_RB_MAP_1                   1
-#       define RASTER_CONFIG_RB_MAP_2                   2
-#       define RASTER_CONFIG_RB_MAP_3                   3
+// #define PA_SC_RASTER_CONFIG                             0xA0D4
 #	define RB_XSEL2(x)				((x) << 4)
 #	define RB_XSEL2_MASK				(0x3 << 4)
 #	define RB_XSEL					(1 << 6)
 #	define RB_YSEL					(1 << 7)
 #	define PKR_MAP(x)				((x) << 8)
-#	define PKR_MAP_MASK				(0x3 << 8)
-#       define RASTER_CONFIG_PKR_MAP_0			0
-#       define RASTER_CONFIG_PKR_MAP_1			1
-#       define RASTER_CONFIG_PKR_MAP_2			2
-#       define RASTER_CONFIG_PKR_MAP_3			3
 #	define PKR_XSEL(x)				((x) << 10)
 #	define PKR_XSEL_MASK				(0x3 << 10)
 #	define PKR_YSEL(x)				((x) << 12)
@@ -1426,56 +1180,11 @@
 #	define SC_YSEL(x)				((x) << 20)
 #	define SC_YSEL_MASK				(0x3 << 20)
 #	define SE_MAP(x)				((x) << 24)
-#	define SE_MAP_MASK				(0x3 << 24)
-#       define RASTER_CONFIG_SE_MAP_0			0
-#       define RASTER_CONFIG_SE_MAP_1			1
-#       define RASTER_CONFIG_SE_MAP_2			2
-#       define RASTER_CONFIG_SE_MAP_3			3
 #	define SE_XSEL(x)				((x) << 26)
 #	define SE_XSEL_MASK				(0x3 << 26)
 #	define SE_YSEL(x)				((x) << 28)
 #	define SE_YSEL_MASK				(0x3 << 28)
 
-
-#define VGT_EVENT_INITIATOR                             0xA2A4
-#       define SAMPLE_STREAMOUTSTATS1                   (1 << 0)
-#       define SAMPLE_STREAMOUTSTATS2                   (2 << 0)
-#       define SAMPLE_STREAMOUTSTATS3                   (3 << 0)
-#       define CACHE_FLUSH_TS                           (4 << 0)
-#       define CACHE_FLUSH                              (6 << 0)
-#       define CS_PARTIAL_FLUSH                         (7 << 0)
-#       define VGT_STREAMOUT_RESET                      (10 << 0)
-#       define END_OF_PIPE_INCR_DE                      (11 << 0)
-#       define END_OF_PIPE_IB_END                       (12 << 0)
-#       define RST_PIX_CNT                              (13 << 0)
-#       define VS_PARTIAL_FLUSH                         (15 << 0)
-#       define PS_PARTIAL_FLUSH                         (16 << 0)
-#       define CACHE_FLUSH_AND_INV_TS_EVENT             (20 << 0)
-#       define ZPASS_DONE                               (21 << 0)
-#       define CACHE_FLUSH_AND_INV_EVENT                (22 << 0)
-#       define PERFCOUNTER_START                        (23 << 0)
-#       define PERFCOUNTER_STOP                         (24 << 0)
-#       define PIPELINESTAT_START                       (25 << 0)
-#       define PIPELINESTAT_STOP                        (26 << 0)
-#       define PERFCOUNTER_SAMPLE                       (27 << 0)
-#       define SAMPLE_PIPELINESTAT                      (30 << 0)
-#       define SAMPLE_STREAMOUTSTATS                    (32 << 0)
-#       define RESET_VTX_CNT                            (33 << 0)
-#       define VGT_FLUSH                                (36 << 0)
-#       define BOTTOM_OF_PIPE_TS                        (40 << 0)
-#       define DB_CACHE_FLUSH_AND_INV                   (42 << 0)
-#       define FLUSH_AND_INV_DB_DATA_TS                 (43 << 0)
-#       define FLUSH_AND_INV_DB_META                    (44 << 0)
-#       define FLUSH_AND_INV_CB_DATA_TS                 (45 << 0)
-#       define FLUSH_AND_INV_CB_META                    (46 << 0)
-#       define CS_DONE                                  (47 << 0)
-#       define PS_DONE                                  (48 << 0)
-#       define FLUSH_AND_INV_CB_PIXEL_DATA              (49 << 0)
-#       define THREAD_TRACE_START                       (51 << 0)
-#       define THREAD_TRACE_STOP                        (52 << 0)
-#       define THREAD_TRACE_FLUSH                       (54 << 0)
-#       define THREAD_TRACE_FINISH                      (55 << 0)
-
 /* PIF PHY0 registers idx/data 0x8/0xc */
 #define PB0_PIF_CNTL                                      0x10
 #       define LS2_EXIT_TIME(x)                           ((x) << 17)
@@ -1991,12 +1700,29 @@
 
 //#dce stupp
 /* display controller offsets used for crtc/cur/lut/grph/viewport/etc. */
-#define SI_CRTC0_REGISTER_OFFSET                0 //(0x6df0 - 0x6df0)/4
-#define SI_CRTC1_REGISTER_OFFSET                0x300 //(0x79f0 - 0x6df0)/4
-#define SI_CRTC2_REGISTER_OFFSET                0x2600 //(0x105f0 - 0x6df0)/4
-#define SI_CRTC3_REGISTER_OFFSET                0x2900 //(0x111f0 - 0x6df0)/4
-#define SI_CRTC4_REGISTER_OFFSET                0x2c00 //(0x11df0 - 0x6df0)/4
-#define SI_CRTC5_REGISTER_OFFSET                0x2f00 //(0x129f0 - 0x6df0)/4
+#define CRTC0_REGISTER_OFFSET                 (0x1b7c - 0x1b7c) //(0x6df0 - 0x6df0)/4
+#define CRTC1_REGISTER_OFFSET                 (0x1e7c - 0x1b7c) //(0x79f0 - 0x6df0)/4
+#define CRTC2_REGISTER_OFFSET                 (0x417c - 0x1b7c) //(0x105f0 - 0x6df0)/4
+#define CRTC3_REGISTER_OFFSET                 (0x447c - 0x1b7c) //(0x111f0 - 0x6df0)/4
+#define CRTC4_REGISTER_OFFSET                 (0x477c - 0x1b7c) //(0x11df0 - 0x6df0)/4
+#define CRTC5_REGISTER_OFFSET                 (0x4a7c - 0x1b7c) //(0x129f0 - 0x6df0)/4
+
+/* hpd instance offsets */
+#define HPD0_REGISTER_OFFSET                 (0x1807 - 0x1807)
+#define HPD1_REGISTER_OFFSET                 (0x180a - 0x1807)
+#define HPD2_REGISTER_OFFSET                 (0x180d - 0x1807)
+#define HPD3_REGISTER_OFFSET                 (0x1810 - 0x1807)
+#define HPD4_REGISTER_OFFSET                 (0x1813 - 0x1807)
+#define HPD5_REGISTER_OFFSET                 (0x1816 - 0x1807)
+
+/* audio endpt instance offsets */
+#define AUD0_REGISTER_OFFSET                 (0x1780 - 0x1780)
+#define AUD1_REGISTER_OFFSET                 (0x1786 - 0x1780)
+#define AUD2_REGISTER_OFFSET                 (0x178c - 0x1780)
+#define AUD3_REGISTER_OFFSET                 (0x1792 - 0x1780)
+#define AUD4_REGISTER_OFFSET                 (0x1798 - 0x1780)
+#define AUD5_REGISTER_OFFSET                 (0x179d - 0x1780)
+#define AUD6_REGISTER_OFFSET                 (0x17a4 - 0x1780)
 
 #define CURSOR_WIDTH 64
 #define CURSOR_HEIGHT 64
@@ -2036,9 +1762,6 @@
 #define EVERGREEN_DATA_FORMAT                           0x1ac0
 #       define EVERGREEN_INTERLEAVE_EN                  (1 << 0)
 
-#define MC_SHARED_CHMAP__NOOFCHAN_MASK 0xf000
-#define MC_SHARED_CHMAP__NOOFCHAN__SHIFT 0xc
-
 #define R600_D1GRPH_ARRAY_MODE_LINEAR_GENERAL            (0 << 20)
 #define R600_D1GRPH_ARRAY_MODE_LINEAR_ALIGNED            (1 << 20)
 #define R600_D1GRPH_ARRAY_MODE_1D_TILED_THIN1            (2 << 20)
@@ -2050,32 +1773,6 @@
 #define R700_D2GRPH_SECONDARY_SURFACE_ADDRESS_HIGH              0x1847
 #define R700_D1GRPH_SECONDARY_SURFACE_ADDRESS_HIGH              0x1a47
 
-#define DISP_INTERRUPT_STATUS__LB_D1_VBLANK_INTERRUPT_MASK 0x8
-#define DISP_INTERRUPT_STATUS_CONTINUE__LB_D2_VBLANK_INTERRUPT_MASK 0x8
-#define DISP_INTERRUPT_STATUS_CONTINUE2__LB_D3_VBLANK_INTERRUPT_MASK 0x8
-#define DISP_INTERRUPT_STATUS_CONTINUE3__LB_D4_VBLANK_INTERRUPT_MASK 0x8
-#define DISP_INTERRUPT_STATUS_CONTINUE4__LB_D5_VBLANK_INTERRUPT_MASK 0x8
-#define DISP_INTERRUPT_STATUS_CONTINUE5__LB_D6_VBLANK_INTERRUPT_MASK 0x8
-
-#define DISP_INTERRUPT_STATUS__LB_D1_VLINE_INTERRUPT_MASK 0x4
-#define DISP_INTERRUPT_STATUS_CONTINUE__LB_D2_VLINE_INTERRUPT_MASK 0x4
-#define DISP_INTERRUPT_STATUS_CONTINUE2__LB_D3_VLINE_INTERRUPT_MASK 0x4
-#define DISP_INTERRUPT_STATUS_CONTINUE3__LB_D4_VLINE_INTERRUPT_MASK 0x4
-#define DISP_INTERRUPT_STATUS_CONTINUE4__LB_D5_VLINE_INTERRUPT_MASK 0x4
-#define DISP_INTERRUPT_STATUS_CONTINUE5__LB_D6_VLINE_INTERRUPT_MASK 0x4
-
-#define DISP_INTERRUPT_STATUS__DC_HPD1_INTERRUPT_MASK 0x20000
-#define DISP_INTERRUPT_STATUS_CONTINUE__DC_HPD2_INTERRUPT_MASK 0x20000
-#define DISP_INTERRUPT_STATUS_CONTINUE2__DC_HPD3_INTERRUPT_MASK 0x20000
-#define DISP_INTERRUPT_STATUS_CONTINUE3__DC_HPD4_INTERRUPT_MASK 0x20000
-#define DISP_INTERRUPT_STATUS_CONTINUE4__DC_HPD5_INTERRUPT_MASK 0x20000
-#define DISP_INTERRUPT_STATUS_CONTINUE5__DC_HPD6_INTERRUPT_MASK 0x20000
-
-#define GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK 0x1
-#define GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK 0x100
-
-#define DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK 0x1
-
 #define R600_D1GRPH_SWAP_CONTROL                               0x1843
 #define R600_D1GRPH_SWAP_ENDIAN_NONE                    (0 << 0)
 #define R600_D1GRPH_SWAP_ENDIAN_16BIT                   (1 << 0)
@@ -2099,8 +1796,6 @@
 #       define R600_SCK_PRESCALE_CRYSTAL_CLK_SHIFT 28
 #       define R600_SCK_PRESCALE_CRYSTAL_CLK_MASK  (0xf << 28)
 
-#define GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK 0x1
-
 #define FMT_BIT_DEPTH_CONTROL                0x1bf2
 #define FMT_TRUNCATE_EN               (1 << 0)
 #define FMT_TRUNCATE_DEPTH            (1 << 4)
@@ -2404,19 +2099,6 @@
 #define mmSRBM_SOFT_RESET__xxSOFT_RESET_MC_MASK 0x800
 #define mmSRBM_SOFT_RESET__xxSOFT_RESET_MC__SHIFT 0xb
 
-#define VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x8
-#define VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0x3
-#define VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x40
-#define VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0x6
-#define VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x200
-#define VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0x9
-#define VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x1000
-#define VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0xc
-#define VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x8000
-#define VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0xf
-#define VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK 0x40000
-#define VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT__SHIFT 0x12
-
 #define MC_SEQ_MISC0__MT__MASK	0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
 #define MC_SEQ_MISC0__MT__DDR2   0x20000000
@@ -2426,10 +2108,7 @@
 #define MC_SEQ_MISC0__MT__HBM    0x60000000
 #define MC_SEQ_MISC0__MT__DDR3   0xB0000000
 
-#define GRBM_STATUS__GUI_ACTIVE_MASK 0x80000000
 #define CP_INT_CNTL_RING__TIME_STAMP_INT_ENABLE_MASK 0x4000000
-#define CP_INT_CNTL_RING0__PRIV_REG_INT_ENABLE_MASK 0x800000
-#define CP_INT_CNTL_RING0__PRIV_INSTR_INT_ENABLE_MASK 0x400000
 #define PACKET3_SEM_WAIT_ON_SIGNAL    (0x1 << 12)
 #define PACKET3_SEM_SEL_SIGNAL	    (0x6 << 29)
 #define PACKET3_SEM_SEL_WAIT	    (0x7 << 29)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index e98fb3fa36a8..659eab9b90be 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -28,7 +28,6 @@
 #include <drm/amdgpu_drm.h>
 
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "amdgpu_ih.h"
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
@@ -604,12 +603,10 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
 {
 	/* Will reset for the following suspend abort cases.
-	 * 1) Only reset on APU side, dGPU hasn't checked yet.
-	 * 2) S3 suspend aborted in the normal S3 suspend or
-	 *    performing pm core test.
+	 * 1) S3 suspend aborted in the normal S3 suspend
+	 * 2) S3 suspend aborted in performing pm core test.
 	 */
-	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
-			!pm_resume_via_firmware())
+	if (adev->in_s3 && !pm_resume_via_firmware())
 		return true;
 	else
 		return false;
@@ -1362,7 +1359,7 @@ static int soc15_common_resume(struct amdgpu_ip_block *ip_block)
 	return soc15_common_hw_init(ip_block);
 }
 
