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, 753 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
new file mode 100644
index 000000000..752a72499
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -0,0 +1,753 @@
+/*
+ * Copyright (c) 2011 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * 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 AUTHORS OR COPYRIGHT HOLDERS
+ * 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/dcbnl.h>
+#include <linux/math64.h>
+
+#include "mlx4_en.h"
+#include "fw_qos.h"
+
+enum {
+	MLX4_CEE_STATE_DOWN   = 0,
+	MLX4_CEE_STATE_UP     = 1,
+};
+
+/* Definitions for QCN
+ */
+
+struct mlx4_congestion_control_mb_prio_802_1_qau_params {
+	__be32 modify_enable_high;
+	__be32 modify_enable_low;
+	__be32 reserved1;
+	__be32 extended_enable;
+	__be32 rppp_max_rps;
+	__be32 rpg_time_reset;
+	__be32 rpg_byte_reset;
+	__be32 rpg_threshold;
+	__be32 rpg_max_rate;
+	__be32 rpg_ai_rate;
+	__be32 rpg_hai_rate;
+	__be32 rpg_gd;
+	__be32 rpg_min_dec_fac;
+	__be32 rpg_min_rate;
+	__be32 max_time_rise;
+	__be32 max_byte_rise;
+	__be32 max_qdelta;
+	__be32 min_qoffset;
+	__be32 gd_coefficient;
+	__be32 reserved2[5];
+	__be32 cp_sample_base;
+	__be32 reserved3[39];
+};
+
+struct mlx4_congestion_control_mb_prio_802_1_qau_statistics {
+	__be64 rppp_rp_centiseconds;
+	__be32 reserved1;
+	__be32 ignored_cnm;
+	__be32 rppp_created_rps;
+	__be32 estimated_total_rate;
+	__be32 max_active_rate_limiter_index;
+	__be32 dropped_cnms_busy_fw;
+	__be32 reserved2;
+	__be32 cnms_handled_successfully;
+	__be32 min_total_limiters_rate;
+	__be32 max_total_limiters_rate;
+	__be32 reserved3[4];
+};
+
+static u8 mlx4_en_dcbnl_getcap(struct net_device *dev, int capid, u8 *cap)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PFC:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = priv->dcbx_cap;
+		break;
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 1 <<  mlx4_max_tc(priv->mdev->dev);
+		break;
+	default:
+		*cap = false;
+		break;
+	}
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	return priv->cee_config.pfc_state;
+}
+
+static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_config.pfc_state = state;
+}
+
+static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 *setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	*setting = priv->cee_config.dcb_pfc[priority];
+}
+
+static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_config.dcb_pfc[priority] = setting;
+	priv->cee_config.pfc_state = true;
+}
+
+static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	if (!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return -EINVAL;
+
+	if (tcid == DCB_NUMTCS_ATTR_PFC)
+		*num = mlx4_max_tc(priv->mdev->dev);
+	else
+		*num = 0;
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_port_profile *prof = priv->prof;
+	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
+
+	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 1;
+
+	if (priv->cee_config.pfc_state) {
+		int tc;
+		rx_ppp = prof->rx_ppp;
+		tx_ppp = prof->tx_ppp;
+
+		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
+			u8 tc_mask = 1 << tc;
+
+			switch (priv->cee_config.dcb_pfc[tc]) {
+			case pfc_disabled:
+				tx_ppp &= ~tc_mask;
+				rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_full:
+				tx_ppp |= tc_mask;
+				rx_ppp |= tc_mask;
+				break;
+			case pfc_enabled_tx:
+				tx_ppp |= tc_mask;
+				rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_rx:
+				tx_ppp &= ~tc_mask;
+				rx_ppp |= tc_mask;
+				break;
+			default:
+				break;
+			}
+		}
+		rx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->rx_pause;
+		tx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->tx_pause;
+	} else {
+		rx_ppp = 0;
+		tx_ppp = 0;
+		rx_pause = prof->rx_pause;
+		tx_pause = prof->tx_pause;
+	}
+
+	if (mlx4_SET_PORT_general(mdev->dev, priv->port,
+				  priv->rx_skb_size + ETH_FCS_LEN,
+				  tx_pause, tx_ppp, rx_pause, rx_ppp)) {
+		en_err(priv, "Failed setting pause params\n");
+		return 1;
+	}
+
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->tx_pause = tx_pause;
+	prof->rx_pause = rx_pause;
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (priv->flags & MLX4_EN_FLAG_DCB_ENABLED)
+		return MLX4_CEE_STATE_UP;
+
+	return MLX4_CEE_STATE_DOWN;
+}
+
+static u8 mlx4_en_dcbnl_set_state(struct net_device *dev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int num_tcs = 0;
+
+	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 1;
+
+	if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return 0;
+
+	if (state) {
+		priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		num_tcs = IEEE_8021QAZ_MAX_TCS;
+	} else {
+		priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+	}
+
+	if (mlx4_en_alloc_tx_queue_per_tc(dev, num_tcs))
+		return 1;
+
+	return 0;
+}
+
+/* On success returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to
+ * indicate an error.
