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, 308 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h
new file mode 100644
index 000000000..7199b6b0b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h
@@ -0,0 +1,308 @@
+/*
+ * Copyright 2018 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.
+ *
+ */
+
+/*
+ * GPU doorbell structures, functions & helpers
+ */
+struct amdgpu_doorbell {
+	/* doorbell mmio */
+	resource_size_t		base;
+	resource_size_t		size;
+	u32 __iomem		*ptr;
+	u32			num_doorbells;	/* Number of doorbells actually reserved for amdgpu. */
+};
+
+/* Reserved doorbells for amdgpu (including multimedia).
+ * KFD can use all the rest in the 2M doorbell bar.
+ * For asic before vega10, doorbell is 32-bit, so the
+ * index/offset is in dword. For vega10 and after, doorbell
+ * can be 64-bit, so the index defined is in qword.
+ */
+struct amdgpu_doorbell_index {
+	uint32_t kiq;
+	uint32_t mec_ring0;
+	uint32_t mec_ring1;
+	uint32_t mec_ring2;
+	uint32_t mec_ring3;
+	uint32_t mec_ring4;
+	uint32_t mec_ring5;
+	uint32_t mec_ring6;
+	uint32_t mec_ring7;
+	uint32_t userqueue_start;
+	uint32_t userqueue_end;
+	uint32_t gfx_ring0;
+	uint32_t gfx_ring1;
+	uint32_t gfx_userqueue_start;
+	uint32_t gfx_userqueue_end;
+	uint32_t sdma_engine[8];
+	uint32_t mes_ring0;
+	uint32_t mes_ring1;
+	uint32_t ih;
+	union {
+		struct {
+			uint32_t vcn_ring0_1;
+			uint32_t vcn_ring2_3;
+			uint32_t vcn_ring4_5;
+			uint32_t vcn_ring6_7;
+		} vcn;
+		struct {
+			uint32_t uvd_ring0_1;
+			uint32_t uvd_ring2_3;
+			uint32_t uvd_ring4_5;
+			uint32_t uvd_ring6_7;
+			uint32_t vce_ring0_1;
+			uint32_t vce_ring2_3;
+			uint32_t vce_ring4_5;
+			uint32_t vce_ring6_7;
+		} uvd_vce;
+	};
+	uint32_t first_non_cp;
+	uint32_t last_non_cp;
+	uint32_t max_assignment;
+	/* Per engine SDMA doorbell size in dword */
+	uint32_t sdma_doorbell_range;
+};
+
+typedef enum _AMDGPU_DOORBELL_ASSIGNMENT
+{
+	AMDGPU_DOORBELL_KIQ                     = 0x000,
+	AMDGPU_DOORBELL_HIQ                     = 0x001,
+	AMDGPU_DOORBELL_DIQ                     = 0x002,
+	AMDGPU_DOORBELL_MEC_RING0               = 0x010,
+	AMDGPU_DOORBELL_MEC_RING1               = 0x011,
+	AMDGPU_DOORBELL_MEC_RING2               = 0x012,
+	AMDGPU_DOORBELL_MEC_RING3               = 0x013,
+	AMDGPU_DOORBELL_MEC_RING4               = 0x014,
+	AMDGPU_DOORBELL_MEC_RING5               = 0x015,
+	AMDGPU_DOORBELL_MEC_RING6               = 0x016,
+	AMDGPU_DOORBELL_MEC_RING7               = 0x017,
+	AMDGPU_DOORBELL_GFX_RING0               = 0x020,
+	AMDGPU_DOORBELL_sDMA_ENGINE0            = 0x1E0,
+	AMDGPU_DOORBELL_sDMA_ENGINE1            = 0x1E1,
+	AMDGPU_DOORBELL_IH                      = 0x1E8,
+	AMDGPU_DOORBELL_MAX_ASSIGNMENT          = 0x3FF,
+	AMDGPU_DOORBELL_INVALID                 = 0xFFFF
+} AMDGPU_DOORBELL_ASSIGNMENT;
+
+typedef enum _AMDGPU_VEGA20_DOORBELL_ASSIGNMENT
+{
+	/* Compute + GFX: 0~255 */