-static bool soc15_common_is_idle(void *handle)
+static bool soc15_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
@@ -1463,9 +1460,9 @@ static int soc15_common_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
+static void soc15_common_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
index b9cbeb389edc..a5000c171c02 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
@@ -93,11 +93,25 @@
 #define	PACKET3_DISPATCH_INDIRECT			0x16
 #define	PACKET3_ATOMIC_GDS				0x1D
 #define	PACKET3_ATOMIC_MEM				0x1E
+#define		PACKET3_ATOMIC_MEM__ATOMIC(x) ((((unsigned)(x)) & 0x3F) << 0)
+#define		PACKET3_ATOMIC_MEM__COMMAND(x) ((((unsigned)(x)) & 0xF) << 8)
+#define		PACKET3_ATOMIC_MEM__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_ATOMIC_MEM__ADDR_LO(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__ADDR_HI(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__SRC_DATA_LO(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__SRC_DATA_HI(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__CMP_DATA_LO(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__CMP_DATA_HI(x) (((unsigned)(x)) << 0)
+#define		PACKET3_ATOMIC_MEM__LOOP_INTERVAL(x) ((((unsigned)(x)) & 0x1FFF) << 0)
+#define 	PACKET3_ATOMIC_MEM__COMMAND__SINGLE_PASS_ATOMIC	0
+#define 	PACKET3_ATOMIC_MEM__COMMAND__LOOP_UNTIL_COMPARE_SATISFIED 1
 #define	PACKET3_OCCLUSION_QUERY				0x1F
 #define	PACKET3_SET_PREDICATION				0x20
 #define	PACKET3_REG_RMW					0x21
 #define	PACKET3_COND_EXEC				0x22
 #define	PACKET3_PRED_EXEC				0x23
+#define		PACKET3_PRED_EXEC__EXEC_COUNT(x)	((((unsigned)(x)) & 0x3FFF) << 0)
+#define		PACKET3_PRED_EXEC__VIRTUAL_XCC_ID_SELECT(x)	((((unsigned)(x)) & 0xFF) << 24)
 #define	PACKET3_DRAW_INDIRECT				0x24
 #define	PACKET3_DRAW_INDEX_INDIRECT			0x25
 #define	PACKET3_INDEX_BASE				0x26
@@ -132,6 +146,28 @@
 		 * 1 - pfp
 		 * 2 - ce
 		 */
+#define		PACKET3_WRITE_DATA__DST_SEL(x) ((((unsigned)(x)) & 0xF) << 8)
+#define		PACKET3_WRITE_DATA__ADDR_INCR(x) ((((unsigned)(x)) & 0x1) << 16)
+#define		PACKET3_WRITE_DATA__RESUME_VF_MI300(x) ((((unsigned)(x)) & 0x1) << 19)
+#define		PACKET3_WRITE_DATA__WR_CONFIRM(x) ((((unsigned)(x)) & 0x1) << 20)
+#define		PACKET3_WRITE_DATA__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_WRITE_DATA__DST_MMREG_ADDR(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_WRITE_DATA__DST_GDS_ADDR(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define		PACKET3_WRITE_DATA__DST_MEM_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_WRITE_DATA__DST_MEM_ADDR_HI(x) ((unsigned)(x))
+#define		PACKET3_WRITE_DATA__DST_SEL__MEM_MAPPED_REGISTER	0
+#define		PACKET3_WRITE_DATA__DST_SEL__TC_L2	2
+#define		PACKET3_WRITE_DATA__DST_SEL__GDS	3
+#define		PACKET3_WRITE_DATA__DST_SEL__MEMORY	5
+#define		PACKET3_WRITE_DATA__DST_SEL__MEMORY_MAPPED_ADC_PERSISTENT_STATE	6
+#define		PACKET3_WRITE_DATA__ADDR_INCR__INCREMENT_ADDRESS	0
+#define		PACKET3_WRITE_DATA__ADDR_INCR__DO_NOT_INCREMENT_ADDRESS	1
+#define		PACKET3_WRITE_DATA__WR_CONFIRM__DO_NOT_WAIT_FOR_WRITE_CONFIRMATION	0
+#define		PACKET3_WRITE_DATA__WR_CONFIRM__WAIT_FOR_WRITE_CONFIRMATION	1
+#define		PACKET3_WRITE_DATA__CACHE_POLICY__LRU	0
+#define		PACKET3_WRITE_DATA__CACHE_POLICY__STREAM	1
+#define		PACKET3_WRITE_DATA__CACHE_POLICY__NOA	2
+#define		PACKET3_WRITE_DATA__CACHE_POLICY__BYPASS	3
 #define	PACKET3_DRAW_INDEX_INDIRECT_MULTI		0x38
 #define	PACKET3_MEM_SEMAPHORE				0x39
 #              define PACKET3_SEM_USE_MAILBOX       (0x1 << 16)
@@ -160,6 +196,33 @@
 		/* 0 - me
 		 * 1 - pfp
 		 */
+#define		PACKET3_WAIT_REG_MEM__FUNCTION(x) ((((unsigned)(x)) & 0x7) << 0)
+#define		PACKET3_WAIT_REG_MEM__MEM_SPACE(x) ((((unsigned)(x)) & 0x3) << 4)
+#define		PACKET3_WAIT_REG_MEM__OPERATION(x) ((((unsigned)(x)) & 0x3) << 6)
+#define		PACKET3_WAIT_REG_MEM__MES_INTR_PIPE(x) ((((unsigned)(x)) & 0x3) << 22)
+#define		PACKET3_WAIT_REG_MEM__MES_ACTION(x) ((((unsigned)(x)) & 0x1) << 24)
+#define		PACKET3_WAIT_REG_MEM__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_WAIT_REG_MEM__MEM_POLL_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_WAIT_REG_MEM__REG_POLL_ADDR(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__REG_WRITE_ADDR1(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__MEM_POLL_ADDR_HI(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__REG_WRITE_ADDR2(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__REFERENCE(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__MASK(x) ((unsigned)(x))
+#define		PACKET3_WAIT_REG_MEM__POLL_INTERVAL(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define		PACKET3_WAIT_REG_MEM__OPTIMIZE_ACE_OFFLOAD_MODE(x) ((((unsigned)(x)) & 0x1) << 31)
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__ALWAYS_PASS	0
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__LESS_THAN_REF_VALUE	1
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__LESS_THAN_EQUAL_TO_THE_REF_VALUE	2
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__EQUAL_TO_THE_REFERENCE_VALUE	3
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__NOT_EQUAL_REFERENCE_VALUE	4
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__GREATER_THAN_OR_EQUAL_REFERENCE_VALUE	5
+#define		PACKET3_WAIT_REG_MEM__FUNCTION__GREATER_THAN_REFERENCE_VALUE	6
+#define		PACKET3_WAIT_REG_MEM__MEM_SPACE__REGISTER_SPACE	0
+#define		PACKET3_WAIT_REG_MEM__MEM_SPACE__MEMORY_SPACE	1
+#define		PACKET3_WAIT_REG_MEM__OPERATION__WAIT_REG_MEM	0
+#define		PACKET3_WAIT_REG_MEM__OPERATION__WR_WAIT_WR_REG	1
+#define		PACKET3_WAIT_REG_MEM__OPERATION__WAIT_MEM_PREEMPTABLE	3
 #define	PACKET3_INDIRECT_BUFFER				0x3F
 #define		INDIRECT_BUFFER_VALID                   (1 << 23)
 #define		INDIRECT_BUFFER_CACHE_POLICY(x)         ((x) << 28)
@@ -169,7 +232,63 @@
 		 */
 #define     INDIRECT_BUFFER_PRE_ENB(x)		 ((x) << 21)
 #define     INDIRECT_BUFFER_PRE_RESUME(x)               ((x) << 30)
+#define		PACKET3_INDIRECT_BUFFER__IB_BASE_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_INDIRECT_BUFFER__IB_BASE_HI(x) ((unsigned)(x))
+#define		PACKET3_INDIRECT_BUFFER__IB_SIZE(x) ((((unsigned)(x)) & 0xFFFFF) << 0)
+#define		PACKET3_INDIRECT_BUFFER__CHAIN(x) ((((unsigned)(x)) & 0x1) << 20)
+#define		PACKET3_INDIRECT_BUFFER__OFFLOAD_POLLING(x) ((((unsigned)(x)) & 0x1) << 21)
+#define		PACKET3_INDIRECT_BUFFER__VALID(x) ((((unsigned)(x)) & 0x1) << 23)
+#define		PACKET3_INDIRECT_BUFFER__VMID(x) ((((unsigned)(x)) & 0xF) << 24)
+#define		PACKET3_INDIRECT_BUFFER__CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 28)
+#define		PACKET3_INDIRECT_BUFFER__PRIV(x) ((((unsigned)(x)) & 0x1) << 31)
+#define		PACKET3_INDIRECT_BUFFER__CACHE_POLICY__LRU	0
+#define		PACKET3_INDIRECT_BUFFER__CACHE_POLICY__STREAM	1
 #define	PACKET3_COPY_DATA				0x40
+#define		PACKET3_COPY_DATA__SRC_SEL(x) ((((unsigned)(x)) & 0xF) << 0)
+#define		PACKET3_COPY_DATA__DST_SEL(x) ((((unsigned)(x)) & 0xF) << 8)
+#define		PACKET3_COPY_DATA__SRC_CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 13)
+#define		PACKET3_COPY_DATA__COUNT_SEL(x) ((((unsigned)(x)) & 0x1) << 16)
+#define		PACKET3_COPY_DATA__WR_CONFIRM(x) ((((unsigned)(x)) & 0x1) << 20)
+#define		PACKET3_COPY_DATA__DST_CACHE_POLICY(x) ((((unsigned)(x)) & 0x3) << 25)
+#define		PACKET3_COPY_DATA__PQ_EXE_STATUS(x) ((((unsigned)(x)) & 0x1) << 29)
+#define		PACKET3_COPY_DATA__SRC_REG_OFFSET(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_COPY_DATA__SRC_32B_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_COPY_DATA__SRC_64B_ADDR_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define		PACKET3_COPY_DATA__SRC_GDS_ADDR_LO(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define		PACKET3_COPY_DATA__IMM_DATA(x) ((unsigned)(x))
+#define		PACKET3_COPY_DATA__SRC_MEMTC_ADDR_HI(x) ((unsigned)(x))
+#define		PACKET3_COPY_DATA__SRC_IMM_DATA(x) ((unsigned)(x))
+#define		PACKET3_COPY_DATA__DST_REG_OFFSET(x) ((((unsigned)(x)) & 0x3FFFF) << 0)
+#define		PACKET3_COPY_DATA__DST_32B_ADDR_LO(x) ((((unsigned)(x)) & 0x3FFFFFFF) << 2)
+#define		PACKET3_COPY_DATA__DST_64B_ADDR_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define		PACKET3_COPY_DATA__DST_GDS_ADDR_LO(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define		PACKET3_COPY_DATA__DST_ADDR_HI(x) ((unsigned)(x))
+#define		PACKET3_COPY_DATA__SRC_SEL__MEM_MAPPED_REGISTER	0
+#define		PACKET3_COPY_DATA__SRC_SEL__MEMORY	1
+#define		PACKET3_COPY_DATA__SRC_SEL__TC_L2	2
+#define		PACKET3_COPY_DATA__SRC_SEL__GDS	3
+#define		PACKET3_COPY_DATA__SRC_SEL__PERFCOUNTERS	4
+#define		PACKET3_COPY_DATA__SRC_SEL__IMMEDIATE_DATA	5
+#define		PACKET3_COPY_DATA__SRC_SEL__ATOMIC_RETURN_DATA	6
+#define		PACKET3_COPY_DATA__SRC_SEL__GDS_ATOMIC_RETURN_DATA0	7
+#define		PACKET3_COPY_DATA__SRC_SEL__GDS_ATOMIC_RETURN_DATA1	8
+#define		PACKET3_COPY_DATA__SRC_SEL__GPU_CLOCK_COUNT	9
+#define		PACKET3_COPY_DATA__DST_SEL__MEM_MAPPED_REGISTER	0
+#define		PACKET3_COPY_DATA__DST_SEL__TC_L2	2
+#define		PACKET3_COPY_DATA__DST_SEL__GDS	3
+#define		PACKET3_COPY_DATA__DST_SEL__PERFCOUNTERS	4
+#define		PACKET3_COPY_DATA__DST_SEL__MEMORY	5
+#define		PACKET3_COPY_DATA__DST_SEL__MEM_MAPPED_REG_DC	6
+#define		PACKET3_COPY_DATA__SRC_CACHE_POLICY__LRU	0
+#define		PACKET3_COPY_DATA__SRC_CACHE_POLICY__STREAM 1
+#define		PACKET3_COPY_DATA__COUNT_SEL__32_BITS_OF_DATA	0
+#define		PACKET3_COPY_DATA__COUNT_SEL__64_BITS_OF_DATA	1
+#define		PACKET3_COPY_DATA__WR_CONFIRM__DO_NOT_WAIT_FOR_CONFIRMATION	0
+#define		PACKET3_COPY_DATA__WR_CONFIRM__WAIT_FOR_CONFIRMATION	1
+#define		PACKET3_COPY_DATA__DST_CACHE_POLICY__LRU	0
+#define		PACKET3_COPY_DATA__DST_CACHE_POLICY__STREAM	1
+#define		PACKET3_COPY_DATA__PQ_EXE_STATUS__DEFAULT	0
+#define		PACKET3_COPY_DATA__PQ_EXE_STATUS__PHASE_UPDATE	1
 #define	PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_COND_WRITE				0x45
 #define	PACKET3_EVENT_WRITE				0x46
@@ -181,6 +300,15 @@
 		 * 3 - SAMPLE_STREAMOUTSTAT*
 		 * 4 - *S_PARTIAL_FLUSH
 		 */
+#define		PACKET3_EVENT_WRITE__EVENT_TYPE(x) ((((unsigned)(x)) & 0x3F) << 0)
+#define		PACKET3_EVENT_WRITE__EVENT_INDEX(x) ((((unsigned)(x)) & 0xF) << 8)
+#define		PACKET3_EVENT_WRITE__OFFLOAD_ENABLE(x) ((((unsigned)(x)) & 0x1) << 31)
+#define		PACKET3_EVENT_WRITE__SAMP_PLST_CNTR_MODE(x) ((((unsigned)(x)) & 0x3) << 29)
+#define		PACKET3_EVENT_WRITE__ADDRESS_LO(x) ((((unsigned)(x)) & 0x1FFFFFFF) << 3)
+#define		PACKET3_EVENT_WRITE__ADDRESS_HI(x) (((unsigned)(x)) << 0)
+#define		PACKET3_EVENT_WRITE__EVENT_INDEX__OTHER	0
+#define		PACKET3_EVENT_WRITE__EVENT_INDEX__SAMPLE_PIPELINESTATS	2
+#define		PACKET3_EVENT_WRITE__EVENT_INDEX__CS_PARTIAL_FLUSH	4
 #define	PACKET3_RELEASE_MEM				0x49
 #define		EVENT_TYPE(x)                           ((x) << 0)
 #define		EVENT_INDEX(x)                          ((x) << 8)
@@ -286,6 +414,13 @@
 #define 	PACKET3_ACQUIRE_MEM_CP_COHER_CNTL_SH_ICACHE_ACTION_ENA(x) ((x) << 29)
 #define 	PACKET3_ACQUIRE_MEM_CP_COHER_CNTL_SH_KCACHE_WB_ACTION_ENA(x) ((x) << 30)
 #define	PACKET3_REWIND					0x59
+#define		PACKET3_ACQUIRE_MEM__COHER_SIZE(x) ((unsigned)(x))
+#define 	PACKET3_ACQUIRE_MEM__COHER_SIZE_HI(x) ((((unsigned)(x)) & 0xFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__COHER_SIZE_HI_VG10(x) ((((unsigned)(x)) & 0xFFFFFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__COHER_BASE_LO(x) ((unsigned)(x))
+#define 	PACKET3_ACQUIRE_MEM__COHER_BASE_HI(x) ((((unsigned)(x)) & 0xFFFFFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__POLL_INTERVAL(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_ACQUIRE_MEM__GCR_CNTL(x) ((((unsigned)(x)) & 0x7FF) << 0)
 #define	PACKET3_LOAD_UCONFIG_REG			0x5E
 #define	PACKET3_LOAD_SH_REG				0x5F
 #define	PACKET3_LOAD_CONFIG_REG				0x60
@@ -300,12 +435,16 @@
 #define	PACKET3_SET_SH_REG				0x76
 #define		PACKET3_SET_SH_REG_START			0x00002c00
 #define		PACKET3_SET_SH_REG_END				0x00003000
+#define 	PACKET3_SET_SH_REG__REG_OFFSET(x) ((((unsigned)(x)) & 0xFFFF) << 0)
+#define 	PACKET3_SET_SH_REG__VMID_SHIFT(x) ((((unsigned)(x)) & 0x1F) << 23)
+#define 	PACKET3_SET_SH_REG__INDEX(x) ((((unsigned)(x)) & 0xF) << 28)
 #define	PACKET3_SET_SH_REG_OFFSET			0x77
 #define	PACKET3_SET_QUEUE_REG				0x78
 #define	PACKET3_SET_UCONFIG_REG				0x79
 #define		PACKET3_SET_UCONFIG_REG_START			0x0000c000
 #define		PACKET3_SET_UCONFIG_REG_END			0x0000c400
 #define		PACKET3_SET_UCONFIG_REG_INDEX_TYPE		(2 << 28)
+#define 	PACKET3_SET_UCONFIG_REG__REG_OFFSET(x) ((((unsigned)(x)) & 0xFFFF) << 0)
 #define	PACKET3_SCRATCH_RAM_WRITE			0x7D
 #define	PACKET3_SCRATCH_RAM_READ			0x7E
 #define	PACKET3_LOAD_CONST_RAM				0x80
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 62ad67d0b598..ad36c96478a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -117,23 +117,17 @@ static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn1 = {
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
@@ -390,6 +384,7 @@ soc21_asic_reset_method(struct amdgpu_device *adev)
 	case IP_VERSION(14, 0, 0):
 	case IP_VERSION(14, 0, 1):
 	case IP_VERSION(14, 0, 4):
+	case IP_VERSION(14, 0, 5):
 		return AMD_RESET_METHOD_MODE2;
 	default:
 		if (amdgpu_dpm_is_baco_supported(adev))
@@ -781,6 +776,34 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block)
 			AMD_PG_SUPPORT_GFX_PG;
 		adev->external_rev_id = adev->rev_id + 0x40;
 		break;
+	case IP_VERSION(11, 5, 3):
+		adev->cg_flags = AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_FGCG |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_PERF_CLK |
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_DS |
+			AMD_CG_SUPPORT_HDP_SD |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS;
+		adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG_DPG |
+			AMD_PG_SUPPORT_JPEG |
+			AMD_PG_SUPPORT_GFX_PG;
+		adev->external_rev_id = adev->rev_id + 0x50;
+		break;
 	default:
 		/* FIXME: not supported yet */
 		return -EINVAL;
@@ -923,7 +946,7 @@ static int soc21_common_resume(struct amdgpu_ip_block *ip_block)
 	return soc21_common_hw_init(ip_block);
 }
 
-static bool soc21_common_is_idle(void *handle)
+static bool soc21_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
@@ -940,6 +963,7 @@ static int soc21_common_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	case IP_VERSION(7, 7, 1):
 	case IP_VERSION(7, 11, 0):
 	case IP_VERSION(7, 11, 1):
+	case IP_VERSION(7, 11, 2):
 	case IP_VERSION(7, 11, 3):
 		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
@@ -972,9 +996,9 @@ static int soc21_common_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void soc21_common_get_clockgating_state(void *handle, u64 *flags)
+static void soc21_common_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	adev->nbio.funcs->get_clockgating_state(adev, flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index 6b8e078ee7c7..972b449ab89f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -26,7 +26,6 @@
 #include <linux/pci.h>
 
 #include "amdgpu.h"
-#include "amdgpu_atombios.h"
 #include "amdgpu_ih.h"
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
@@ -532,7 +531,7 @@ static int soc24_common_resume(struct amdgpu_ip_block *ip_block)
 	return soc24_common_hw_init(ip_block);
 }
 
-static bool soc24_common_is_idle(void *handle)
+static bool soc24_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
@@ -575,9 +574,9 @@ static int soc24_common_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void soc24_common_get_clockgating_state(void *handle, u64 *flags)
+static void soc24_common_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	adev->nbio.funcs->get_clockgating_state(adev, flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h b/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h
index 64891f099366..a3b5fda22432 100644
--- a/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h
@@ -151,6 +151,7 @@ struct ta_ras_init_flags {
 	uint16_t xcc_mask;
 	uint8_t channel_dis_num;
 	uint8_t nps_mode;
+	uint32_t active_umc_mask;
 };
 
 struct ta_ras_mca_addr {
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 0968e551f7b5..7d17ae56f901 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -353,9 +353,9 @@ static int tonga_ih_resume(struct amdgpu_ip_block *ip_block)
 	return tonga_ih_hw_init(ip_block);
 }
 
-static bool tonga_ih_is_idle(void *handle)
+static bool tonga_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 tmp = RREG32(mmSRBM_STATUS);
 
 	if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY))
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index a7b9c358a2d4..74f57b2d30a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -415,6 +415,7 @@ static int umc_v12_0_aca_bank_parser(struct aca_handle *handle, struct aca_bank
 		err_type = ACA_ERROR_TYPE_CE;
 	else
 		return 0;
+	bank->aca_err_type = err_type;
 
 	ret = aca_bank_info_decode(bank, &info);
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
index 5830e799c0a3..5dbaebb592b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
@@ -98,7 +98,7 @@ static void uvd_v3_1_ring_emit_ib(struct amdgpu_ring *ring,
 }
 
 /**
- * uvd_v3_1_ring_emit_fence - emit an fence & trap command
+ * uvd_v3_1_ring_emit_fence - emit a fence & trap command
  *
  * @ring: amdgpu_ring pointer
  * @addr: address
@@ -242,7 +242,7 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev)
 	uint64_t addr;
 	uint32_t size;
 
-	/* programm the VCPU memory controller bits 0-27 */
+	/* program the VCPU memory controller bits 0-27 */
 	addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3;
 	size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3;
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr);
@@ -416,7 +416,7 @@ static int uvd_v3_1_start(struct amdgpu_device *adev)
 	/* Set the write pointer delay */
 	WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0);
 
-	/* programm the 4GB memory segment for rptr and ring buffer */
+	/* Program the 4GB memory segment for rptr and ring buffer */
 	WREG32(mmUVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) |
 		   (0x7 << 16) | (0x1 << 31));
 
@@ -758,9 +758,9 @@ static int uvd_v3_1_resume(struct amdgpu_ip_block *ip_block)
 	return uvd_v3_1_hw_init(ip_block);
 }
 
-static bool uvd_v3_1_is_idle(void *handle)
+static bool uvd_v3_1_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index f93079e09215..4b96fd583772 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -302,7 +302,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev)
 	/* enable VCPU clock */
 	WREG32(mmUVD_VCPU_CNTL,  1 << 9);
 
-	/* disable interupt */
+	/* disable interrupt */
 	WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1));
 
 #ifdef __BIG_ENDIAN
@@ -312,6 +312,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev)
 #endif
 	WREG32(mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl);
 	WREG32(mmUVD_MP_SWAP_CNTL, mp_swap_cntl);
+
 	/* initialize UVD memory controller */
 	WREG32(mmUVD_LMI_CTRL, 0x203108);
 
@@ -658,9 +659,9 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
 	WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2);
 }
 
-static bool uvd_v4_2_is_idle(void *handle)
+static bool uvd_v4_2_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 050a0f309390..71409ad8b7ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -580,9 +580,9 @@ static void uvd_v5_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
 	}
 }
 
-static bool uvd_v5_0_is_idle(void *handle)
+static bool uvd_v5_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK);
 }
@@ -837,9 +837,9 @@ out:
 	return ret;
 }
 
-static void uvd_v5_0_get_clockgating_state(void *handle, u64 *flags)
+static void uvd_v5_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	mutex_lock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d9d036ee51fb..1c07b701d0e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -1143,9 +1143,9 @@ static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, vmid);
 }
 
-static bool uvd_v6_0_is_idle(void *handle)
+static bool uvd_v6_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK);
 }
@@ -1156,7 +1156,7 @@ static int uvd_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (uvd_v6_0_is_idle(adev))
+		if (uvd_v6_0_is_idle(ip_block))
 			return 0;
 	}
 	return -ETIMEDOUT;
@@ -1498,9 +1498,9 @@ out:
 	return ret;
 }
 
-static void uvd_v6_0_get_clockgating_state(void *handle, u64 *flags)
+static void uvd_v6_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	mutex_lock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 09fd6ef99b3d..bee3e904a6bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -201,9 +201,9 @@ static void vce_v2_0_mc_resume(struct amdgpu_device *adev)
 	WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1);
 }
 
-static bool vce_v2_0_is_idle(void *handle)
+static bool vce_v2_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK);
 }
@@ -214,7 +214,7 @@ static int vce_v2_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	unsigned i;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (vce_v2_0_is_idle(adev))
+		if (vce_v2_0_is_idle(ip_block))
 			return 0;
 	}
 	return -ETIMEDOUT;
@@ -280,7 +280,7 @@ static int vce_v2_0_stop(struct amdgpu_device *adev)
 
 
 	if (vce_v2_0_lmi_clean(adev)) {
-		DRM_INFO("vce is not idle \n");
+		DRM_INFO("VCE is not idle \n");
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index f8bddcd19b68..708123899c41 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -597,9 +597,9 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx)
 	WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1);
 }
 
-static bool vce_v3_0_is_idle(void *handle)
+static bool vce_v3_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	u32 mask = 0;
 
 	mask |= (adev->vce.harvest_config & AMDGPU_VCE_HARVEST_VCE0) ? 0 : SRBM_STATUS2__VCE0_BUSY_MASK;
@@ -614,7 +614,7 @@ static int vce_v3_0_wait_for_idle(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (i = 0; i < adev->usec_timeout; i++)
-		if (vce_v3_0_is_idle(adev))
+		if (vce_v3_0_is_idle(ip_block))
 			return 0;
 
 	return -ETIMEDOUT;
@@ -828,9 +828,9 @@ out:
 	return ret;
 }
 
-static void vce_v3_0_get_clockgating_state(void *handle, u64 *flags)
+static void vce_v3_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	mutex_lock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 5ea96c983517..21b57c29bf7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -81,14 +81,14 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_1_0[] = {
 	SOC15_REG_ENTRY_STR(VCN, 0, mmUVD_DPG_PAUSE)
 };
 
-static int vcn_v1_0_stop(struct amdgpu_device *adev);
+static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-				enum amd_powergating_state state);
-static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state);
+static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state);
 
 static void vcn_v1_0_idle_work_handler(struct work_struct *work);
 static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
@@ -105,7 +105,8 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	adev->vcn.num_enc_rings = 2;
+	adev->vcn.inst[0].num_enc_rings = 2;
+	adev->vcn.inst[0].set_pg_state = vcn_v1_0_set_pg_state;
 
 	vcn_v1_0_set_dec_ring_funcs(adev);
 	vcn_v1_0_set_enc_ring_funcs(adev);
@@ -113,7 +114,7 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block)
 
 	jpeg_v1_0_early_init(ip_block);
 
-	return amdgpu_vcn_early_init(adev);
+	return amdgpu_vcn_early_init(adev, 0);
 }
 
 /**
@@ -138,23 +139,23 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	/* VCN ENC TRAP */
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE,
 					&adev->vcn.inst->irq);
 		if (r)
 			return r;
 	}
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, 0);
 	if (r)
 		return r;
 
 	/* Override the work func */
-	adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler;
+	adev->vcn.inst[0].idle_work.work.func = vcn_v1_0_idle_work_handler;
 
-	amdgpu_vcn_setup_ucode(adev);
+	amdgpu_vcn_setup_ucode(adev, 0);
 
