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().
  ...

3 files changed, 696 insertions, 0 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nic/dcb.c b/drivers/net/ethernet/netronome/nfp/nic/dcb.c
new file mode 100644
index 000000000..bb498ac6b
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nic/dcb.c
@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2023 Corigine, Inc. */
+
+#include <linux/device.h>
+#include <linux/netdevice.h>
+#include <net/dcbnl.h>
+
+#include "../nfp_app.h"
+#include "../nfp_net.h"
+#include "../nfp_main.h"
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfpcore/nfp_nffw.h"
+#include "../nfp_net_sriov.h"
+
+#include "main.h"
+
+#define NFP_DCB_TRUST_PCP	1
+#define NFP_DCB_TRUST_DSCP	2
+#define NFP_DCB_TRUST_INVALID	0xff
+
+#define NFP_DCB_TSA_VENDOR	1
+#define NFP_DCB_TSA_STRICT	2
+#define NFP_DCB_TSA_ETS		3
+
+#define NFP_DCB_GBL_ENABLE	BIT(0)
+#define NFP_DCB_QOS_ENABLE	BIT(1)
+#define NFP_DCB_DISABLE		0
+#define NFP_DCB_ALL_QOS_ENABLE	(NFP_DCB_GBL_ENABLE | NFP_DCB_QOS_ENABLE)
+
+#define NFP_DCB_UPDATE_MSK_SZ	4
+#define NFP_DCB_TC_RATE_MAX	0xffff
+
+#define NFP_DCB_DATA_OFF_DSCP2IDX	0
+#define NFP_DCB_DATA_OFF_PCP2IDX	64
+#define NFP_DCB_DATA_OFF_TSA		80
+#define NFP_DCB_DATA_OFF_IDX_BW_PCT	88
+#define NFP_DCB_DATA_OFF_RATE		96
+#define NFP_DCB_DATA_OFF_CAP		112
+#define NFP_DCB_DATA_OFF_ENABLE		116
+#define NFP_DCB_DATA_OFF_TRUST		120
+
+#define NFP_DCB_MSG_MSK_ENABLE	BIT(31)
+#define NFP_DCB_MSG_MSK_TRUST	BIT(30)
+#define NFP_DCB_MSG_MSK_TSA	BIT(29)
+#define NFP_DCB_MSG_MSK_DSCP	BIT(28)
+#define NFP_DCB_MSG_MSK_PCP	BIT(27)
+#define NFP_DCB_MSG_MSK_RATE	BIT(26)
+#define NFP_DCB_MSG_MSK_PCT	BIT(25)
+
+static struct nfp_dcb *get_dcb_priv(struct nfp_net *nn)
+{
+	struct nfp_dcb *dcb = &((struct nfp_app_nic_private *)nn->app_priv)->dcb;
+
+	return dcb;
+}
+
+static u8 nfp_tsa_ieee2nfp(u8 tsa)
+{
+	switch (tsa) {
+	case IEEE_8021QAZ_TSA_STRICT:
+		return NFP_DCB_TSA_STRICT;
+	case IEEE_8021QAZ_TSA_ETS:
+		return NFP_DCB_TSA_ETS;
+	default:
+		return NFP_DCB_TSA_VENDOR;
+	}
+}
+
+static int nfp_nic_dcbnl_ieee_getets(struct net_device *dev,
+				     struct ieee_ets *ets)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_dcb *dcb;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		ets->prio_tc[i] = dcb->prio2tc[i];
+		ets->tc_tx_bw[i] = dcb->tc_tx_pct[i];
+		ets->tc_tsa[i] = dcb->tc_tsa[i];
+	}
+
+	return 0;
+}
+
+static bool nfp_refresh_tc2idx(struct nfp_net *nn)
+{
+	u8 tc2idx[IEEE_8021QAZ_MAX_TCS];
+	bool change = false;
+	struct nfp_dcb *dcb;
+	int maxstrict = 0;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		tc2idx[i] = i;
+		if (dcb->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT)
+			maxstrict = i;
+	}
+
+	if (maxstrict > 0 && dcb->tc_tsa[0] != IEEE_8021QAZ_TSA_STRICT) {
+		tc2idx[0] = maxstrict;
+		tc2idx[maxstrict] = 0;
+	}
+
+	for (unsigned int j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
