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, 813 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
new file mode 100644
index 000000000..c108b8381
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -0,0 +1,813 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+
+#include "amdgpu.h"
+#include "amdgpu_uvd.h"
+#include "cikd.h"
+
+#include "uvd/uvd_4_2_d.h"
+#include "uvd/uvd_4_2_sh_mask.h"
+
+#include "oss/oss_2_0_d.h"
+#include "oss/oss_2_0_sh_mask.h"
+
+#include "bif/bif_4_1_d.h"
+
+#include "smu/smu_7_0_1_d.h"
+#include "smu/smu_7_0_1_sh_mask.h"
+
+static void uvd_v4_2_mc_resume(struct amdgpu_device *adev);
+static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev);
+static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev);
+static int uvd_v4_2_start(struct amdgpu_device *adev);
+static void uvd_v4_2_stop(struct amdgpu_device *adev);
+static int uvd_v4_2_set_clockgating_state(void *handle,
+				enum amd_clockgating_state state);
+static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
+			     bool sw_mode);
+/**
+ * uvd_v4_2_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t uvd_v4_2_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32(mmUVD_RBC_RB_RPTR);
+}
+
+/**
+ * uvd_v4_2_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t uvd_v4_2_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32(mmUVD_RBC_RB_WPTR);
+}
+
+/**
+ * uvd_v4_2_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void uvd_v4_2_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+static int uvd_v4_2_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	adev->uvd.num_uvd_inst = 1;
+
+	uvd_v4_2_set_ring_funcs(adev);
+	uvd_v4_2_set_irq_funcs(adev);
+
+	return 0;
+}
+
+static int uvd_v4_2_sw_init(void *handle)
+{
+	struct amdgpu_ring *ring;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	/* UVD TRAP */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	if (r)
+		return r;
+
+	r = amdgpu_uvd_sw_init(adev);
+	if (r)
+		return r;
+
+	ring = &adev->uvd.inst->ring;
+	sprintf(ring->name, "uvd");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0,
+			     AMDGPU_RING_PRIO_DEFAULT, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_uvd_resume(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_uvd_entity_init(adev);
+
+	return r;
+}
+
+static int uvd_v4_2_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_uvd_suspend(adev);
+	if (r)
+		return r;
+
+	return amdgpu_uvd_sw_fini(adev);
+}
+
+static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
+				 bool enable);
+/**
+ * uvd_v4_2_hw_init - start and test UVD block
+ *
+ * @handle: handle used to pass amdgpu_device pointer
+ *
+ * Initialize the hardware, boot up the VCPU and do some testing
+ */
+static int uvd_v4_2_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
+	uint32_t tmp;
+	int r;
+
+	uvd_v4_2_enable_mgcg(adev, true);
+	amdgpu_asic_set_uvd_clocks(adev, 10000, 10000);
+
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		goto done;
+
+	r = amdgpu_ring_alloc(ring, 10);
+	if (r) {
+		DRM_ERROR("amdgpu: ring failed to lock UVD ring (%d).\n", r);
+		goto done;
+	}
+
+	tmp = PACKET0(mmUVD_SEMA_WAIT_FAULT_TIMEOUT_CNTL, 0);
+	amdgpu_ring_write(ring, tmp);
+	amdgpu_ring_write(ring, 0xFFFFF);
+
+	tmp = PACKET0(mmUVD_SEMA_WAIT_INCOMPLETE_TIMEOUT_CNTL, 0);
+	amdgpu_ring_write(ring, tmp);
+	amdgpu_ring_write(ring, 0xFFFFF);
+
+	tmp = PACKET0(mmUVD_SEMA_SIGNAL_INCOMPLETE_TIMEOUT_CNTL, 0);
+	amdgpu_ring_write(ring, tmp);
