Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 683 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
new file mode 100644
index 000000000..67eb01fef
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -0,0 +1,683 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+
+#include "amdgpu.h"
+#include "amdgpu_vce.h"
+#include "cikd.h"
+#include "vce/vce_2_0_d.h"
+#include "vce/vce_2_0_sh_mask.h"
+#include "smu/smu_7_0_1_d.h"
+#include "smu/smu_7_0_1_sh_mask.h"
+#include "oss/oss_2_0_d.h"
+#include "oss/oss_2_0_sh_mask.h"
+
+#define VCE_V2_0_FW_SIZE	(256 * 1024)
+#define VCE_V2_0_STACK_SIZE	(64 * 1024)
+#define VCE_V2_0_DATA_SIZE	(23552 * AMDGPU_MAX_VCE_HANDLES)
+#define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
+
+static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev);
+static void vce_v2_0_set_irq_funcs(struct amdgpu_device *adev);
+
+/**
+ * vce_v2_0_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->me == 0)
+		return RREG32(mmVCE_RB_RPTR);
+	else
+		return RREG32(mmVCE_RB_RPTR2);
+}
+
+/**
+ * vce_v2_0_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->me == 0)
+		return RREG32(mmVCE_RB_WPTR);
+	else
+		return RREG32(mmVCE_RB_WPTR2);
+}
+
+/**
+ * vce_v2_0_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->me == 0)
+		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
+	else
+		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
+}
+
+static int vce_v2_0_lmi_clean(struct amdgpu_device *adev)
+{
+	int i, j;
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			uint32_t status = RREG32(mmVCE_LMI_STATUS);
+
+			if (status & 0x337f)
+				return 0;
+			mdelay(10);
+		}
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int vce_v2_0_firmware_loaded(struct amdgpu_device *adev)
+{
+	int i, j;
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			uint32_t status = RREG32(mmVCE_STATUS);
+
+			if (status & VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK)
+				return 0;
+			mdelay(10);
+		}
+
+		DRM_ERROR("VCE not responding, trying to reset the ECPU!!!\n");
+		WREG32_P(mmVCE_SOFT_RESET,
+			VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
+			~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
+		mdelay(10);
+		WREG32_P(mmVCE_SOFT_RESET, 0,
+			~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
+		mdelay(10);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static void vce_v2_0_disable_cg(struct amdgpu_device *adev)
+{
+	WREG32(mmVCE_CGTT_CLK_OVERRIDE, 7);
+}
+
+static void vce_v2_0_init_cg(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	tmp = RREG32(mmVCE_CLOCK_GATING_A);
+	tmp &= ~0xfff;
+	tmp |= ((0 << 0) | (4 << 4));
+	tmp |= 0x40000;
+	WREG32(mmVCE_CLOCK_GATING_A, tmp);
+
+	tmp = RREG32(mmVCE_UENC_CLOCK_GATING);
+	tmp &= ~0xfff;
+	tmp |= ((0 << 0) | (4 << 4));
+	WREG32(mmVCE_UENC_CLOCK_GATING, tmp);
+
+	tmp = RREG32(mmVCE_CLOCK_GATING_B);
+	tmp |= 0x10;
+	tmp &= ~0x100000;
+	WREG32(mmVCE_CLOCK_GATING_B, tmp);
+}
+
+static void vce_v2_0_mc_resume(struct amdgpu_device *adev)
+{
+	uint32_t size, offset;
+
+	WREG32_P(mmVCE_CLOCK_GATING_A, 0, ~(1 << 16));
+	WREG32_P(mmVCE_UENC_CLOCK_GATING, 0x1FF000, ~0xFF9FF000);
+	WREG32_P(mmVCE_UENC_REG_CLOCK_GATING, 0x3F, ~0x3F);
+	WREG32(mmVCE_CLOCK_GATING_B, 0xf7);
+
+	WREG32(mmVCE_LMI_CTRL, 0x00398000);
+	WREG32_P(mmVCE_LMI_CACHE_CTRL, 0x0, ~0x1);
+	WREG32(mmVCE_LMI_SWAP_CNTL, 0);
+	WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
+	WREG32(mmVCE_LMI_VM_CTRL, 0);
+
+	WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+
+	offset = AMDGPU_VCE_FIRMWARE_OFFSET;
+	size = VCE_V2_0_FW_SIZE;
+	WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_SIZE0, size);
+
+	offset += size;
+	size = VCE_V2_0_STACK_SIZE;
+	WREG32(mmVCE_VCPU_CACHE_OFFSET1, offset & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_SIZE1, size);
+
+	offset += size;
+	size = VCE_V2_0_DATA_SIZE;