+		if (dcb->tc2idx[j] != tc2idx[j]) {
+			change = true;
+			dcb->tc2idx[j] = tc2idx[j];
+		}
+	}
+
+	return change;
+}
+
+static int nfp_fill_maxrate(struct nfp_net *nn, u64 *max_rate_array)
+{
+	struct nfp_app *app  = nn->app;
+	struct nfp_dcb *dcb;
+	u32 ratembps;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		/* Convert bandwidth from kbps to mbps. */
+		ratembps = max_rate_array[i] / 1024;
+
+		/* Reject input values >= NFP_DCB_TC_RATE_MAX */
+		if (ratembps >= NFP_DCB_TC_RATE_MAX) {
+			nfp_warn(app->cpp, "ratembps(%d) must less than %d.",
+				 ratembps, NFP_DCB_TC_RATE_MAX);
+			return -EINVAL;
+		}
+		/* Input value 0 mapped to NFP_DCB_TC_RATE_MAX for firmware. */
+		if (ratembps == 0)
+			ratembps = NFP_DCB_TC_RATE_MAX;
+
+		writew((u16)ratembps, dcb->dcbcfg_tbl +
+		       dcb->cfg_offset + NFP_DCB_DATA_OFF_RATE + dcb->tc2idx[i] * 2);
+		/* for rate value from user space, need to sync to dcb structure */
+		if (dcb->tc_maxrate != max_rate_array)
+			dcb->tc_maxrate[i] = max_rate_array[i];
+	}
+
+	return 0;
+}
+
+static int update_dscp_maxrate(struct net_device *dev, u32 *update)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_dcb *dcb;
+	int err;
+
+	dcb = get_dcb_priv(nn);
+
+	err = nfp_fill_maxrate(nn, dcb->tc_maxrate);
+	if (err)
+		return err;
+
+	*update |= NFP_DCB_MSG_MSK_RATE;
+
+	/* We only refresh dscp in dscp trust mode. */
+	if (dcb->dscp_cnt > 0) {
+		for (unsigned int i = 0; i < NFP_NET_MAX_DSCP; i++) {
+			writeb(dcb->tc2idx[dcb->prio2tc[dcb->dscp2prio[i]]],
+			       dcb->dcbcfg_tbl + dcb->cfg_offset +
+			       NFP_DCB_DATA_OFF_DSCP2IDX + i);
+		}
+		*update |= NFP_DCB_MSG_MSK_DSCP;
+	}
+
+	return 0;
+}
+
+static void nfp_nic_set_trust(struct nfp_net *nn, u32 *update)
+{
+	struct nfp_dcb *dcb;
+	u8 trust;
+
+	dcb = get_dcb_priv(nn);
+
+	if (dcb->trust_status != NFP_DCB_TRUST_INVALID)
+		return;
+
+	trust = dcb->dscp_cnt > 0 ? NFP_DCB_TRUST_DSCP : NFP_DCB_TRUST_PCP;
+	writeb(trust, dcb->dcbcfg_tbl + dcb->cfg_offset +
+	       NFP_DCB_DATA_OFF_TRUST);
+
+	dcb->trust_status = trust;
+	*update |= NFP_DCB_MSG_MSK_TRUST;
+}
+
+static void nfp_nic_set_enable(struct nfp_net *nn, u32 enable, u32 *update)
+{
+	struct nfp_dcb *dcb;
+	u32 value = 0;
+
+	dcb = get_dcb_priv(nn);
+
+	value = readl(dcb->dcbcfg_tbl + dcb->cfg_offset +
+		      NFP_DCB_DATA_OFF_ENABLE);
+	if (value != enable) {
+		writel(enable, dcb->dcbcfg_tbl + dcb->cfg_offset +
+		       NFP_DCB_DATA_OFF_ENABLE);
+		*update |= NFP_DCB_MSG_MSK_ENABLE;
+	}
+}
+
+static int dcb_ets_check(struct net_device *dev, struct ieee_ets *ets)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_app *app = nn->app;
+	bool ets_exists = false;
+	int sum = 0;
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		/* For ets mode, check bw percentage sum. */
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			ets_exists = true;
+			sum += ets->tc_tx_bw[i];
+		} else if (ets->tc_tx_bw[i]) {
