Merge tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main pull request for 5.4-rc1 merge window. I don't think
  there is anything outstanding so next week should just be fixes, but
  we'll see if I missed anything. I landed some fixes earlier in the
  week but got delayed writing summary and sending it out, due to a mix
  of sick kid and jetlag!

  There are some fixes pending, but I'd rather get the main merge out of
  the way instead of delaying it longer.

  It's also pretty large in commit count and new amd header file size.
  The largest thing is four new amdgpu products (navi12/14, arcturus and
  renoir APU support).

  Otherwise it's pretty much lots of work across the board, i915 has
  started landing tigerlake support, lots of icelake fixes and lots of
  locking reworking for future gpu support, lots of header file rework
  (drmP.h is nearly gone), some old legacy hacks (DRM_WAIT_ON) have been
  put into the places they are needed.

  uapi:
   - content protection type property for HDCP

  core:
   - rework include dependencies
   - lots of drmP.h removals
   - link rate calculation robustness fix
   - make fb helper map only when required
   - add connector->DDC adapter link
   - DRM_WAIT_ON removed
   - drop DRM_AUTH usage from drivers

  dma-buf:
   - reservation object fence helper

  dma-fence:
   - shrink dma_fence struct
   - merge signal functions
   - store timestamps in dma_fence
   - selftests

  ttm:
   - embed drm_get_object struct into ttm_buffer_object
   - release_notify callback

  bridges:
   - sii902x - audio graph card support
   - tc358767 - aux data handling rework
   - ti-snd64dsi86 - debugfs support, DSI mode flags support

  panels:
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191, Boe
     Himax8279d, Sharp LD-D5116Z01B
   - TI nspire, NEC NL8048HL11, LG Philips LB035Q02, Sharp LS037V7DW01,
     Sony ACX565AKM, Toppoly TD028TTEC1 Toppoly TD043MTEA1

  i915:
   - Initial tigerlake platform support
   - Locking simplification work, general all over refactoring.
   - Selftests
   - HDCP debug info improvements
   - DSI properties
   - Icelake display PLL fixes, colorspace fixes, bandwidth fixes, DSI
     suspend/resume
   - GuC fixes
   - Perf fixes
   - ElkhartLake enablement
   - DP MST fixes
   - GVT - command parser enhancements

  amdgpu:
   - add wipe memory on release flag for buffer creation
   - Navi12/14 support (may be marked experimental)
   - Arcturus support
   - Renoir APU support
   - mclk DPM for Navi
   - DC display fixes
   - Raven scatter/gather support
   - RAS support for GFX
   - Navi12 + Arcturus power features
   - GPU reset for Picasso
   - smu11 i2c controller support

  amdkfd:
   - navi12/14 support
   - Arcturus support

  radeon:
   - kexec fix

  nouveau:
   - improved display color management
   - detect lack of GPU power cables

  vmwgfx:
   - evicition priority support
   - remove unused security feature

  msm:
   - msm8998 display support
   - better async commit support for cursor updates

  etnaviv:
   - per-process address space support
   - performance counter fixes
   - softpin support

  mcde:
   - DCS transfers fix

  exynos:
   - drmP.h cleanup

  lima:
   - reduce logging

  kirin:
   - misc clenaups

  komeda:
   - dual-link support
   - DT memory regions

  hisilicon:
   - misc fixes

  imx:
   - IPUv3 image converter fixes
   - 32-bit RGB V4L2 pixel format support

  ingenic:
   - more support for panel related cases

  mgag200:
   - cursor support fix

  panfrost:
   - export GPU features register to userspace
   - gpu heap allocations
   - per-fd address space support

  pl111:
   - CLD pads wiring support removed from DT

  rockchip:
   - rework to use DRM PSR helpers
   - fix bug in VOP_WIN_GET macro
   - DSI DT binding rework

  sun4i:
   - improve support for color encoding and range
   - DDC enabled GPIO

  tinydrm:
   - rework SPI support
   - improve MIPI-DBI support
   - moved to drm/tiny

  vkms:
   - rework CRC tracking

  dw-hdmi:
   - get_eld and i2s improvements

  gm12u320:
   - misc fixes

  meson:
   - global code cleanup
   - vpu feature detect

  omap:
   - alpha/pixel blend mode properties

  rcar-du:
   - misc fixes"

* tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm: (2112 commits)
  drm/nouveau/bar/gm20b: Avoid BAR1 teardown during init
  drm/nouveau: Fix ordering between TTM and GEM release
  drm/nouveau/prime: Extend DMA reservation object lock
  drm/nouveau: Fix fallout from reservation object rework
  drm/nouveau/kms/nv50-: Don't create MSTMs for eDP connectors
  drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap
  drm/i915: to make vgpu ppgtt notificaiton as atomic operation
  drm/i915: Flush the existing fence before GGTT read/write
  drm/i915: Hold irq-off for the entire fake lock period
  drm/i915/gvt: update RING_START reg of vGPU when the context is submitted to i915
  drm/i915/gvt: update vgpu workload head pointer correctly
  drm/mcde: Fix DSI transfers
  drm/msm: Use the correct dma_sync calls harder
  drm/msm: remove unlikely() from WARN_ON() conditions
  drm/msm/dsi: Fix return value check for clk_get_parent
  drm/msm: add atomic traces
  drm/msm/dpu: async commit support
  drm/msm: async commit support
  drm/msm: split power control from prepare/complete_commit
  drm/msm: add kms->flush_commit()
  ...

1 files changed, 144 insertions, 131 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index dfde886cc6bd..36ad0c0e8efb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -22,7 +22,7 @@
  */
 
 #include <linux/firmware.h>
-#include <drm/drmP.h>
+
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
 #include "soc15.h"
@@ -92,6 +92,7 @@ static int vcn_v2_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	adev->vcn.num_vcn_inst = 1;
 	adev->vcn.num_enc_rings = 2;
 
 	vcn_v2_0_set_dec_ring_funcs(adev);
@@ -118,7 +119,7 @@ static int vcn_v2_0_sw_init(void *handle)
 	/* VCN DEC TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
 			      VCN_2_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT,
-			      &adev->vcn.irq);
+			      &adev->vcn.inst->irq);
 	if (r)
 		return r;
 
@@ -126,15 +127,14 @@ static int vcn_v2_0_sw_init(void *handle)
 	for (i = 0; i < adev->vcn.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.irq);
+				      &adev->vcn.inst->irq);
 		if (r)
 			return r;
 	}
 
 	/* VCN JPEG TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-			      VCN_2_0__SRCID__JPEG_DECODE,
-			      &adev->vcn.irq);
+			      VCN_2_0__SRCID__JPEG_DECODE, &adev->vcn.inst->irq);
 	if (r)
 		return r;
 
@@ -156,49 +156,56 @@ static int vcn_v2_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	ring = &adev->vcn.ring_dec;
+	ring = &adev->vcn.inst->ring_dec;
 
 	ring->use_doorbell = true;
 	ring->doorbell_index = adev->doorbell_index.vcn.vcn_ring0_1 << 1;
 
 	sprintf(ring->name, "vcn_dec");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.irq, 0);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
 	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.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
-	adev->vcn.external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9);
+	adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9);
 	adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
-	adev->vcn.external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0);
+	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.external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1);
+	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.external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD);
+	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.external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP);
+	adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP);
 
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		ring = &adev->vcn.ring_enc[i];
+		ring = &adev->vcn.inst->ring_enc[i];
 		ring->use_doorbell = true;
 		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + i;
 		sprintf(ring->name, "vcn_enc%d", i);
-		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.irq, 0);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
 		if (r)
 			return r;
 	}
 
-	ring = &adev->vcn.ring_jpeg;
+	ring = &adev->vcn.inst->ring_jpeg;
 	ring->use_doorbell = true;
 	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1;
 	sprintf(ring->name, "vcn_jpeg");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.irq, 0);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
 	if (r)
 		return r;
 
 	adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode;
 
 	adev->vcn.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
-	adev->vcn.external.jpeg_pitch = SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
+	adev->vcn.inst->external.jpeg_pitch = SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
 
 	return 0;
 }
@@ -234,11 +241,11 @@ static int vcn_v2_0_sw_fini(void *handle)
 static int vcn_v2_0_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
+	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	int i, r;
 
 	adev->nbio_funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-		ring->doorbell_index);
+					     ring->doorbell_index, 0);
 
 	ring->sched.ready = true;
 	r = amdgpu_ring_test_ring(ring);
@@ -248,7 +255,7 @@ static int vcn_v2_0_hw_init(void *handle)
 	}
 