+	amdgpu_ring_write(ring, 0xFFFFF);
+
+	/* Clear timeout status bits */
+	amdgpu_ring_write(ring, PACKET0(mmUVD_SEMA_TIMEOUT_STATUS, 0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_SEMA_CNTL, 0));
+	amdgpu_ring_write(ring, 3);
+
+	amdgpu_ring_commit(ring);
+
+done:
+	if (!r)
+		DRM_INFO("UVD initialized successfully.\n");
+
+	return r;
+}
+
+/**
+ * uvd_v4_2_hw_fini - stop the hardware block
+ *
+ * @handle: handle used to pass amdgpu_device pointer
+ *
+ * Stop the UVD block, mark ring as not ready any more
+ */
+static int uvd_v4_2_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v4_2_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v4_2_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->uvd.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_uvd(adev, false);
+	} else {
+		amdgpu_asic_set_uvd_clocks(adev, 0, 0);
+		/* shutdown the UVD block */
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_CG_STATE_GATE);
+	}
+
+	r = uvd_v4_2_hw_fini(adev);
+	if (r)
+		return r;
+
+	return amdgpu_uvd_suspend(adev);
+}
+
+static int uvd_v4_2_resume(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_uvd_resume(adev);
+	if (r)
+		return r;
+
+	return uvd_v4_2_hw_init(adev);
+}
+
+/**
+ * uvd_v4_2_start - start UVD block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the UVD block
+ */
+static int uvd_v4_2_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
+	uint32_t rb_bufsz;
+	int i, j, r;
+	u32 tmp;
+	/* disable byte swapping */
+	u32 lmi_swap_cntl = 0;
+	u32 mp_swap_cntl = 0;
+
+	/* set uvd busy */
+	WREG32_P(mmUVD_STATUS, 1<<2, ~(1<<2));
+
+	uvd_v4_2_set_dcm(adev, true);
+	WREG32(mmUVD_CGC_GATE, 0);
+
+	/* take UVD block out of reset */
+	WREG32_P(mmSRBM_SOFT_RESET, 0, ~SRBM_SOFT_RESET__SOFT_RESET_UVD_MASK);
+	mdelay(5);
+
+	/* enable VCPU clock */
+	WREG32(mmUVD_VCPU_CNTL,  1 << 9);
+
+	/* disable interupt */
+	WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1));
+
+#ifdef __BIG_ENDIAN
+	/* swap (8 in 32) RB and IB */
+	lmi_swap_cntl = 0xa;
+	mp_swap_cntl = 0;
+#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);
+
+	tmp = RREG32(mmUVD_MPC_CNTL);
+	WREG32(mmUVD_MPC_CNTL, tmp | 0x10);
+
+	WREG32(mmUVD_MPC_SET_MUXA0, 0x40c2040);
+	WREG32(mmUVD_MPC_SET_MUXA1, 0x0);
+	WREG32(mmUVD_MPC_SET_MUXB0, 0x40c2040);
+	WREG32(mmUVD_MPC_SET_MUXB1, 0x0);
+	WREG32(mmUVD_MPC_SET_ALU, 0);
+	WREG32(mmUVD_MPC_SET_MUX, 0x88);
+
+	uvd_v4_2_mc_resume(adev);
+
+	tmp = RREG32_UVD_CTX(ixUVD_LMI_CACHE_CTRL);
+	WREG32_UVD_CTX(ixUVD_LMI_CACHE_CTRL, tmp & (~0x10));
+
+	/* enable UMC */
+	WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8));
+
+	WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK);
+
+	WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK);
+
+	WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+
+	mdelay(10);
+
+	for (i = 0; i < 10; ++i) {
+		uint32_t status;
+		for (j = 0; j < 100; ++j) {
+			status = RREG32(mmUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+		}
+		r = 0;
+		if (status & 2)
+			break;
+
+		DRM_ERROR("UVD not responding, trying to reset the VCPU!!!\n");
+		WREG32_P(mmUVD_SOFT_RESET, UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK,
+				~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+		mdelay(10);
+		WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+		mdelay(10);
+		r = -1;
+	}
+
+	if (r) {
+		DRM_ERROR("UVD not responding, giving up!!!\n");
+		return r;
+	}
+
+	/* enable interupt */