+ */
+static int mlx4_en_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app = {
+				.selector = idtype,
+				.protocol = id,
+			     };
+	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 0;
+
+	return dcb_getapp(netdev, &app);
+}
+
+static int mlx4_en_dcbnl_setapp(struct net_device *netdev, u8 idtype,
+				u16 id, u8 up)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app;
+
+	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	memset(&app, 0, sizeof(struct dcb_app));
+	app.selector = idtype;
+	app.protocol = id;
+	app.priority = up;
+
+	return dcb_setapp(netdev, &app);
+}
+
+static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev,
+				   struct ieee_ets *ets)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct ieee_ets *my_ets = &priv->ets;
+
+	if (!my_ets)
+		return -EINVAL;
+
+	ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
+	ets->cbs = my_ets->cbs;
+	memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw));
+	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
+	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
+
+	return 0;
+}
+
+static int mlx4_en_ets_validate(struct mlx4_en_priv *priv, struct ieee_ets *ets)
+{
+	int i;
+	int total_ets_bw = 0;
+	int has_ets_tc = 0;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (ets->prio_tc[i] >= MLX4_EN_NUM_UP_HIGH) {
+			en_err(priv, "Bad priority in UP <=> TC mapping. TC: %d, UP: %d\n",
+					i, ets->prio_tc[i]);
+			return -EINVAL;
+		}
+
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
+		case IEEE_8021QAZ_TSA_STRICT:
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			has_ets_tc = 1;
+			total_ets_bw += ets->tc_tx_bw[i];
+			break;
+		default:
+			en_err(priv, "TC[%d]: Not supported TSA: %d\n",
+					i, ets->tc_tsa[i]);
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (has_ets_tc && total_ets_bw != MLX4_EN_BW_MAX) {
+		en_err(priv, "Bad ETS BW sum: %d. Should be exactly 100%%\n",
+				total_ets_bw);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mlx4_en_config_port_scheduler(struct mlx4_en_priv *priv,
+		struct ieee_ets *ets, u16 *ratelimit)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int num_strict = 0;
+	int i;
+	__u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS] = { 0 };
+	__u8 pg[IEEE_8021QAZ_MAX_TCS] = { 0 };
+
+	ets = ets ?: &priv->ets;
+	ratelimit = ratelimit ?: priv->maxrate;
+
+	/* higher TC means higher priority => lower pg */
+	for (i = IEEE_8021QAZ_MAX_TCS - 1; i >= 0; i--) {
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
+			pg[i] = MLX4_EN_TC_VENDOR;
+			tc_tx_bw[i] = MLX4_EN_BW_MAX;
+			break;
+		case IEEE_8021QAZ_TSA_STRICT:
+			pg[i] = num_strict++;
+			tc_tx_bw[i] = MLX4_EN_BW_MAX;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			pg[i] = MLX4_EN_TC_ETS;
+			tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX4_EN_BW_MIN;
+			break;
+		}
+	}
+
+	return mlx4_SET_PORT_SCHEDULER(mdev->dev, priv->port, tc_tx_bw, pg,
+			ratelimit);
+}
+
+static int
+mlx4_en_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	err = mlx4_en_ets_validate(priv, ets);
+	if (err)
+		return err;
+
+	err = mlx4_SET_PORT_PRIO2TC(mdev->dev, priv->port, ets->prio_tc);
+	if (err)
+		return err;
+
+	err = mlx4_en_config_port_scheduler(priv, ets, NULL);
