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, 752 insertions, 0 deletions

diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
new file mode 100644
index 000000000..a557a477d
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -0,0 +1,752 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Texas Instruments Ethernet Switch Driver ethtool intf
+ *
+ * Copyright (C) 2019 Texas Instruments
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+#include <linux/pm_runtime.h>
+#include <linux/skbuff.h>
+
+#include "cpsw.h"
+#include "cpts.h"
+#include "cpsw_ale.h"
+#include "cpsw_priv.h"
+#include "davinci_cpdma.h"
+
+struct cpsw_hw_stats {
+	u32	rxgoodframes;
+	u32	rxbroadcastframes;
+	u32	rxmulticastframes;
+	u32	rxpauseframes;
+	u32	rxcrcerrors;
+	u32	rxaligncodeerrors;
+	u32	rxoversizedframes;
+	u32	rxjabberframes;
+	u32	rxundersizedframes;
+	u32	rxfragments;
+	u32	__pad_0[2];
+	u32	rxoctets;
+	u32	txgoodframes;
+	u32	txbroadcastframes;
+	u32	txmulticastframes;
+	u32	txpauseframes;
+	u32	txdeferredframes;
+	u32	txcollisionframes;
+	u32	txsinglecollframes;
+	u32	txmultcollframes;
+	u32	txexcessivecollisions;
+	u32	txlatecollisions;
+	u32	txunderrun;
+	u32	txcarriersenseerrors;
+	u32	txoctets;
+	u32	octetframes64;
+	u32	octetframes65t127;
+	u32	octetframes128t255;
+	u32	octetframes256t511;
+	u32	octetframes512t1023;
+	u32	octetframes1024tup;
+	u32	netoctets;
+	u32	rxsofoverruns;
+	u32	rxmofoverruns;
+	u32	rxdmaoverruns;
+};
+
+struct cpsw_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int type;
+	int sizeof_stat;
+	int stat_offset;
+};
+
+enum {
+	CPSW_STATS,
+	CPDMA_RX_STATS,
+	CPDMA_TX_STATS,
+};
+
+#define CPSW_STAT(m)		CPSW_STATS,				\
+				sizeof_field(struct cpsw_hw_stats, m), \
+				offsetof(struct cpsw_hw_stats, m)
+#define CPDMA_RX_STAT(m)	CPDMA_RX_STATS,				   \
+				sizeof_field(struct cpdma_chan_stats, m), \
+				offsetof(struct cpdma_chan_stats, m)
+#define CPDMA_TX_STAT(m)	CPDMA_TX_STATS,				   \
+				sizeof_field(struct cpdma_chan_stats, m), \
+				offsetof(struct cpdma_chan_stats, m)
+
+static const struct cpsw_stats cpsw_gstrings_stats[] = {
+	{ "Good Rx Frames", CPSW_STAT(rxgoodframes) },
+	{ "Broadcast Rx Frames", CPSW_STAT(rxbroadcastframes) },
+	{ "Multicast Rx Frames", CPSW_STAT(rxmulticastframes) },
+	{ "Pause Rx Frames", CPSW_STAT(rxpauseframes) },
+	{ "Rx CRC Errors", CPSW_STAT(rxcrcerrors) },
+	{ "Rx Align/Code Errors", CPSW_STAT(rxaligncodeerrors) },
+	{ "Oversize Rx Frames", CPSW_STAT(rxoversizedframes) },
+	{ "Rx Jabbers", CPSW_STAT(rxjabberframes) },
+	{ "Undersize (Short) Rx Frames", CPSW_STAT(rxundersizedframes) },
+	{ "Rx Fragments", CPSW_STAT(rxfragments) },
+	{ "Rx Octets", CPSW_STAT(rxoctets) },
+	{ "Good Tx Frames", CPSW_STAT(txgoodframes) },
+	{ "Broadcast Tx Frames", CPSW_STAT(txbroadcastframes) },
+	{ "Multicast Tx Frames", CPSW_STAT(txmulticastframes) },
+	{ "Pause Tx Frames", CPSW_STAT(txpauseframes) },
+	{ "Deferred Tx Frames", CPSW_STAT(txdeferredframes) },