+			nfp_warn(app->cpp, "ETS BW for strict/vendor TC must be 0.");
+			return -EINVAL;
+		}
+	}
+
+	if (ets_exists && sum != 100) {
+		nfp_warn(app->cpp, "Failed to validate ETS BW: sum must be 100.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void nfp_nic_fill_ets(struct nfp_net *nn)
+{
+	struct nfp_dcb *dcb;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		writeb(dcb->tc2idx[dcb->prio2tc[i]],
+		       dcb->dcbcfg_tbl + dcb->cfg_offset + NFP_DCB_DATA_OFF_PCP2IDX + i);
+		writeb(dcb->tc_tx_pct[i], dcb->dcbcfg_tbl +
+		       dcb->cfg_offset + NFP_DCB_DATA_OFF_IDX_BW_PCT + dcb->tc2idx[i]);
+		writeb(nfp_tsa_ieee2nfp(dcb->tc_tsa[i]), dcb->dcbcfg_tbl +
+		       dcb->cfg_offset + NFP_DCB_DATA_OFF_TSA + dcb->tc2idx[i]);
+	}
+}
+
+static void nfp_nic_ets_init(struct nfp_net *nn, u32 *update)
+{
+	struct nfp_dcb *dcb = get_dcb_priv(nn);
+
+	if (dcb->ets_init)
+		return;
+
+	nfp_nic_fill_ets(nn);
+	dcb->ets_init = true;
+	*update |= NFP_DCB_MSG_MSK_TSA | NFP_DCB_MSG_MSK_PCT | NFP_DCB_MSG_MSK_PCP;
+}
+
+static int nfp_nic_dcbnl_ieee_setets(struct net_device *dev,
+				     struct ieee_ets *ets)
+{
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE;
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_app *app = nn->app;
+	struct nfp_dcb *dcb;
+	u32 update = 0;
+	bool change;
+	int err;
+
+	err = dcb_ets_check(dev, ets);
+	if (err)
+		return err;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		dcb->prio2tc[i] = ets->prio_tc[i];
+		dcb->tc_tx_pct[i] = ets->tc_tx_bw[i];
+		dcb->tc_tsa[i] = ets->tc_tsa[i];
+	}
+
+	change = nfp_refresh_tc2idx(nn);
+	nfp_nic_fill_ets(nn);
+	dcb->ets_init = true;
+	if (change || !dcb->rate_init) {
+		err = update_dscp_maxrate(dev, &update);
+		if (err) {
+			nfp_warn(app->cpp,
+				 "nfp dcbnl ieee setets ERROR:%d.",
+				 err);
+			return err;
+		}
+
+		dcb->rate_init = true;
+	}
+	nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update);
+	nfp_nic_set_trust(nn, &update);
+	err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ);
+	if (err)
+		return err;
+
+	nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL,
+		  update | NFP_DCB_MSG_MSK_TSA | NFP_DCB_MSG_MSK_PCT |
+		  NFP_DCB_MSG_MSK_PCP);
+
+	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
+}
+
+static int nfp_nic_dcbnl_ieee_getmaxrate(struct net_device *dev,
+					 struct ieee_maxrate *maxrate)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_dcb *dcb;
+
+	dcb = get_dcb_priv(nn);
+
+	for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		maxrate->tc_maxrate[i] = dcb->tc_maxrate[i];
+
+	return 0;
+}
+
+static int nfp_nic_dcbnl_ieee_setmaxrate(struct net_device *dev,
+					 struct ieee_maxrate *maxrate)
+{
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE;
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_app *app = nn->app;
+	struct nfp_dcb *dcb;
+	u32 update = 0;
+	int err;
+
+	err = nfp_fill_maxrate(nn, maxrate->tc_maxrate);
+	if (err) {
+		nfp_warn(app->cpp,