+	if (err)
+		return err;
+
+	memcpy(&priv->ets, ets, sizeof(priv->ets));
+
+	return 0;
+}
+
+static int mlx4_en_dcbnl_ieee_getpfc(struct net_device *dev,
+		struct ieee_pfc *pfc)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc->pfc_en = priv->prof->tx_ppp;
+
+	return 0;
+}
+
+static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
+		struct ieee_pfc *pfc)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_port_profile *prof = priv->prof;
+	struct mlx4_en_dev *mdev = priv->mdev;
+	u32 tx_pause, tx_ppp, rx_pause, rx_ppp;
+	int err;
+
+	en_dbg(DRV, priv, "cap: 0x%x en: 0x%x mbc: 0x%x delay: %d\n",
+			pfc->pfc_cap,
+			pfc->pfc_en,
+			pfc->mbc,
+			pfc->delay);
+
+	rx_pause = prof->rx_pause && !pfc->pfc_en;
+	tx_pause = prof->tx_pause && !pfc->pfc_en;
+	rx_ppp = pfc->pfc_en;
+	tx_ppp = pfc->pfc_en;
+
+	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
+				    priv->rx_skb_size + ETH_FCS_LEN,
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
+		en_err(priv, "Failed setting pause params\n");
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->rx_pause = rx_pause;
+	prof->tx_pause = tx_pause;
+
+	return err;
+}
+
+static u8 mlx4_en_dcbnl_getdcbx(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->dcbx_cap;
+}
+
+static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct ieee_ets ets = {0};
+	struct ieee_pfc pfc = {0};
+
+	if (mode == priv->dcbx_cap)
+		return 0;
+
+	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
+	    ((mode & DCB_CAP_DCBX_VER_IEEE) &&
+	     (mode & DCB_CAP_DCBX_VER_CEE)) ||
+	    !(mode & DCB_CAP_DCBX_HOST))
+		goto err;
+
+	priv->dcbx_cap = mode;
+
+	ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+	} else if (mode & DCB_CAP_DCBX_VER_CEE) {
+		if (mlx4_en_dcbnl_set_all(dev))
+			goto err;
+	} else {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+		if (mlx4_en_alloc_tx_queue_per_tc(dev, 0))
+			goto err;
+	}
+
+	return 0;
+err:
+	return 1;
+}
+
+#define MLX4_RATELIMIT_UNITS_IN_KB 100000 /* rate-limit HW unit in Kbps */
+static int mlx4_en_dcbnl_ieee_getmaxrate(struct net_device *dev,
+				   struct ieee_maxrate *maxrate)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		maxrate->tc_maxrate[i] =
+			priv->maxrate[i] * MLX4_RATELIMIT_UNITS_IN_KB;
+
+	return 0;
+}
+
+static int mlx4_en_dcbnl_ieee_setmaxrate(struct net_device *dev,
+		struct ieee_maxrate *maxrate)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	u16 tmp[IEEE_8021QAZ_MAX_TCS];
+	int i, err;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		/* Convert from Kbps into HW units, rounding result up.
+		 * Setting to 0, means unlimited BW.
+		 */
+		tmp[i] = div_u64(maxrate->tc_maxrate[i] +
+				 MLX4_RATELIMIT_UNITS_IN_KB - 1,
+				 MLX4_RATELIMIT_UNITS_IN_KB);
+	}
+
+	err = mlx4_en_config_port_scheduler(priv, NULL, tmp);
+	if (err)
+		return err;
+
+	memcpy(priv->maxrate, tmp, sizeof(priv->maxrate));
+
+	return 0;
+}
+
+#define RPG_ENABLE_BIT	31
+#define CN_TAG_BIT	30
+
+static int mlx4_en_dcbnl_ieee_getqcn(struct net_device *dev,
+				     struct ieee_qcn *qcn)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_congestion_control_mb_prio_802_1_qau_params *hw_qcn;
+	struct mlx4_cmd_mailbox *mailbox_out = NULL;