-	r = amdgpu_vcn_resume(adev);
+	r = amdgpu_vcn_resume(adev, 0);
 	if (r)
 		return r;
 
@@ -166,18 +167,18 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	adev->vcn.internal.scratch9 = adev->vcn.inst->external.scratch9 =
+	adev->vcn.inst[0].internal.scratch9 = adev->vcn.inst->external.scratch9 =
 		SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9);
-	adev->vcn.internal.data0 = adev->vcn.inst->external.data0 =
+	adev->vcn.inst[0].internal.data0 = adev->vcn.inst->external.data0 =
 		SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0);
-	adev->vcn.internal.data1 = adev->vcn.inst->external.data1 =
+	adev->vcn.inst[0].internal.data1 = adev->vcn.inst->external.data1 =
 		SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1);
-	adev->vcn.internal.cmd = adev->vcn.inst->external.cmd =
+	adev->vcn.inst[0].internal.cmd = adev->vcn.inst->external.cmd =
 		SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD);
-	adev->vcn.internal.nop = adev->vcn.inst->external.nop =
+	adev->vcn.inst[0].internal.nop = adev->vcn.inst->external.nop =
 		SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP);
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i);
 
 		ring = &adev->vcn.inst->ring_enc[i];
@@ -189,7 +190,7 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode;
+	adev->vcn.inst[0].pause_dpg_mode = vcn_v1_0_pause_dpg_mode;
 
 	if (amdgpu_vcnfw_log) {
 		volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
@@ -223,13 +224,13 @@ static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	int r;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	r = amdgpu_vcn_suspend(adev);
+	r = amdgpu_vcn_suspend(adev, 0);
 	if (r)
 		return r;
 
 	jpeg_v1_0_sw_fini(ip_block);
 
-	r = amdgpu_vcn_sw_fini(adev);
+	r = amdgpu_vcn_sw_fini(adev, 0);
 
 	kfree(adev->vcn.ip_dump);
 
@@ -253,7 +254,7 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		ring = &adev->vcn.inst->ring_enc[i];
 		r = amdgpu_ring_test_helper(ring);
 		if (r)
@@ -276,13 +277,14 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v1_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_vcn_inst *vinst = adev->vcn.inst;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&vinst->idle_work);
 
 	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-		(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
-		 RREG32_SOC15(VCN, 0, mmUVD_STATUS))) {
-		vcn_v1_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+	    (vinst->cur_state != AMD_PG_STATE_GATE &&
+	     RREG32_SOC15(VCN, 0, mmUVD_STATUS))) {
+		vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 	}
 
 	return 0;
@@ -301,7 +303,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	bool idle_work_unexecuted;
 
-	idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work);
+	idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
 	if (idle_work_unexecuted) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_vcn(adev, false, 0);
@@ -311,7 +313,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(adev);
+	r = amdgpu_vcn_suspend(adev, 0);
 
 	return r;
 }
@@ -327,7 +329,7 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block)
 {
 	int r;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
+	r = amdgpu_vcn_resume(ip_block->adev, 0);
 	if (r)
 		return r;
 
@@ -339,12 +341,13 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v1_0_mc_resume_spg_mode - memory controller programming
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
+static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4);
 	uint32_t offset;
 
@@ -410,8 +413,9 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
 			adev->gfx.config.gb_addr_config);
 }
 
-static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
+static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4);
 	uint32_t offset;
 
@@ -485,12 +489,13 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
 /**
  * vcn_v1_0_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v1_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data;
 
 	/* JPEG disable CGC */
@@ -611,12 +616,13 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev)
 /**
  * vcn_v1_0_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: Pointer to the VCN instance structure
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v1_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	/* enable JPEG CGC */
@@ -680,8 +686,10 @@ static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev)
 	WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel)
+static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					   uint8_t sram_sel)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t reg_data = 0;
 
 	/* disable JPEG CGC */
@@ -734,8 +742,9 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s
 	WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SUVD_CGC_CTRL, 0, 0xFFFFFFFF, sram_sel);
 }
 
-static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
+static void vcn_1_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -779,8 +788,9 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
 	WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data);
 }
 
-static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev)
+static void vcn_1_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -823,12 +833,13 @@ static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev)
 /**
  * vcn_v1_0_start_spg_mode - start VCN block
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Setup and start the VCN block
  */
-static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
+static int vcn_v1_0_start_spg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
@@ -837,13 +848,13 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
 
-	vcn_1_0_disable_static_power_gating(adev);
+	vcn_1_0_disable_static_power_gating(vinst);
 
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
 	WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp);
 
 	/* disable clock gating */
-	vcn_v1_0_disable_clock_gating(adev);
+	vcn_v1_0_disable_clock_gating(vinst);
 
 	/* disable interupt */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
@@ -885,7 +896,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 		(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
 
-	vcn_v1_0_mc_resume_spg_mode(adev);
+	vcn_v1_0_mc_resume_spg_mode(vinst);
 
 	WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10);
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0,
@@ -1001,8 +1012,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
+static int vcn_v1_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
@@ -1010,7 +1022,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
 
-	vcn_1_0_enable_static_power_gating(adev);
+	vcn_1_0_enable_static_power_gating(vinst);
 
 	/* enable dynamic power gating mode */
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS);
@@ -1019,7 +1031,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, tmp);
 
 	/* enable clock gating */
-	vcn_v1_0_clock_gating_dpg_mode(adev, 0);
+	vcn_v1_0_clock_gating_dpg_mode(vinst, 0);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -1068,7 +1080,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0xFFFFFFFF, 0);
 
-	vcn_v1_0_mc_resume_dpg_mode(adev);
+	vcn_v1_0_mc_resume_dpg_mode(vinst);
 
 	WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_REG_XX_MASK, 0x10, 0xFFFFFFFF, 0);
 	WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK, 0x3, 0xFFFFFFFF, 0);
@@ -1085,7 +1097,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MASTINT_EN,
 			UVD_MASTINT_EN__VCPU_EN_MASK, UVD_MASTINT_EN__VCPU_EN_MASK, 0);
 
-	vcn_v1_0_clock_gating_dpg_mode(adev, 1);
+	vcn_v1_0_clock_gating_dpg_mode(vinst, 1);
 	/* setup mmUVD_LMI_CTRL */
 	WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL,
 		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
@@ -1145,21 +1157,24 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v1_0_start(struct amdgpu_device *adev)
+static int vcn_v1_0_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+
 	return (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ?
-		vcn_v1_0_start_dpg_mode(adev) : vcn_v1_0_start_spg_mode(adev);
+		vcn_v1_0_start_dpg_mode(vinst) : vcn_v1_0_start_spg_mode(vinst);
 }
 
 /**
  * vcn_v1_0_stop_spg_mode - stop VCN block
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * stop the VCN block
  */
-static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
+static int vcn_v1_0_stop_spg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	int tmp;
 
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
@@ -1199,13 +1214,14 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
 
 	WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0);
 
-	vcn_v1_0_enable_clock_gating(adev);
-	vcn_1_0_enable_static_power_gating(adev);
+	vcn_v1_0_enable_clock_gating(vinst);
+	vcn_1_0_enable_static_power_gating(vinst);
 	return 0;
 }
 
-static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev)
+static int vcn_v1_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t tmp;
 
 	/* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */
@@ -1237,21 +1253,24 @@ static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v1_0_stop(struct amdgpu_device *adev)
+static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	int r;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		r = vcn_v1_0_stop_dpg_mode(adev);
+		r = vcn_v1_0_stop_dpg_mode(vinst);
 	else
-		r = vcn_v1_0_stop_spg_mode(adev);
+		r = vcn_v1_0_stop_spg_mode(vinst);
 
 	return r;
 }
 
-static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state)
+static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	int ret_code;
 	uint32_t reg_data = 0;
 	uint32_t reg_data2 = 0;
@@ -1377,9 +1396,9 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
 	return 0;
 }
 
-static bool vcn_v1_0_is_idle(void *handle)
+static bool vcn_v1_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE);
 }
@@ -1399,16 +1418,17 @@ static int vcn_v1_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_vcn_inst *vinst = adev->vcn.inst;
 	bool enable = (state == AMD_CG_STATE_GATE);
 
 	if (enable) {
 		/* wait for STATUS to clear */
-		if (!vcn_v1_0_is_idle(adev))
+		if (!vcn_v1_0_is_idle(ip_block))
 			return -EBUSY;
-		vcn_v1_0_enable_clock_gating(adev);
+		vcn_v1_0_enable_clock_gating(vinst);
 	} else {
 		/* disable HW gating and enable Sw gating */
-		vcn_v1_0_disable_clock_gating(adev);
+		vcn_v1_0_disable_clock_gating(vinst);
 	}
 	return 0;
 }
@@ -1800,8 +1820,8 @@ static void vcn_v1_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t coun
 	}
 }
 
-static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state)
 {
 	/* This doesn't actually powergate the VCN block.
 	 * That's done in the dpm code via the SMC.  This
@@ -1811,28 +1831,29 @@ static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	 * the smc and the hw blocks
 	 */
 	int ret;
-	struct amdgpu_device *adev = ip_block->adev;
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v1_0_stop(adev);
+		ret = vcn_v1_0_stop(vinst);
 	else
-		ret = vcn_v1_0_start(adev);
+		ret = vcn_v1_0_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
+
 	return ret;
 }
 
 static void vcn_v1_0_idle_work_handler(struct work_struct *work)
 {
-	struct amdgpu_device *adev =
-		container_of(work, struct amdgpu_device, vcn.idle_work.work);
+	struct amdgpu_vcn_inst *vcn_inst =
+		container_of(work, struct amdgpu_vcn_inst, idle_work.work);
+	struct amdgpu_device *adev = vcn_inst->adev;
 	unsigned int fences = 0, i;
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i)
 		fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
@@ -1848,7 +1869,7 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work)
 		else
 			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
 
-		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+		adev->vcn.inst->pause_dpg_mode(vcn_inst, &new_state);
 	}
 
 	fences += amdgpu_fence_count_emitted(adev->jpeg.inst->ring_dec);
@@ -1862,16 +1883,16 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work)
 			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 			       AMD_PG_STATE_GATE);
 	} else {
-		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+		schedule_delayed_work(&adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT);
 	}
 }
 
 static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct	amdgpu_device *adev = ring->adev;
-	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
 
-	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+	mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround);
 
 	if (amdgpu_fence_wait_empty(ring->adev->jpeg.inst->ring_dec))
 		DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n");
@@ -1897,7 +1918,7 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks)
 		struct dpg_pause_state new_state;
 		unsigned int fences = 0, i;
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+		for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i)
 			fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
 
 		if (fences)
@@ -1915,14 +1936,14 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks)
 		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
 			new_state.jpeg = VCN_DPG_STATE__PAUSE;
 
-		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+		adev->vcn.inst->pause_dpg_mode(adev->vcn.inst, &new_state);
 	}
 }
 
 void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring)
 {
-	schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
-	mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround);
+	schedule_delayed_work(&ring->adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT);
+	mutex_unlock(&ring->adev->vcn.inst[0].vcn1_jpeg1_workaround);
 }
 
 static void vcn_v1_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
@@ -1997,7 +2018,7 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.is_idle = vcn_v1_0_is_idle,
 	.wait_for_idle = vcn_v1_0_wait_for_idle,
 	.set_clockgating_state = vcn_v1_0_set_clockgating_state,
-	.set_powergating_state = vcn_v1_0_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v1_0_dump_ip_state,
 	.print_ip_state = vcn_v1_0_print_ip_state,
 };
@@ -2056,11 +2077,11 @@ static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 		uint32_t reg = amdgpu_ib_get_value(ib, i);
 		uint32_t val = amdgpu_ib_get_value(ib, i + 1);
 
-		if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) {
+		if (reg == PACKET0(p->adev->vcn.inst[0].internal.data0, 0)) {
 			msg_lo = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) {
+		} else if (reg == PACKET0(p->adev->vcn.inst[0].internal.data1, 0)) {
 			msg_hi = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) {
+		} else if (reg == PACKET0(p->adev->vcn.inst[0].internal.cmd, 0)) {
 			r = vcn_v1_0_validate_bo(p, job,
 						 ((u64)msg_hi) << 32 | msg_lo);
 			if (r)
@@ -2145,7 +2166,7 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i)
 		adev->vcn.inst->ring_enc[i].funcs = &vcn_v1_0_enc_ring_vm_funcs;
 }
 
@@ -2156,7 +2177,7 @@ static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2;
+	adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 2;
 	adev->vcn.inst->irq.funcs = &vcn_v1_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index e42cfc731ad8..8e7a36f26e9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -92,10 +92,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_0[] = {
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-				enum amd_powergating_state state);
-static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state);
+static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state);
 static int vcn_v2_0_start_sriov(struct amdgpu_device *adev);
 /**
  * vcn_v2_0_early_init - set function pointers and load microcode
@@ -110,15 +110,16 @@ static int vcn_v2_0_early_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	if (amdgpu_sriov_vf(adev))
-		adev->vcn.num_enc_rings = 1;
+		adev->vcn.inst[0].num_enc_rings = 1;
 	else
-		adev->vcn.num_enc_rings = 2;
+		adev->vcn.inst[0].num_enc_rings = 2;
 
+	adev->vcn.inst->set_pg_state = vcn_v2_0_set_pg_state;
 	vcn_v2_0_set_dec_ring_funcs(adev);
 	vcn_v2_0_set_enc_ring_funcs(adev);
 	vcn_v2_0_set_irq_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	return amdgpu_vcn_early_init(adev, 0);
 }
 
 /**
@@ -145,7 +146,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	/* VCN ENC TRAP */
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
 				      i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE,
 				      &adev->vcn.inst->irq);
@@ -153,13 +154,13 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	r = amdgpu_vcn_sw_init(adev);
+	r = amdgpu_vcn_sw_init(adev, 0);
 	if (r)
 		return r;
 
-	amdgpu_vcn_setup_ucode(adev);
+	amdgpu_vcn_setup_ucode(adev, 0);
 
-	r = amdgpu_vcn_resume(adev);
+	r = amdgpu_vcn_resume(adev, 0);
 	if (r)
 		return r;
 
@@ -175,25 +176,25 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
-	adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
-	adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
-	adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
-	adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
-	adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
 
-	adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
 	adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9);
-	adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
 	adev->vcn.inst->external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0);
-	adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
 	adev->vcn.inst->external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1);
-	adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
 	adev->vcn.inst->external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD);
-	adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
+	adev->vcn.inst[0].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 	adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP);
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i);
 
 		ring = &adev->vcn.inst->ring_enc[i];
@@ -210,7 +211,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode;
+	adev->vcn.inst[0].pause_dpg_mode = vcn_v2_0_pause_dpg_mode;
 
 	r = amdgpu_virt_alloc_mm_table(adev);
 	if (r)
@@ -254,11 +255,11 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block)
 
 	amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
+	r = amdgpu_vcn_suspend(adev, 0);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_sw_fini(adev);
+	r = amdgpu_vcn_sw_fini(adev, 0);
 
 	kfree(adev->vcn.ip_dump);
 
@@ -292,7 +293,7 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		ring->sched.ready = false;
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		ring = &adev->vcn.inst->ring_enc[i];
 		r = amdgpu_ring_test_helper(ring);
 		if (r)
@@ -312,13 +313,14 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v2_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_vcn_inst *vinst = adev->vcn.inst;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&vinst->idle_work);
 
 	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-	    (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
-	      RREG32_SOC15(VCN, 0, mmUVD_STATUS)))
-		vcn_v2_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+	    (vinst->cur_state != AMD_PG_STATE_GATE &&
+	     RREG32_SOC15(VCN, 0, mmUVD_STATUS)))
+		vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 
 	return 0;
 }
@@ -338,7 +340,7 @@ static int vcn_v2_0_suspend(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	r = amdgpu_vcn_suspend(ip_block->adev, 0);
 
 	return r;
 }
@@ -354,7 +356,7 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block)
 {
 	int r;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
+	r = amdgpu_vcn_resume(ip_block->adev, 0);
 	if (r)
 		return r;
 
@@ -366,12 +368,13 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v2_0_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
+ * @vinst: Pointer to the VCN instance structure
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
+static void vcn_v2_0_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4);
 	uint32_t offset;
 
@@ -426,8 +429,10 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
 }
 
-static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect)
+static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4);
 	uint32_t offset;
 
@@ -525,12 +530,13 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 /**
  * vcn_v2_0_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data;
 
 	if (amdgpu_sriov_vf(adev))
@@ -634,9 +640,10 @@ static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev)
 	WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
+static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		uint8_t sram_sel, uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t reg_data = 0;
 
 	/* enable sw clock gating control */
@@ -685,12 +692,13 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v2_0_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	if (amdgpu_sriov_vf(adev))
@@ -743,8 +751,9 @@ static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev)
 	WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev)
+static void vcn_v2_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	if (amdgpu_sriov_vf(adev))
@@ -792,8 +801,9 @@ static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev)
 	WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data);
 }
 
-static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev)
+static void vcn_v2_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t data = 0;
 
 	if (amdgpu_sriov_vf(adev))
@@ -834,13 +844,14 @@ static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev)
 	}
 }
 
-static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
+static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
 
-	vcn_v2_0_enable_static_power_gating(adev);
+	vcn_v2_0_enable_static_power_gating(vinst);
 
 	/* enable dynamic power gating mode */
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS);
@@ -852,7 +863,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 		adev->vcn.inst->dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst->dpg_sram_cpu_addr;
 
 	/* enable clock gating */
-	vcn_v2_0_clock_gating_dpg_mode(adev, 0, indirect);
+	vcn_v2_0_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -901,7 +912,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v2_0_mc_resume_dpg_mode(adev, indirect);
+	vcn_v2_0_mc_resume_dpg_mode(vinst, indirect);
 
 	WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET(
 		UVD, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
@@ -969,8 +980,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	return 0;
 }
 
-static int vcn_v2_0_start(struct amdgpu_device *adev)
+static int vcn_v2_0_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
@@ -981,16 +993,16 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 		amdgpu_dpm_enable_vcn(adev, true, 0);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		return vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram);
+		return vcn_v2_0_start_dpg_mode(vinst, adev->vcn.inst->indirect_sram);
 
-	vcn_v2_0_disable_static_power_gating(adev);
+	vcn_v2_0_disable_static_power_gating(vinst);
 
 	/* set uvd status busy */
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
 	WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp);
 
 	/*SW clock gating */
-	vcn_v2_0_disable_clock_gating(adev);
+	vcn_v2_0_disable_clock_gating(vinst);
 
 	/* enable VCPU clock */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CNTL),
@@ -1034,7 +1046,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 		(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
 
-	vcn_v2_0_mc_resume(adev);
+	vcn_v2_0_mc_resume(vinst);
 
 	/* release VCPU reset to boot */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), 0,
@@ -1142,12 +1154,13 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
+static int vcn_v2_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
-	vcn_v2_0_pause_dpg_mode(adev, 0, &state);
+	vcn_v2_0_pause_dpg_mode(vinst, &state);
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, 1,
 		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
@@ -1172,13 +1185,14 @@ static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v2_0_stop(struct amdgpu_device *adev)
+static int vcn_v2_0_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
 	uint32_t tmp;
 	int r;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-		r = vcn_v2_0_stop_dpg_mode(adev);
+		r = vcn_v2_0_stop_dpg_mode(vinst);
 		if (r)
 			return r;
 		goto power_off;
@@ -1230,8 +1244,8 @@ static int vcn_v2_0_stop(struct amdgpu_device *adev)
 	/* clear status */
 	WREG32_SOC15(VCN, 0, mmUVD_STATUS, 0);
 
-	vcn_v2_0_enable_clock_gating(adev);
-	vcn_v2_0_enable_static_power_gating(adev);
+	vcn_v2_0_enable_clock_gating(vinst);
+	vcn_v2_0_enable_static_power_gating(vinst);
 
 power_off:
 	if (adev->pm.dpm_enabled)
@@ -1240,9 +1254,11 @@ power_off:
 	return 0;
 }
 
-static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state)
+static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	struct amdgpu_ring *ring;
 	uint32_t reg_data = 0;
 	int ret_code;
@@ -1317,9 +1333,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
 	return 0;
 }
 
-static bool vcn_v2_0_is_idle(void *handle)
+static bool vcn_v2_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE);
 }
@@ -1346,12 +1362,12 @@ static int vcn_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 
 	if (enable) {
 		/* wait for STATUS to clear */
-		if (!vcn_v2_0_is_idle(adev))
+		if (!vcn_v2_0_is_idle(ip_block))
 			return -EBUSY;
-		vcn_v2_0_enable_clock_gating(adev);
+		vcn_v2_0_enable_clock_gating(&adev->vcn.inst[0]);
 	} else {
 		/* disable HW gating and enable Sw gating */
-		vcn_v2_0_disable_clock_gating(adev);
+		vcn_v2_0_disable_clock_gating(&adev->vcn.inst[0]);
 	}
 	return 0;
 }
@@ -1421,9 +1437,9 @@ void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0));
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1));
 }
 
@@ -1438,7 +1454,7 @@ void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[0].internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_END << 1));
 }
 