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		ring = &adev->vcn.ring_enc[i];
+		ring = &adev->vcn.inst->ring_enc[i];
 		ring->sched.ready = true;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
@@ -257,7 +264,7 @@ static int vcn_v2_0_hw_init(void *handle)
 		}
 	}
 
-	ring = &adev->vcn.ring_jpeg;
+	ring = &adev->vcn.inst->ring_jpeg;
 	ring->sched.ready = true;
 	r = amdgpu_ring_test_ring(ring);
 	if (r) {
@@ -283,7 +290,7 @@ done:
 static int vcn_v2_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
+	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	int i;
 
 	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
@@ -294,11 +301,11 @@ static int vcn_v2_0_hw_fini(void *handle)
 	ring->sched.ready = false;
 
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		ring = &adev->vcn.ring_enc[i];
+		ring = &adev->vcn.inst->ring_enc[i];
 		ring->sched.ready = false;
 	}
 
-	ring = &adev->vcn.ring_jpeg;
+	ring = &adev->vcn.inst->ring_jpeg;
 	ring->sched.ready = false;
 
 	return 0;
@@ -368,9 +375,9 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 		offset = 0;
 	} else {
 		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.gpu_addr));
+			lower_32_bits(adev->vcn.inst->gpu_addr));
 		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.gpu_addr));
+			upper_32_bits(adev->vcn.inst->gpu_addr));
 		offset = size;
 		WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
 			AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
@@ -380,17 +387,17 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 
 	/* cache window 1: stack */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
-		lower_32_bits(adev->vcn.gpu_addr + offset));
+		lower_32_bits(adev->vcn.inst->gpu_addr + offset));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
-		upper_32_bits(adev->vcn.gpu_addr + offset));
+		upper_32_bits(adev->vcn.inst->gpu_addr + offset));
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0);
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
 
 	/* cache window 2: context */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-		lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+		lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-		upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+		upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0);
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
 
@@ -426,10 +433,10 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 	} else {
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
-			lower_32_bits(adev->vcn.gpu_addr), 0, indirect);
+			lower_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
-			upper_32_bits(adev->vcn.gpu_addr), 0, indirect);
+			upper_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
 		offset = size;
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
@@ -447,10 +454,10 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 	if (!indirect) {
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
-			lower_32_bits(adev->vcn.gpu_addr + offset), 0, indirect);
+			lower_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
-			upper_32_bits(adev->vcn.gpu_addr + offset), 0, indirect);
+			upper_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
 		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
 	} else {
@@ -467,10 +474,10 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 	/* cache window 2: context */
 	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
-		lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+		lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
 	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
-		upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+		upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
 	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
 	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
@@ -658,7 +665,7 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
  */
 static int jpeg_v2_0_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->vcn.ring_jpeg;
+	struct amdgpu_ring *ring = &adev->vcn.inst->ring_jpeg;
 	uint32_t tmp;
 	int r = 0;
 
@@ -920,7 +927,7 @@ 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)
 {
-	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
+	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
 
 	vcn_v2_0_enable_static_power_gating(adev);
@@ -1046,7 +1053,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 
 static int vcn_v2_0_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
+	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
 	int i, j, r;
@@ -1197,14 +1204,14 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 			lower_32_bits(ring->wptr));
 
-	ring = &adev->vcn.ring_enc[0];
+	ring = &adev->vcn.inst->ring_enc[0];
 	WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr);
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4);
 
-	ring = &adev->vcn.ring_enc[1];
+	ring = &adev->vcn.inst->ring_enc[1];
 	WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr);
@@ -1351,14 +1358,14 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
 					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
 