+			 "nfp dcbnl ieee setmaxrate ERROR:%d.",
+			 err);
+		return err;
+	}
+
+	dcb = get_dcb_priv(nn);
+
+	dcb->rate_init = true;
+	nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update);
+	nfp_nic_set_trust(nn, &update);
+	nfp_nic_ets_init(nn, &update);
+
+	err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ);
+	if (err)
+		return err;
+
+	nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL,
+		  update | NFP_DCB_MSG_MSK_RATE);
+
+	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
+}
+
+static int nfp_nic_set_trust_status(struct nfp_net *nn, u8 status)
+{
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE;
+	struct nfp_dcb *dcb;
+	u32 update = 0;
+	int err;
+
+	dcb = get_dcb_priv(nn);
+	if (!dcb->rate_init) {
+		err = nfp_fill_maxrate(nn, dcb->tc_maxrate);
+		if (err)
+			return err;
+
+		update |= NFP_DCB_MSG_MSK_RATE;
+		dcb->rate_init = true;
+	}
+
+	err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ);
+	if (err)
+		return err;
+
+	nfp_nic_ets_init(nn, &update);
+	writeb(status, dcb->dcbcfg_tbl + dcb->cfg_offset +
+	       NFP_DCB_DATA_OFF_TRUST);
+	nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update);
+	nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL,
+		  update | NFP_DCB_MSG_MSK_TRUST);
+
+	err = nfp_net_mbox_reconfig_and_unlock(nn, cmd);
+	if (err)
+		return err;
+
+	dcb->trust_status = status;
+
+	return 0;
+}
+
+static int nfp_nic_set_dscp2prio(struct nfp_net *nn, u8 dscp, u8 prio)
+{
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE;
+	struct nfp_dcb *dcb;
+	u8 idx, tc;
+	int err;
+
+	err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ);
+	if (err)
+		return err;
+
+	dcb = get_dcb_priv(nn);
+
+	tc = dcb->prio2tc[prio];
+	idx = dcb->tc2idx[tc];
+
+	writeb(idx, dcb->dcbcfg_tbl + dcb->cfg_offset +
+	       NFP_DCB_DATA_OFF_DSCP2IDX + dscp);
+
+	nn_writel(nn, nn->tlv_caps.mbox_off +
+		  NFP_NET_CFG_MBOX_SIMPLE_VAL, NFP_DCB_MSG_MSK_DSCP);
+
+	err = nfp_net_mbox_reconfig_and_unlock(nn, cmd);
+	if (err)
+		return err;
+
+	dcb->dscp2prio[dscp] = prio;
+
+	return 0;
+}
+
+static int nfp_nic_dcbnl_ieee_setapp(struct net_device *dev,
+				     struct dcb_app *app)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct dcb_app old_app;
+	struct nfp_dcb *dcb;
+	bool is_new;
+	int err;
+
+	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
+		return -EINVAL;
+
+	dcb = get_dcb_priv(nn);
+
+	/* Save the old entry info */
+	old_app.selector = IEEE_8021QAZ_APP_SEL_DSCP;
+	old_app.protocol = app->protocol;
+	old_app.priority = dcb->dscp2prio[app->protocol];
+
+	/* Check trust status */
+	if (!dcb->dscp_cnt) {
+		err = nfp_nic_set_trust_status(nn, NFP_DCB_TRUST_DSCP);
+		if (err)
+			return err;
+	}
+
+	/* Check if the new mapping is same as old or in init stage */
+	if (app->priority != old_app.priority || app->priority == 0) {
+		err = nfp_nic_set_dscp2prio(nn, app->protocol, app->priority);
+		if (err)
+			return err;
+	}
+