@@ -1458,7 +1474,7 @@ void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
 	WARN_ON(ring->wptr % 2 || count % 2);
 
 	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.nop, 0));
+		amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.nop, 0));
 		amdgpu_ring_write(ring, 0);
 	}
 }
@@ -1479,25 +1495,25 @@ void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 	struct amdgpu_device *adev = ring->adev;
 
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.context_id, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.context_id, 0));
 	amdgpu_ring_write(ring, seq);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0));
 	amdgpu_ring_write(ring, addr & 0xffffffff);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0));
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_FENCE << 1));
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0));
 	amdgpu_ring_write(ring, 0);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0));
 	amdgpu_ring_write(ring, 0);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_TRAP << 1));
 }
@@ -1520,14 +1536,14 @@ void vcn_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_vmid, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_vmid, 0));
 	amdgpu_ring_write(ring, vmid);
 
-	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_bar_low, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_low, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_bar_high, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_high, 0));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_size, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.inst[ring->me].internal.ib_size, 0));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
@@ -1536,16 +1552,16 @@ void vcn_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0));
 	amdgpu_ring_write(ring, reg << 2);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0));
 	amdgpu_ring_write(ring, val);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.gp_scratch8, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.gp_scratch8, 0));
 	amdgpu_ring_write(ring, mask);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_REG_READ_COND_WAIT << 1));
 }
@@ -1570,13 +1586,13 @@ void vcn_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring,
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0));
 	amdgpu_ring_write(ring, reg << 2);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0));
 	amdgpu_ring_write(ring, val);
 
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_WRITE_REG << 1));
 }
@@ -1777,9 +1793,9 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 4);
 	if (r)
 		return r;
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1));
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0));
 	amdgpu_ring_write(ring, 0xDEADBEEF);
 	amdgpu_ring_commit(ring);
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -1796,8 +1812,8 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 
-static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state)
 {
 	/* This doesn't actually powergate the VCN block.
 	 * That's done in the dpm code via the SMC.  This
@@ -1807,23 +1823,24 @@ static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	 * the smc and the hw blocks
 	 */
 	int ret;
-	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_device *adev = vinst->adev;
 
 	if (amdgpu_sriov_vf(adev)) {
-		adev->vcn.cur_state = AMD_PG_STATE_UNGATE;
+		vinst->cur_state = AMD_PG_STATE_UNGATE;
 		return 0;
 	}
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v2_0_stop(adev);
+		ret = vcn_v2_0_stop(vinst);
 	else
-		ret = vcn_v2_0_start(adev);
+		ret = vcn_v2_0_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
+
 	return ret;
 }
 
@@ -1862,7 +1879,7 @@ static int vcn_v2_0_start_mmsch(struct amdgpu_device *adev,
 	adev->vcn.inst->ring_dec.wptr_old = 0;
 	vcn_v2_0_dec_ring_set_wptr(&adev->vcn.inst->ring_dec);
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) {
 		adev->vcn.inst->ring_enc[i].wptr = 0;
 		adev->vcn.inst->ring_enc[i].wptr_old = 0;
 		vcn_v2_0_enc_ring_set_wptr(&adev->vcn.inst->ring_enc[i]);
@@ -1988,7 +2005,7 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev)
 			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2),
 			AMDGPU_VCN_CONTEXT_SIZE);
 
-		for (r = 0; r < adev->vcn.num_enc_rings; ++r) {
+		for (r = 0; r < adev->vcn.inst[0].num_enc_rings; ++r) {
 			ring = &adev->vcn.inst->ring_enc[r];
 			ring->wptr = 0;
 			MMSCH_V2_0_INSERT_DIRECT_WT(
@@ -2104,7 +2121,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = {
 	.is_idle = vcn_v2_0_is_idle,
 	.wait_for_idle = vcn_v2_0_wait_for_idle,
 	.set_clockgating_state = vcn_v2_0_set_clockgating_state,
-	.set_powergating_state = vcn_v2_0_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v2_0_dump_ip_state,
 	.print_ip_state = vcn_v2_0_print_ip_state,
 };
@@ -2177,7 +2194,7 @@ static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+	for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i)
 		adev->vcn.inst->ring_enc[i].funcs = &vcn_v2_0_enc_ring_vm_funcs;
 }
 
@@ -2188,7 +2205,7 @@ static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = {
 
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 1;
+	adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 1;
 	adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index b518202955ca..d716510b8dd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -95,10 +95,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_5[] = {
 static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
-				enum amd_powergating_state state);
-static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state);
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state);
 static int vcn_v2_5_sriov_start(struct amdgpu_device *adev);
 static void vcn_v2_5_set_ras_funcs(struct amdgpu_device *adev);
 
@@ -107,6 +107,133 @@ static int amdgpu_ih_clientid_vcns[] = {
 	SOC15_IH_CLIENTID_VCN1
 };
 
+static void vcn_v2_5_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_vcn_inst *vcn_inst =
+		container_of(work, struct amdgpu_vcn_inst, idle_work.work);
+	struct amdgpu_device *adev = vcn_inst->adev;
+	unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0};
+	unsigned int i, j;
+	int r = 0;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *v = &adev->vcn.inst[i];
+
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
+		for (j = 0; j < v->num_enc_rings; ++j)
+			fence[i] += amdgpu_fence_count_emitted(&v->ring_enc[j]);
+
+		/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+		    !v->using_unified_queue) {
+			struct dpg_pause_state new_state;
+
+			if (fence[i] ||
+			    unlikely(atomic_read(&v->dpg_enc_submission_cnt)))
+				new_state.fw_based = VCN_DPG_STATE__PAUSE;
+			else
+				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+			v->pause_dpg_mode(v, &new_state);
+		}
+
+		fence[i] += amdgpu_fence_count_emitted(&v->ring_dec);
+		fences += fence[i];
+
+	}
+
+	if (!fences && !atomic_read(&adev->vcn.inst[0].total_submission_cnt)) {
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+						       AMD_PG_STATE_GATE);
+		mutex_lock(&adev->vcn.workload_profile_mutex);
+		if (adev->vcn.workload_profile_active) {
+			r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+							    false);
+			if (r)
+				dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
+			adev->vcn.workload_profile_active = false;
+		}
+		mutex_unlock(&adev->vcn.workload_profile_mutex);
+	} else {
+		schedule_delayed_work(&adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT);
+	}
+}
+
+static void vcn_v2_5_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_vcn_inst *v = &adev->vcn.inst[ring->me];
+	int r = 0;
+
+	atomic_inc(&adev->vcn.inst[0].total_submission_cnt);
+
+	cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
+
+	/* We can safely return early here because we've cancelled the
+	 * the delayed work so there is no one else to set it to false
+	 * and we don't care if someone else sets it to true.
+	 */
+	if (adev->vcn.workload_profile_active)
+		goto pg_lock;
+
+	mutex_lock(&adev->vcn.workload_profile_mutex);
+	if (!adev->vcn.workload_profile_active) {
+		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+						    true);
+		if (r)
+			dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r);
+		adev->vcn.workload_profile_active = true;
+	}
+	mutex_unlock(&adev->vcn.workload_profile_mutex);
+
+pg_lock:
+	mutex_lock(&adev->vcn.inst[0].vcn_pg_lock);
+	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+					       AMD_PG_STATE_UNGATE);
+
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    !v->using_unified_queue) {
+		struct dpg_pause_state new_state;
+
+		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
+			atomic_inc(&v->dpg_enc_submission_cnt);
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		} else {
+			unsigned int fences = 0;
+			unsigned int i;
+
+			for (i = 0; i < v->num_enc_rings; ++i)
+				fences += amdgpu_fence_count_emitted(&v->ring_enc[i]);
+
+			if (fences || atomic_read(&v->dpg_enc_submission_cnt))
+				new_state.fw_based = VCN_DPG_STATE__PAUSE;
+			else
+				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+		}
+		v->pause_dpg_mode(v, &new_state);
+	}
+	mutex_unlock(&adev->vcn.inst[0].vcn_pg_lock);
+}
+
+static void vcn_v2_5_ring_end_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
+	    !adev->vcn.inst[ring->me].using_unified_queue)
+		atomic_dec(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
+
+	atomic_dec(&adev->vcn.inst[0].total_submission_cnt);
+
+	schedule_delayed_work(&adev->vcn.inst[0].idle_work,
+			      VCN_IDLE_TIMEOUT);
+}
+
 /**
  * vcn_v2_5_early_init - set function pointers and load microcode
  *
@@ -118,11 +245,13 @@ static int amdgpu_ih_clientid_vcns[] = {
 static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
 
 	if (amdgpu_sriov_vf(adev)) {
 		adev->vcn.num_vcn_inst = 2;
 		adev->vcn.harvest_config = 0;
-		adev->vcn.num_enc_rings = 1;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++)
+			adev->vcn.inst[i].num_enc_rings = 1;
 	} else {
 		u32 harvest;
 		int i;
@@ -131,13 +260,12 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block)
 			harvest = RREG32_SOC15(VCN, i, mmCC_UVD_HARVESTING);
 			if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
 				adev->vcn.harvest_config |= 1 << i;
+			adev->vcn.inst[i].num_enc_rings = 2;
 		}
 		if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 |
-					AMDGPU_VCN_HARVEST_VCN1))
+						 AMDGPU_VCN_HARVEST_VCN1))
 			/* both instances are harvested, disable the block */
 			return -ENOENT;
-
-		adev->vcn.num_enc_rings = 2;
 	}
 
 	vcn_v2_5_set_dec_ring_funcs(adev);
@@ -145,7 +273,15 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block)
 	vcn_v2_5_set_irq_funcs(adev);
 	vcn_v2_5_set_ras_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		adev->vcn.inst[i].set_pg_state = vcn_v2_5_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
 }
 
 /**
@@ -164,6 +300,8 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (j = 0; j < adev->vcn.num_vcn_inst; j++) {
+		volatile struct amdgpu_fw_shared *fw_shared;
+
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
 		/* VCN DEC TRAP */
@@ -173,7 +311,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 
 		/* VCN ENC TRAP */
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+		for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) {
 			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j],
 				i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[j].irq);
 			if (r)
@@ -185,39 +323,36 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 			VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].ras_poison_irq);
 		if (r)
 			return r;
-	}
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
+		r = amdgpu_vcn_sw_init(adev, j);
+		if (r)
+			return r;
 
-	amdgpu_vcn_setup_ucode(adev);
+		/* Override the work func */
+		adev->vcn.inst[j].idle_work.work.func = vcn_v2_5_idle_work_handler;
 
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
+		amdgpu_vcn_setup_ucode(adev, j);
 
-	for (j = 0; j < adev->vcn.num_vcn_inst; j++) {
-		volatile struct amdgpu_fw_shared *fw_shared;
+		r = amdgpu_vcn_resume(adev, j);
+		if (r)
+			return r;
 
-		if (adev->vcn.harvest_config & (1 << j))
-			continue;
-		adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
-		adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
-
-		adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
+
+		adev->vcn.inst[j].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.scratch9 = SOC15_REG_OFFSET(VCN, j, mmUVD_SCRATCH9);
-		adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.data0 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA0);
-		adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.data1 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA1);
-		adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.cmd = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_CMD);
-		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
+		adev->vcn.inst[j].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.nop = SOC15_REG_OFFSET(VCN, j, mmUVD_NO_OP);
 
 		ring = &adev->vcn.inst[j].ring_dec;
@@ -237,7 +372,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+		for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) {
 			enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i);
 
 			ring = &adev->vcn.inst[j].ring_enc[i];
@@ -265,6 +400,9 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[j].pause_dpg_mode = vcn_v2_5_pause_dpg_mode;
 	}
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -273,9 +411,6 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v2_5_pause_dpg_mode;
-
 	r = amdgpu_vcn_ras_sw_init(adev);
 	if (r)
 		return r;
@@ -319,15 +454,18 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
-
-	r = amdgpu_vcn_sw_fini(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -366,7 +504,7 @@ static int vcn_v2_5_hw_init(struct amdgpu_ip_block *ip_block)
 			if (r)
 				return r;
 
-			for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+			for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) {
 				ring = &adev->vcn.inst[j].ring_enc[i];
 				r = amdgpu_ring_test_helper(ring);
 				if (r)
@@ -390,19 +528,21 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		cancel_delayed_work_sync(&vinst->idle_work);
+
 		if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-		    (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+		    (vinst->cur_state != AMD_PG_STATE_GATE &&
 		     RREG32_SOC15(VCN, i, mmUVD_STATUS)))
-			vcn_v2_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 
 		if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
-			amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0);
+			amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0);
 	}
 
 	return 0;
@@ -417,15 +557,20 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v2_5_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return 0;
 }
 
 /**
@@ -437,11 +582,14 @@ static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v2_5_hw_init(ip_block);
 
@@ -451,69 +599,71 @@ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v2_5_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
+static void vcn_v2_5_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	uint32_t size;
 	uint32_t offset;
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
 
-		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[i].fw->size + 4);
-		/* cache window 0: fw */
-		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
-			WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
-			offset = 0;
-		} else {
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				lower_32_bits(adev->vcn.inst[i].gpu_addr));
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				upper_32_bits(adev->vcn.inst[i].gpu_addr));
-			offset = size;
-			WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0,
-				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
-		}
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE0, size);
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
 
-		/* cache window 1: stack */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET1, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
-
-		/* cache window 2: context */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET2, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
-
-		/* non-cache window */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_OFFSET0, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_SIZE0,
-			AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
+	size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[i].fw->size + 4);
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
+		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
+		offset = 0;
+	} else {
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			     lower_32_bits(adev->vcn.inst[i].gpu_addr));
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			     upper_32_bits(adev->vcn.inst[i].gpu_addr));
+		offset = size;
+		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0,
+			     AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
 	}
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE0, size);
+
+	/* cache window 1: stack */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET1, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
+
+	/* cache window 2: context */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET2, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
+
+	/* non-cache window */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_OFFSET0, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_SIZE0,
+		     AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
 }
 
-static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4);
 	uint32_t offset;
 
@@ -611,123 +761,124 @@ static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 /**
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	uint32_t data;
-	int i;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* UVD disable CGC */
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
-			data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		else
-			data &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
-		data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_GATE);
-		data &= ~(UVD_CGC_GATE__SYS_MASK
-			| UVD_CGC_GATE__UDEC_MASK
-			| UVD_CGC_GATE__MPEG2_MASK
-			| UVD_CGC_GATE__REGS_MASK
-			| UVD_CGC_GATE__RBC_MASK
-			| UVD_CGC_GATE__LMI_MC_MASK
-			| UVD_CGC_GATE__LMI_UMC_MASK
-			| UVD_CGC_GATE__IDCT_MASK
-			| UVD_CGC_GATE__MPRD_MASK
-			| UVD_CGC_GATE__MPC_MASK
-			| UVD_CGC_GATE__LBSI_MASK
-			| UVD_CGC_GATE__LRBBM_MASK
-			| UVD_CGC_GATE__UDEC_RE_MASK
-			| UVD_CGC_GATE__UDEC_CM_MASK
-			| UVD_CGC_GATE__UDEC_IT_MASK
-			| UVD_CGC_GATE__UDEC_DB_MASK
-			| UVD_CGC_GATE__UDEC_MP_MASK
-			| UVD_CGC_GATE__WCB_MASK
-			| UVD_CGC_GATE__VCPU_MASK
-			| UVD_CGC_GATE__MMSCH_MASK);
-
-		WREG32_SOC15(VCN, i, mmUVD_CGC_GATE, data);
-
-		SOC15_WAIT_ON_RREG(VCN, i, mmUVD_CGC_GATE, 0,  0xFFFFFFFF);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_CM_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_IT_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_DB_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MP_MODE_MASK
-			| UVD_CGC_CTRL__SYS_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MODE_MASK
-			| UVD_CGC_CTRL__MPEG2_MODE_MASK
-			| UVD_CGC_CTRL__REGS_MODE_MASK
-			| UVD_CGC_CTRL__RBC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_MC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_UMC_MODE_MASK
-			| UVD_CGC_CTRL__IDCT_MODE_MASK
-			| UVD_CGC_CTRL__MPRD_MODE_MASK
-			| UVD_CGC_CTRL__MPC_MODE_MASK
-			| UVD_CGC_CTRL__LBSI_MODE_MASK
-			| UVD_CGC_CTRL__LRBBM_MODE_MASK
-			| UVD_CGC_CTRL__WCB_MODE_MASK
-			| UVD_CGC_CTRL__VCPU_MODE_MASK
-			| UVD_CGC_CTRL__MMSCH_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		/* turn on */
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE);
-		data |= (UVD_SUVD_CGC_GATE__SRE_MASK
-			| UVD_SUVD_CGC_GATE__SIT_MASK
-			| UVD_SUVD_CGC_GATE__SMP_MASK
-			| UVD_SUVD_CGC_GATE__SCM_MASK
-			| UVD_SUVD_CGC_GATE__SDB_MASK
-			| UVD_SUVD_CGC_GATE__SRE_H264_MASK
-			| UVD_SUVD_CGC_GATE__SRE_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SIT_H264_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SCM_H264_MASK
-			| UVD_SUVD_CGC_GATE__SCM_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SDB_H264_MASK
-			| UVD_SUVD_CGC_GATE__SDB_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SCLR_MASK
-			| UVD_SUVD_CGC_GATE__UVD_SC_MASK
-			| UVD_SUVD_CGC_GATE__ENT_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_DEC_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_ENC_MASK
-			| UVD_SUVD_CGC_GATE__SITE_MASK
-			| UVD_SUVD_CGC_GATE__SRE_VP9_MASK
-			| UVD_SUVD_CGC_GATE__SCM_VP9_MASK
-			| UVD_SUVD_CGC_GATE__SIT_VP9_DEC_MASK
-			| UVD_SUVD_CGC_GATE__SDB_VP9_MASK
-			| UVD_SUVD_CGC_GATE__IME_HEVC_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
-		data &= ~(UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
+	/* UVD disable CGC */
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
+	data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_GATE);
+	data &= ~(UVD_CGC_GATE__SYS_MASK
+		  | UVD_CGC_GATE__UDEC_MASK
+		  | UVD_CGC_GATE__MPEG2_MASK
+		  | UVD_CGC_GATE__REGS_MASK
+		  | UVD_CGC_GATE__RBC_MASK
+		  | UVD_CGC_GATE__LMI_MC_MASK
+		  | UVD_CGC_GATE__LMI_UMC_MASK
+		  | UVD_CGC_GATE__IDCT_MASK
+		  | UVD_CGC_GATE__MPRD_MASK
+		  | UVD_CGC_GATE__MPC_MASK
+		  | UVD_CGC_GATE__LBSI_MASK
+		  | UVD_CGC_GATE__LRBBM_MASK
+		  | UVD_CGC_GATE__UDEC_RE_MASK
+		  | UVD_CGC_GATE__UDEC_CM_MASK
+		  | UVD_CGC_GATE__UDEC_IT_MASK
+		  | UVD_CGC_GATE__UDEC_DB_MASK
+		  | UVD_CGC_GATE__UDEC_MP_MASK
+		  | UVD_CGC_GATE__WCB_MASK
+		  | UVD_CGC_GATE__VCPU_MASK
+		  | UVD_CGC_GATE__MMSCH_MASK);
+
+	WREG32_SOC15(VCN, i, mmUVD_CGC_GATE, data);
+
+	SOC15_WAIT_ON_RREG(VCN, i, mmUVD_CGC_GATE, 0,  0xFFFFFFFF);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_CM_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_IT_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_DB_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_MP_MODE_MASK
+		  | UVD_CGC_CTRL__SYS_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_MODE_MASK
+		  | UVD_CGC_CTRL__MPEG2_MODE_MASK
+		  | UVD_CGC_CTRL__REGS_MODE_MASK
+		  | UVD_CGC_CTRL__RBC_MODE_MASK
+		  | UVD_CGC_CTRL__LMI_MC_MODE_MASK
+		  | UVD_CGC_CTRL__LMI_UMC_MODE_MASK
+		  | UVD_CGC_CTRL__IDCT_MODE_MASK
+		  | UVD_CGC_CTRL__MPRD_MODE_MASK
+		  | UVD_CGC_CTRL__MPC_MODE_MASK
+		  | UVD_CGC_CTRL__LBSI_MODE_MASK
+		  | UVD_CGC_CTRL__LRBBM_MODE_MASK
+		  | UVD_CGC_CTRL__WCB_MODE_MASK
+		  | UVD_CGC_CTRL__VCPU_MODE_MASK
+		  | UVD_CGC_CTRL__MMSCH_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	/* turn on */
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE);
+	data |= (UVD_SUVD_CGC_GATE__SRE_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_MASK
+		 | UVD_SUVD_CGC_GATE__SMP_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SCLR_MASK
+		 | UVD_SUVD_CGC_GATE__UVD_SC_MASK
+		 | UVD_SUVD_CGC_GATE__ENT_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_DEC_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_ENC_MASK
+		 | UVD_SUVD_CGC_GATE__SITE_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_VP9_DEC_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__IME_HEVC_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
+	data &= ~(UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
 			| UVD_SUVD_CGC_CTRL__IME_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
-	}
+		  | UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
-		uint8_t sram_sel, int inst_idx, uint8_t indirect)
+static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+		uint8_t sram_sel, uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 
 	/* enable sw clock gating control */
@@ -776,68 +927,69 @@ static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	uint32_t data = 0;
-	int i;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* enable UVD CGC */
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
-			data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		else
-			data |= 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		data |= (UVD_CGC_CTRL__UDEC_RE_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_CM_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_IT_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_DB_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MP_MODE_MASK
-			| UVD_CGC_CTRL__SYS_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MODE_MASK
-			| UVD_CGC_CTRL__MPEG2_MODE_MASK
-			| UVD_CGC_CTRL__REGS_MODE_MASK
-			| UVD_CGC_CTRL__RBC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_MC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_UMC_MODE_MASK
-			| UVD_CGC_CTRL__IDCT_MODE_MASK
-			| UVD_CGC_CTRL__MPRD_MODE_MASK
-			| UVD_CGC_CTRL__MPC_MODE_MASK
-			| UVD_CGC_CTRL__LBSI_MODE_MASK
-			| UVD_CGC_CTRL__LRBBM_MODE_MASK
-			| UVD_CGC_CTRL__WCB_MODE_MASK
-			| UVD_CGC_CTRL__VCPU_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
-		data |= (UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__IME_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
+	/* enable UVD CGC */
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data |= 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	data |= (UVD_CGC_CTRL__UDEC_RE_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_CM_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_IT_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_DB_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_MP_MODE_MASK
+		 | UVD_CGC_CTRL__SYS_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_MODE_MASK
+		 | UVD_CGC_CTRL__MPEG2_MODE_MASK
+		 | UVD_CGC_CTRL__REGS_MODE_MASK
+		 | UVD_CGC_CTRL__RBC_MODE_MASK
+		 | UVD_CGC_CTRL__LMI_MC_MODE_MASK
+		 | UVD_CGC_CTRL__LMI_UMC_MODE_MASK
+		 | UVD_CGC_CTRL__IDCT_MODE_MASK
+		 | UVD_CGC_CTRL__MPRD_MODE_MASK
+		 | UVD_CGC_CTRL__MPC_MODE_MASK
+		 | UVD_CGC_CTRL__LBSI_MODE_MASK
+		 | UVD_CGC_CTRL__LRBBM_MODE_MASK
+		 | UVD_CGC_CTRL__WCB_MODE_MASK
+		 | UVD_CGC_CTRL__VCPU_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
+	data |= (UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__IME_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx,
+static void vcn_v2_6_enable_ras(struct amdgpu_vcn_inst *vinst,
 				bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 
 	if (amdgpu_ip_version(adev, UVD_HWIP, 0) != IP_VERSION(2, 6, 0))
@@ -862,8 +1014,10 @@ static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx,
 			      tmp, 0, indirect);
 }
 