 				/* Restore */
-				ring = &adev->vcn.ring_enc[0];
+				ring = &adev->vcn.inst->ring_enc[0];
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 
-				ring = &adev->vcn.ring_enc[1];
+				ring = &adev->vcn.inst->ring_enc[1];
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
@@ -1480,11 +1487,13 @@ static void vcn_v2_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
  *
  * Write a start command to the ring.
  */
-static void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
+void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
 {
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1));
 }
 
@@ -1495,9 +1504,11 @@ static void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
  *
  * Write a end command to the ring.
  */
-static void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
+void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
 {
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_END << 1));
 }
 
@@ -1508,14 +1519,15 @@ static void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
  *
  * Write a nop command to the ring.
  */
-static void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
 {
+	struct amdgpu_device *adev = ring->adev;
 	int i;
 
 	WARN_ON(ring->wptr % 2 || count % 2);
 
 	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKET0(mmUVD_NO_OP_INTERNAL_OFFSET, 0));
+		amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.nop, 0));
 		amdgpu_ring_write(ring, 0);
 	}
 }
@@ -1528,30 +1540,31 @@ static void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t coun
  *
  * Write a fence and a trap command to the ring.
  */
-static void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				     unsigned flags)
+void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags)
 {
-	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+	struct amdgpu_device *adev = ring->adev;
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_CONTEXT_ID_INTERNAL_OFFSET, 0));
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.context_id, 0));
 	amdgpu_ring_write(ring, seq);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
 	amdgpu_ring_write(ring, addr & 0xffffffff);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_FENCE << 1));
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
 	amdgpu_ring_write(ring, 0);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
 	amdgpu_ring_write(ring, 0);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_TRAP << 1));
 }
@@ -1564,44 +1577,46 @@ static void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64
  *
  * Write ring commands to execute the indirect buffer
  */
-static void vcn_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
-				      struct amdgpu_job *job,
-				      struct amdgpu_ib *ib,
-				      uint32_t flags)
+void vcn_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
+			       struct amdgpu_job *job,
+			       struct amdgpu_ib *ib,
+			       uint32_t flags)
 {
+	struct amdgpu_device *adev = ring->adev;
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_vmid, 0));
 	amdgpu_ring_write(ring, vmid);
 
-	amdgpu_ring_write(ring,	PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_bar_low, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-	amdgpu_ring_write(ring,	PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_bar_high, 0));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-	amdgpu_ring_write(ring,	PACKET0(mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring,	PACKET0(adev->vcn.internal.ib_size, 0));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
-static void vcn_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring,
-					    uint32_t reg, uint32_t val,
-					    uint32_t mask)
+void vcn_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
 {
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
 	amdgpu_ring_write(ring, reg << 2);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
 	amdgpu_ring_write(ring, val);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.gp_scratch8, 0));
 	amdgpu_ring_write(ring, mask);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_REG_READ_COND_WAIT << 1));
 }
 
-static void vcn_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned vmid, uint64_t pd_addr)
+void vcn_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	uint32_t data0, data1, mask;
@@ -1615,16 +1630,18 @@ static void vcn_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	vcn_v2_0_dec_ring_emit_reg_wait(ring, data0, data1, mask);
 }
 
-static void vcn_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring,
-					uint32_t reg, uint32_t val)
+void vcn_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring,
+				uint32_t reg, uint32_t val)
 {
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0));
 	amdgpu_ring_write(ring, reg << 2);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0));
 	amdgpu_ring_write(ring, val);
 
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0));
 
