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, 576 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
new file mode 100644
index 000000000..aa761ff3a
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -0,0 +1,576 @@
+/*
+ * Copyright 2019 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 "amdgpu.h"
+#include "amdgpu_atombios.h"
+#include "nbio_v2_3.h"
+
+#include "nbio/nbio_2_3_default.h"
+#include "nbio/nbio_2_3_offset.h"
+#include "nbio/nbio_2_3_sh_mask.h"
+#include <uapi/linux/kfd_ioctl.h>
+#include <linux/pci.h>
+
+#define smnPCIE_CONFIG_CNTL	0x11180044
+#define smnCPM_CONTROL		0x11180460
+#define smnPCIE_CNTL2		0x11180070
+#define smnPCIE_LC_CNTL		0x11140280
+#define smnPCIE_LC_CNTL3	0x111402d4
+#define smnPCIE_LC_CNTL6	0x111402ec
+#define smnPCIE_LC_CNTL7	0x111402f0
+#define smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2	0x1014008c
+#define smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL	0x10123538
+#define smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP	0x10140324
+#define smnPSWUSP0_PCIE_LC_CNTL2		0x111402c4
+#define smnNBIF_MGCG_CTRL_LCLK			0x1013a21c
+
+#define mmBIF_SDMA2_DOORBELL_RANGE		0x01d6
+#define mmBIF_SDMA2_DOORBELL_RANGE_BASE_IDX	2
+#define mmBIF_SDMA3_DOORBELL_RANGE		0x01d7
+#define mmBIF_SDMA3_DOORBELL_RANGE_BASE_IDX	2
+
+#define mmBIF_MMSCH1_DOORBELL_RANGE		0x01d8
+#define mmBIF_MMSCH1_DOORBELL_RANGE_BASE_IDX	2
+
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG0_MASK	0x00001000L /* Don't use.  Firmware uses this bit internally */
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK	0x00002000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK	0x00004000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK	0x00008000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK	0x00010000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK	0x00020000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG6_MASK	0x00040000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG7_MASK	0x00080000L
+#define GPU_HDP_FLUSH_DONE__RSVD_ENG8_MASK	0x00100000L
+
+static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev)
+{
+	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
+		adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL);
+	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_REG_FLUSH_CNTL,
+		adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL);
+}
+
+static u32 nbio_v2_3_get_rev_id(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	/*
+	 * guest vm gets 0xffffffff when reading RCC_DEV0_EPF0_STRAP0,
+	 * therefore we force rev_id to 0 (which is the default value)
+	 */
+	if (amdgpu_sriov_vf(adev)) {
+		return 0;
+	}
+
+	tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
+	tmp &= RCC_DEV0_EPF0_STRAP0__STRAP_ATI_REV_ID_DEV0_F0_MASK;
+	tmp >>= RCC_DEV0_EPF0_STRAP0__STRAP_ATI_REV_ID_DEV0_F0__SHIFT;
+
+	return tmp;
+}
+
+static void nbio_v2_3_mc_access_enable(struct amdgpu_device *adev, bool enable)
+{
+	if (enable)
+		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN,
+			     BIF_FB_EN__FB_READ_EN_MASK |
+			     BIF_FB_EN__FB_WRITE_EN_MASK);
+	else
+		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN, 0);
+}
+
+static u32 nbio_v2_3_get_memsize(struct amdgpu_device *adev)
+{
+	return RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_RCC_CONFIG_MEMSIZE);
+}
+
+static void nbio_v2_3_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
+					  bool use_doorbell, int doorbell_index,
+					  int doorbell_size)
+{
+	u32 reg = instance == 0 ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA0_DOORBELL_RANGE) :
+			instance == 1 ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE) :
+			instance == 2 ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA2_DOORBELL_RANGE) :
+			SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA3_DOORBELL_RANGE);
+
+	u32 doorbell_range = RREG32(reg);
+
+	if (use_doorbell) {
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_SDMA0_DOORBELL_RANGE, OFFSET,
+					       doorbell_index);