+	{ "Collisions", CPSW_STAT(txcollisionframes) },
+	{ "Single Collision Tx Frames", CPSW_STAT(txsinglecollframes) },
+	{ "Multiple Collision Tx Frames", CPSW_STAT(txmultcollframes) },
+	{ "Excessive Collisions", CPSW_STAT(txexcessivecollisions) },
+	{ "Late Collisions", CPSW_STAT(txlatecollisions) },
+	{ "Tx Underrun", CPSW_STAT(txunderrun) },
+	{ "Carrier Sense Errors", CPSW_STAT(txcarriersenseerrors) },
+	{ "Tx Octets", CPSW_STAT(txoctets) },
+	{ "Rx + Tx 64 Octet Frames", CPSW_STAT(octetframes64) },
+	{ "Rx + Tx 65-127 Octet Frames", CPSW_STAT(octetframes65t127) },
+	{ "Rx + Tx 128-255 Octet Frames", CPSW_STAT(octetframes128t255) },
+	{ "Rx + Tx 256-511 Octet Frames", CPSW_STAT(octetframes256t511) },
+	{ "Rx + Tx 512-1023 Octet Frames", CPSW_STAT(octetframes512t1023) },
+	{ "Rx + Tx 1024-Up Octet Frames", CPSW_STAT(octetframes1024tup) },
+	{ "Net Octets", CPSW_STAT(netoctets) },
+	{ "Rx Start of Frame Overruns", CPSW_STAT(rxsofoverruns) },
+	{ "Rx Middle of Frame Overruns", CPSW_STAT(rxmofoverruns) },
+	{ "Rx DMA Overruns", CPSW_STAT(rxdmaoverruns) },
+};
+
+static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
+	{ "head_enqueue", CPDMA_RX_STAT(head_enqueue) },
+	{ "tail_enqueue", CPDMA_RX_STAT(tail_enqueue) },
+	{ "pad_enqueue", CPDMA_RX_STAT(pad_enqueue) },
+	{ "misqueued", CPDMA_RX_STAT(misqueued) },
+	{ "desc_alloc_fail", CPDMA_RX_STAT(desc_alloc_fail) },
+	{ "pad_alloc_fail", CPDMA_RX_STAT(pad_alloc_fail) },
+	{ "runt_receive_buf", CPDMA_RX_STAT(runt_receive_buff) },
+	{ "runt_transmit_buf", CPDMA_RX_STAT(runt_transmit_buff) },
+	{ "empty_dequeue", CPDMA_RX_STAT(empty_dequeue) },
+	{ "busy_dequeue", CPDMA_RX_STAT(busy_dequeue) },
+	{ "good_dequeue", CPDMA_RX_STAT(good_dequeue) },
+	{ "requeue", CPDMA_RX_STAT(requeue) },
+	{ "teardown_dequeue", CPDMA_RX_STAT(teardown_dequeue) },
+};
+
+#define CPSW_STATS_COMMON_LEN	ARRAY_SIZE(cpsw_gstrings_stats)
+#define CPSW_STATS_CH_LEN	ARRAY_SIZE(cpsw_gstrings_ch_stats)
+
+u32 cpsw_get_msglevel(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	return priv->msg_enable;
+}
+
+void cpsw_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	priv->msg_enable = value;
+}
+
+int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	coal->rx_coalesce_usecs = cpsw->coal_intvl;
+	return 0;
+}
+
+int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	u32 int_ctrl;
+	u32 num_interrupts = 0;
+	u32 prescale = 0;
+	u32 addnl_dvdr = 1;
+	u32 coal_intvl = 0;
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	coal_intvl = coal->rx_coalesce_usecs;
+
+	int_ctrl =  readl(&cpsw->wr_regs->int_control);
+	prescale = cpsw->bus_freq_mhz * 4;
+
+	if (!coal->rx_coalesce_usecs) {
+		int_ctrl &= ~(CPSW_INTPRESCALE_MASK | CPSW_INTPACEEN);
+		goto update_return;
+	}
+
+	if (coal_intvl < CPSW_CMINTMIN_INTVL)
+		coal_intvl = CPSW_CMINTMIN_INTVL;
+
+	if (coal_intvl > CPSW_CMINTMAX_INTVL) {
+		/* Interrupt pacer works with 4us Pulse, we can
+		 * throttle further by dilating the 4us pulse.