 	amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_WRITE_REG << 1));
 }
@@ -1640,7 +1657,7 @@ static uint64_t vcn_v2_0_enc_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vcn.ring_enc[0])
+	if (ring == &adev->vcn.inst->ring_enc[0])
 		return RREG32_SOC15(UVD, 0, mmUVD_RB_RPTR);
 	else
 		return RREG32_SOC15(UVD, 0, mmUVD_RB_RPTR2);
@@ -1657,7 +1674,7 @@ static uint64_t vcn_v2_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vcn.ring_enc[0]) {
+	if (ring == &adev->vcn.inst->ring_enc[0]) {
 		if (ring->use_doorbell)
 			return adev->wb.wb[ring->wptr_offs];
 		else
@@ -1681,7 +1698,7 @@ static void vcn_v2_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vcn.ring_enc[0]) {
+	if (ring == &adev->vcn.inst->ring_enc[0]) {
 		if (ring->use_doorbell) {
 			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
@@ -1706,8 +1723,8 @@ static void vcn_v2_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
  *
  * Write enc a fence and a trap command to the ring.
  */
-static void vcn_v2_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
-			u64 seq, unsigned flags)
+void vcn_v2_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
+				u64 seq, unsigned flags)
 {
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
@@ -1718,7 +1735,7 @@ static void vcn_v2_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 	amdgpu_ring_write(ring, VCN_ENC_CMD_TRAP);
 }
 
-static void vcn_v2_0_enc_ring_insert_end(struct amdgpu_ring *ring)
+void vcn_v2_0_enc_ring_insert_end(struct amdgpu_ring *ring)
 {
 	amdgpu_ring_write(ring, VCN_ENC_CMD_END);
 }
@@ -1731,10 +1748,10 @@ static void vcn_v2_0_enc_ring_insert_end(struct amdgpu_ring *ring)
  *
  * Write enc ring commands to execute the indirect buffer
  */
-static void vcn_v2_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
-				      struct amdgpu_job *job,
-				      struct amdgpu_ib *ib,
-				      uint32_t flags)
+void vcn_v2_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
+			       struct amdgpu_job *job,
+			       struct amdgpu_ib *ib,
+			       uint32_t flags)
 {
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
@@ -1745,9 +1762,8 @@ static void vcn_v2_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
-static void vcn_v2_0_enc_ring_emit_reg_wait(struct amdgpu_ring *ring,
-					    uint32_t reg, uint32_t val,
-					    uint32_t mask)
+void vcn_v2_0_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
 {
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
 	amdgpu_ring_write(ring, reg << 2);
@@ -1755,8 +1771,8 @@ static void vcn_v2_0_enc_ring_emit_reg_wait(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
-static void vcn_v2_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned int vmid, uint64_t pd_addr)
+void vcn_v2_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned int vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 
@@ -1767,8 +1783,7 @@ static void vcn_v2_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					lower_32_bits(pd_addr), 0xffffffff);
 }
 
-static void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
-					uint32_t reg, uint32_t val)
+void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
 {
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
 	amdgpu_ring_write(ring,	reg << 2);
@@ -1832,7 +1847,7 @@ static void vcn_v2_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
  *
  * Write a start command to the ring.
  */
-static void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
+void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
 {
 	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
@@ -1850,7 +1865,7 @@ static void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
  *
  * Write a end command to the ring.
  */
-static void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
+void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
 {
 	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
@@ -1869,8 +1884,8 @@ static void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
  *
  * Write a fence and a trap command to the ring.
  */
-static void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				     unsigned flags)
+void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags)
 {
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
@@ -1918,10 +1933,10 @@ static void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u6
  *
  * Write ring commands to execute the indirect buffer.
  */
-static void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
-				       struct amdgpu_job *job,
-				       struct amdgpu_ib *ib,
-				       uint32_t flags)
+void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
+				struct amdgpu_job *job,
+				struct amdgpu_ib *ib,
+				uint32_t flags)
 {
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
@@ -1969,9 +1984,8 @@ static void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, 0x2);
 }
 
-static void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
-					    uint32_t reg, uint32_t val,
-					    uint32_t mask)
+void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
 {
 	uint32_t reg_offset = (reg << 2);
 
@@ -1997,8 +2011,8 @@ static void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, mask);
 }
 
-static void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-		unsigned vmid, uint64_t pd_addr)
+void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	uint32_t data0, data1, mask;
@@ -2012,8 +2026,7 @@ static void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	vcn_v2_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
 }
 
-static void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
-					uint32_t reg, uint32_t val)
+void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
 {
 	uint32_t reg_offset = (reg << 2);
 
@@ -2031,7 +2044,7 @@ static void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
-static void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
 {
 	int i;
 