+	/* Delete the old entry if exists */
+	is_new = !!dcb_ieee_delapp(dev, &old_app);
+
+	/* Add new entry and update counter */
+	err = dcb_ieee_setapp(dev, app);
+	if (err)
+		return err;
+
+	if (is_new)
+		dcb->dscp_cnt++;
+
+	return 0;
+}
+
+static int nfp_nic_dcbnl_ieee_delapp(struct net_device *dev,
+				     struct dcb_app *app)
+{
+	struct nfp_net *nn = netdev_priv(dev);
+	struct nfp_dcb *dcb;
+	int err;
+
+	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
+		return -EINVAL;
+
+	dcb = get_dcb_priv(nn);
+
+	/* Check if the dcb_app param match fw */
+	if (app->priority != dcb->dscp2prio[app->protocol])
+		return -ENOENT;
+
+	/* Set fw dscp mapping to 0 */
+	err = nfp_nic_set_dscp2prio(nn, app->protocol, 0);
+	if (err)
+		return err;
+
+	/* Delete app from dcb list */
+	err = dcb_ieee_delapp(dev, app);
+	if (err)
+		return err;
+
+	/* Decrease dscp counter */
+	dcb->dscp_cnt--;
+
+	/* If no dscp mapping is configured, trust pcp */
+	if (dcb->dscp_cnt == 0)
+		return nfp_nic_set_trust_status(nn, NFP_DCB_TRUST_PCP);
+
+	return 0;
+}
+
+static const struct dcbnl_rtnl_ops nfp_nic_dcbnl_ops = {
+	/* ieee 802.1Qaz std */
+	.ieee_getets	= nfp_nic_dcbnl_ieee_getets,
+	.ieee_setets	= nfp_nic_dcbnl_ieee_setets,
+	.ieee_getmaxrate = nfp_nic_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate = nfp_nic_dcbnl_ieee_setmaxrate,
+	.ieee_setapp	= nfp_nic_dcbnl_ieee_setapp,
+	.ieee_delapp	= nfp_nic_dcbnl_ieee_delapp,
+};
+
+int nfp_nic_dcb_init(struct nfp_net *nn)
+{
+	struct nfp_app *app = nn->app;
+	struct nfp_dcb *dcb;
+	int err;
+
+	dcb = get_dcb_priv(nn);
+	dcb->cfg_offset = NFP_DCB_CFG_STRIDE * nn->id;
+	dcb->dcbcfg_tbl = nfp_pf_map_rtsym(app->pf, "net.dcbcfg_tbl",
+					   "_abi_dcb_cfg",
+					   dcb->cfg_offset, &dcb->dcbcfg_tbl_area);
+	if (IS_ERR(dcb->dcbcfg_tbl)) {
+		if (PTR_ERR(dcb->dcbcfg_tbl) != -ENOENT) {
+			err = PTR_ERR(dcb->dcbcfg_tbl);
+			dcb->dcbcfg_tbl = NULL;
+			nfp_err(app->cpp,
+				"Failed to map dcbcfg_tbl area, min_size %u.\n",
+				dcb->cfg_offset);
+			return err;
+		}
+		dcb->dcbcfg_tbl = NULL;
+	}
+
+	if (dcb->dcbcfg_tbl) {
+		for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+			dcb->prio2tc[i] = i;
+			dcb->tc2idx[i] = i;
+			dcb->tc_tx_pct[i] = 0;
+			dcb->tc_maxrate[i] = 0;
+			dcb->tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR;
+		}
+		dcb->trust_status = NFP_DCB_TRUST_INVALID;
+		dcb->rate_init = false;
+		dcb->ets_init = false;
+
+		nn->dp.netdev->dcbnl_ops = &nfp_nic_dcbnl_ops;
+	}
+
+	return 0;
+}
+
+void nfp_nic_dcb_clean(struct nfp_net *nn)
+{
+	struct nfp_dcb *dcb;
+
+	dcb = get_dcb_priv(nn);
+	if (dcb->dcbcfg_tbl_area)
+		nfp_cpp_area_release_free(dcb->dcbcfg_tbl_area);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.c b/drivers/net/ethernet/netronome/nfp/nic/main.c
new file mode 100644
index 000000000..9dd5afe37
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nic/main.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2017 Netronome Systems, Inc. */