-static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
@@ -881,7 +1035,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
 
 	/* enable clock gating */
-	vcn_v2_5_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+	vcn_v2_5_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -930,7 +1084,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v2_5_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v2_5_mc_resume_dpg_mode(vinst, indirect);
 
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
@@ -941,7 +1095,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, 0, mmUVD_LMI_CTRL2), 0, 0, indirect);
 
-	vcn_v2_6_enable_ras(adev, inst_idx, indirect);
+	vcn_v2_6_enable_ras(vinst, indirect);
 
 	/* unblock VCPU register access */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
@@ -1006,197 +1160,187 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	return 0;
 }
 
-static int vcn_v2_5_start(struct amdgpu_device *adev)
+static int vcn_v2_5_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
+	volatile struct amdgpu_fw_shared *fw_shared =
+		adev->vcn.inst[i].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v2_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-		/* disable register anti-hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0,
-			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+	/* disable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0,
+		 ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
 
-		/* set uvd status busy */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
-	}
+	/* set uvd status busy */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
 		return 0;
 
-	/*SW clock gating */
-	vcn_v2_5_disable_clock_gating(adev);
+	/* SW clock gating */
+	vcn_v2_5_disable_clock_gating(vinst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* setup mmUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
-		tmp &= ~0xff;
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | 0x8|
-			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
-			UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup mmUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
-			((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
-			((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup mmUVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
-			((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-			(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-	}
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
 
-	vcn_v2_5_mc_resume(adev);
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
+	/* setup mmUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
+	tmp &= ~0xff;
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | 0x8|
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup mmUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup mmUVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v2_5_mc_resume(vinst);
 
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+	WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
 
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (k = 0; k < 10; ++k) {
-			uint32_t status;
-
-			for (j = 0; j < 100; ++j) {
-				status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
-				if (status & 2)
-					break;
-				if (amdgpu_emu_mode == 1)
-					msleep(500);
-				else
-					mdelay(10);
-			}
-			r = 0;
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (k = 0; k < 10; ++k) {
+		uint32_t status;
+
+		for (j = 0; j < 100; ++j) {
+			status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
 			if (status & 2)
 				break;
+			if (amdgpu_emu_mode == 1)
+				msleep(500);
+			else
+				mdelay(10);
+		}
+		r = 0;
+		if (status & 2)
+			break;
 
-			DRM_ERROR("VCN decode not responding, trying to reset the VCPU!!!\n");
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-			mdelay(10);
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+		DRM_ERROR("VCN decode not responding, trying to reset the VCPU!!!\n");
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+			 UVD_VCPU_CNTL__BLK_RST_MASK,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+		mdelay(10);
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-			mdelay(10);
-			r = -1;
-		}
+		mdelay(10);
+		r = -1;
+	}
 
-		if (r) {
-			DRM_ERROR("VCN decode not responding, giving up!!!\n");
-			return r;
-		}
+	if (r) {
+		DRM_ERROR("VCN decode not responding, giving up!!!\n");
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
-			UVD_MASTINT_EN__VCPU_EN_MASK,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
 
-		ring = &adev->vcn.inst[i].ring_dec;
-		/* force RBC into idle state */
-		rb_bufsz = order_base_2(ring->ring_size);
-		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
+	ring = &adev->vcn.inst[i].ring_dec;
+	/* force RBC into idle state */
+	rb_bufsz = order_base_2(ring->ring_size);
+	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
 
-		fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
-		/* program the RB_BASE for ring buffer */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
+	fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
+	/* program the RB_BASE for ring buffer */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		     lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+		     upper_32_bits(ring->gpu_addr));
 
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
 
-		ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
-				lower_32_bits(ring->wptr));
-		fw_shared->multi_queue.decode_queue_mode &= ~FW_QUEUE_RING_RESET;
+	ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
+		     lower_32_bits(ring->wptr));
+	fw_shared->multi_queue.decode_queue_mode &= ~FW_QUEUE_RING_RESET;
 
-		fw_shared->multi_queue.encode_generalpurpose_queue_mode |= FW_QUEUE_RING_RESET;
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
-		fw_shared->multi_queue.encode_generalpurpose_queue_mode &= ~FW_QUEUE_RING_RESET;
-
-		fw_shared->multi_queue.encode_lowlatency_queue_mode |= FW_QUEUE_RING_RESET;
-		ring = &adev->vcn.inst[i].ring_enc[1];
-		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
-		fw_shared->multi_queue.encode_lowlatency_queue_mode &= ~FW_QUEUE_RING_RESET;
-	}
+	fw_shared->multi_queue.encode_generalpurpose_queue_mode |= FW_QUEUE_RING_RESET;
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
+	fw_shared->multi_queue.encode_generalpurpose_queue_mode &= ~FW_QUEUE_RING_RESET;
+
+	fw_shared->multi_queue.encode_lowlatency_queue_mode |= FW_QUEUE_RING_RESET;
+	ring = &adev->vcn.inst[i].ring_enc[1];
+	WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
+	fw_shared->multi_queue.encode_lowlatency_queue_mode &= ~FW_QUEUE_RING_RESET;
 
 	return 0;
 }
@@ -1397,8 +1541,10 @@ static int vcn_v2_5_sriov_start(struct amdgpu_device *adev)
 	return vcn_v2_5_mmsch_start(adev, &adev->virt.mm_table);
 }
 
-static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static int vcn_v2_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 
 	/* Wait for power status to be 1 */
@@ -1425,79 +1571,81 @@ static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	return 0;
 }
 
-static int vcn_v2_5_stop(struct amdgpu_device *adev)
+static int vcn_v2_5_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	uint32_t tmp;
-	int i, r = 0;
+	int r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v2_5_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		r = vcn_v2_5_stop_dpg_mode(vinst);
+		goto done;
+	}
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		/* block LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* block LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
-			UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		vcn_v2_5_enable_clock_gating(adev);
+	/* clear status */
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
 
-		/* enable register anti-hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS),
-			UVD_POWER_STATUS__UVD_POWER_STATUS_MASK,
-			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
-	}
+	vcn_v2_5_enable_clock_gating(vinst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+	/* enable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS),
+		 UVD_POWER_STATUS__UVD_POWER_STATUS_MASK,
+		 ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
 
-	return 0;
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
+
+	return r;
 }
 
-static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
-				int inst_idx, struct dpg_pause_state *new_state)
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	struct amdgpu_ring *ring;
 	uint32_t reg_data = 0;
 	int ret_code = 0;
@@ -1643,8 +1791,8 @@ static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = {
 	.insert_start = vcn_v2_0_dec_ring_insert_start,
 	.insert_end = vcn_v2_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.begin_use = vcn_v2_5_ring_begin_use,
+	.end_use = vcn_v2_5_ring_end_use,
 	.emit_wreg = vcn_v2_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v2_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -1741,8 +1889,8 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = {
 	.insert_nop = amdgpu_ring_insert_nop,
 	.insert_end = vcn_v2_0_enc_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.begin_use = vcn_v2_5_ring_begin_use,
+	.end_use = vcn_v2_5_ring_end_use,
 	.emit_wreg = vcn_v2_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -1767,16 +1915,16 @@ static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev)
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+		for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) {
 			adev->vcn.inst[j].ring_enc[i].funcs = &vcn_v2_5_enc_ring_vm_funcs;
 			adev->vcn.inst[j].ring_enc[i].me = j;
 		}
 	}
 }
 
-static bool vcn_v2_5_is_idle(void *handle)
+static bool vcn_v2_5_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -1811,40 +1959,45 @@ static int vcn_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 {
 	struct amdgpu_device *adev = ip_block->adev;
 	bool enable = (state == AMD_CG_STATE_GATE);
+	int i;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	if (enable) {
-		if (!vcn_v2_5_is_idle(adev))
-			return -EBUSY;
-		vcn_v2_5_enable_clock_gating(adev);
-	} else {
-		vcn_v2_5_disable_clock_gating(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		if (enable) {
+			if (!vcn_v2_5_is_idle(ip_block))
+				return -EBUSY;
+			vcn_v2_5_enable_clock_gating(vinst);
+		} else {
+			vcn_v2_5_disable_clock_gating(vinst);
+		}
 	}
 
 	return 0;
 }
 
-static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_device *adev = vinst->adev;
 	int ret;
 
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	if(state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v2_5_stop(adev);
+		ret = vcn_v2_5_stop(vinst);
 	else
-		ret = vcn_v2_5_start(adev);
+		ret = vcn_v2_5_start(vinst);
 
-	if(!ret)
-		adev->vcn.cur_state = state;
+	if (!ret)
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -1921,10 +2074,10 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs;
 
-		adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v2_6_ras_irq_funcs;
 	}
 }
@@ -2001,7 +2154,7 @@ static const struct amd_ip_funcs vcn_v2_5_ip_funcs = {
 	.is_idle = vcn_v2_5_is_idle,
 	.wait_for_idle = vcn_v2_5_wait_for_idle,
 	.set_clockgating_state = vcn_v2_5_set_clockgating_state,
-	.set_powergating_state = vcn_v2_5_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v2_5_dump_ip_state,
 	.print_ip_state = vcn_v2_5_print_ip_state,
 };
@@ -2018,7 +2171,7 @@ static const struct amd_ip_funcs vcn_v2_6_ip_funcs = {
         .is_idle = vcn_v2_5_is_idle,
         .wait_for_idle = vcn_v2_5_wait_for_idle,
         .set_clockgating_state = vcn_v2_5_set_clockgating_state,
-        .set_powergating_state = vcn_v2_5_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v2_5_dump_ip_state,
 	.print_ip_state = vcn_v2_5_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 63ddd4cca910..22ae1939476f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -105,10 +105,10 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev);
 static void vcn_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-			enum amd_powergating_state state);
-static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
-			int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state);
+static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state);
 
 static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring);
 static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring);
@@ -124,11 +124,13 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
 
 	if (amdgpu_sriov_vf(adev)) {
 		adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
 		adev->vcn.harvest_config = 0;
-		adev->vcn.num_enc_rings = 1;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++)
+			adev->vcn.inst[i].num_enc_rings = 1;
 
 	} else {
 		if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 |
@@ -136,18 +138,27 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
 			/* both instances are harvested, disable the block */
 			return -ENOENT;
 
-		if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
-		    IP_VERSION(3, 0, 33))
-			adev->vcn.num_enc_rings = 0;
-		else
-			adev->vcn.num_enc_rings = 2;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+			if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
+			    IP_VERSION(3, 0, 33))
+				adev->vcn.inst[i].num_enc_rings = 0;
+			else
+				adev->vcn.inst[i].num_enc_rings = 2;
+		}
 	}
 
 	vcn_v3_0_set_dec_ring_funcs(adev);
 	vcn_v3_0_set_enc_ring_funcs(adev);
 	vcn_v3_0_set_irq_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		adev->vcn.inst[i].set_pg_state = vcn_v3_0_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+	return 0;
 }
 
 /**
@@ -166,16 +177,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 	uint32_t *ptr;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
-
 	/*
 	 * Note: doorbell assignment is fixed for SRIOV multiple VCN engines
 	 * Formula:
@@ -195,22 +196,32 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
-		adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
+		adev->vcn.inst[i].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
 
-		adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.scratch9 = SOC15_REG_OFFSET(VCN, i, mmUVD_SCRATCH9);
-		adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.data0 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA0);
-		adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.data1 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA1);
-		adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.cmd = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_CMD);
-		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.nop = SOC15_REG_OFFSET(VCN, i, mmUVD_NO_OP);
 
 		/* VCN DEC TRAP */
@@ -224,7 +235,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		ring = &adev->vcn.inst[i].ring_dec;
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev)) {
-			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1);
+			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1);
 		} else {
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i;
 		}
@@ -236,7 +247,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j);
 
 			/* VCN ENC TRAP */
@@ -248,7 +259,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->use_doorbell = true;
 			if (amdgpu_sriov_vf(adev)) {
-				ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1 + j;
+				ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1 + j;
 			} else {
 				ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i;
 			}
@@ -274,6 +285,9 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v3_0_pause_dpg_mode;
 	}
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -281,8 +295,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 	}
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v3_0_pause_dpg_mode;
 
 	/* Allocate memory for VCN IP Dump buffer */
 	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
@@ -325,14 +337,18 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
 
-	r = amdgpu_vcn_sw_fini(adev);
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
-	return r;
+	return 0;
 }
 
 /**
@@ -370,7 +386,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
 				ring->sched.ready = true;
 			}
 
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			for (j = 0; j < adev->vcn.inst[i].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;
@@ -398,7 +414,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
 			if (r)
 				return r;
 
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 				ring = &adev->vcn.inst[i].ring_enc[j];
 				r = amdgpu_ring_test_helper(ring);
 				if (r)
@@ -422,17 +438,19 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		cancel_delayed_work_sync(&vinst->idle_work);
+
 		if (!amdgpu_sriov_vf(adev)) {
 			if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-				(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
-				 RREG32_SOC15(VCN, i, mmUVD_STATUS))) {
-				vcn_v3_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+			    (vinst->cur_state != AMD_PG_STATE_GATE &&
+			     RREG32_SOC15(VCN, i, mmUVD_STATUS))) {
+				vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 			}
 		}
 	}
@@ -449,15 +467,20 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v3_0_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return 0;
 }
 
 /**
@@ -469,11 +492,14 @@ static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v3_0_hw_init(ip_block);
 
@@ -483,13 +509,14 @@ static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v3_0_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst)
+static void vcn_v3_0_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst].fw->size + 4);
 	uint32_t offset;
 
@@ -538,8 +565,11 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst)
 		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
 }
 
-static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4);
 	uint32_t offset;
 
@@ -634,8 +664,10 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 		UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
-static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v3_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -685,8 +717,10 @@ static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int
 	WREG32_SOC15(VCN, inst, mmUVD_POWER_STATUS, data);
 }
 
-static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v3_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -733,13 +767,14 @@ static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int
 /**
  * vcn_v3_0_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: Pointer to the VCN instance structure
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v3_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	/* VCN disable CGC */
@@ -866,9 +901,12 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
 	WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
-		uint8_t sram_sel, int inst_idx, uint8_t indirect)
+static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					   uint8_t sram_sel,
+					   uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 
 	/* enable sw clock gating control */
@@ -917,13 +955,14 @@ static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v3_0_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: Pointer to the VCN instance structure
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v3_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	/* enable VCN CGC */
@@ -982,8 +1021,10 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
 	WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data);
 }
 
-static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
@@ -1001,7 +1042,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
 
 	/* enable clock gating */
-	vcn_v3_0_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+	vcn_v3_0_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -1050,7 +1091,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v3_0_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v3_0_mc_resume_dpg_mode(vinst, indirect);
 
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, inst_idx, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
@@ -1134,192 +1175,188 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	return 0;
 }
 
-static int vcn_v3_0_start(struct amdgpu_device *adev)
+static int vcn_v3_0_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v3_0_start_dpg_mode(vinst, vinst->indirect_sram);
 
-		/* disable VCN power gating */
-		vcn_v3_0_disable_static_power_gating(adev, i);
+	/* disable VCN power gating */
+	vcn_v3_0_disable_static_power_gating(vinst);
 
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
 
-		/*SW clock gating */
-		vcn_v3_0_disable_clock_gating(adev, i);
+	/* SW clock gating */
+	vcn_v3_0_disable_clock_gating(vinst);
 
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
-
-		/* setup mmUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp |
-			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
-			UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup mmUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
-			((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
-			((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup mmUVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
-			((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-			(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-
-		vcn_v3_0_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
 
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-			}
-			r = 0;
-			if (status & 2)
-				break;
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-			DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i);
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-			mdelay(10);
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+	tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
 
+	/* setup mmUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup mmUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup mmUVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v3_0_mc_resume(vinst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
+			if (status & 2)
+				break;
 			mdelay(10);
-			r = -1;
 		}
+		r = 0;
+		if (status & 2)
+			break;
 
-		if (r) {
-			DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i);
-			return r;
-		}
+		DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i);
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+			 UVD_VCPU_CNTL__BLK_RST_MASK,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+		mdelay(10);
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
-			UVD_MASTINT_EN__VCPU_EN_MASK,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
+		mdelay(10);
+		r = -1;
+	}
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	if (r) {
+		DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		ring = &adev->vcn.inst[i].ring_dec;
-		/* force RBC into idle state */
-		rb_bufsz = order_base_2(ring->ring_size);
-		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
 
-		/* programm the RB_BASE for ring buffer */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
+	ring = &adev->vcn.inst[i].ring_dec;
+	/* force RBC into idle state */
+	rb_bufsz = order_base_2(ring->ring_size);
+	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
 
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
 
-		WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0);
-		ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
-			lower_32_bits(ring->wptr));
-		fw_shared->rb.wptr = lower_32_bits(ring->wptr);
-		fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
-		if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
-		    IP_VERSION(3, 0, 33)) {
-			fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
-			ring = &adev->vcn.inst[i].ring_enc[0];
-			WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
-			WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
-			fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
-			fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
-			ring = &adev->vcn.inst[i].ring_enc[1];
-			WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
-			WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
-			WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
-			fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-		}
+	/* programm the RB_BASE for ring buffer */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		     lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+		     upper_32_bits(ring->gpu_addr));
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
+
+	WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0);
+	ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
+		     lower_32_bits(ring->wptr));
+	fw_shared->rb.wptr = lower_32_bits(ring->wptr);
+	fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+	if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
+	    IP_VERSION(3, 0, 33)) {
+		fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+		ring = &adev->vcn.inst[i].ring_enc[0];
+		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
+		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
+		fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+		fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+		ring = &adev->vcn.inst[i].ring_enc[1];
+		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
+		fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
 	}
 
 	return 0;
@@ -1434,7 +1471,7 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 			mmUVD_VCPU_CACHE_SIZE2),
 			AMDGPU_VCN_CONTEXT_SIZE);
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->wptr = 0;
 			rb_addr = ring->gpu_addr;
@@ -1534,12 +1571,14 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static int vcn_v3_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
-	vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state);
+	vcn_v3_0_pause_dpg_mode(vinst, &state);
 
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1,
@@ -1565,86 +1604,87 @@ static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	return 0;
 }
 
-static int vcn_v3_0_stop(struct amdgpu_device *adev)
+static int vcn_v3_0_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	uint32_t tmp;
-	int i, r = 0;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	int r = 0;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v3_0_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		r = vcn_v3_0_stop_dpg_mode(vinst);
+		goto done;
+	}
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
-			UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v3_0_enable_clock_gating(adev, i);
+	/* apply HW clock gating */
+	vcn_v3_0_enable_clock_gating(vinst);
 