+	AMDGPU_VEGA20_DOORBELL_KIQ                     = 0x000,
+	AMDGPU_VEGA20_DOORBELL_HIQ                     = 0x001,
+	AMDGPU_VEGA20_DOORBELL_DIQ                     = 0x002,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING0               = 0x003,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING1               = 0x004,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING2               = 0x005,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING3               = 0x006,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING4               = 0x007,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING5               = 0x008,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING6               = 0x009,
+	AMDGPU_VEGA20_DOORBELL_MEC_RING7               = 0x00A,
+	AMDGPU_VEGA20_DOORBELL_USERQUEUE_START	       = 0x00B,
+	AMDGPU_VEGA20_DOORBELL_USERQUEUE_END	       = 0x08A,
+	AMDGPU_VEGA20_DOORBELL_GFX_RING0               = 0x08B,
+	/* SDMA:256~335*/
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE0            = 0x100,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE1            = 0x10A,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE2            = 0x114,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE3            = 0x11E,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE4            = 0x128,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE5            = 0x132,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE6            = 0x13C,
+	AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE7            = 0x146,
+	/* IH: 376~391 */
+	AMDGPU_VEGA20_DOORBELL_IH                      = 0x178,
+	/* MMSCH: 392~407
+	 * overlap the doorbell assignment with VCN as they are  mutually exclusive
+	 * VCN engine's doorbell is 32 bit and two VCN ring share one QWORD
+	 */
+	AMDGPU_VEGA20_DOORBELL64_VCN0_1                  = 0x188, /* VNC0 */
+	AMDGPU_VEGA20_DOORBELL64_VCN2_3                  = 0x189,
+	AMDGPU_VEGA20_DOORBELL64_VCN4_5                  = 0x18A,
+	AMDGPU_VEGA20_DOORBELL64_VCN6_7                  = 0x18B,
+
+	AMDGPU_VEGA20_DOORBELL64_VCN8_9                  = 0x18C, /* VNC1 */
+	AMDGPU_VEGA20_DOORBELL64_VCNa_b                  = 0x18D,
+	AMDGPU_VEGA20_DOORBELL64_VCNc_d                  = 0x18E,
+	AMDGPU_VEGA20_DOORBELL64_VCNe_f                  = 0x18F,
+
+	AMDGPU_VEGA20_DOORBELL64_UVD_RING0_1             = 0x188,
+	AMDGPU_VEGA20_DOORBELL64_UVD_RING2_3             = 0x189,
+	AMDGPU_VEGA20_DOORBELL64_UVD_RING4_5             = 0x18A,
+	AMDGPU_VEGA20_DOORBELL64_UVD_RING6_7             = 0x18B,
+
+	AMDGPU_VEGA20_DOORBELL64_VCE_RING0_1             = 0x18C,
+	AMDGPU_VEGA20_DOORBELL64_VCE_RING2_3             = 0x18D,
+	AMDGPU_VEGA20_DOORBELL64_VCE_RING4_5             = 0x18E,
+	AMDGPU_VEGA20_DOORBELL64_VCE_RING6_7             = 0x18F,
+
+	AMDGPU_VEGA20_DOORBELL64_FIRST_NON_CP            = AMDGPU_VEGA20_DOORBELL_sDMA_ENGINE0,