@@ -2059,16 +2072,16 @@ static int vcn_v2_0_process_interrupt(struct amdgpu_device *adev,
 
 	switch (entry->src_id) {
 	case VCN_2_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT:
-		amdgpu_fence_process(&adev->vcn.ring_dec);
+		amdgpu_fence_process(&adev->vcn.inst->ring_dec);
 		break;
 	case VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE:
-		amdgpu_fence_process(&adev->vcn.ring_enc[0]);
+		amdgpu_fence_process(&adev->vcn.inst->ring_enc[0]);
 		break;
 	case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY:
-		amdgpu_fence_process(&adev->vcn.ring_enc[1]);
+		amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
 		break;
 	case VCN_2_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(&adev->vcn.ring_jpeg);
+		amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
 		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
@@ -2086,20 +2099,20 @@ static int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring)
 	unsigned i;
 	int r;
 
-	WREG32(adev->vcn.external.scratch9, 0xCAFEDEAD);
+	WREG32(adev->vcn.inst[ring->me].external.scratch9, 0xCAFEDEAD);
 	r = amdgpu_ring_alloc(ring, 4);
 	if (r)
 		return r;
-	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+	amdgpu_ring_write(ring, PACKET0(adev->vcn.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, 0xDEADBEEF);
 	amdgpu_ring_commit(ring);
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(adev->vcn.external.scratch9);
+		tmp = RREG32(adev->vcn.inst[ring->me].external.scratch9);
 		if (tmp == 0xDEADBEEF)
 			break;
-		DRM_UDELAY(1);
+		udelay(1);
 	}
 
 	if (i >= adev->usec_timeout)
@@ -2158,7 +2171,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = {
 static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_DEC,
 	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB,
+	.vmhub = AMDGPU_MMHUB_0,
 	.get_rptr = vcn_v2_0_dec_ring_get_rptr,
 	.get_wptr = vcn_v2_0_dec_ring_get_wptr,
 	.set_wptr = vcn_v2_0_dec_ring_set_wptr,
@@ -2189,7 +2202,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_ENC,
 	.align_mask = 0x3f,
 	.nop = VCN_ENC_CMD_NO_OP,
-	.vmhub = AMDGPU_MMHUB,
+	.vmhub = AMDGPU_MMHUB_0,
 	.get_rptr = vcn_v2_0_enc_ring_get_rptr,
 	.get_wptr = vcn_v2_0_enc_ring_get_wptr,
 	.set_wptr = vcn_v2_0_enc_ring_set_wptr,
@@ -2218,7 +2231,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = {
 static const struct amdgpu_ring_funcs vcn_v2_0_jpeg_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_JPEG,
 	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB,
+	.vmhub = AMDGPU_MMHUB_0,
 	.get_rptr = vcn_v2_0_jpeg_ring_get_rptr,
 	.get_wptr = vcn_v2_0_jpeg_ring_get_wptr,
 	.set_wptr = vcn_v2_0_jpeg_ring_set_wptr,
@@ -2247,7 +2260,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_jpeg_ring_vm_funcs = {
 
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.ring_dec.funcs = &vcn_v2_0_dec_ring_vm_funcs;
+	adev->vcn.inst->ring_dec.funcs = &vcn_v2_0_dec_ring_vm_funcs;
 	DRM_INFO("VCN decode is enabled in VM mode\n");
 }
 
@@ -2256,14 +2269,14 @@ 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)
-		adev->vcn.ring_enc[i].funcs = &vcn_v2_0_enc_ring_vm_funcs;
+		adev->vcn.inst->ring_enc[i].funcs = &vcn_v2_0_enc_ring_vm_funcs;
 
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
 static void vcn_v2_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.ring_jpeg.funcs = &vcn_v2_0_jpeg_ring_vm_funcs;
+	adev->vcn.inst->ring_jpeg.funcs = &vcn_v2_0_jpeg_ring_vm_funcs;
 	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
 }
 
@@ -2274,8 +2287,8 @@ 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.irq.num_types = adev->vcn.num_enc_rings + 2;
-	adev->vcn.irq.funcs = &vcn_v2_0_irq_funcs;
+	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2;
+	adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs;
 }
 
 const struct amdgpu_ip_block_version vcn_v2_0_ip_block =