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_SDMA0_DOORBELL_RANGE, SIZE,
+					       doorbell_size);
+	} else
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_SDMA0_DOORBELL_RANGE, SIZE,
+					       0);
+
+	WREG32(reg, doorbell_range);
+}
+
+static void nbio_v2_3_vcn_doorbell_range(struct amdgpu_device *adev, bool use_doorbell,
+					 int doorbell_index, int instance)
+{
+	u32 reg = instance ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_MMSCH1_DOORBELL_RANGE) :
+		SOC15_REG_OFFSET(NBIO, 0, mmBIF_MMSCH0_DOORBELL_RANGE);
+
+	u32 doorbell_range = RREG32(reg);
+
+	if (use_doorbell) {
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_MMSCH0_DOORBELL_RANGE, OFFSET,
+					       doorbell_index);
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_MMSCH0_DOORBELL_RANGE, SIZE, 8);
+	} else
+		doorbell_range = REG_SET_FIELD(doorbell_range,
+					       BIF_MMSCH0_DOORBELL_RANGE, SIZE, 0);
+
+	WREG32(reg, doorbell_range);
+}
+
+static void nbio_v2_3_enable_doorbell_aperture(struct amdgpu_device *adev,
+					       bool enable)
+{
+	WREG32_FIELD15(NBIO, 0, RCC_DEV0_EPF0_RCC_DOORBELL_APER_EN, BIF_DOORBELL_APER_EN,
+		       enable ? 1 : 0);
+}
+
+static void nbio_v2_3_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
+							bool enable)
+{
+	u32 tmp = 0;
+
+	if (enable) {
+		tmp = REG_SET_FIELD(tmp, BIF_BX_PF_DOORBELL_SELFRING_GPA_APER_CNTL,
+				    DOORBELL_SELFRING_GPA_APER_EN, 1) |
+		      REG_SET_FIELD(tmp, BIF_BX_PF_DOORBELL_SELFRING_GPA_APER_CNTL,
+				    DOORBELL_SELFRING_GPA_APER_MODE, 1) |
+		      REG_SET_FIELD(tmp, BIF_BX_PF_DOORBELL_SELFRING_GPA_APER_CNTL,
+				    DOORBELL_SELFRING_GPA_APER_SIZE, 0);
+
+		WREG32_SOC15(NBIO, 0, mmBIF_BX_PF_DOORBELL_SELFRING_GPA_APER_BASE_LOW,
+			     lower_32_bits(adev->doorbell.base));
+		WREG32_SOC15(NBIO, 0, mmBIF_BX_PF_DOORBELL_SELFRING_GPA_APER_BASE_HIGH,
+			     upper_32_bits(adev->doorbell.base));
+	}
+
+	WREG32_SOC15(NBIO, 0, mmBIF_BX_PF_DOORBELL_SELFRING_GPA_APER_CNTL,
+		     tmp);
+}
+
+
+static void nbio_v2_3_ih_doorbell_range(struct amdgpu_device *adev,
+					bool use_doorbell, int doorbell_index)
+{
+	u32 ih_doorbell_range = RREG32_SOC15(NBIO, 0, mmBIF_IH_DOORBELL_RANGE);
+
+	if (use_doorbell) {
+		ih_doorbell_range = REG_SET_FIELD(ih_doorbell_range,
+						  BIF_IH_DOORBELL_RANGE, OFFSET,
+						  doorbell_index);
+		ih_doorbell_range = REG_SET_FIELD(ih_doorbell_range,
+						  BIF_IH_DOORBELL_RANGE, SIZE,
+						  2);
+	} else
+		ih_doorbell_range = REG_SET_FIELD(ih_doorbell_range,
+						  BIF_IH_DOORBELL_RANGE, SIZE,
+						  0);
+
+	WREG32_SOC15(NBIO, 0, mmBIF_IH_DOORBELL_RANGE, ih_doorbell_range);
+}
+
+static void nbio_v2_3_ih_control(struct amdgpu_device *adev)
+{
+	u32 interrupt_cntl;
+
+	/* setup interrupt control */
+	WREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL2, adev->dummy_page_addr >> 8);
+
+	interrupt_cntl = RREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL);
+	/*
+	 * INTERRUPT_CNTL__IH_DUMMY_RD_OVERRIDE_MASK=0 - dummy read disabled with msi, enabled without msi
+	 * INTERRUPT_CNTL__IH_DUMMY_RD_OVERRIDE_MASK=1 - dummy read controlled by IH_DUMMY_RD_EN
+	 */
+	interrupt_cntl = REG_SET_FIELD(interrupt_cntl, INTERRUPT_CNTL,
+				       IH_DUMMY_RD_OVERRIDE, 0);
+
+	/* INTERRUPT_CNTL__IH_REQ_NONSNOOP_EN_MASK=1 if ring is in non-cacheable memory, e.g., vram */
+	interrupt_cntl = REG_SET_FIELD(interrupt_cntl, INTERRUPT_CNTL,
+				       IH_REQ_NONSNOOP_EN, 0);
+
+	WREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL, interrupt_cntl);
+}
+
+static void nbio_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						       bool enable)
+{
+	uint32_t def, data;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG))
+		return;
+
+	def = data = RREG32_PCIE(smnCPM_CONTROL);
+	if (enable) {
+		data |= (CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			 CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			 CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			 CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			 CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			 CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	} else {