+	WREG32_P(mmUVD_MASTINT_EN, 3<<1, ~(3 << 1));
+
+	WREG32_P(mmUVD_STATUS, 0, ~(1<<2));
+
+	/* force RBC into idle state */
+	WREG32(mmUVD_RBC_RB_CNTL, 0x11010101);
+
+	/* Set the write pointer delay */
+	WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0);
+
+	/* 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));
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32(mmUVD_RBC_RB_RPTR, 0x0);
+
+	ring->wptr = RREG32(mmUVD_RBC_RB_RPTR);
+	WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
+
+	/* set the ring address */
+	WREG32(mmUVD_RBC_RB_BASE, ring->gpu_addr);
+
+	/* Set ring buffer size */
+	rb_bufsz = order_base_2(ring->ring_size);
+	rb_bufsz = (0x1 << 8) | rb_bufsz;
+	WREG32_P(mmUVD_RBC_RB_CNTL, rb_bufsz, ~0x11f1f);
+
+	return 0;
+}
+
+/**
+ * uvd_v4_2_stop - stop UVD block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * stop the UVD block
+ */
+static void uvd_v4_2_stop(struct amdgpu_device *adev)
+{
+	uint32_t i, j;
+	uint32_t status;
+
+	WREG32(mmUVD_RBC_RB_CNTL, 0x11010101);
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			status = RREG32(mmUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(1);
+		}
+		if (status & 2)
+			break;
+	}
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			status = RREG32(mmUVD_LMI_STATUS);
+			if (status & 0xf)
+				break;
+			mdelay(1);
+		}
+		if (status & 0xf)
+			break;
+	}
+
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(mmUVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			status = RREG32(mmUVD_LMI_STATUS);
+			if (status & 0x240)
+				break;
+			mdelay(1);
+		}
+		if (status & 0x240)
+			break;
+	}
+
+	WREG32_P(0x3D49, 0, ~(1 << 2));
+
+	WREG32_P(mmUVD_VCPU_CNTL, 0, ~(1 << 9));
+
+	/* put LMI, VCPU, RBC etc... into reset */
+	WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK);
+
+	WREG32(mmUVD_STATUS, 0);
+
+	uvd_v4_2_set_dcm(adev, false);
+}
+
+/**
+ * uvd_v4_2_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @addr: address
+ * @seq: sequence number
+ * @flags: fence related flags
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void uvd_v4_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				     unsigned flags)
+{
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_CONTEXT_ID, 0));
+	amdgpu_ring_write(ring, seq);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, addr & 0xffffffff);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 2);
+}
+
+/**
+ * uvd_v4_2_ring_test_ring - register write test
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Test if we can successfully write to the context register
+ */
+static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(mmUVD_CONTEXT_ID, 0xCAFEDEAD);
+	r = amdgpu_ring_alloc(ring, 3);
+	if (r)
+		return r;
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_CONTEXT_ID, 0));
+	amdgpu_ring_write(ring, 0xDEADBEEF);
+	amdgpu_ring_commit(ring);
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(mmUVD_CONTEXT_ID);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	return r;
+}
+
+/**
+ * uvd_v4_2_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @job: iob associated with the indirect buffer
+ * @ib: indirect buffer to execute
+ * @flags: flags associated with the indirect buffer
+ *
+ * Write ring commands to execute the indirect buffer
+ */
+static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring,
+				  struct amdgpu_job *job,
+				  struct amdgpu_ib *ib,
+				  uint32_t flags)
+{
+	amdgpu_ring_write(ring, PACKET0(mmUVD_RBC_IB_BASE, 0));
