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, 507 insertions, 0 deletions

diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
new file mode 100644
index 000000000..8ba017ec9
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -0,0 +1,507 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+#include "sxgbe_dma.h"
+
+struct sxgbe_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define SXGBE_STAT(m)						\
+{								\
+	#m,							\
+	sizeof_field(struct sxgbe_extra_stats, m),		\
+	offsetof(struct sxgbe_priv_data, xstats.m)		\
+}
+
+static const struct sxgbe_stats sxgbe_gstrings_stats[] = {
+	/* TX/RX IRQ events */
+	SXGBE_STAT(tx_process_stopped_irq),
+	SXGBE_STAT(tx_ctxt_desc_err),
+	SXGBE_STAT(tx_threshold),
+	SXGBE_STAT(rx_threshold),
+	SXGBE_STAT(tx_pkt_n),
+	SXGBE_STAT(rx_pkt_n),
+	SXGBE_STAT(normal_irq_n),
+	SXGBE_STAT(tx_normal_irq_n),
+	SXGBE_STAT(rx_normal_irq_n),
+	SXGBE_STAT(napi_poll),
+	SXGBE_STAT(tx_clean),
+	SXGBE_STAT(tx_reset_ic_bit),
+	SXGBE_STAT(rx_process_stopped_irq),
+	SXGBE_STAT(rx_underflow_irq),
+
+	/* Bus access errors */
+	SXGBE_STAT(fatal_bus_error_irq),
+	SXGBE_STAT(tx_read_transfer_err),
+	SXGBE_STAT(tx_write_transfer_err),
+	SXGBE_STAT(tx_desc_access_err),
+	SXGBE_STAT(tx_buffer_access_err),
+	SXGBE_STAT(tx_data_transfer_err),
+	SXGBE_STAT(rx_read_transfer_err),
+	SXGBE_STAT(rx_write_transfer_err),
+	SXGBE_STAT(rx_desc_access_err),
+	SXGBE_STAT(rx_buffer_access_err),
+	SXGBE_STAT(rx_data_transfer_err),
+
+	/* EEE-LPI stats */
+	SXGBE_STAT(tx_lpi_entry_n),
+	SXGBE_STAT(tx_lpi_exit_n),
+	SXGBE_STAT(rx_lpi_entry_n),
+	SXGBE_STAT(rx_lpi_exit_n),
+	SXGBE_STAT(eee_wakeup_error_n),
+
+	/* RX specific */
+	/* L2 error */
+	SXGBE_STAT(rx_code_gmii_err),
+	SXGBE_STAT(rx_watchdog_err),
+	SXGBE_STAT(rx_crc_err),
+	SXGBE_STAT(rx_gaint_pkt_err),
+	SXGBE_STAT(ip_hdr_err),
+	SXGBE_STAT(ip_payload_err),
+	SXGBE_STAT(overflow_error),
+
+	/* L2 Pkt type */
+	SXGBE_STAT(len_pkt),
+	SXGBE_STAT(mac_ctl_pkt),
+	SXGBE_STAT(dcb_ctl_pkt),
+	SXGBE_STAT(arp_pkt),
+	SXGBE_STAT(oam_pkt),
+	SXGBE_STAT(untag_okt),
+	SXGBE_STAT(other_pkt),
+	SXGBE_STAT(svlan_tag_pkt),
+	SXGBE_STAT(cvlan_tag_pkt),
+	SXGBE_STAT(dvlan_ocvlan_icvlan_pkt),
+	SXGBE_STAT(dvlan_osvlan_isvlan_pkt),
+	SXGBE_STAT(dvlan_osvlan_icvlan_pkt),
+	SXGBE_STAT(dvan_ocvlan_icvlan_pkt),
+
+	/* L3/L4 Pkt type */
+	SXGBE_STAT(not_ip_pkt),
+	SXGBE_STAT(ip4_tcp_pkt),
+	SXGBE_STAT(ip4_udp_pkt),
+	SXGBE_STAT(ip4_icmp_pkt),
+	SXGBE_STAT(ip4_unknown_pkt),
+	SXGBE_STAT(ip6_tcp_pkt),
+	SXGBE_STAT(ip6_udp_pkt),
+	SXGBE_STAT(ip6_icmp_pkt),
+	SXGBE_STAT(ip6_unknown_pkt),
+
+	/* Filter specific */
+	SXGBE_STAT(vlan_filter_match),
+	SXGBE_STAT(sa_filter_fail),
+	SXGBE_STAT(da_filter_fail),
+	SXGBE_STAT(hash_filter_pass),
+	SXGBE_STAT(l3_filter_match),
+	SXGBE_STAT(l4_filter_match),
+
+	/* RX context specific */
+	SXGBE_STAT(timestamp_dropped),
+	SXGBE_STAT(rx_msg_type_no_ptp),
+	SXGBE_STAT(rx_ptp_type_sync),
+	SXGBE_STAT(rx_ptp_type_follow_up),
+	SXGBE_STAT(rx_ptp_type_delay_req),
+	SXGBE_STAT(rx_ptp_type_delay_resp),
+	SXGBE_STAT(rx_ptp_type_pdelay_req),
+	SXGBE_STAT(rx_ptp_type_pdelay_resp),
+	SXGBE_STAT(rx_ptp_type_pdelay_follow_up),
+	SXGBE_STAT(rx_ptp_announce),
+	SXGBE_STAT(rx_ptp_mgmt),
+	SXGBE_STAT(rx_ptp_signal),
+	SXGBE_STAT(rx_ptp_resv_msg_type),
+};
+#define SXGBE_STATS_LEN ARRAY_SIZE(sxgbe_gstrings_stats)
+
+static int sxgbe_get_eee(struct net_device *dev,
+			 struct ethtool_eee *edata)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	if (!priv->hw_cap.eee)
+		return -EOPNOTSUPP;
+
+	edata->eee_enabled = priv->eee_enabled;
+	edata->eee_active = priv->eee_active;
+	edata->tx_lpi_timer = priv->tx_lpi_timer;