+		data &= ~(CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			  CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			  CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			  CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			  CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			  CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	}
+
+	if (def != data)
+		WREG32_PCIE(smnCPM_CONTROL, data);
+}
+
+static void nbio_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t def, data;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS))
+		return;
+
+	def = data = RREG32_PCIE(smnPCIE_CNTL2);
+	if (enable) {
+		data |= (PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
+			 PCIE_CNTL2__MST_MEM_LS_EN_MASK |
+			 PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
+	} else {
+		data &= ~(PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
+			  PCIE_CNTL2__MST_MEM_LS_EN_MASK |
+			  PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
+	}
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_CNTL2, data);
+}
+
+static void nbio_v2_3_get_clockgating_state(struct amdgpu_device *adev,
+					    u64 *flags)
+{
+	int data;
+
+	/* AMD_CG_SUPPORT_BIF_MGCG */
+	data = RREG32_PCIE(smnCPM_CONTROL);
+	if (data & CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_MGCG;
+
+	/* AMD_CG_SUPPORT_BIF_LS */
+	data = RREG32_PCIE(smnPCIE_CNTL2);
+	if (data & PCIE_CNTL2__SLV_MEM_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_LS;
+}
+
+static u32 nbio_v2_3_get_hdp_flush_req_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_GPU_HDP_FLUSH_REQ);
+}
+
+static u32 nbio_v2_3_get_hdp_flush_done_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_GPU_HDP_FLUSH_DONE);
+}
+
+static u32 nbio_v2_3_get_pcie_index_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX2);
+}
+
+static u32 nbio_v2_3_get_pcie_data_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2);
+}
+
+const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg = {
+	.ref_and_mask_cp0 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP0_MASK,
+	.ref_and_mask_cp1 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP1_MASK,
+	.ref_and_mask_cp2 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP2_MASK,
+	.ref_and_mask_cp3 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP3_MASK,
+	.ref_and_mask_cp4 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP4_MASK,
+	.ref_and_mask_cp5 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP5_MASK,
+	.ref_and_mask_cp6 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP6_MASK,
+	.ref_and_mask_cp7 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP7_MASK,
+	.ref_and_mask_cp8 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP8_MASK,
+	.ref_and_mask_cp9 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP9_MASK,
+	.ref_and_mask_sdma0 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__SDMA0_MASK,
+	.ref_and_mask_sdma1 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__SDMA1_MASK,
+};
+
+static void nbio_v2_3_init_registers(struct amdgpu_device *adev)
+{
+	uint32_t def, data;
+
+	def = data = RREG32_PCIE(smnPCIE_CONFIG_CNTL);
+	data = REG_SET_FIELD(data, PCIE_CONFIG_CNTL, CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
+	data = REG_SET_FIELD(data, PCIE_CONFIG_CNTL, CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_CONFIG_CNTL, data);
+
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
+}
+
+#define NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT		0x00000000 // off by default, no gains over L1
+#define NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT		0x00000009 // 1=1us, 9=1ms
+#define NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT	0x0000000E // 4ms
+
+static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
+				  bool enable)
+{
+	uint32_t def, data;
