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, 483 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
new file mode 100644
index 000000000..4889865c7
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright 2014-2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/mm_types.h>
+
+#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
+#include "cik_regs.h"
+#include "cik_structs.h"
+#include "oss/oss_2_4_sh_mask.h"
+
+static inline struct cik_mqd *get_mqd(void *mqd)
+{
+	return (struct cik_mqd *)mqd;
+}
+
+static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
+{
+	return (struct cik_sdma_rlc_registers *)mqd;
+}
+
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct mqd_update_info *minfo)
+{
+	struct cik_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) ||
+	    !minfo->cu_mask.ptr)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
+static void set_priority(struct cik_mqd *m, struct queue_properties *q)
+{
+	m->cp_hqd_pipe_priority = pipe_priority_map[q->priority];
+	m->cp_hqd_queue_priority = q->priority;
+}
+
+static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
+					struct queue_properties *q)
+{
+	struct kfd_mem_obj *mqd_mem_obj;
+
+	if (kfd_gtt_sa_allocate(kfd, sizeof(struct cik_mqd),
+			&mqd_mem_obj))
+		return NULL;
+
+	return mqd_mem_obj;
+}
+
+static void init_mqd(struct mqd_manager *mm, void **mqd,
+		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+		struct queue_properties *q)
+{
+	uint64_t addr;
+	struct cik_mqd *m;
+
+	m = (struct cik_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memset(m, 0, ALIGN(sizeof(struct cik_mqd), 256));
+
+	m->header = 0xC0310800;
+	m->compute_pipelinestat_enable = 1;
+	m->compute_static_thread_mgmt_se0 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF;
+
+	/*
+	 * Make sure to use the last queue state saved on mqd when the cp
+	 * reassigns the queue, so when queue is switched on/off (e.g over
+	 * subscription or quantum timeout) the context will be consistent
+	 */
+	m->cp_hqd_persistent_state =
+				DEFAULT_CP_HQD_PERSISTENT_STATE | PRELOAD_REQ;
+
+	m->cp_mqd_control             = MQD_CONTROL_PRIV_STATE_EN;
+	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
+	m->cp_mqd_base_addr_hi        = upper_32_bits(addr);
+
+	m->cp_hqd_quantum = QUANTUM_EN | QUANTUM_SCALE_1MS |
+				QUANTUM_DURATION(10);
+
+	/*
+	 * Pipe Priority
+	 * Identifies the pipe relative priority when this queue is connected
+	 * to the pipeline. The pipe priority is against the GFX pipe and HP3D.
+	 * In KFD we are using a fixed pipe priority set to CS_MEDIUM.
+	 * 0 = CS_LOW (typically below GFX)
+	 * 1 = CS_MEDIUM (typically between HP3D and GFX
+	 * 2 = CS_HIGH (typically above HP3D)
+	 */
+	set_priority(m, q);
+
+	if (q->format == KFD_QUEUE_FORMAT_AQL)
+		m->cp_hqd_iq_rptr = AQL_ENABLE;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+	mm->update_mqd(mm, m, q, NULL);
+}
+
+static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *q)
+{
+	struct cik_sdma_rlc_registers *m;
+
+	m = (struct cik_sdma_rlc_registers *) mqd_mem_obj->cpu_ptr;
+
+	memset(m, 0, sizeof(struct cik_sdma_rlc_registers));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = mqd_mem_obj->gpu_addr;
+
+	mm->update_mqd(mm, m, q, NULL);
+}
+
+static int load_mqd(struct mqd_manager *mm, void *mqd, uint32_t pipe_id,
+		    uint32_t queue_id, struct queue_properties *p,
+		    struct mm_struct *mms)
+{
+	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
+	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
+	uint32_t wptr_mask = (uint32_t)((p->queue_size / 4) - 1);
+
+	return mm->dev->kfd2kgd->hqd_load(mm->dev->adev, mqd, pipe_id, queue_id,
+					  (uint32_t __user *)p->write_ptr,
+					  wptr_shift, wptr_mask, mms);
+}
+
+static void __update_mqd(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q, struct mqd_update_info *minfo,
+			unsigned int atc_bit)
+{
+	struct cik_mqd *m;
+
+	m = get_mqd(mqd);
+	m->cp_hqd_pq_control = DEFAULT_RPTR_BLOCK_SIZE |
+				DEFAULT_MIN_AVAIL_SIZE;
+	m->cp_hqd_ib_control = DEFAULT_MIN_IB_AVAIL_SIZE;
+	if (atc_bit) {
+		m->cp_hqd_pq_control |= PQ_ATC_EN;
+		m->cp_hqd_ib_control |= IB_ATC_EN;
+	}
+
+	/*
+	 * Calculating queue size which is log base 2 of actual queue size -1
+	 * dwords and another -1 for ffs
+	 */
+	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
+	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
+	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
+	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_rptr_report_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(q->doorbell_off);
+
+	m->cp_hqd_vmid = q->vmid;
+
+	if (q->format == KFD_QUEUE_FORMAT_AQL)
+		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
+
+	update_cu_mask(mm, mqd, minfo);
+	set_priority(m, q);
+
+	q->is_active = QUEUE_IS_ACTIVE(*q);
+}
+
+static void update_mqd(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q,
+			struct mqd_update_info *minfo)
+{
+	__update_mqd(mm, mqd, q, minfo, 1);
+}
+
+static uint32_t read_doorbell_id(void *mqd)
+{
+	struct cik_mqd *m = (struct cik_mqd *)mqd;
+
+	return m->queue_doorbell_id0;
+}
+
+static void update_mqd_hawaii(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q,
+			struct mqd_update_info *minfo)
+{
+	__update_mqd(mm, mqd, q, minfo, 0);
+}
+
+static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q,
+			struct mqd_update_info *minfo)
+{
+	struct cik_sdma_rlc_registers *m;
+
+	m = get_sdma_mqd(mqd);
+	m->sdma_rlc_rb_cntl = order_base_2(q->queue_size / 4)
+			<< SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+			q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