+	AMDGPU_VEGA20_DOORBELL64_LAST_NON_CP             = AMDGPU_VEGA20_DOORBELL64_VCE_RING6_7,
+
+	AMDGPU_VEGA20_DOORBELL_MAX_ASSIGNMENT            = 0x18F,
+	AMDGPU_VEGA20_DOORBELL_INVALID                   = 0xFFFF
+} AMDGPU_VEGA20_DOORBELL_ASSIGNMENT;
+
+typedef enum _AMDGPU_NAVI10_DOORBELL_ASSIGNMENT
+{
+	/* Compute + GFX: 0~255 */
+	AMDGPU_NAVI10_DOORBELL_KIQ			= 0x000,
+	AMDGPU_NAVI10_DOORBELL_HIQ			= 0x001,
+	AMDGPU_NAVI10_DOORBELL_DIQ			= 0x002,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING0		= 0x003,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING1		= 0x004,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING2		= 0x005,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING3		= 0x006,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING4		= 0x007,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING5		= 0x008,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING6		= 0x009,
+	AMDGPU_NAVI10_DOORBELL_MEC_RING7		= 0x00A,
+	AMDGPU_NAVI10_DOORBELL_MES_RING0	        = 0x00B,
+	AMDGPU_NAVI10_DOORBELL_MES_RING1		= 0x00C,
+	AMDGPU_NAVI10_DOORBELL_USERQUEUE_START		= 0x00D,
+	AMDGPU_NAVI10_DOORBELL_USERQUEUE_END		= 0x08A,
+	AMDGPU_NAVI10_DOORBELL_GFX_RING0		= 0x08B,
+	AMDGPU_NAVI10_DOORBELL_GFX_RING1		= 0x08C,
+	AMDGPU_NAVI10_DOORBELL_GFX_USERQUEUE_START	= 0x08D,
+	AMDGPU_NAVI10_DOORBELL_GFX_USERQUEUE_END	= 0x0FF,
+
+	/* SDMA:256~335*/
+	AMDGPU_NAVI10_DOORBELL_sDMA_ENGINE0		= 0x100,
+	AMDGPU_NAVI10_DOORBELL_sDMA_ENGINE1		= 0x10A,
+	AMDGPU_NAVI10_DOORBELL_sDMA_ENGINE2		= 0x114,
+	AMDGPU_NAVI10_DOORBELL_sDMA_ENGINE3		= 0x11E,
+	/* IH: 376~391 */
+	AMDGPU_NAVI10_DOORBELL_IH			= 0x178,
+	/* MMSCH: 392~407
+	 * overlap the doorbell assignment with VCN as they are  mutually exclusive
+	 * VCE engine's doorbell is 32 bit and two VCE ring share one QWORD
+	 */
+	AMDGPU_NAVI10_DOORBELL64_VCN0_1			= 0x188, /* lower 32 bits for VNC0 and upper 32 bits for VNC1 */
+	AMDGPU_NAVI10_DOORBELL64_VCN2_3			= 0x189,
+	AMDGPU_NAVI10_DOORBELL64_VCN4_5			= 0x18A,
+	AMDGPU_NAVI10_DOORBELL64_VCN6_7			= 0x18B,
+
+	AMDGPU_NAVI10_DOORBELL64_VCN8_9			= 0x18C,
+	AMDGPU_NAVI10_DOORBELL64_VCNa_b			= 0x18D,
+	AMDGPU_NAVI10_DOORBELL64_VCNc_d			= 0x18E,
+	AMDGPU_NAVI10_DOORBELL64_VCNe_f			= 0x18F,
+
+	AMDGPU_NAVI10_DOORBELL64_FIRST_NON_CP		= AMDGPU_NAVI10_DOORBELL_sDMA_ENGINE0,
+	AMDGPU_NAVI10_DOORBELL64_LAST_NON_CP		= AMDGPU_NAVI10_DOORBELL64_VCNe_f,
+
+	AMDGPU_NAVI10_DOORBELL_MAX_ASSIGNMENT		= 0x18F,
+	AMDGPU_NAVI10_DOORBELL_INVALID			= 0xFFFF
+} AMDGPU_NAVI10_DOORBELL_ASSIGNMENT;
+
+/*
+ * 64bit doorbell, offset are in QWORD, occupy 2KB doorbell space
+ */
+typedef enum _AMDGPU_DOORBELL64_ASSIGNMENT
+{
+	/*
+	 * All compute related doorbells: kiq, hiq, diq, traditional compute queue, user queue, should locate in
+	 * a continues range so that programming CP_MEC_DOORBELL_RANGE_LOWER/UPPER can cover this range.