-		/* enable VCN power gating */
-		vcn_v3_0_enable_static_power_gating(adev, i);
-	}
+	/* enable VCN power gating */
+	vcn_v3_0_enable_static_power_gating(vinst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
 
-	return 0;
+	return r;
 }
 
-static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
-		   int inst_idx, struct dpg_pause_state *new_state)
+static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t reg_data = 0;
@@ -1928,11 +1968,11 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 		uint32_t reg = amdgpu_ib_get_value(ib, i);
 		uint32_t val = amdgpu_ib_get_value(ib, i + 1);
 
-		if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) {
+		if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data0, 0)) {
 			msg_lo = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) {
+		} else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data1, 0)) {
 			msg_hi = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) &&
+		} else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.cmd, 0) &&
 			   val == 0) {
 			r = vcn_v3_0_dec_msg(p, job,
 					     ((u64)msg_hi) << 32 | msg_lo);
@@ -2096,16 +2136,16 @@ static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			adev->vcn.inst[i].ring_enc[j].funcs = &vcn_v3_0_enc_ring_vm_funcs;
 			adev->vcn.inst[i].ring_enc[j].me = i;
 		}
 	}
 }
 
-static bool vcn_v3_0_is_idle(void *handle)
+static bool vcn_v3_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -2144,46 +2184,47 @@ static int vcn_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
 		if (enable) {
 			if (RREG32_SOC15(VCN, i, mmUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v3_0_enable_clock_gating(adev, i);
+			vcn_v3_0_enable_clock_gating(vinst);
 		} else {
-			vcn_v3_0_disable_clock_gating(adev, i);
+			vcn_v3_0_disable_clock_gating(vinst);
 		}
 	}
 
 	return 0;
 }
 
-static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	struct amdgpu_device *adev = vinst->adev;
+	int ret = 0;
 
 	/* for SRIOV, guest should not control VCN Power-gating
 	 * MMSCH FW should control Power-gating and clock-gating
 	 * guest should avoid touching CGC and PG
 	 */
 	if (amdgpu_sriov_vf(adev)) {
-		adev->vcn.cur_state = AMD_PG_STATE_UNGATE;
+		vinst->cur_state = AMD_PG_STATE_UNGATE;
 		return 0;
 	}
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v3_0_stop(adev);
+		ret = vcn_v3_0_stop(vinst);
 	else
-		ret = vcn_v3_0_start(adev);
+		ret = vcn_v3_0_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -2248,7 +2289,7 @@ static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v3_0_irq_funcs;
 	}
 }
@@ -2326,7 +2367,7 @@ static const struct amd_ip_funcs vcn_v3_0_ip_funcs = {
 	.is_idle = vcn_v3_0_is_idle,
 	.wait_for_idle = vcn_v3_0_wait_for_idle,
 	.set_clockgating_state = vcn_v3_0_set_clockgating_state,
-	.set_powergating_state = vcn_v3_0_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v3_0_dump_ip_state,
 	.print_ip_state = vcn_v3_0_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 00551d6f0370..c6f6392c1c20 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -96,10 +96,10 @@ static int amdgpu_ih_clientid_vcns[] = {
 static int vcn_v4_0_start_sriov(struct amdgpu_device *adev);
 static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-        enum amd_powergating_state state);
-static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev,
-        int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state);
+static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state);
 static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev);
 
@@ -114,7 +114,7 @@ static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev);
 static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	int i;
+	int i, r;
 
 	if (amdgpu_sriov_vf(adev)) {
 		adev->vcn.harvest_config = VCN_HARVEST_MMSCH;
@@ -126,14 +126,23 @@ static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
-	/* re-use enc ring as unified ring */
-	adev->vcn.num_enc_rings = 1;
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
 
 	vcn_v4_0_set_unified_ring_funcs(adev);
 	vcn_v4_0_set_irq_funcs(adev);
 	vcn_v4_0_set_ras_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v4_0_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
 }
 
 static int vcn_v4_0_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
@@ -176,20 +185,20 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0);
 	uint32_t *ptr;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
 		/* Init instance 0 sched_score to 1, so it's scheduled after other instances */
 		if (i == 0)
 			atomic_set(&adev->vcn.inst[i].sched_score, 1);
@@ -211,7 +220,8 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 		ring = &adev->vcn.inst[i].ring_enc[0];
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev))
-			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * (adev->vcn.num_enc_rings + 1) + 1;
+			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i *
+				(adev->vcn.inst[i].num_enc_rings + 1) + 1;
 		else
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i;
 		ring->vm_hub = AMDGPU_MMHUB0(0);
@@ -223,6 +233,9 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 
 		vcn_v4_0_fw_shared_init(adev, i);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_pause_dpg_mode;
 	}
 
 	/* TODO: Add queue reset mask when FW fully supports it */
@@ -235,8 +248,6 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v4_0_pause_dpg_mode;
 
 	r = amdgpu_vcn_ras_sw_init(adev);
 	if (r)
@@ -288,16 +299,23 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
 
 	amdgpu_vcn_sysfs_reset_mask_fini(adev);
-	r = amdgpu_vcn_sw_fini(adev);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -359,20 +377,23 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		cancel_delayed_work_sync(&vinst->idle_work);
+
 		if (!amdgpu_sriov_vf(adev)) {
 			if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-				(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+			    (vinst->cur_state != AMD_PG_STATE_GATE &&
 				 RREG32_SOC15(VCN, i, regUVD_STATUS))) {
-				vcn_v4_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+				vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 			}
 		}
 		if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
-			amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0);
+			amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0);
 	}
 
 	return 0;
@@ -387,15 +408,20 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v4_0_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return 0;
 }
 
 /**
@@ -407,11 +433,14 @@ static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v4_0_hw_init(ip_block);
 
@@ -421,13 +450,14 @@ static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v4_0_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -481,14 +511,16 @@ static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v4_0_mc_resume_dpg_mode - memory controller programming for dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Let the VCN memory controller know it's offsets with dpg mode
  */
-static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 	hdr = (const struct common_firmware_header *)adev->vcn.inst[inst_idx].fw->data;
@@ -588,13 +620,14 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 /**
  * vcn_v4_0_disable_static_power_gating - disable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable static power gating for VCN block
  */
-static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -653,13 +686,14 @@ static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int
 /**
  * vcn_v4_0_enable_static_power_gating - enable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable static power gating for VCN block
  */
-static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -708,13 +742,14 @@ static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int
 /**
  * vcn_v4_0_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -819,16 +854,18 @@ static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v4_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  * @sram_sel: sram select
- * @inst_idx: instance number index
  * @indirect: indirectly write sram
  *
  * Disable clock gating for VCN block with dpg mode
  */
-static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel,
-      int inst_idx, uint8_t indirect)
+static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+						   uint8_t sram_sel,
+						   uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -876,13 +913,14 @@ static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, u
 /**
  * vcn_v4_0_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -932,9 +970,11 @@ static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
 	WREG32_SOC15(VCN, inst, regUVD_SUVD_CGC_CTRL, data);
 }
 
-static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx,
+static void vcn_v4_0_enable_ras(struct amdgpu_vcn_inst *vinst,
 				bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
@@ -957,14 +997,15 @@ static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx,
 /**
  * vcn_v4_0_start_dpg_mode - VCN start with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Start VCN block with dpg mode
  */
-static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
@@ -982,7 +1023,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
 
 	/* enable clock gating */
-	vcn_v4_0_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+	vcn_v4_0_disable_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -1030,7 +1071,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v4_0_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v4_0_mc_resume_dpg_mode(vinst, indirect);
 
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
@@ -1042,7 +1083,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, inst_idx, regUVD_LMI_CTRL2), tmp, 0, indirect);
 
-	vcn_v4_0_enable_ras(adev, inst_idx, indirect);
+	vcn_v4_0_enable_ras(vinst, indirect);
 
 	/* enable master interrupt */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
@@ -1086,183 +1127,179 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 /**
  * vcn_v4_0_start - VCN start
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Start VCN block
  */
-static int vcn_v4_0_start(struct amdgpu_device *adev)
+static int vcn_v4_0_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v4_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-		/* disable VCN power gating */
-		vcn_v4_0_disable_static_power_gating(adev, i);
-
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
-
-		/*SW clock gating */
-		vcn_v4_0_disable_clock_gating(adev, i);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
-				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
-				UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-				UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-				UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-				UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup regUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
-				((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
-				((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
-				((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-				 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-
-		vcn_v4_0_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
-				adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
-
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-				if (amdgpu_emu_mode == 1)
-					msleep(1);
-			}
+	/* disable VCN power gating */
+	vcn_v4_0_disable_static_power_gating(vinst);
+
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
+
+	/*SW clock gating */
+	vcn_v4_0_disable_clock_gating(vinst);
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup regUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v4_0_mc_resume(vinst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, i, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+			if (amdgpu_emu_mode == 1)
+				msleep(1);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-						~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
-				~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
-				ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-				VCN_RB1_DB_CTRL__EN_MASK);
-
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
+
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -1518,17 +1555,18 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_stop_dpg_mode - VCN stop with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  *
  * Stop VCN block with dpg mode
  */
-static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
-	vcn_v4_0_pause_dpg_mode(adev, inst_idx, &state);
+	vcn_v4_0_pause_dpg_mode(vinst, &state);
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1,
 		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
@@ -1548,87 +1586,87 @@ static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v4_0_stop - VCN stop
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Stop VCN block
  */
-static int vcn_v4_0_stop(struct amdgpu_device *adev)
+static int vcn_v4_0_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	uint32_t tmp;
-	int i, r = 0;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	int r = 0;
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v4_0_stop_dpg_mode(adev, i);
-			continue;
-		}
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v4_0_stop_dpg_mode(vinst);
+		r = 0;
+		goto done;
+	}
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
-				UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v4_0_enable_clock_gating(adev, i);
+	/* apply HW clock gating */
+	vcn_v4_0_enable_clock_gating(vinst);
 
-		/* enable VCN power gating */
-		vcn_v4_0_enable_static_power_gating(adev, i);
-	}
+	/* enable VCN power gating */
+	vcn_v4_0_enable_static_power_gating(vinst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
 
 	return 0;
 }
@@ -1636,15 +1674,16 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_pause_dpg_mode - VCN pause with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @new_state: pause state
  *
  * Pause dpg mode for VCN block
  */
-static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx,
-      struct dpg_pause_state *new_state)
+static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				   struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 	int ret_code;
 
@@ -1964,13 +2003,13 @@ static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_is_idle - check VCN block is idle
  *
- * @handle: amdgpu_device pointer
+ * @ip_block: Pointer to the amdgpu_ip_block structure
  *
  * Check whether VCN block is idle
  */
-static bool vcn_v4_0_is_idle(void *handle)
+static bool vcn_v4_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -2024,54 +2063,48 @@ static int vcn_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
 		if (enable) {
 			if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v4_0_enable_clock_gating(adev, i);
+			vcn_v4_0_enable_clock_gating(vinst);
 		} else {
-			vcn_v4_0_disable_clock_gating(adev, i);
+			vcn_v4_0_disable_clock_gating(vinst);
 		}
 	}
 
 	return 0;
 }
 
-/**
- * vcn_v4_0_set_powergating_state - set VCN block powergating state
- *
- * @ip_block: amdgpu_ip_block pointer
- * @state: power gating state
- *
- * Set VCN block powergating state
- */
-static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				 enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	struct amdgpu_device *adev = vinst->adev;
+	int ret = 0;
 
 	/* for SRIOV, guest should not control VCN Power-gating
 	 * MMSCH FW should control Power-gating and clock-gating
 	 * guest should avoid touching CGC and PG
 	 */
 	if (amdgpu_sriov_vf(adev)) {
-		adev->vcn.cur_state = AMD_PG_STATE_UNGATE;
+		vinst->cur_state = AMD_PG_STATE_UNGATE;
 		return 0;
 	}
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v4_0_stop(adev);
+		ret = vcn_v4_0_stop(vinst);
 	else
-		ret = vcn_v4_0_start(adev);
+		ret = vcn_v4_0_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -2163,10 +2196,10 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v4_0_irq_funcs;
 
-		adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v4_0_ras_irq_funcs;
 	}
 }
@@ -2244,7 +2277,7 @@ static const struct amd_ip_funcs vcn_v4_0_ip_funcs = {
 	.is_idle = vcn_v4_0_is_idle,
 	.wait_for_idle = vcn_v4_0_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_set_clockgating_state,
-	.set_powergating_state = vcn_v4_0_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v4_0_dump_ip_state,
 	.print_ip_state = vcn_v4_0_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index ecdc027f8220..7446ecc55714 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -31,6 +31,7 @@
 #include "soc15d.h"
 #include "soc15_hw_ip.h"
 #include "vcn_v2_0.h"
+#include "vcn_v4_0_3.h"
 #include "mmsch_v4_0_3.h"
 
 #include "vcn/vcn_4_0_3_offset.h"
@@ -87,10 +88,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = {
 static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state);
-static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev,
-		int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state);
+static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state);
 static void vcn_v4_0_3_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static void vcn_v4_0_3_set_ras_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_enable_ras(struct amdgpu_device *adev,
@@ -98,8 +99,7 @@ static void vcn_v4_0_3_enable_ras(struct amdgpu_device *adev,
 
 static inline bool vcn_v4_0_3_normalizn_reqd(struct amdgpu_device *adev)
 {
-	return (amdgpu_sriov_vf(adev) ||
-		(amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)));
+	return (adev->vcn.caps & AMDGPU_VCN_CAPS(RRMT_ENABLED)) == 0;
 }
 
 /**
@@ -112,15 +112,25 @@ static inline bool vcn_v4_0_3_normalizn_reqd(struct amdgpu_device *adev)
 static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
 
-	/* re-use enc ring as unified ring */
-	adev->vcn.num_enc_rings = 1;
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
 
 	vcn_v4_0_3_set_unified_ring_funcs(adev);
 	vcn_v4_0_3_set_irq_funcs(adev);
 	vcn_v4_0_3_set_ras_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v4_0_3_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
 }
 
 static int vcn_v4_0_3_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
@@ -152,16 +162,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
 	uint32_t *ptr;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
-
 	/* VCN DEC TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
 		VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq);
@@ -169,6 +169,17 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
 		vcn_inst = GET_INST(VCN, i);
 
 		ring = &adev->vcn.inst[i].ring_enc[0];
@@ -192,6 +203,9 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 
 		vcn_v4_0_3_fw_shared_init(adev, i);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode;
 	}
 
 	/* TODO: Add queue reset mask when FW fully supports it */
@@ -204,9 +218,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode;
-
 	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) {
 		r = amdgpu_vcn_ras_sw_init(adev);
 		if (r) {
@@ -257,16 +268,23 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
 
 	amdgpu_vcn_sysfs_reset_mask_fini(adev);
-	r = amdgpu_vcn_sw_fini(adev);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -295,6 +313,11 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
 			ring->sched.ready = true;
 		}
 	} else {
+		/* This flag is not set for VF, assumed to be disabled always */
+		if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) &
+		    0x100)
+			adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED);
+
 		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 			struct amdgpu_vcn4_fw_shared *fw_shared;
 
@@ -345,11 +368,16 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
 
-	if (adev->vcn.cur_state != AMD_PG_STATE_GATE)
-		vcn_v4_0_3_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+		cancel_delayed_work_sync(&vinst->idle_work);
+
+		if (vinst->cur_state != AMD_PG_STATE_GATE)
+			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
+	}
 
 	return 0;
 }
@@ -363,15 +391,20 @@ static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v4_0_3_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return 0;
 }
 
 /**
@@ -383,11 +416,14 @@ static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v4_0_3_hw_init(ip_block);
 
@@ -397,13 +433,14 @@ static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v4_0_3_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_3_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size, vcn_inst;
 	const struct common_firmware_header *hdr;
 
@@ -471,14 +508,16 @@ static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v4_0_3_mc_resume_dpg_mode - memory controller programming for dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Let the VCN memory controller know it's offsets with dpg mode
  */
-static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					  bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -585,13 +624,14 @@ static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 /**
  * vcn_v4_0_3_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t data;
 	int vcn_inst;
 
@@ -678,16 +718,18 @@ static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst
 /**
  * vcn_v4_0_3_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  * @sram_sel: sram select
- * @inst_idx: instance number index
  * @indirect: indirectly write sram
  *
  * Disable clock gating for VCN block with dpg mode
  */
-static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel,
-				int inst_idx, uint8_t indirect)
+static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+						     uint8_t sram_sel,
+						     uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -729,13 +771,14 @@ static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v4_0_3_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t data;
 	int vcn_inst;
 
@@ -780,14 +823,16 @@ static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_
 /**
  * vcn_v4_0_3_start_dpg_mode - VCN start with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Start VCN block with dpg mode
  */
-static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared =
 						adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
@@ -815,7 +860,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 	}
 
 	/* enable clock gating */
-	vcn_v4_0_3_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+	vcn_v4_0_3_disable_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -865,7 +910,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v4_0_3_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v4_0_3_mc_resume_dpg_mode(vinst, indirect);
 
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
@@ -1112,191 +1157,185 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_3_start - VCN start
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Start VCN block
  */
-static int vcn_v4_0_3_start(struct amdgpu_device *adev)
+static int vcn_v4_0_3_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
-	int i, j, k, r, vcn_inst;
+	int j, k, r, vcn_inst;
 	uint32_t tmp;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_3_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	vcn_inst = GET_INST(VCN, i);
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
+		UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
 
-		vcn_inst = GET_INST(VCN, i);
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
-		      UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
-
-		/*SW clock gating */
-		vcn_v4_0_3_disable_clock_gating(adev, i);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
-			 UVD_VCPU_CNTL__CLK_EN_MASK,
-			 ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
-			 ~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
-			 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL,
-			     tmp | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-				     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-				     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-				     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup regUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXA0,
-			     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-			      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-			      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-			      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXB0,
-			     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-			      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-			      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-			      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUX,
-			     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-			      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-			      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-
-		vcn_v4_0_3_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
-			     adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
-			     adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
-			 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
-			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* SW clock gating */
+	vcn_v4_0_3_disable_clock_gating(vinst);
 
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK,
+		 ~UVD_VCPU_CNTL__CLK_EN_MASK);
 
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, vcn_inst,
-						      regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-			}
-			r = 0;
-			if (status & 2)
-				break;
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-			DRM_DEV_ERROR(adev->dev,
-				"VCN decode not responding, trying to reset the VCPU!!!\n");
-			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
-						  regUVD_VCPU_CNTL),
-				 UVD_VCPU_CNTL__BLK_RST_MASK,
-				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
-			mdelay(10);
-			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
-						  regUVD_VCPU_CNTL),
-				 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL,
+		     tmp | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup regUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v4_0_3_mc_resume(vinst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, vcn_inst,
+					      regUVD_STATUS);
+			if (status & 2)
+				break;
 			mdelay(10);
-			r = -1;
 		}
+		r = 0;
+		if (status & 2)
+			break;
 
-		if (r) {
-			DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
-			return r;
-		}
+		DRM_DEV_ERROR(adev->dev,
+			      "VCN decode not responding, trying to reset the VCPU!!!\n");
+		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
+					  regUVD_VCPU_CNTL),
+			 UVD_VCPU_CNTL__BLK_RST_MASK,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+		mdelay(10);
+		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
+					  regUVD_VCPU_CNTL),
+			 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
-			 UVD_MASTINT_EN__VCPU_EN_MASK,
-			 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+		mdelay(10);
+		r = -1;
+	}
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
-			 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	if (r) {
+		DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
+		return r;
+	}
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* program the RB_BASE for ring buffer */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
-			     lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
-			     upper_32_bits(ring->gpu_addr));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
-			     ring->ring_size / sizeof(uint32_t));
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-		/* resetting ring, fw should not check RB ring */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
-		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	/* program the RB_BASE for ring buffer */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
+		     lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
+		     upper_32_bits(ring->gpu_addr));
+
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
+		     ring->ring_size / sizeof(uint32_t));
+
+	/* resetting ring, fw should not check RB ring */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
 
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
 
-		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB_EN_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB_EN_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
 
-		ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
-		fw_shared->sq.queue_mode &=
-			cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
+	ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+	fw_shared->sq.queue_mode &=
+		cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
 
-	}
 	return 0;
 }
 
 /**
  * vcn_v4_0_3_stop_dpg_mode - VCN stop with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  *
  * Stop VCN block with dpg mode
  */
-static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 	int vcn_inst;
 
@@ -1322,102 +1361,97 @@ static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v4_0_3_stop - VCN stop
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Stop VCN block
  */
-static int vcn_v4_0_3_stop(struct amdgpu_device *adev)
+static int vcn_v4_0_3_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
-	int i, r = 0, vcn_inst;
+	int r = 0, vcn_inst;
 	uint32_t tmp;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		vcn_inst = GET_INST(VCN, i);
+	vcn_inst = GET_INST(VCN, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v4_0_3_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v4_0_3_stop_dpg_mode(vinst);
+		goto Done;
+	}
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
-				       UVD_STATUS__IDLE, 0x7);
-		if (r)
-			goto Done;
-
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp,
-				       tmp);
-		if (r)
-			goto Done;
-
-		/* stall UMC channel */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp,
-				       tmp);
-		if (r)
-			goto Done;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
+			       UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto Done;
+
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp,
+			       tmp);
+	if (r)
+		goto Done;
+
+	/* stall UMC channel */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp,
+			       tmp);
+	if (r)
+		goto Done;
 