+			1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
+			6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
+
+	m->sdma_rlc_rb_base = lower_32_bits(q->queue_address >> 8);
+	m->sdma_rlc_rb_base_hi = upper_32_bits(q->queue_address >> 8);
+	m->sdma_rlc_rb_rptr_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->sdma_rlc_rb_rptr_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->sdma_rlc_doorbell =
+		q->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+	m->sdma_rlc_virtual_addr = q->sdma_vm_addr;
+
+	m->sdma_engine_id = q->sdma_engine_id;
+	m->sdma_queue_id = q->sdma_queue_id;
+
+	q->is_active = QUEUE_IS_ACTIVE(*q);
+}
+
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct cik_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct cik_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct cik_mqd *m;
+
+	m = (struct cik_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(qp->doorbell_off);
+
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
+static void checkpoint_mqd_sdma(struct mqd_manager *mm,
+				void *mqd,
+				void *mqd_dst,
+				void *ctl_stack_dst)
+{
+	struct cik_sdma_rlc_registers *m;
+
+	m = get_sdma_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct cik_sdma_rlc_registers));
+}
+
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+				struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+				struct queue_properties *qp,
+				const void *mqd_src,
+				const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct cik_sdma_rlc_registers *m;
+
+	m = (struct cik_sdma_rlc_registers *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	m->sdma_rlc_doorbell =
+		qp->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	qp->is_active = 0;
+}
+
+/*
+ * HIQ MQD Implementation, concrete implementation for HIQ MQD implementation.
+ * The HIQ queue in Kaveri is using the same MQD structure as all the user mode
+ * queues but with different initial values.
+ */
+
+static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
+		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+		struct queue_properties *q)
+{
+	init_mqd(mm, mqd, mqd_mem_obj, gart_addr, q);
+}
+
+static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q,
+			struct mqd_update_info *minfo)
+{
+	struct cik_mqd *m;
+
+	m = get_mqd(mqd);
+	m->cp_hqd_pq_control = DEFAULT_RPTR_BLOCK_SIZE |
+				DEFAULT_MIN_AVAIL_SIZE |
+				PRIV_STATE |
+				KMD_QUEUE;
+
+	/*
+	 * Calculating queue size which is log base 2 of actual queue
+	 * size -1 dwords
+	 */
+	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
+	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
+	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
+	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_rptr_report_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(q->doorbell_off);
+
+	m->cp_hqd_vmid = q->vmid;
+
+	q->is_active = QUEUE_IS_ACTIVE(*q);
+
+	set_priority(m, q);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+static int debugfs_show_mqd(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct cik_mqd), false);
+	return 0;
+}
+
+static int debugfs_show_mqd_sdma(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct cik_sdma_rlc_registers), false);
+	return 0;
+}
+
+#endif
+
+
+struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
+		struct kfd_dev *dev)
+{
+	struct mqd_manager *mqd;
+
+	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
+		return NULL;
+
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
+	if (!mqd)
+		return NULL;
+
+	mqd->dev = dev;
+
+	switch (type) {
+	case KFD_MQD_TYPE_CP:
+		mqd->allocate_mqd = allocate_mqd;
+		mqd->init_mqd = init_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
+		mqd->load_mqd = load_mqd;
+		mqd->update_mqd = update_mqd;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
+		mqd->mqd_size = sizeof(struct cik_mqd);
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
+		break;
+	case KFD_MQD_TYPE_HIQ:
+		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->init_mqd = init_mqd_hiq;
+		mqd->free_mqd = free_mqd_hiq_sdma;
+		mqd->load_mqd = load_mqd;
+		mqd->update_mqd = update_mqd_hiq;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
+		mqd->mqd_size = sizeof(struct cik_mqd);
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
+		mqd->read_doorbell_id = read_doorbell_id;
+		break;
+	case KFD_MQD_TYPE_DIQ:
+		mqd->allocate_mqd = allocate_mqd;
+		mqd->init_mqd = init_mqd_hiq;
+		mqd->free_mqd = kfd_free_mqd_cp;
+		mqd->load_mqd = load_mqd;
+		mqd->update_mqd = update_mqd_hiq;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
+		mqd->mqd_size = sizeof(struct cik_mqd);
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
+		break;
+	case KFD_MQD_TYPE_SDMA:
+		mqd->allocate_mqd = allocate_sdma_mqd;
+		mqd->init_mqd = init_mqd_sdma;
+		mqd->free_mqd = free_mqd_hiq_sdma;
+		mqd->load_mqd = kfd_load_mqd_sdma;
+		mqd->update_mqd = update_mqd_sdma;
+		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
+		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+		mqd->restore_mqd = restore_mqd_sdma;
+		mqd->mqd_size = sizeof(struct cik_sdma_rlc_registers);
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
+#endif
+		break;
+	default:
+		kfree(mqd);
+		return NULL;
+	}
+
+	return mqd;
+}
+
+struct mqd_manager *mqd_manager_init_cik_hawaii(enum KFD_MQD_TYPE type,
+			struct kfd_dev *dev)
+{
+	struct mqd_manager *mqd;
+
+	mqd = mqd_manager_init_cik(type, dev);
+	if (!mqd)
+		return NULL;
+	if (type == KFD_MQD_TYPE_CP)
+		mqd->update_mqd = update_mqd_hawaii;
+	return mqd;
+}