+
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfpcore/nfp_nsp.h"
+#include "../nfp_app.h"
+#include "../nfp_main.h"
+#include "../nfp_net.h"
+#include "main.h"
+
+static int nfp_nic_init(struct nfp_app *app)
+{
+	struct nfp_pf *pf = app->pf;
+
+	if (pf->eth_tbl && pf->max_data_vnics != pf->eth_tbl->count) {
+		nfp_err(pf->cpp, "ETH entries don't match vNICs (%d vs %d)\n",
+			pf->max_data_vnics, pf->eth_tbl->count);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nfp_nic_sriov_enable(struct nfp_app *app, int num_vfs)
+{
+	return 0;
+}
+
+static void nfp_nic_sriov_disable(struct nfp_app *app)
+{
+}
+
+static int nfp_nic_vnic_init(struct nfp_app *app, struct nfp_net *nn)
+{
+	return nfp_nic_dcb_init(nn);
+}
+
+static void nfp_nic_vnic_clean(struct nfp_app *app, struct nfp_net *nn)
+{
+	nfp_nic_dcb_clean(nn);
+}
+
+static int nfp_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
+			      unsigned int id)
+{
+	struct nfp_app_nic_private *app_pri = nn->app_priv;
+	int err;
+
+	err = nfp_app_nic_vnic_alloc(app, nn, id);
+	if (err)
+		return err;
+
+	if (sizeof(*app_pri)) {
+		nn->app_priv = kzalloc(sizeof(*app_pri), GFP_KERNEL);
+		if (!nn->app_priv)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nfp_nic_vnic_free(struct nfp_app *app, struct nfp_net *nn)
+{
+	kfree(nn->app_priv);
+}
+
+const struct nfp_app_type app_nic = {
+	.id		= NFP_APP_CORE_NIC,
+	.name		= "nic",
+
+	.init		= nfp_nic_init,
+	.vnic_alloc	= nfp_nic_vnic_alloc,
+	.vnic_free	= nfp_nic_vnic_free,
+	.sriov_enable	= nfp_nic_sriov_enable,
+	.sriov_disable	= nfp_nic_sriov_disable,
+
+	.vnic_init      = nfp_nic_vnic_init,
+	.vnic_clean     = nfp_nic_vnic_clean,
+};
diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h
new file mode 100644
index 000000000..094374df4
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nic/main.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2023 Corigine, Inc. */
+
+#ifndef __NFP_NIC_H__
+#define __NFP_NIC_H__ 1
+
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_DCB
+/* DCB feature definitions */
+#define NFP_NET_MAX_DSCP	4
+#define NFP_NET_MAX_TC		IEEE_8021QAZ_MAX_TCS
+#define NFP_NET_MAX_PRIO	8
+#define NFP_DCB_CFG_STRIDE	256
+
+struct nfp_dcb {
+	u8 dscp2prio[NFP_NET_MAX_DSCP];
+	u8 prio2tc[NFP_NET_MAX_PRIO];
+	u8 tc2idx[IEEE_8021QAZ_MAX_TCS];
+	u64 tc_maxrate[IEEE_8021QAZ_MAX_TCS];
+	u8 tc_tx_pct[IEEE_8021QAZ_MAX_TCS];
+	u8 tc_tsa[IEEE_8021QAZ_MAX_TCS];
+	u8 dscp_cnt;
+	u8 trust_status;
+	bool rate_init;
+	bool ets_init;
+
+	struct nfp_cpp_area *dcbcfg_tbl_area;
+	u8 __iomem *dcbcfg_tbl;
+	u32 cfg_offset;
+};
+
+int nfp_nic_dcb_init(struct nfp_net *nn);
+void nfp_nic_dcb_clean(struct nfp_net *nn);
+#else
+static inline int nfp_nic_dcb_init(struct nfp_net *nn) { return 0; }
+static inline void nfp_nic_dcb_clean(struct nfp_net *nn) {}
+#endif
+
+struct nfp_app_nic_private {
+#ifdef CONFIG_DCB
+	struct nfp_dcb dcb;
+#endif
+};
+
+#endif