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
+
+	if (enable) {
+		/* Disable ASPM L0s/L1 first */
+		data &= ~(PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK | PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK);
+
+		data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT;
+
+		if (pci_is_thunderbolt_attached(adev->pdev))
+			data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT  << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
+		else
+			data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
+
+		data &= ~PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK;
+	} else {
+		/* Disbale ASPM L1 */
+		data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK;
+		/* Disable ASPM TxL0s */
+		data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
+		/* Disable ACPI L1 */
+		data |= PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK;
+	}
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL, data);
+}
+
+#ifdef CONFIG_PCIEASPM
+static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
+{
+	uint32_t def, data;
+
+	WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, 0x75EB);
+
+	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP2);
+	data &= ~RCC_BIF_STRAP2__STRAP_LTR_IN_ASPML1_DIS_MASK;
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP2, data);
+
+	def = data = RREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL);
+	data &= ~EP_PCIE_TX_LTR_CNTL__LTR_PRIV_MSG_DIS_IN_PM_NON_D0_MASK;
+	if (def != data)
+		WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, data);
+
+	def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2);
+	data |= BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK;
+	if (def != data)
+		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
+}
+#endif
+
+static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
+{
+#ifdef CONFIG_PCIEASPM
+	uint32_t def, data;
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
+	data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK;
+	data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
+	data |= PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL, data);
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL7);
+	data |= PCIE_LC_CNTL7__LC_NBIF_ASPM_INPUT_EN_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL7, data);
+
+	def = data = RREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK);
+	data |= NBIF_MGCG_CTRL_LCLK__NBIF_MGCG_REG_DIS_LCLK_MASK;
+	if (def != data)
+		WREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK, data);
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL3);
+	data |= PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+
+	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3);
+	data &= ~RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER_MASK;
+	data &= ~RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER_MASK;
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3, data);
+
+	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP5);
+	data &= ~RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER_MASK;
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP5, data);
+
+	def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2);
+	data &= ~BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK;
+	if (def != data)
+		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
+
+	WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP, 0x10011001);
+
+	def = data = RREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2);
+	data |= PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L1_MASK |
+		PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L23_MASK;
+	data &= ~PSWUSP0_PCIE_LC_CNTL2__LC_RCV_L0_TO_RCV_L0S_DIS_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2, data);
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL6);
+	data |= PCIE_LC_CNTL6__LC_L1_POWERDOWN_MASK |
+		PCIE_LC_CNTL6__LC_RX_L0S_STANDBY_EN_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
+
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v2_3_program_ltr(adev);