+	amdgpu_ring_write(ring, ib->gpu_addr);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_RBC_IB_SIZE, 0));
+	amdgpu_ring_write(ring, ib->length_dw);
+}
+
+static void uvd_v4_2_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(mmUVD_NO_OP, 0));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+/**
+ * uvd_v4_2_mc_resume - memory controller programming
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Let the UVD memory controller know it's offsets
+ */
+static void uvd_v4_2_mc_resume(struct amdgpu_device *adev)
+{
+	uint64_t addr;
+	uint32_t size;
+
+	/* 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);
+	WREG32(mmUVD_VCPU_CACHE_SIZE0, size);
+
+	addr += size;
+	size = AMDGPU_UVD_HEAP_SIZE >> 3;
+	WREG32(mmUVD_VCPU_CACHE_OFFSET1, addr);
+	WREG32(mmUVD_VCPU_CACHE_SIZE1, size);
+
+	addr += size;
+	size = (AMDGPU_UVD_STACK_SIZE +
+	       (AMDGPU_UVD_SESSION_SIZE * adev->uvd.max_handles)) >> 3;
+	WREG32(mmUVD_VCPU_CACHE_OFFSET2, addr);
+	WREG32(mmUVD_VCPU_CACHE_SIZE2, size);
+
+	/* bits 28-31 */
+	addr = (adev->uvd.inst->gpu_addr >> 28) & 0xF;
+	WREG32(mmUVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
+
+	/* bits 32-39 */
+	addr = (adev->uvd.inst->gpu_addr >> 32) & 0xFF;
+	WREG32(mmUVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
+
+	WREG32(mmUVD_UDEC_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+	WREG32(mmUVD_UDEC_DB_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+	WREG32(mmUVD_UDEC_DBW_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+}
+
+static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
+				 bool enable)
+{
+	u32 orig, data;
+
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) {
+		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
+		data |= 0xfff;
+		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
+
+		orig = data = RREG32(mmUVD_CGC_CTRL);
+		data |= UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
+		if (orig != data)
+			WREG32(mmUVD_CGC_CTRL, data);
+	} else {
+		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
+		data &= ~0xfff;
+		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
+
+		orig = data = RREG32(mmUVD_CGC_CTRL);
+		data &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
+		if (orig != data)
+			WREG32(mmUVD_CGC_CTRL, data);
+	}
+}
+
+static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
+			     bool sw_mode)
+{
+	u32 tmp, tmp2;
+
+	WREG32_FIELD(UVD_CGC_GATE, REGS, 0);
+
+	tmp = RREG32(mmUVD_CGC_CTRL);
+	tmp &= ~(UVD_CGC_CTRL__CLK_OFF_DELAY_MASK | UVD_CGC_CTRL__CLK_GATE_DLY_TIMER_MASK);
+	tmp |= UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK |
+		(1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT) |
+		(4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT);
+
+	if (sw_mode) {
+		tmp &= ~0x7ffff800;
+		tmp2 = UVD_CGC_CTRL2__DYN_OCLK_RAMP_EN_MASK |
+			UVD_CGC_CTRL2__DYN_RCLK_RAMP_EN_MASK |
+			(7 << UVD_CGC_CTRL2__GATER_DIV_ID__SHIFT);
+	} else {
+		tmp |= 0x7ffff800;
+		tmp2 = 0;
+	}
+
+	WREG32(mmUVD_CGC_CTRL, tmp);
+	WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2);
+}
+
+static bool uvd_v4_2_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK);
+}
+
+static int uvd_v4_2_wait_for_idle(void *handle)
+{
+	unsigned i;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (!(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK))
+			return 0;
+	}
+	return -ETIMEDOUT;
+}
+
+static int uvd_v4_2_soft_reset(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	uvd_v4_2_stop(adev);