+
+	return phy_ethtool_get_eee(dev->phydev, edata);
+}
+
+static int sxgbe_set_eee(struct net_device *dev,
+			 struct ethtool_eee *edata)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	priv->eee_enabled = edata->eee_enabled;
+
+	if (!priv->eee_enabled) {
+		sxgbe_disable_eee_mode(priv);
+	} else {
+		/* We are asking for enabling the EEE but it is safe
+		 * to verify all by invoking the eee_init function.
+		 * In case of failure it will return an error.
+		 */
+		priv->eee_enabled = sxgbe_eee_init(priv);
+		if (!priv->eee_enabled)
+			return -EOPNOTSUPP;
+
+		/* Do not change tx_lpi_timer in case of failure */
+		priv->tx_lpi_timer = edata->tx_lpi_timer;
+	}
+
+	return phy_ethtool_set_eee(dev->phydev, edata);
+}
+
+static void sxgbe_getdrvinfo(struct net_device *dev,
+			     struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strscpy(info->version, DRV_VERSION, sizeof(info->version));
+}
+
+static u32 sxgbe_getmsglevel(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	return priv->msg_enable;
+}
+
+static void sxgbe_setmsglevel(struct net_device *dev, u32 level)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	priv->msg_enable = level;
+}
+
+static void sxgbe_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	int i;
+	u8 *p = data;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < SXGBE_STATS_LEN; i++) {
+			memcpy(p, sxgbe_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static int sxgbe_get_sset_count(struct net_device *netdev, int sset)
+{
+	int len;
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		len = SXGBE_STATS_LEN;
+		return len;
+	default:
+		return -EINVAL;
+	}
+}
+
+static void sxgbe_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *dummy, u64 *data)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int i;
+	char *p;
+
+	if (priv->eee_enabled) {
+		int val = phy_get_eee_err(dev->phydev);
+
+		if (val)
+			priv->xstats.eee_wakeup_error_n = val;
+	}
+
+	for (i = 0; i < SXGBE_STATS_LEN; i++) {
+		p = (char *)priv + sxgbe_gstrings_stats[i].stat_offset;
+		data[i] = (sxgbe_gstrings_stats[i].sizeof_stat == sizeof(u64))
+			? (*(u64 *)p) : (*(u32 *)p);
+	}
+}
+
+static void sxgbe_get_channels(struct net_device *dev,
+			       struct ethtool_channels *channel)
+{
+	channel->max_rx = SXGBE_MAX_RX_CHANNELS;
+	channel->max_tx = SXGBE_MAX_TX_CHANNELS;
+	channel->rx_count = SXGBE_RX_QUEUES;
+	channel->tx_count = SXGBE_TX_QUEUES;
+}
+
+static u32 sxgbe_riwt2usec(u32 riwt, struct sxgbe_priv_data *priv)
+{
+	unsigned long clk = clk_get_rate(priv->sxgbe_clk);
+
+	if (!clk)
+		return 0;
+
+	return (riwt * 256) / (clk / 1000000);
+}
+
+static u32 sxgbe_usec2riwt(u32 usec, struct sxgbe_priv_data *priv)
+{
+	unsigned long clk = clk_get_rate(priv->sxgbe_clk);
+
+	if (!clk)
+		return 0;
+
+	return (usec * (clk / 1000000)) / 256;
+}
+
+static int sxgbe_get_coalesce(struct net_device *dev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	if (priv->use_riwt)
+		ec->rx_coalesce_usecs = sxgbe_riwt2usec(priv->rx_riwt, priv);
+
+	return 0;
+}
+
+static int sxgbe_set_coalesce(struct net_device *dev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	unsigned int rx_riwt;
+
+	if (!ec->rx_coalesce_usecs)
+		return -EINVAL;
+
+	rx_riwt = sxgbe_usec2riwt(ec->rx_coalesce_usecs, priv);
+
+	if ((rx_riwt > SXGBE_MAX_DMA_RIWT) || (rx_riwt < SXGBE_MIN_DMA_RIWT))
+		return -EINVAL;
+	else if (!priv->use_riwt)
+		return -EOPNOTSUPP;
+
+	priv->rx_riwt = rx_riwt;
+	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+
+	return 0;
+}
+
+static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
+				   struct ethtool_rxnfc *cmd)
+{
+	cmd->data = 0;
+