-		/* Unblock VCPU Register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
-			 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* Unblock VCPU Register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
-			 UVD_VCPU_CNTL__BLK_RST_MASK,
-			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
-			 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* reset LMI UMC/LMI/VCPU */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+	/* reset LMI UMC/LMI/VCPU */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
 
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
 
-		/* clear VCN status */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
+	/* clear VCN status */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v4_0_3_enable_clock_gating(adev, i);
-	}
-Done:
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+	/* apply HW clock gating */
+	vcn_v4_0_3_enable_clock_gating(vinst);
 
+Done:
 	return 0;
 }
 
 /**
  * vcn_v4_0_3_pause_dpg_mode - VCN pause with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @new_state: pause state
  *
  * Pause dpg mode for VCN block
  */
-static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx,
-				struct dpg_pause_state *new_state)
+static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state)
 {
 
 	return 0;
@@ -1461,8 +1495,8 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
 				    regUVD_RB_WPTR);
 }
 
-static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
-				uint32_t val, uint32_t mask)
+void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				       uint32_t val, uint32_t mask)
 {
 	/* Use normalized offsets when required */
 	if (vcn_v4_0_3_normalizn_reqd(ring->adev))
@@ -1474,7 +1508,8 @@ static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t
 	amdgpu_ring_write(ring, val);
 }
 
-static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg,
+				   uint32_t val)
 {
 	/* Use normalized offsets when required */
 	if (vcn_v4_0_3_normalizn_reqd(ring->adev))
@@ -1485,8 +1520,8 @@ static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg
 	amdgpu_ring_write(ring, val);
 }
 
-static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				unsigned int vmid, uint64_t pd_addr)
+void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				       unsigned int vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub];
 
@@ -1498,7 +1533,7 @@ static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					lower_32_bits(pd_addr), 0xffffffff);
 }
 
-static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	/* VCN engine access for HDP flush doesn't work when RRMT is enabled.
 	 * This is a workaround to avoid any HDP flush through VCN ring.
@@ -1581,13 +1616,13 @@ static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_3_is_idle - check VCN block is idle
  *
- * @handle: amdgpu_device pointer
+ * @ip_block: Pointer to the amdgpu_ip_block structure
  *
  * Check whether VCN block is idle
  */
-static bool vcn_v4_0_3_is_idle(void *handle)
+static bool vcn_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -1635,51 +1670,45 @@ static int vcn_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (enable) {
 			if (RREG32_SOC15(VCN, GET_INST(VCN, i),
 					 regUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v4_0_3_enable_clock_gating(adev, i);
+			vcn_v4_0_3_enable_clock_gating(vinst);
 		} else {
-			vcn_v4_0_3_disable_clock_gating(adev, i);
+			vcn_v4_0_3_disable_clock_gating(vinst);
 		}
 	}
 	return 0;
 }
 
-/**
- * vcn_v4_0_3_set_powergating_state - set VCN block powergating state
- *
- * @ip_block: amdgpu_ip_block pointer
- * @state: power gating state
- *
- * Set VCN block powergating state
- */
-static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					  enum amd_powergating_state state)
+static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	struct amdgpu_device *adev = vinst->adev;
+	int ret = 0;
 
 	/* for SRIOV, guest should not control VCN Power-gating
 	 * MMSCH FW should control Power-gating and clock-gating
 	 * guest should avoid touching CGC and PG
 	 */
 	if (amdgpu_sriov_vf(adev)) {
-		adev->vcn.cur_state = AMD_PG_STATE_UNGATE;
+		vinst->cur_state = AMD_PG_STATE_UNGATE;
 		return 0;
 	}
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v4_0_3_stop(adev);
+		ret = vcn_v4_0_3_stop(vinst);
 	else
-		ret = vcn_v4_0_3_start(adev);
+		ret = vcn_v4_0_3_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -1841,7 +1870,7 @@ static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = {
 	.is_idle = vcn_v4_0_3_is_idle,
 	.wait_for_idle = vcn_v4_0_3_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_3_set_clockgating_state,
-	.set_powergating_state = vcn_v4_0_3_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v4_0_3_dump_ip_state,
 	.print_ip_state = vcn_v4_0_3_print_ip_state,
 };
@@ -1931,11 +1960,13 @@ static int vcn_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_bank
 	misc0 = bank->regs[ACA_REG_IDX_MISC0];
 	switch (type) {
 	case ACA_SMU_TYPE_UE:
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
 		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE,
 						     1ULL);
 		break;
 	case ACA_SMU_TYPE_CE:
-		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE,
+		bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type,
 						     ACA_REG__MISC0__ERRCNT(misc0));
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h
index 0b046114373a..03572a1d0c9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h
@@ -26,4 +26,13 @@
 
 extern const struct amdgpu_ip_block_version vcn_v4_0_3_ip_block;
 
+void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				       uint32_t val, uint32_t mask);
+
+void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg,
+				   uint32_t val);
+void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				       unsigned int vmid, uint64_t pd_addr);
+void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring);
+
 #endif /* __VCN_V4_0_3_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 23d3c16c9d9f..ba603b2246e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -95,10 +95,10 @@ static int amdgpu_ih_clientid_vcns[] = {
 
 static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state);
-static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev,
-		int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state);
+static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state);
 static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring);
 
 /**
@@ -112,13 +112,26 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v4_0_5_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
+
+	if (amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 6))
+		adev->vcn.per_inst_fw = true;
 
-	/* re-use enc ring as unified ring */
-	adev->vcn.num_enc_rings = 1;
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
 	vcn_v4_0_5_set_unified_ring_funcs(adev);
 	vcn_v4_0_5_set_irq_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v4_0_5_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
 }
 
 /**
@@ -136,15 +149,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5);
 	uint32_t *ptr;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		volatile struct amdgpu_vcn4_fw_shared *fw_shared;
@@ -152,6 +156,16 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
 		atomic_set(&adev->vcn.inst[i].sched_score, 0);
 
 		/* VCN UNIFIED TRAP */
@@ -170,7 +184,7 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev))
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
-						i * (adev->vcn.num_enc_rings + 1) + 1;
+						i * (adev->vcn.inst[i].num_enc_rings + 1) + 1;
 		else
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
 						2 + 8 * i;
@@ -195,6 +209,9 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode;
 	}
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -203,9 +220,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode;
-
 	/* Allocate memory for VCN IP Dump buffer */
 	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
 	if (!ptr) {
@@ -247,15 +261,19 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_free_mm_table(adev);
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
 
-	r = amdgpu_vcn_sw_fini(adev);
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -300,16 +318,19 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		cancel_delayed_work_sync(&vinst->idle_work);
+
 		if (!amdgpu_sriov_vf(adev)) {
 			if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-				(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
-				RREG32_SOC15(VCN, i, regUVD_STATUS))) {
-				vcn_v4_0_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+			    (vinst->cur_state != AMD_PG_STATE_GATE &&
+			     RREG32_SOC15(VCN, i, regUVD_STATUS))) {
+				vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 			}
 		}
 	}
@@ -326,13 +347,18 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v4_0_5_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	return r;
 }
@@ -346,11 +372,14 @@ static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v4_0_5_hw_init(ip_block);
 
@@ -360,13 +389,14 @@ static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v4_0_5_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_5_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -420,14 +450,16 @@ static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v4_0_5_mc_resume_dpg_mode - memory controller programming for dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Let the VCN memory controller know it's offsets with dpg mode
  */
-static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					  bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -534,13 +566,14 @@ static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 /**
  * vcn_v4_0_5_disable_static_power_gating - disable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable static power gating for VCN block
  */
-static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -593,13 +626,14 @@ static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, i
 /**
  * vcn_v4_0_5_enable_static_power_gating - enable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable static power gating for VCN block
  */
-static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -635,13 +669,14 @@ static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, in
 /**
  * vcn_v4_0_5_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -746,16 +781,18 @@ static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst
 /**
  * vcn_v4_0_5_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  * @sram_sel: sram select
- * @inst_idx: instance number index
  * @indirect: indirectly write sram
  *
  * Disable clock gating for VCN block with dpg mode
  */
-static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel,
-		int inst_idx, uint8_t indirect)
+static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+						     uint8_t sram_sel,
+						     uint8_t indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -803,13 +840,14 @@ static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v4_0_5_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -862,14 +900,16 @@ static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v4_0_5_start_dpg_mode - VCN start with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Start VCN block with dpg mode
  */
-static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
@@ -888,7 +928,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 					(uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
 
 	/* enable clock gating */
-	vcn_v4_0_5_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+	vcn_v4_0_5_disable_clock_gating_dpg_mode(vinst, 0, indirect);
 
 	/* enable VCPU clock */
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
@@ -936,7 +976,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
 
-	vcn_v4_0_5_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v4_0_5_mc_resume_dpg_mode(vinst, indirect);
 
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
@@ -989,184 +1029,180 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 /**
  * vcn_v4_0_5_start - VCN start
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Start VCN block
  */
-static int vcn_v4_0_5_start(struct amdgpu_device *adev)
+static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v4_0_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-		/* disable VCN power gating */
-		vcn_v4_0_5_disable_static_power_gating(adev, i);
-
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
-
-		/*SW clock gating */
-		vcn_v4_0_5_disable_clock_gating(adev, i);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
-				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
-				UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-				UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-				UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-				UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup regUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
-				((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
-				((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
-				((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-				 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-
-		vcn_v4_0_5_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
-				adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
-
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-				if (amdgpu_emu_mode == 1)
-					msleep(1);
-			}
+	/* disable VCN power gating */
+	vcn_v4_0_5_disable_static_power_gating(vinst);
+
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+	/* SW clock gating */
+	vcn_v4_0_5_disable_clock_gating(vinst);
+
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup regUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v4_0_5_mc_resume(vinst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, i, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+			if (amdgpu_emu_mode == 1)
+				msleep(1);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev,
-					"VCN[%d] is not responding, trying to reset VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-						~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
-				~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
-				ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-				VCN_RB1_DB_CTRL__EN_MASK);
-
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
+
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -1174,13 +1210,14 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_5_stop_dpg_mode - VCN stop with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  *
  * Stop VCN block with dpg mode
  */
-static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 
 	/* Wait for power status to be 1 */
@@ -1202,103 +1239,104 @@ static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v4_0_5_stop - VCN stop
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Stop VCN block
  */
-static int vcn_v4_0_5_stop(struct amdgpu_device *adev)
+static int vcn_v4_0_5_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	uint32_t tmp;
-	int i, r = 0;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	int r = 0;
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v4_0_5_stop_dpg_mode(adev, i);
-			continue;
-		}
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v4_0_5_stop_dpg_mode(vinst);
+		r = 0;
+		goto done;
+	}
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
-				UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v4_0_5_enable_clock_gating(adev, i);
+	/* apply HW clock gating */
+	vcn_v4_0_5_enable_clock_gating(vinst);
 
-		/* enable VCN power gating */
-		vcn_v4_0_5_enable_static_power_gating(adev, i);
-	}
+	/* enable VCN power gating */
+	vcn_v4_0_5_enable_static_power_gating(vinst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
 
-	return 0;
+	return r;
 }
 
 /**
  * vcn_v4_0_5_pause_dpg_mode - VCN pause with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @new_state: pause state
  *
  * Pause dpg mode for VCN block
  */
-static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx,
-		struct dpg_pause_state *new_state)
+static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 	int ret_code;
 
@@ -1397,7 +1435,7 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
-static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
+static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_ENC,
 	.align_mask = 0x3f,
 	.nop = VCN_ENC_CMD_NO_OP,
@@ -1441,6 +1479,9 @@ static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5))
+			vcn_v4_0_5_unified_ring_vm_funcs.secure_submission_supported = true;
+
 		adev->vcn.inst[i].ring_enc[0].funcs = &vcn_v4_0_5_unified_ring_vm_funcs;
 		adev->vcn.inst[i].ring_enc[0].me = i;
 	}
@@ -1449,13 +1490,13 @@ static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev)
 /**
  * vcn_v4_0_5_is_idle - check VCN block is idle
  *
- * @handle: amdgpu_device pointer
+ * @ip_block: Pointer to the amdgpu_ip_block structure
  *
  * Check whether VCN block is idle
  */
-static bool vcn_v4_0_5_is_idle(void *handle)
+static bool vcn_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -1509,45 +1550,38 @@ static int vcn_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
 		if (enable) {
 			if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v4_0_5_enable_clock_gating(adev, i);
+			vcn_v4_0_5_enable_clock_gating(vinst);
 		} else {
-			vcn_v4_0_5_disable_clock_gating(adev, i);
+			vcn_v4_0_5_disable_clock_gating(vinst);
 		}
 	}
 
 	return 0;
 }
 
-/**
- * vcn_v4_0_5_set_powergating_state - set VCN block powergating state
- *
- * @ip_block: amdgpu_ip_block pointer
- * @state: power gating state
- *
- * Set VCN block powergating state
- */
-static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state)
+static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	int ret = 0;
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v4_0_5_stop(adev);
+		ret = vcn_v4_0_5_stop(vinst);
 	else
-		ret = vcn_v4_0_5_start(adev);
+		ret = vcn_v4_0_5_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -1615,7 +1649,7 @@ static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v4_0_5_irq_funcs;
 	}
 }
@@ -1693,7 +1727,7 @@ static const struct amd_ip_funcs vcn_v4_0_5_ip_funcs = {
 	.is_idle = vcn_v4_0_5_is_idle,
 	.wait_for_idle = vcn_v4_0_5_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_5_set_clockgating_state,
-	.set_powergating_state = vcn_v4_0_5_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v4_0_5_dump_ip_state,
 	.print_ip_state = vcn_v4_0_5_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index b6d78381ebfb..d99d05f42f1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -78,10 +78,10 @@ static int amdgpu_ih_clientid_vcns[] = {
 
 static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state);
-static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev,
-		int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state);
+static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state);
 static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring);
 
 /**
@@ -95,14 +95,24 @@ static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v5_0_0_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
 
-	/* re-use enc ring as unified ring */
-	adev->vcn.num_enc_rings = 1;
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
 
 	vcn_v5_0_0_set_unified_ring_funcs(adev);
 	vcn_v5_0_0_set_irq_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v5_0_0_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
 }
 
 void vcn_v5_0_0_alloc_ip_dump(struct amdgpu_device *adev)
@@ -133,22 +143,22 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i, r;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
 		atomic_set(&adev->vcn.inst[i].sched_score, 0);
 
 		/* VCN UNIFIED TRAP */
@@ -181,15 +191,15 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode;
 	}
 
 	/* TODO: Add queue reset mask when FW fully supports it */
 	adev->vcn.supported_reset =
 		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode;
-
 	vcn_v5_0_0_alloc_ip_dump(adev);
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
@@ -226,16 +236,23 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
 		drm_dev_exit(idx);
 	}
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
 
 	amdgpu_vcn_sysfs_reset_mask_fini(adev);
-	r = amdgpu_vcn_sw_fini(adev);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -280,16 +297,19 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		cancel_delayed_work_sync(&vinst->idle_work);
+
 		if (!amdgpu_sriov_vf(adev)) {
 			if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-				(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
-				RREG32_SOC15(VCN, i, regUVD_STATUS))) {
-				vcn_v5_0_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
+			    (vinst->cur_state != AMD_PG_STATE_GATE &&
+			     RREG32_SOC15(VCN, i, regUVD_STATUS))) {
+				vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 			}
 		}
 	}
@@ -306,13 +326,18 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
 	r = vcn_v5_0_0_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(ip_block->adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	return r;
 }
@@ -326,11 +351,14 @@ static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block)
  */
 static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block)
 {
-	int r;
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
 
-	r = amdgpu_vcn_resume(ip_block->adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v5_0_0_hw_init(ip_block);
 
@@ -340,13 +368,14 @@ static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v5_0_0_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_0_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -400,14 +429,16 @@ static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v5_0_0_mc_resume_dpg_mode - memory controller programming for dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Let the VCN memory controller know it's offsets with dpg mode
  */
-static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					  bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -510,13 +541,14 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 /**
  * vcn_v5_0_0_disable_static_power_gating - disable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable static power gating for VCN block
  */
-static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data = 0;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -577,13 +609,14 @@ static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, i
 /**
  * vcn_v5_0_0_enable_static_power_gating - enable VCN static power gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable static power gating for VCN block
  */
-static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t data;
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
@@ -623,12 +656,11 @@ static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, in
 /**
  * vcn_v5_0_0_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
 	return;
 }
@@ -637,15 +669,15 @@ static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst
 /**
  * vcn_v5_0_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  * @sram_sel: sram select
- * @inst_idx: instance number index
  * @indirect: indirectly write sram
  *
  * Disable clock gating for VCN block with dpg mode
  */
-static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel,
-	int inst_idx, uint8_t indirect)
+static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst,
+						     uint8_t sram_sel,
+						     uint8_t indirect)
 {
 	return;
 }
@@ -654,12 +686,11 @@ static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev,
 /**
  * vcn_v5_0_0_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
 	return;
 }
@@ -667,14 +698,16 @@ static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
 /**
  * vcn_v5_0_0_start_dpg_mode - VCN start with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Start VCN block with dpg mode
  */
-static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
@@ -714,7 +747,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
 		VCN, inst_idx, regUVD_LMI_CTRL), tmp, 0, indirect);
 
-	vcn_v5_0_0_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v5_0_0_mc_resume_dpg_mode(vinst, indirect);
 
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
@@ -766,155 +799,151 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 /**
  * vcn_v5_0_0_start - VCN start
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Start VCN block
  */
-static int vcn_v5_0_0_start(struct amdgpu_device *adev)
+static int vcn_v5_0_0_start(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v5_0_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v5_0_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-		/* disable VCN power gating */
-		vcn_v5_0_0_disable_static_power_gating(adev, i);
-
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
-			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-			UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		vcn_v5_0_0_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
-
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-				if (amdgpu_emu_mode == 1)
-					msleep(1);
-			}
+	/* disable VCN power gating */
+	vcn_v5_0_0_disable_static_power_gating(vinst);
+
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
+
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	vcn_v5_0_0_mc_resume(vinst);
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, i, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+			if (amdgpu_emu_mode == 1)
+				msleep(1);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev,
-					"VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
-			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-			VCN_RB1_DB_CTRL__EN_MASK);
-
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
+
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -922,17 +951,18 @@ static int vcn_v5_0_0_start(struct amdgpu_device *adev)
 /**
  * vcn_v5_0_0_stop_dpg_mode - VCN stop with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  *
  * Stop VCN block with dpg mode
  */
-static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
-	vcn_v5_0_0_pause_dpg_mode(adev, inst_idx, &state);
+	vcn_v5_0_0_pause_dpg_mode(vinst, &state);
 
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1,
@@ -952,100 +982,101 @@ static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v5_0_0_stop - VCN stop
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Stop VCN block
  */
-static int vcn_v5_0_0_stop(struct amdgpu_device *adev)
+static int vcn_v5_0_0_stop(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	uint32_t tmp;
-	int i, r = 0;
+	int r = 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v5_0_0_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v5_0_0_stop_dpg_mode(vinst);
+		r = 0;
+		goto done;
+	}
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-		      UVD_LMI_STATUS__READ_CLEAN_MASK |
-		      UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-		      UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-		      UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
-			UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
-
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* clear status */
-		WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
-
-		/* enable VCN power gating */
-		vcn_v5_0_0_enable_static_power_gating(adev, i);
-	}
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-	return 0;
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+
+	/* clear status */
+	WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
+
+	/* enable VCN power gating */
+	vcn_v5_0_0_enable_static_power_gating(vinst);
+
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
+
+	return r;
 }
 
 /**
  * vcn_v5_0_0_pause_dpg_mode - VCN pause with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @new_state: pause state
  *
  * Pause dpg mode for VCN block
  */
-static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx,
-	struct dpg_pause_state *new_state)
+static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t reg_data = 0;
 	int ret_code;
 