+	WREG32(mmVCE_VCPU_CACHE_OFFSET2, offset & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_SIZE2, size);
+
+	WREG32_P(mmVCE_LMI_CTRL2, 0x0, ~0x100);
+	WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1);
+}
+
+static bool vce_v2_0_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK);
+}
+
+static int vce_v2_0_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	unsigned i;
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (vce_v2_0_is_idle(handle))
+			return 0;
+	}
+	return -ETIMEDOUT;
+}
+
+/**
+ * vce_v2_0_start - start VCE block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the VCE block
+ */
+static int vce_v2_0_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	int r;
+
+	/* set BUSY flag */
+	WREG32_P(mmVCE_STATUS, 1, ~1);
+
+	vce_v2_0_init_cg(adev);
+	vce_v2_0_disable_cg(adev);
+
+	vce_v2_0_mc_resume(adev);
+
+	ring = &adev->vce.ring[0];
+	WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
+	WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
+
+	ring = &adev->vce.ring[1];
+	WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
+	WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+	WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
+
+	WREG32_FIELD(VCE_VCPU_CNTL, CLK_EN, 1);
+	WREG32_FIELD(VCE_SOFT_RESET, ECPU_SOFT_RESET, 1);
+	mdelay(100);
+	WREG32_FIELD(VCE_SOFT_RESET, ECPU_SOFT_RESET, 0);
+
+	r = vce_v2_0_firmware_loaded(adev);
+
+	/* clear BUSY flag */
+	WREG32_P(mmVCE_STATUS, 0, ~1);
+
+	if (r) {
+		DRM_ERROR("VCE not responding, giving up!!!\n");
+		return r;
+	}
+
+	return 0;
+}
+
+static int vce_v2_0_stop(struct amdgpu_device *adev)
+{
+	int i;
+	int status;
+
+	if (vce_v2_0_lmi_clean(adev)) {
+		DRM_INFO("vce is not idle \n");
+		return 0;
+	}
+
+	if (vce_v2_0_wait_for_idle(adev)) {
+		DRM_INFO("VCE is busy, Can't set clock gating");
+		return 0;
+	}
+
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(mmVCE_LMI_CTRL2, 1 << 8, ~(1 << 8));
+
+	for (i = 0; i < 100; ++i) {
+		status = RREG32(mmVCE_LMI_STATUS);
+		if (status & 0x240)
+			break;
+		mdelay(1);
+	}
+
+	WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x80001);
+
+	/* put LMI, VCPU, RBC etc... into reset */
+	WREG32_P(mmVCE_SOFT_RESET, 1, ~0x1);
+
+	WREG32(mmVCE_STATUS, 0);
+
+	return 0;
+}
+
+static void vce_v2_0_set_sw_cg(struct amdgpu_device *adev, bool gated)
+{
+	u32 tmp;
+
+	if (gated) {
+		tmp = RREG32(mmVCE_CLOCK_GATING_B);
+		tmp |= 0xe70000;
+		WREG32(mmVCE_CLOCK_GATING_B, tmp);
+
+		tmp = RREG32(mmVCE_UENC_CLOCK_GATING);
+		tmp |= 0xff000000;
+		WREG32(mmVCE_UENC_CLOCK_GATING, tmp);
+
+		tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
+		tmp &= ~0x3fc;
+		WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp);
+
+		WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0);
+	} else {
+		tmp = RREG32(mmVCE_CLOCK_GATING_B);
+		tmp |= 0xe7;
+		tmp &= ~0xe70000;
+		WREG32(mmVCE_CLOCK_GATING_B, tmp);
+
+		tmp = RREG32(mmVCE_UENC_CLOCK_GATING);
+		tmp |= 0x1fe000;
+		tmp &= ~0xff000000;
+		WREG32(mmVCE_UENC_CLOCK_GATING, tmp);
+
+		tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
+		tmp |= 0x3fc;
+		WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp);
+	}
+}
+
+static void vce_v2_0_set_dyn_cg(struct amdgpu_device *adev, bool gated)
+{
+	u32 orig, tmp;
+
+/* LMI_MC/LMI_UMC always set in dynamic,
+ * set {CGC_*_GATE_MODE, CGC_*_SW_GATE} = {0, 0}
+ */
+	tmp = RREG32(mmVCE_CLOCK_GATING_B);
+	tmp &= ~0x00060006;
+
+/* Exception for ECPU, IH, SEM, SYS blocks needs to be turned on/off by SW */
+	if (gated) {
+		tmp |= 0xe10000;
+		WREG32(mmVCE_CLOCK_GATING_B, tmp);
+	} else {
+		tmp |= 0xe1;
+		tmp &= ~0xe10000;
+		WREG32(mmVCE_CLOCK_GATING_B, tmp);
+	}
+
+	orig = tmp = RREG32(mmVCE_UENC_CLOCK_GATING);
+	tmp &= ~0x1fe000;
+	tmp &= ~0xff000000;
+	if (tmp != orig)
+		WREG32(mmVCE_UENC_CLOCK_GATING, tmp);
+
+	orig = tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
+	tmp &= ~0x3fc;
+	if (tmp != orig)