+	 *  Compute related doorbells are allocated from 0x00 to 0x8a
+	 */
+
+
+	/* kernel scheduling */
+	AMDGPU_DOORBELL64_KIQ                     = 0x00,
+
+	/* HSA interface queue and debug queue */
+	AMDGPU_DOORBELL64_HIQ                     = 0x01,
+	AMDGPU_DOORBELL64_DIQ                     = 0x02,
+
+	/* Compute engines */
+	AMDGPU_DOORBELL64_MEC_RING0               = 0x03,
+	AMDGPU_DOORBELL64_MEC_RING1               = 0x04,
+	AMDGPU_DOORBELL64_MEC_RING2               = 0x05,
+	AMDGPU_DOORBELL64_MEC_RING3               = 0x06,
+	AMDGPU_DOORBELL64_MEC_RING4               = 0x07,
+	AMDGPU_DOORBELL64_MEC_RING5               = 0x08,
+	AMDGPU_DOORBELL64_MEC_RING6               = 0x09,
+	AMDGPU_DOORBELL64_MEC_RING7               = 0x0a,
+
+	/* User queue doorbell range (128 doorbells) */
+	AMDGPU_DOORBELL64_USERQUEUE_START         = 0x0b,
+	AMDGPU_DOORBELL64_USERQUEUE_END           = 0x8a,
+
+	/* Graphics engine */
+	AMDGPU_DOORBELL64_GFX_RING0               = 0x8b,
+
+	/*
+	 * Other graphics doorbells can be allocated here: from 0x8c to 0xdf
+	 * Graphics voltage island aperture 1
+	 * default non-graphics QWORD index is 0xe0 - 0xFF inclusive
+	 */
+
+	/* For vega10 sriov, the sdma doorbell must be fixed as follow
+	 * to keep the same setting with host driver, or it will
+	 * happen conflicts
+	 */
+	AMDGPU_DOORBELL64_sDMA_ENGINE0            = 0xF0,
+	AMDGPU_DOORBELL64_sDMA_HI_PRI_ENGINE0     = 0xF1,
+	AMDGPU_DOORBELL64_sDMA_ENGINE1            = 0xF2,
+	AMDGPU_DOORBELL64_sDMA_HI_PRI_ENGINE1     = 0xF3,
+
+	/* Interrupt handler */
+	AMDGPU_DOORBELL64_IH                      = 0xF4,  /* For legacy interrupt ring buffer */
+	AMDGPU_DOORBELL64_IH_RING1                = 0xF5,  /* For page migration request log */
+	AMDGPU_DOORBELL64_IH_RING2                = 0xF6,  /* For page migration translation/invalidation log */
+
+	/* VCN engine use 32 bits doorbell  */
+	AMDGPU_DOORBELL64_VCN0_1                  = 0xF8, /* lower 32 bits for VNC0 and upper 32 bits for VNC1 */
+	AMDGPU_DOORBELL64_VCN2_3                  = 0xF9,
+	AMDGPU_DOORBELL64_VCN4_5                  = 0xFA,
+	AMDGPU_DOORBELL64_VCN6_7                  = 0xFB,
+
+	/* overlap the doorbell assignment with VCN as they are  mutually exclusive
+	 * VCE engine's doorbell is 32 bit and two VCE ring share one QWORD
+	 */
+	AMDGPU_DOORBELL64_UVD_RING0_1             = 0xF8,
+	AMDGPU_DOORBELL64_UVD_RING2_3             = 0xF9,
+	AMDGPU_DOORBELL64_UVD_RING4_5             = 0xFA,
+	AMDGPU_DOORBELL64_UVD_RING6_7             = 0xFB,
+
+	AMDGPU_DOORBELL64_VCE_RING0_1             = 0xFC,
+	AMDGPU_DOORBELL64_VCE_RING2_3             = 0xFD,
+	AMDGPU_DOORBELL64_VCE_RING4_5             = 0xFE,
+	AMDGPU_DOORBELL64_VCE_RING6_7             = 0xFF,
+
+	AMDGPU_DOORBELL64_FIRST_NON_CP            = AMDGPU_DOORBELL64_sDMA_ENGINE0,
+	AMDGPU_DOORBELL64_LAST_NON_CP             = AMDGPU_DOORBELL64_VCE_RING6_7,
+
+	AMDGPU_DOORBELL64_MAX_ASSIGNMENT          = 0xFF,
+	AMDGPU_DOORBELL64_INVALID                 = 0xFFFF
+} AMDGPU_DOORBELL64_ASSIGNMENT;
+
+u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index);
+void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v);
+u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index);
+void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v);
+
+#define RDOORBELL32(index) amdgpu_mm_rdoorbell(adev, (index))
+#define WDOORBELL32(index, v) amdgpu_mm_wdoorbell(adev, (index), (v))
+#define RDOORBELL64(index) amdgpu_mm_rdoorbell64(adev, (index))
+#define WDOORBELL64(index, v) amdgpu_mm_wdoorbell64(adev, (index), (v))
+