+	u64 mailbox_in_dma = 0;
+	u32 inmod = 0;
+	int i, err;
+
+	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QCN))
+		return -EOPNOTSUPP;
+
+	mailbox_out = mlx4_alloc_cmd_mailbox(priv->mdev->dev);
+	if (IS_ERR(mailbox_out))
+		return -ENOMEM;
+	hw_qcn =
+	(struct mlx4_congestion_control_mb_prio_802_1_qau_params *)
+	mailbox_out->buf;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		inmod = priv->port | ((1 << i) << 8) |
+			 (MLX4_CTRL_ALGO_802_1_QAU_REACTION_POINT << 16);
+		err = mlx4_cmd_box(priv->mdev->dev, mailbox_in_dma,
+				   mailbox_out->dma,
+				   inmod, MLX4_CONGESTION_CONTROL_GET_PARAMS,
+				   MLX4_CMD_CONGESTION_CTRL_OPCODE,
+				   MLX4_CMD_TIME_CLASS_C,
+				   MLX4_CMD_NATIVE);
+		if (err) {
+			mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_out);
+			return err;
+		}
+
+		qcn->rpg_enable[i] =
+			be32_to_cpu(hw_qcn->extended_enable) >> RPG_ENABLE_BIT;
+		qcn->rppp_max_rps[i] =
+			be32_to_cpu(hw_qcn->rppp_max_rps);
+		qcn->rpg_time_reset[i] =
+			be32_to_cpu(hw_qcn->rpg_time_reset);
+		qcn->rpg_byte_reset[i] =
+			be32_to_cpu(hw_qcn->rpg_byte_reset);
+		qcn->rpg_threshold[i] =
+			be32_to_cpu(hw_qcn->rpg_threshold);
+		qcn->rpg_max_rate[i] =
+			be32_to_cpu(hw_qcn->rpg_max_rate);
+		qcn->rpg_ai_rate[i] =
+			be32_to_cpu(hw_qcn->rpg_ai_rate);
+		qcn->rpg_hai_rate[i] =
+			be32_to_cpu(hw_qcn->rpg_hai_rate);
+		qcn->rpg_gd[i] =
+			be32_to_cpu(hw_qcn->rpg_gd);
+		qcn->rpg_min_dec_fac[i] =
+			be32_to_cpu(hw_qcn->rpg_min_dec_fac);
+		qcn->rpg_min_rate[i] =
+			be32_to_cpu(hw_qcn->rpg_min_rate);
+		qcn->cndd_state_machine[i] =
+			priv->cndd_state[i];
+	}
+	mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_out);
+	return 0;
+}
+
+static int mlx4_en_dcbnl_ieee_setqcn(struct net_device *dev,
+				     struct ieee_qcn *qcn)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_congestion_control_mb_prio_802_1_qau_params *hw_qcn;
+	struct mlx4_cmd_mailbox *mailbox_in = NULL;
+	u64 mailbox_in_dma = 0;
+	u32 inmod = 0;
+	int i, err;
+#define MODIFY_ENABLE_HIGH_MASK 0xc0000000
+#define MODIFY_ENABLE_LOW_MASK 0xffc00000
+
+	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QCN))
+		return -EOPNOTSUPP;
+
+	mailbox_in = mlx4_alloc_cmd_mailbox(priv->mdev->dev);
+	if (IS_ERR(mailbox_in))
+		return -ENOMEM;
+
+	mailbox_in_dma = mailbox_in->dma;
+	hw_qcn =
+	(struct mlx4_congestion_control_mb_prio_802_1_qau_params *)mailbox_in->buf;
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		inmod = priv->port | ((1 << i) << 8) |
+			 (MLX4_CTRL_ALGO_802_1_QAU_REACTION_POINT << 16);
+
+		/* Before updating QCN parameter,
+		 * need to set it's modify enable bit to 1
+		 */
+
+		hw_qcn->modify_enable_high = cpu_to_be32(
+						MODIFY_ENABLE_HIGH_MASK);
+		hw_qcn->modify_enable_low = cpu_to_be32(MODIFY_ENABLE_LOW_MASK);
+
+		hw_qcn->extended_enable = cpu_to_be32(qcn->rpg_enable[i] << RPG_ENABLE_BIT);
+		hw_qcn->rppp_max_rps = cpu_to_be32(qcn->rppp_max_rps[i]);
+		hw_qcn->rpg_time_reset = cpu_to_be32(qcn->rpg_time_reset[i]);
+		hw_qcn->rpg_byte_reset = cpu_to_be32(qcn->rpg_byte_reset[i]);
+		hw_qcn->rpg_threshold = cpu_to_be32(qcn->rpg_threshold[i]);
+		hw_qcn->rpg_max_rate = cpu_to_be32(qcn->rpg_max_rate[i]);
+		hw_qcn->rpg_ai_rate = cpu_to_be32(qcn->rpg_ai_rate[i]);