@@ -1192,13 +1223,13 @@ static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev)
 /**
  * vcn_v5_0_0_is_idle - check VCN block is idle
  *
- * @handle: amdgpu_device pointer
+ * @ip_block: Pointer to the amdgpu_ip_block structure
  *
  * Check whether VCN block is idle
  */
-static bool vcn_v5_0_0_is_idle(void *handle)
+static bool vcn_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
@@ -1252,45 +1283,38 @@ static int vcn_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
 		if (enable) {
 			if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v5_0_0_enable_clock_gating(adev, i);
+			vcn_v5_0_0_enable_clock_gating(vinst);
 		} else {
-			vcn_v5_0_0_disable_clock_gating(adev, i);
+			vcn_v5_0_0_disable_clock_gating(vinst);
 		}
 	}
 
 	return 0;
 }
 
-/**
- * vcn_v5_0_0_set_powergating_state - set VCN block powergating state
- *
- * @ip_block: amdgpu_ip_block pointer
- * @state: power gating state
- *
- * Set VCN block powergating state
- */
-static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state)
+static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	int ret = 0;
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v5_0_0_stop(adev);
+		ret = vcn_v5_0_0_stop(vinst);
 	else
-		ret = vcn_v5_0_0_start(adev);
+		ret = vcn_v5_0_0_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -1358,7 +1382,7 @@ static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v5_0_0_irq_funcs;
 	}
 }
@@ -1436,7 +1460,7 @@ static const struct amd_ip_funcs vcn_v5_0_0_ip_funcs = {
 	.is_idle = vcn_v5_0_0_is_idle,
 	.wait_for_idle = vcn_v5_0_0_wait_for_idle,
 	.set_clockgating_state = vcn_v5_0_0_set_clockgating_state,
-	.set_powergating_state = vcn_v5_0_0_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v5_0_0_dump_ip_state,
 	.print_ip_state = vcn_v5_0_0_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 8b463c977d08..581d8629b9d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -29,6 +29,7 @@
 #include "soc15d.h"
 #include "soc15_hw_ip.h"
 #include "vcn_v2_0.h"
+#include "vcn_v4_0_3.h"
 
 #include "vcn/vcn_5_0_0_offset.h"
 #include "vcn/vcn_5_0_0_sh_mask.h"
@@ -40,8 +41,8 @@
 
 static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev);
-static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block,
-		enum amd_powergating_state state);
+static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state);
 static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring);
 
 /**
@@ -55,14 +56,40 @@ static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v5_0_1_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
 
-	/* re-use enc ring as unified ring */
-	adev->vcn.num_enc_rings = 1;
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
 
 	vcn_v5_0_1_set_unified_ring_funcs(adev);
 	vcn_v5_0_1_set_irq_funcs(adev);
 
-	return amdgpu_vcn_early_init(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v5_0_1_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+static void vcn_v5_0_1_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
+{
+	struct amdgpu_vcn5_fw_shared *fw_shared;
+
+	fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
+
+	if (fw_shared->sq.is_enabled)
+		return;
+	fw_shared->present_flag_0 =
+		cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
+	fw_shared->sq.is_enabled = 1;
+
+	if (amdgpu_vcnfw_log)
+		amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst_idx]);
 }
 
 /**
@@ -78,16 +105,6 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_ring *ring;
 	int i, r, vcn_inst;
 
-	r = amdgpu_vcn_sw_init(adev);
-	if (r)
-		return r;
-
-	amdgpu_vcn_setup_ucode(adev);
-
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
-
 	/* VCN UNIFIED TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
 		VCN_5_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq);
@@ -95,10 +112,18 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		volatile struct amdgpu_vcn5_fw_shared *fw_shared;
-
 		vcn_inst = GET_INST(VCN, i);
 
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
 		ring = &adev->vcn.inst[i].ring_enc[0];
 		ring->use_doorbell = true;
 		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 9 * vcn_inst;
@@ -111,12 +136,7 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
-		fw_shared->sq.is_enabled = true;
-
-		if (amdgpu_vcnfw_log)
-			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+		vcn_v5_0_1_fw_shared_init(adev, i);
 	}
 
 	/* TODO: Add queue reset mask when FW fully supports it */
@@ -142,7 +162,7 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
 
 	if (drm_dev_enter(adev_to_drm(adev), &idx)) {
 		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			volatile struct amdgpu_vcn4_fw_shared *fw_shared;
+			volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 
 			fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 			fw_shared->present_flag_0 = 0;
@@ -152,17 +172,23 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
 		drm_dev_exit(idx);
 	}
 
-	r = amdgpu_vcn_suspend(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
 
-	r = amdgpu_vcn_sw_fini(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
 
 	amdgpu_vcn_sysfs_reset_mask_fini(adev);
 
 	kfree(adev->vcn.ip_dump);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -178,6 +204,8 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_ring *ring;
 	int i, r, vcn_inst;
 
+	if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100)
+		adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED);
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		vcn_inst = GET_INST(VCN, i);
 		ring = &adev->vcn.inst[i].ring_enc[0];
@@ -188,6 +216,9 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 				 9 * vcn_inst),
 				adev->vcn.inst[i].aid_id);
 
+		/* Re-init fw_shared, if required */
+		vcn_v5_0_1_fw_shared_init(adev, i);
+
 		r = amdgpu_ring_test_helper(ring);
 		if (r)
 			return r;
@@ -206,8 +237,15 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work);
+		if (vinst->cur_state != AMD_PG_STATE_GATE)
+			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
+	}
 
 	return 0;
 }
@@ -222,13 +260,17 @@ static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	int r;
+	int r, i;
 
 	r = vcn_v5_0_1_hw_fini(ip_block);
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_suspend(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	return r;
 }
@@ -243,11 +285,18 @@ static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block)
 static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	int r;
+	int r, i;
 
-	r = amdgpu_vcn_resume(adev);
-	if (r)
-		return r;
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		if (amdgpu_in_reset(adev))
+			vinst->cur_state = AMD_PG_STATE_GATE;
+
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
 
 	r = vcn_v5_0_1_hw_init(ip_block);
 
@@ -257,13 +306,14 @@ static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block)
 /**
  * vcn_v5_0_1_mc_resume - memory controller programming
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_1_mc_resume(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
 	uint32_t offset, size, vcn_inst;
 	const struct common_firmware_header *hdr;
 
@@ -313,20 +363,22 @@ static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst)
 		upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr));
 	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_OFFSET0, 0);
 	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_SIZE0,
-		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared)));
+		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)));
 }
 
 /**
  * vcn_v5_0_1_mc_resume_dpg_mode - memory controller programming for dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Let the VCN memory controller know it's offsets with dpg mode
  */
-static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					  bool indirect)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
@@ -421,7 +473,7 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 		VCN, 0, regUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
 		VCN, 0, regUVD_VCPU_NONCACHE_SIZE0),
-		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared)), 0, indirect);
+		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)), 0, indirect);
 
 	/* VCN global tiling registers */
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
@@ -431,39 +483,39 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 /**
  * vcn_v5_0_1_disable_clock_gating - disable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
 }
 
 /**
  * vcn_v5_0_1_enable_clock_gating - enable VCN clock gating
  *
- * @adev: amdgpu_device pointer
- * @inst: instance number
+ * @vinst: VCN instance
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_device *adev, int inst)
+static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 {
 }
 
 /**
  * vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  * @indirect: indirectly write sram
  *
  * Start VCN block with dpg mode
  */
-static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     bool indirect)
 {
-	volatile struct amdgpu_vcn4_fw_shared *fw_shared =
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared =
 		adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	int vcn_inst;
@@ -510,7 +562,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
 		VCN, 0, regUVD_LMI_CTRL), tmp, 0, indirect);
 
-	vcn_v5_0_1_mc_resume_dpg_mode(adev, inst_idx, indirect);
+	vcn_v5_0_1_mc_resume_dpg_mode(vinst, indirect);
 
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
@@ -564,153 +616,148 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 /**
  * vcn_v5_0_1_start - VCN start
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Start VCN block
  */
-static int vcn_v5_0_1_start(struct amdgpu_device *adev)
+static int vcn_v5_0_1_start(struct amdgpu_vcn_inst *vinst)
 {
-	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, j, k, r, vcn_inst;
+	int j, k, r, vcn_inst;
 
-	if (adev->pm.dpm_enabled)
-		amdgpu_dpm_enable_uvd(adev, true);
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v5_0_1_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v5_0_1_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	vcn_inst = GET_INST(VCN, i);
 
-		vcn_inst = GET_INST(VCN, i);
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
 
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, tmp |
-			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-			UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		vcn_v5_0_1_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
-
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(100);
-				if (amdgpu_emu_mode == 1)
-					msleep(20);
-			}
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	vcn_v5_0_1_mc_resume(vinst);
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(100);
+			if (amdgpu_emu_mode == 1)
+				msleep(20);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev,
-				    "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
+	ring = &adev->vcn.inst[i].ring_enc[0];
 
-		WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,
-			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-			VCN_RB1_DB_CTRL__EN_MASK);
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
 
-		/* Read DB_CTRL to flush the write DB_CTRL command. */
-		RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL);
+	/* Read DB_CTRL to flush the write DB_CTRL command. */
+	RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL);
 
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4);
 
-		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
 
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
 
-		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -718,13 +765,14 @@ static int vcn_v5_0_1_start(struct amdgpu_device *adev)
 /**
  * vcn_v5_0_1_stop_dpg_mode - VCN stop with dpg mode
  *
- * @adev: amdgpu_device pointer
- * @inst_idx: instance number index
+ * @vinst: VCN instance
  *
  * Stop VCN block with dpg mode
  */
-static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 {
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
 	uint32_t tmp;
 	int vcn_inst;
 
@@ -746,78 +794,75 @@ static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 /**
  * vcn_v5_0_1_stop - VCN stop
  *
- * @adev: amdgpu_device pointer
+ * @vinst: VCN instance
  *
  * Stop VCN block
  */
-static int vcn_v5_0_1_stop(struct amdgpu_device *adev)
+static int vcn_v5_0_1_stop(struct amdgpu_vcn_inst *vinst)
 {
-	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	uint32_t tmp;
-	int i, r = 0, vcn_inst;
+	int r = 0, vcn_inst;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		vcn_inst = GET_INST(VCN, i);
+	vcn_inst = GET_INST(VCN, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v5_0_1_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v5_0_1_stop_dpg_mode(vinst);
+		return 0;
+	}
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		return r;
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-		      UVD_LMI_STATUS__READ_CLEAN_MASK |
-		      UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-		      UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-		      UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
-			UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
-
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
-
-		/* clear status */
-		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
-	}
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
+
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
 
-	if (adev->pm.dpm_enabled)
-		amdgpu_dpm_enable_uvd(adev, false);
+	/* clear status */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
 
 	return 0;
 }
@@ -889,16 +934,17 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = {
 	.get_rptr = vcn_v5_0_1_unified_ring_get_rptr,
 	.get_wptr = vcn_v5_0_1_unified_ring_get_wptr,
 	.set_wptr = vcn_v5_0_1_unified_ring_set_wptr,
-	.emit_frame_size =
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 +
-		4 + /* vcn_v2_0_enc_ring_emit_vm_flush */
-		5 + 5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */
-		1, /* vcn_v2_0_enc_ring_insert_end */
+	.emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
+			   SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 +
+			   4 + /* vcn_v2_0_enc_ring_emit_vm_flush */
+			   5 +
+			   5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */
+			   1, /* vcn_v2_0_enc_ring_insert_end */
 	.emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
 	.emit_ib = vcn_v2_0_enc_ring_emit_ib,
 	.emit_fence = vcn_v2_0_enc_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush,
+	.emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
+	.emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_vcn_enc_ring_test_ring,
 	.test_ib = amdgpu_vcn_unified_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
@@ -906,8 +952,8 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_vcn_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_enc_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait,
+	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
+	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
@@ -933,13 +979,13 @@ static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev)
 /**
  * vcn_v5_0_1_is_idle - check VCN block is idle
  *
- * @handle: amdgpu_device pointer
+ * @ip_block: Pointer to the amdgpu_ip_block structure
  *
  * Check whether VCN block is idle
  */
-static bool vcn_v5_0_1_is_idle(void *handle)
+static bool vcn_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int i, ret = 1;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
@@ -986,42 +1032,35 @@ static int vcn_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
 		if (enable) {
 			if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE)
 				return -EBUSY;
-			vcn_v5_0_1_enable_clock_gating(adev, i);
+			vcn_v5_0_1_enable_clock_gating(vinst);
 		} else {
-			vcn_v5_0_1_disable_clock_gating(adev, i);
+			vcn_v5_0_1_disable_clock_gating(vinst);
 		}
 	}
 
 	return 0;
 }
 
-/**
- * vcn_v5_0_1_set_powergating_state - set VCN block powergating state
- *
- * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
- * @state: power gating state
- *
- * Set VCN block powergating state
- */
-static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block,
-					    enum amd_powergating_state state)
+static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	int ret = 0;
 
-	if (state == adev->vcn.cur_state)
+	if (state == vinst->cur_state)
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v5_0_1_stop(adev);
+		ret = vcn_v5_0_1_stop(vinst);
 	else
-		ret = vcn_v5_0_1_start(adev);
+		ret = vcn_v5_0_1_start(vinst);
 
 	if (!ret)
-		adev->vcn.cur_state = state;
+		vinst->cur_state = state;
 
 	return ret;
 }
@@ -1104,7 +1143,7 @@ static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = {
 	.soft_reset = NULL,
 	.post_soft_reset = NULL,
 	.set_clockgating_state = vcn_v5_0_1_set_clockgating_state,
-	.set_powergating_state = vcn_v5_0_1_set_powergating_state,
+	.set_powergating_state = vcn_set_powergating_state,
 	.dump_ip_state = vcn_v5_0_0_dump_ip_state,
 	.print_ip_state = vcn_v5_0_0_print_ip_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h
index 82ac709f44bf..8fd90bd10807 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h
@@ -24,6 +24,9 @@
 #ifndef __VCN_v5_0_1_H__
 #define __VCN_v5_0_1_H__
 
+#define regVCN_RRMT_CNTL                          0x0940
+#define regVCN_RRMT_CNTL_BASE_IDX                 1
+
 extern const struct amdgpu_ip_block_version vcn_v5_0_1_ip_block;
 
 #endif /* __VCN_v5_0_1_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 98fc6941159e..eb16916c6473 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -555,7 +555,7 @@ static int vega10_ih_resume(struct amdgpu_ip_block *ip_block)
 	return vega10_ih_hw_init(ip_block);
 }
 
-static bool vega10_ih_is_idle(void *handle)
+static bool vega10_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_sdma_pkt_open.h b/drivers/gpu/drm/amd/amdgpu/vega10_sdma_pkt_open.h
index 8de4ccce5e38..3ca8a417c6d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_sdma_pkt_open.h
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_sdma_pkt_open.h
@@ -64,6 +64,9 @@
 #define HEADER_BARRIER  5
 #define SDMA_OP_AQL_COPY  0
 #define SDMA_OP_AQL_BARRIER_OR  0
+/* vm invalidation is only available for GC9.4.3/GC9.4.4/GC9.5.0 */
+#define SDMA_OP_VM_INVALIDATE 8
+#define SDMA_SUBOP_VM_INVALIDATE 4
 
 /*define for op field*/
 #define SDMA_PKT_HEADER_op_offset 0
@@ -3331,5 +3334,72 @@
 #define SDMA_AQL_PKT_BARRIER_OR_COMPLETION_SIGNAL_HI_completion_signal_63_32_shift  0
 #define SDMA_AQL_PKT_BARRIER_OR_COMPLETION_SIGNAL_HI_COMPLETION_SIGNAL_63_32(x) (((x) & SDMA_AQL_PKT_BARRIER_OR_COMPLETION_SIGNAL_HI_completion_signal_63_32_mask) << SDMA_AQL_PKT_BARRIER_OR_COMPLETION_SIGNAL_HI_completion_signal_63_32_shift)
 
+/*
+** Definitions for SDMA_PKT_VM_INVALIDATION packet
+*/
+
+/*define for HEADER word*/
+/*define for op field*/
+#define SDMA_PKT_VM_INVALIDATION_HEADER_op_offset 0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_op_mask   0x000000FF
+#define SDMA_PKT_VM_INVALIDATION_HEADER_op_shift  0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_OP(x) ((x & SDMA_PKT_VM_INVALIDATION_HEADER_op_mask) << SDMA_PKT_VM_INVALIDATION_HEADER_op_shift)
+
+/*define for sub_op field*/
+#define SDMA_PKT_VM_INVALIDATION_HEADER_sub_op_offset 0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_sub_op_mask   0x000000FF
+#define SDMA_PKT_VM_INVALIDATION_HEADER_sub_op_shift  8
+#define SDMA_PKT_VM_INVALIDATION_HEADER_SUB_OP(x) ((x & SDMA_PKT_VM_INVALIDATION_HEADER_sub_op_mask) << SDMA_PKT_VM_INVALIDATION_HEADER_sub_op_shift)
+
+/*define for xcc0_eng_id field*/
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc0_eng_id_offset 0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc0_eng_id_mask   0x0000001F
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc0_eng_id_shift  16
+#define SDMA_PKT_VM_INVALIDATION_HEADER_XCC0_ENG_ID(x) ((x & SDMA_PKT_VM_INVALIDATION_HEADER_xcc0_eng_id_mask) << SDMA_PKT_VM_INVALIDATION_HEADER_xcc0_eng_id_shift)
+
+/*define for xcc1_eng_id field*/
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc1_eng_id_offset 0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc1_eng_id_mask   0x0000001F
+#define SDMA_PKT_VM_INVALIDATION_HEADER_xcc1_eng_id_shift  21
+#define SDMA_PKT_VM_INVALIDATION_HEADER_XCC1_ENG_ID(x) ((x & SDMA_PKT_VM_INVALIDATION_HEADER_xcc1_eng_id_mask) << SDMA_PKT_VM_INVALIDATION_HEADER_xcc1_eng_id_shift)
+
+/*define for mmhub_eng_id field*/
+#define SDMA_PKT_VM_INVALIDATION_HEADER_mmhub_eng_id_offset 0
+#define SDMA_PKT_VM_INVALIDATION_HEADER_mmhub_eng_id_mask   0x0000001F
+#define SDMA_PKT_VM_INVALIDATION_HEADER_mmhub_eng_id_shift  26
+#define SDMA_PKT_VM_INVALIDATION_HEADER_MMHUB_ENG_ID(x) ((x & SDMA_PKT_VM_INVALIDATION_HEADER_mmhub_eng_id_mask) << SDMA_PKT_VM_INVALIDATION_HEADER_mmhub_eng_id_shift)
+
+/*define for INVALIDATEREQ word*/
+/*define for invalidatereq field*/
+#define SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_invalidatereq_offset 1
+#define SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_invalidatereq_mask   0xFFFFFFFF
+#define SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_invalidatereq_shift  0
+#define SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_INVALIDATEREQ(x) ((x & SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_invalidatereq_mask) << SDMA_PKT_VM_INVALIDATION_INVALIDATEREQ_invalidatereq_shift)
+
+/*define for ADDRESSRANGELO word*/
+/*define for addressrangelo field*/
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_addressrangelo_offset 2
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_addressrangelo_mask   0xFFFFFFFF
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_addressrangelo_shift  0
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_ADDRESSRANGELO(x) ((x & SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_addressrangelo_mask) << SDMA_PKT_VM_INVALIDATION_ADDRESSRANGELO_addressrangelo_shift)
+
+/*define for ADDRESSRANGEHI word*/
+/*define for invalidateack field*/
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_invalidateack_offset 3
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_invalidateack_mask   0x0000FFFF
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_invalidateack_shift  0
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_INVALIDATEACK(x) ((x & SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_invalidateack_mask) << SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_invalidateack_shift)
+
+/*define for addressrangehi field*/
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_addressrangehi_offset 3
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_addressrangehi_mask   0x0000001F
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_addressrangehi_shift  16
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_ADDRESSRANGEHI(x) ((x & SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_addressrangehi_mask) << SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_addressrangehi_shift)
+
+/*define for reserved field*/
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_reserved_offset 3
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_reserved_mask   0x000001FF
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_reserved_shift  23
+#define SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_RESERVED(x) ((x & SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_reserved_mask) << SDMA_PKT_VM_INVALIDATION_ADDRESSRANGEHI_reserved_shift)
 
 #endif /* __SDMA_PKT_OPEN_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index e9e3b2ed4b7b..faa0dd75dd6d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -651,7 +651,7 @@ static int vega20_ih_resume(struct amdgpu_ip_block *ip_block)
 	return vega20_ih_hw_init(ip_block);
 }
 
-static bool vega20_ih_is_idle(void *handle)
+static bool vega20_ih_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	/* todo */
 	return true;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 0c9c4d8b7b71..86d8bc10d90a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1729,7 +1729,7 @@ static int vi_common_resume(struct amdgpu_ip_block *ip_block)
 	return vi_common_hw_init(ip_block);
 }
 
-static bool vi_common_is_idle(void *handle)
+static bool vi_common_is_idle(struct amdgpu_ip_block *ip_block)
 {
 	return true;
 }
@@ -1987,9 +1987,9 @@ static int vi_common_set_powergating_state(struct amdgpu_ip_block *ip_block,
 	return 0;
 }
 
-static void vi_common_get_clockgating_state(void *handle, u64 *flags)
+static void vi_common_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64 *flags)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	int data;
 
 	if (amdgpu_sriov_vf(adev))
author	Linus Torvalds <torvalds@linux-foundation.org>	2025-03-29 03:44:52 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2025-03-29 03:44:52 +0300
commit	0c86b42439b6c11d758b3392a21117934fef00c1 (patch)
tree	6aa7071476067661867af33767cc0e1863397a04 /drivers/gpu/drm/amd/amdgpu
parent	51aad189f8e0f926c0977d180cae6a78df445f27 (diff)
parent	cf05922d63e2ae6a9b1b52ff5236a44c3b29f78c (diff)
download	linux-0c86b42439b6c11d758b3392a21117934fef00c1.tar.xz