+	/* Report default options for RSS on sxgbe */
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case IPV4_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV6_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sxgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXFH:
+		ret = sxgbe_get_rss_hash_opts(priv, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int sxgbe_set_rss_hash_opt(struct sxgbe_priv_data *priv,
+				  struct ethtool_rxnfc *cmd)
+{
+	u32 reg_val = 0;
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (cmd->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		if (!(cmd->data & RXH_IP_SRC) ||
+		    !(cmd->data & RXH_IP_DST) ||
+		    !(cmd->data & RXH_L4_B_0_1) ||
+		    !(cmd->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		reg_val = SXGBE_CORE_RSS_CTL_TCP4TE;
+		break;
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		if (!(cmd->data & RXH_IP_SRC) ||
+		    !(cmd->data & RXH_IP_DST) ||
+		    !(cmd->data & RXH_L4_B_0_1) ||
+		    !(cmd->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		reg_val = SXGBE_CORE_RSS_CTL_UDP4TE;
+		break;
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		if (!(cmd->data & RXH_IP_SRC) ||
+		    !(cmd->data & RXH_IP_DST) ||
+		    (cmd->data & RXH_L4_B_0_1) ||
+		    (cmd->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		reg_val = SXGBE_CORE_RSS_CTL_IP2TE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Read SXGBE RSS control register and update */
+	reg_val |= readl(priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+	writel(reg_val, priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+	readl(priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+
+	return 0;
+}
+
+static int sxgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = sxgbe_set_rss_hash_opt(priv, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void sxgbe_get_regs(struct net_device *dev,
+			   struct ethtool_regs *regs, void *space)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	u32 *reg_space = (u32 *)space;
+	int reg_offset;
+	int reg_ix = 0;
+	void __iomem *ioaddr = priv->ioaddr;
+
+	memset(reg_space, 0x0, REG_SPACE_SIZE);
+
+	/* MAC registers */
+	for (reg_offset = START_MAC_REG_OFFSET;
+	     reg_offset <= MAX_MAC_REG_OFFSET; reg_offset += 4) {
+		reg_space[reg_ix] = readl(ioaddr + reg_offset);
+		reg_ix++;
+	}
+
+	/* MTL registers */
+	for (reg_offset = START_MTL_REG_OFFSET;
+	     reg_offset <= MAX_MTL_REG_OFFSET; reg_offset += 4) {
+		reg_space[reg_ix] = readl(ioaddr + reg_offset);
+		reg_ix++;
+	}
+
+	/* DMA registers */
+	for (reg_offset = START_DMA_REG_OFFSET;
+	     reg_offset <= MAX_DMA_REG_OFFSET; reg_offset += 4) {
+		reg_space[reg_ix] = readl(ioaddr + reg_offset);
+		reg_ix++;
+	}
+
+	BUG_ON(reg_ix * 4 > REG_SPACE_SIZE);
+}
+
+static int sxgbe_get_regs_len(struct net_device *dev)
+{
+	return REG_SPACE_SIZE;
+}
+
+static const struct ethtool_ops sxgbe_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS,
+	.get_drvinfo = sxgbe_getdrvinfo,
+	.get_msglevel = sxgbe_getmsglevel,
+	.set_msglevel = sxgbe_setmsglevel,
+	.get_link = ethtool_op_get_link,
+	.get_strings = sxgbe_get_strings,
+	.get_ethtool_stats = sxgbe_get_ethtool_stats,
+	.get_sset_count = sxgbe_get_sset_count,
+	.get_channels = sxgbe_get_channels,
+	.get_coalesce = sxgbe_get_coalesce,
+	.set_coalesce = sxgbe_set_coalesce,
+	.get_rxnfc = sxgbe_get_rxnfc,
+	.set_rxnfc = sxgbe_set_rxnfc,
+	.get_regs = sxgbe_get_regs,
+	.get_regs_len = sxgbe_get_regs_len,
+	.get_eee = sxgbe_get_eee,
+	.set_eee = sxgbe_set_eee,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+};
+
+void sxgbe_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &sxgbe_ethtool_ops;
+}