+
+	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3);
+	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
+	data |= 0x0010 << RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER__SHIFT;
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3, data);
+
+	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP5);
+	data |= 0x0010 << RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER__SHIFT;
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP5, data);
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
+	data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
+	data |= 0x9 << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
+	data |= 0x1 << PCIE_LC_CNTL__LC_PMI_TO_L1_DIS__SHIFT;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL, data);
+
+	def = data = RREG32_PCIE(smnPCIE_LC_CNTL3);
+	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
+	if (def != data)
+		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
+}
+
+static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+	uint32_t link_width = 0;
+
+	if (!((adev->asic_type >= CHIP_NAVI10) &&
+	     (adev->asic_type <= CHIP_NAVI12)))
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	link_width = (reg_data & PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+
+	/*
+	 * Program PCIE_LC_CNTL6.LC_SPC_MODE_8GT to 0x2 (4 symbols per clock data)
+	 * if link_width is 0x3 (x4)
+	 */
+	if (0x3 == link_width) {
+		reg_data = RREG32_PCIE(smnPCIE_LC_CNTL6);
+		reg_data &= ~PCIE_LC_CNTL6__LC_SPC_MODE_8GT_MASK;
+		reg_data |= (0x2 << PCIE_LC_CNTL6__LC_SPC_MODE_8GT__SHIFT);
+		WREG32_PCIE(smnPCIE_LC_CNTL6, reg_data);
+	}
+}
+
+static void nbio_v2_3_apply_l1_link_width_reconfig_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+
+	if (adev->asic_type != CHIP_NAVI10)
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	reg_data |= PCIE_LC_LINK_WIDTH_CNTL__LC_L1_RECONFIG_EN_MASK;
+	WREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL, reg_data);
+}
+
+static void nbio_v2_3_clear_doorbell_interrupt(struct amdgpu_device *adev)
+{
+	uint32_t reg, reg_data;
+
+	if (adev->ip_versions[NBIO_HWIP][0] != IP_VERSION(3, 3, 0))
+		return;
+
+	reg = RREG32_SOC15(NBIO, 0, mmBIF_RB_CNTL);
+
+	/* Clear Interrupt Status
+	 */
+	if ((reg & BIF_RB_CNTL__RB_ENABLE_MASK) == 0) {
+		reg = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+		if (reg & BIF_DOORBELL_INT_CNTL__DOORBELL_INTERRUPT_STATUS_MASK) {
+			reg_data = 1 << BIF_DOORBELL_INT_CNTL__DOORBELL_INTERRUPT_CLEAR__SHIFT;
+			WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, reg_data);
+		}
+	}
+}
+
+const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
+	.get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset,
+	.get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset,
+	.get_pcie_index_offset = nbio_v2_3_get_pcie_index_offset,
+	.get_pcie_data_offset = nbio_v2_3_get_pcie_data_offset,
+	.get_rev_id = nbio_v2_3_get_rev_id,
+	.mc_access_enable = nbio_v2_3_mc_access_enable,
+	.get_memsize = nbio_v2_3_get_memsize,
+	.sdma_doorbell_range = nbio_v2_3_sdma_doorbell_range,
+	.vcn_doorbell_range = nbio_v2_3_vcn_doorbell_range,
+	.enable_doorbell_aperture = nbio_v2_3_enable_doorbell_aperture,
+	.enable_doorbell_selfring_aperture = nbio_v2_3_enable_doorbell_selfring_aperture,
+	.ih_doorbell_range = nbio_v2_3_ih_doorbell_range,
+	.update_medium_grain_clock_gating = nbio_v2_3_update_medium_grain_clock_gating,
+	.update_medium_grain_light_sleep = nbio_v2_3_update_medium_grain_light_sleep,
+	.get_clockgating_state = nbio_v2_3_get_clockgating_state,
+	.ih_control = nbio_v2_3_ih_control,
+	.init_registers = nbio_v2_3_init_registers,
+	.remap_hdp_registers = nbio_v2_3_remap_hdp_registers,
+	.enable_aspm = nbio_v2_3_enable_aspm,
+	.program_aspm =  nbio_v2_3_program_aspm,
+	.apply_lc_spc_mode_wa = nbio_v2_3_apply_lc_spc_mode_wa,
+	.apply_l1_link_width_reconfig_wa = nbio_v2_3_apply_l1_link_width_reconfig_wa,
+	.clear_doorbell_interrupt = nbio_v2_3_clear_doorbell_interrupt,
+};