+
+	WREG32_P(mmSRBM_SOFT_RESET, SRBM_SOFT_RESET__SOFT_RESET_UVD_MASK,
+			~SRBM_SOFT_RESET__SOFT_RESET_UVD_MASK);
+	mdelay(5);
+
+	return uvd_v4_2_start(adev);
+}
+
+static int uvd_v4_2_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	// TODO
+	return 0;
+}
+
+static int uvd_v4_2_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: UVD TRAP\n");
+	amdgpu_fence_process(&adev->uvd.inst->ring);
+	return 0;
+}
+
+static int uvd_v4_2_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	return 0;
+}
+
+static int uvd_v4_2_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	/* This doesn't actually powergate the UVD 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) {
+		uvd_v4_2_stop(adev);
+		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && !adev->pm.dpm_enabled) {
+			if (!(RREG32_SMC(ixCURRENT_PG_STATUS) &
+				CURRENT_PG_STATUS__UVD_PG_STATUS_MASK)) {
+				WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK   |
+							UVD_PGFSM_CONFIG__UVD_PGFSM_POWER_DOWN_MASK |
+							UVD_PGFSM_CONFIG__UVD_PGFSM_P1_SELECT_MASK));
+				mdelay(20);
+			}
+		}
+		return 0;
+	} else {
+		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && !adev->pm.dpm_enabled) {
+			if (RREG32_SMC(ixCURRENT_PG_STATUS) &
+				CURRENT_PG_STATUS__UVD_PG_STATUS_MASK) {
+				WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK   |
+						UVD_PGFSM_CONFIG__UVD_PGFSM_POWER_UP_MASK |
+						UVD_PGFSM_CONFIG__UVD_PGFSM_P1_SELECT_MASK));
+				mdelay(30);
+			}
+		}
+		return uvd_v4_2_start(adev);
+	}
+}
+
+static const struct amd_ip_funcs uvd_v4_2_ip_funcs = {
+	.name = "uvd_v4_2",
+	.early_init = uvd_v4_2_early_init,
+	.late_init = NULL,
+	.sw_init = uvd_v4_2_sw_init,
+	.sw_fini = uvd_v4_2_sw_fini,
+	.hw_init = uvd_v4_2_hw_init,
+	.hw_fini = uvd_v4_2_hw_fini,
+	.suspend = uvd_v4_2_suspend,
+	.resume = uvd_v4_2_resume,
+	.is_idle = uvd_v4_2_is_idle,
+	.wait_for_idle = uvd_v4_2_wait_for_idle,
+	.soft_reset = uvd_v4_2_soft_reset,
+	.set_clockgating_state = uvd_v4_2_set_clockgating_state,
+	.set_powergating_state = uvd_v4_2_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = {
+	.type = AMDGPU_RING_TYPE_UVD,
+	.align_mask = 0xf,
+	.support_64bit_ptrs = false,
+	.no_user_fence = true,
+	.get_rptr = uvd_v4_2_ring_get_rptr,
+	.get_wptr = uvd_v4_2_ring_get_wptr,
+	.set_wptr = uvd_v4_2_ring_set_wptr,
+	.parse_cs = amdgpu_uvd_ring_parse_cs,
+	.emit_frame_size =
+		14, /* uvd_v4_2_ring_emit_fence  x1 no user fence */
+	.emit_ib_size = 4, /* uvd_v4_2_ring_emit_ib */
+	.emit_ib = uvd_v4_2_ring_emit_ib,
+	.emit_fence = uvd_v4_2_ring_emit_fence,
+	.test_ring = uvd_v4_2_ring_test_ring,
+	.test_ib = amdgpu_uvd_ring_test_ib,
+	.insert_nop = uvd_v4_2_ring_insert_nop,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_uvd_ring_begin_use,
+	.end_use = amdgpu_uvd_ring_end_use,
+};
+
+static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->uvd.inst->ring.funcs = &uvd_v4_2_ring_funcs;
+}
+
+static const struct amdgpu_irq_src_funcs uvd_v4_2_irq_funcs = {
+	.set = uvd_v4_2_set_interrupt_state,
+	.process = uvd_v4_2_process_interrupt,
+};
+
+static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->uvd.inst->irq.num_types = 1;
+	adev->uvd.inst->irq.funcs = &uvd_v4_2_irq_funcs;
+}
+
+const struct amdgpu_ip_block_version uvd_v4_2_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_UVD,
+		.major = 4,
+		.minor = 2,
+		.rev = 0,
+		.funcs = &uvd_v4_2_ip_funcs,
+};