+		hw_qcn->rpg_hai_rate = cpu_to_be32(qcn->rpg_hai_rate[i]);
+		hw_qcn->rpg_gd = cpu_to_be32(qcn->rpg_gd[i]);
+		hw_qcn->rpg_min_dec_fac = cpu_to_be32(qcn->rpg_min_dec_fac[i]);
+		hw_qcn->rpg_min_rate = cpu_to_be32(qcn->rpg_min_rate[i]);
+		priv->cndd_state[i] = qcn->cndd_state_machine[i];
+		if (qcn->cndd_state_machine[i] == DCB_CNDD_INTERIOR_READY)
+			hw_qcn->extended_enable |= cpu_to_be32(1 << CN_TAG_BIT);
+
+		err = mlx4_cmd(priv->mdev->dev, mailbox_in_dma, inmod,
+			       MLX4_CONGESTION_CONTROL_SET_PARAMS,
+			       MLX4_CMD_CONGESTION_CTRL_OPCODE,
+			       MLX4_CMD_TIME_CLASS_C,
+			       MLX4_CMD_NATIVE);
+		if (err) {
+			mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_in);
+			return err;
+		}
+	}
+	mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_in);
+	return 0;
+}
+
+static int mlx4_en_dcbnl_ieee_getqcnstats(struct net_device *dev,
+					  struct ieee_qcn_stats *qcn_stats)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_congestion_control_mb_prio_802_1_qau_statistics *hw_qcn_stats;
+	struct mlx4_cmd_mailbox *mailbox_out = NULL;
+	u64 mailbox_in_dma = 0;
+	u32 inmod = 0;
+	int i, err;
+
+	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QCN))
+		return -EOPNOTSUPP;
+
+	mailbox_out = mlx4_alloc_cmd_mailbox(priv->mdev->dev);
+	if (IS_ERR(mailbox_out))
+		return -ENOMEM;
+
+	hw_qcn_stats =
+	(struct mlx4_congestion_control_mb_prio_802_1_qau_statistics *)
+	mailbox_out->buf;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		inmod = priv->port | ((1 << i) << 8) |
+			 (MLX4_CTRL_ALGO_802_1_QAU_REACTION_POINT << 16);
+		err = mlx4_cmd_box(priv->mdev->dev, mailbox_in_dma,
+				   mailbox_out->dma, inmod,
+				   MLX4_CONGESTION_CONTROL_GET_STATISTICS,
+				   MLX4_CMD_CONGESTION_CTRL_OPCODE,
+				   MLX4_CMD_TIME_CLASS_C,
+				   MLX4_CMD_NATIVE);
+		if (err) {
+			mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_out);
+			return err;
+		}
+		qcn_stats->rppp_rp_centiseconds[i] =
+			be64_to_cpu(hw_qcn_stats->rppp_rp_centiseconds);
+		qcn_stats->rppp_created_rps[i] =
+			be32_to_cpu(hw_qcn_stats->rppp_created_rps);
+	}
+	mlx4_free_cmd_mailbox(priv->mdev->dev, mailbox_out);
+	return 0;
+}
+
+const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops = {
+	.ieee_getets		= mlx4_en_dcbnl_ieee_getets,
+	.ieee_setets		= mlx4_en_dcbnl_ieee_setets,
+	.ieee_getmaxrate	= mlx4_en_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate	= mlx4_en_dcbnl_ieee_setmaxrate,
+	.ieee_getqcn		= mlx4_en_dcbnl_ieee_getqcn,
+	.ieee_setqcn		= mlx4_en_dcbnl_ieee_setqcn,
+	.ieee_getqcnstats	= mlx4_en_dcbnl_ieee_getqcnstats,
+	.ieee_getpfc		= mlx4_en_dcbnl_ieee_getpfc,
+	.ieee_setpfc		= mlx4_en_dcbnl_ieee_setpfc,
+
+	.getstate	= mlx4_en_dcbnl_get_state,
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getcap		= mlx4_en_dcbnl_getcap,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
+
+	.getdcbx	= mlx4_en_dcbnl_getdcbx,
+	.setdcbx	= mlx4_en_dcbnl_setdcbx,
+};
+
+const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops = {
+	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
+
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
+
+	.getdcbx	= mlx4_en_dcbnl_getdcbx,
+	.setdcbx	= mlx4_en_dcbnl_setdcbx,
+};