+		WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp);
+
+	/* set VCE_UENC_REG_CLOCK_GATING always in dynamic mode */
+	WREG32(mmVCE_UENC_REG_CLOCK_GATING, 0x00);
+
+	if(gated)
+		WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0);
+}
+
+static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable,
+								bool sw_cg)
+{
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) {
+		if (sw_cg)
+			vce_v2_0_set_sw_cg(adev, true);
+		else
+			vce_v2_0_set_dyn_cg(adev, true);
+	} else {
+		vce_v2_0_disable_cg(adev);
+
+		if (sw_cg)
+			vce_v2_0_set_sw_cg(adev, false);
+		else
+			vce_v2_0_set_dyn_cg(adev, false);
+	}
+}
+
+static int vce_v2_0_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev->vce.num_rings = 2;
+
+	vce_v2_0_set_ring_funcs(adev);
+	vce_v2_0_set_irq_funcs(adev);
+
+	return 0;
+}
+
+static int vce_v2_0_sw_init(void *handle)
+{
+	struct amdgpu_ring *ring;
+	int r, i;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	/* VCE */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 167, &adev->vce.irq);
+	if (r)
+		return r;
+
+	r = amdgpu_vce_sw_init(adev, VCE_V2_0_FW_SIZE +
+		VCE_V2_0_STACK_SIZE + VCE_V2_0_DATA_SIZE);
+	if (r)
+		return r;
+
+	r = amdgpu_vce_resume(adev);
+	if (r)
+		return r;
+
+	for (i = 0; i < adev->vce.num_rings; i++) {
+		enum amdgpu_ring_priority_level hw_prio = amdgpu_vce_get_ring_prio(i);
+
+		ring = &adev->vce.ring[i];
+		sprintf(ring->name, "vce%d", i);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->vce.irq, 0,
+				     hw_prio, NULL);
+		if (r)
+			return r;
+	}
+
+	r = amdgpu_vce_entity_init(adev);
+
+	return r;
+}
+
+static int vce_v2_0_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_vce_suspend(adev);
+	if (r)
+		return r;
+
+	return amdgpu_vce_sw_fini(adev);
+}
+
+static int vce_v2_0_hw_init(void *handle)
+{
+	int r, i;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	amdgpu_asic_set_vce_clocks(adev, 10000, 10000);
+	vce_v2_0_enable_mgcg(adev, true, false);
+
+	for (i = 0; i < adev->vce.num_rings; i++) {
+		r = amdgpu_ring_test_helper(&adev->vce.ring[i]);
+		if (r)
+			return r;
+	}
+
+	DRM_INFO("VCE initialized successfully.\n");
+
+	return 0;
+}
+
+static int vce_v2_0_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	return 0;
+}
+
+static int vce_v2_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_vce(adev, false);
+	} else {
+		amdgpu_asic_set_vce_clocks(adev, 0, 0);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_CG_STATE_GATE);
+	}
+
+	r = vce_v2_0_hw_fini(adev);
+	if (r)
+		return r;
+
+	return amdgpu_vce_suspend(adev);
+}
+
+static int vce_v2_0_resume(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_vce_resume(adev);
+	if (r)
+		return r;
+
+	return vce_v2_0_hw_init(adev);
+}
+
+static int vce_v2_0_soft_reset(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	WREG32_FIELD(SRBM_SOFT_RESET, SOFT_RESET_VCE, 1);
+	mdelay(5);
+
+	return vce_v2_0_start(adev);
+}
+
+static int vce_v2_0_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	uint32_t val = 0;
+
+	if (state == AMDGPU_IRQ_STATE_ENABLE)
+		val |= VCE_SYS_INT_EN__VCE_SYS_INT_TRAP_INTERRUPT_EN_MASK;
+
+	WREG32_P(mmVCE_SYS_INT_EN, val, ~VCE_SYS_INT_EN__VCE_SYS_INT_TRAP_INTERRUPT_EN_MASK);
+	return 0;
+}
+
+static int vce_v2_0_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: VCE\n");
+	switch (entry->src_data[0]) {
+	case 0:
+	case 1:
+		amdgpu_fence_process(&adev->vce.ring[entry->src_data[0]]);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static int vce_v2_0_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	bool gate = false;
+	bool sw_cg = false;
+
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (state == AMD_CG_STATE_GATE) {
+		gate = true;
+		sw_cg = true;
+	}
+
+	vce_v2_0_enable_mgcg(adev, gate, sw_cg);
+
+	return 0;
+}
+
+static int vce_v2_0_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	/* This doesn't actually powergate the VCE block.
+	 * That's done in the dpm code via the SMC.  This
+	 * just re-inits the block as necessary.  The actual
+	 * gating still happens in the dpm code.  We should
+	 * revisit this when there is a cleaner line between
+	 * the smc and the hw blocks
+	 */
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (state == AMD_PG_STATE_GATE)
+		return vce_v2_0_stop(adev);
+	else
+		return vce_v2_0_start(adev);
+}
+
+static const struct amd_ip_funcs vce_v2_0_ip_funcs = {
+	.name = "vce_v2_0",
+	.early_init = vce_v2_0_early_init,
+	.late_init = NULL,
+	.sw_init = vce_v2_0_sw_init,
+	.sw_fini = vce_v2_0_sw_fini,
+	.hw_init = vce_v2_0_hw_init,
+	.hw_fini = vce_v2_0_hw_fini,
+	.suspend = vce_v2_0_suspend,
+	.resume = vce_v2_0_resume,
+	.is_idle = vce_v2_0_is_idle,
+	.wait_for_idle = vce_v2_0_wait_for_idle,
+	.soft_reset = vce_v2_0_soft_reset,
+	.set_clockgating_state = vce_v2_0_set_clockgating_state,
+	.set_powergating_state = vce_v2_0_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs vce_v2_0_ring_funcs = {
+	.type = AMDGPU_RING_TYPE_VCE,
+	.align_mask = 0xf,
+	.nop = VCE_CMD_NO_OP,
+	.support_64bit_ptrs = false,
+	.no_user_fence = true,
+	.get_rptr = vce_v2_0_ring_get_rptr,
+	.get_wptr = vce_v2_0_ring_get_wptr,
+	.set_wptr = vce_v2_0_ring_set_wptr,
+	.parse_cs = amdgpu_vce_ring_parse_cs,
+	.emit_frame_size = 6, /* amdgpu_vce_ring_emit_fence  x1 no user fence */
+	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
+	.emit_ib = amdgpu_vce_ring_emit_ib,
+	.emit_fence = amdgpu_vce_ring_emit_fence,
+	.test_ring = amdgpu_vce_ring_test_ring,
+	.test_ib = amdgpu_vce_ring_test_ib,
+	.insert_nop = amdgpu_ring_insert_nop,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vce_ring_begin_use,
+	.end_use = amdgpu_vce_ring_end_use,
+};
+
+static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->vce.num_rings; i++) {
+		adev->vce.ring[i].funcs = &vce_v2_0_ring_funcs;
+		adev->vce.ring[i].me = i;
+	}
+}
+
+static const struct amdgpu_irq_src_funcs vce_v2_0_irq_funcs = {
+	.set = vce_v2_0_set_interrupt_state,
+	.process = vce_v2_0_process_interrupt,
+};
+
+static void vce_v2_0_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->vce.irq.num_types = 1;
+	adev->vce.irq.funcs = &vce_v2_0_irq_funcs;
+};
+
+const struct amdgpu_ip_block_version vce_v2_0_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_VCE,
+		.major = 2,
+		.minor = 0,
+		.rev = 0,
+		.funcs = &vce_v2_0_ip_funcs,
+};