+		 */
+		addnl_dvdr = CPSW_INTPRESCALE_MASK / prescale;
+
+		if (addnl_dvdr > 1) {
+			prescale *= addnl_dvdr;
+			if (coal_intvl > (CPSW_CMINTMAX_INTVL * addnl_dvdr))
+				coal_intvl = (CPSW_CMINTMAX_INTVL
+						* addnl_dvdr);
+		} else {
+			addnl_dvdr = 1;
+			coal_intvl = CPSW_CMINTMAX_INTVL;
+		}
+	}
+
+	num_interrupts = (1000 * addnl_dvdr) / coal_intvl;
+	writel(num_interrupts, &cpsw->wr_regs->rx_imax);
+	writel(num_interrupts, &cpsw->wr_regs->tx_imax);
+
+	int_ctrl |= CPSW_INTPACEEN;
+	int_ctrl &= (~CPSW_INTPRESCALE_MASK);
+	int_ctrl |= (prescale & CPSW_INTPRESCALE_MASK);
+
+update_return:
+	writel(int_ctrl, &cpsw->wr_regs->int_control);
+
+	cpsw_notice(priv, timer, "Set coalesce to %d usecs.\n", coal_intvl);
+	cpsw->coal_intvl = coal_intvl;
+
+	return 0;
+}
+
+int cpsw_get_sset_count(struct net_device *ndev, int sset)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return (CPSW_STATS_COMMON_LEN +
+		       (cpsw->rx_ch_num + cpsw->tx_ch_num) *
+		       CPSW_STATS_CH_LEN);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void cpsw_add_ch_strings(u8 **p, int ch_num, int rx_dir)
+{
+	int ch_stats_len;
+	int line;
+	int i;
+
+	ch_stats_len = CPSW_STATS_CH_LEN * ch_num;
+	for (i = 0; i < ch_stats_len; i++) {
+		line = i % CPSW_STATS_CH_LEN;
+		snprintf(*p, ETH_GSTRING_LEN,
+			 "%s DMA chan %ld: %s", rx_dir ? "Rx" : "Tx",
+			 (long)(i / CPSW_STATS_CH_LEN),
+			 cpsw_gstrings_ch_stats[line].stat_string);
+		*p += ETH_GSTRING_LEN;
+	}
+}
+
+void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < CPSW_STATS_COMMON_LEN; i++) {
+			memcpy(p, cpsw_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		cpsw_add_ch_strings(&p, cpsw->rx_ch_num, 1);
+		cpsw_add_ch_strings(&p, cpsw->tx_ch_num, 0);
+		break;
+	}
+}
+
+void cpsw_get_ethtool_stats(struct net_device *ndev,
+			    struct ethtool_stats *stats, u64 *data)
+{
+	u8 *p;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpdma_chan_stats ch_stats;
+	int i, l, ch;
+
+	/* Collect Davinci CPDMA stats for Rx and Tx Channel */
+	for (l = 0; l < CPSW_STATS_COMMON_LEN; l++)
+		data[l] = readl(cpsw->hw_stats +
+				cpsw_gstrings_stats[l].stat_offset);
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		cpdma_chan_get_stats(cpsw->rxv[ch].ch, &ch_stats);
+		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
+			p = (u8 *)&ch_stats +
+				cpsw_gstrings_ch_stats[i].stat_offset;
+			data[l] = *(u32 *)p;
+		}
+	}
+
+	for (ch = 0; ch < cpsw->tx_ch_num; ch++) {
+		cpdma_chan_get_stats(cpsw->txv[ch].ch, &ch_stats);
+		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
+			p = (u8 *)&ch_stats +
+				cpsw_gstrings_ch_stats[i].stat_offset;
+			data[l] = *(u32 *)p;
+		}
+	}
+}
+
+void cpsw_get_pauseparam(struct net_device *ndev,
+			 struct ethtool_pauseparam *pause)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	pause->autoneg = AUTONEG_DISABLE;
+	pause->rx_pause = priv->rx_pause ? true : false;
+	pause->tx_pause = priv->tx_pause ? true : false;
+}
+
+void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+
+	if (cpsw->slaves[slave_no].phy)
+		phy_ethtool_get_wol(cpsw->slaves[slave_no].phy, wol);
+}
+
+int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_set_wol(cpsw->slaves[slave_no].phy, wol);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_get_regs_len(struct net_device *ndev)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	return cpsw_ale_get_num_entries(cpsw->ale) *
+	       ALE_ENTRY_WORDS * sizeof(u32);
+}
+
+void cpsw_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *p)
+{
+	u32 *reg = p;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	/* update CPSW IP version */
+	regs->version = cpsw->version;
+
+	cpsw_ale_dump(cpsw->ale, reg);
+}
+
+int cpsw_ethtool_op_begin(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+
+	ret = pm_runtime_resume_and_get(cpsw->dev);
+	if (ret < 0)
+		cpsw_err(priv, drv, "ethtool begin failed %d\n", ret);
+
+	return ret;
+}
+
+void cpsw_ethtool_op_complete(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = pm_runtime_put(priv->cpsw->dev);
+	if (ret < 0)
+		cpsw_err(priv, drv, "ethtool complete failed %d\n", ret);
+}
+
+void cpsw_get_channels(struct net_device *ndev, struct ethtool_channels *ch)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	ch->max_rx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
+	ch->max_tx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
+	ch->max_combined = 0;
+	ch->max_other = 0;
+	ch->other_count = 0;
+	ch->rx_count = cpsw->rx_ch_num;
+	ch->tx_count = cpsw->tx_ch_num;
+	ch->combined_count = 0;
+}
+
+int cpsw_get_link_ksettings(struct net_device *ndev,
+			    struct ethtool_link_ksettings *ecmd)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (!cpsw->slaves[slave_no].phy)
+		return -EOPNOTSUPP;
+
+	phy_ethtool_ksettings_get(cpsw->slaves[slave_no].phy, ecmd);
+	return 0;
+}
+
+int cpsw_set_link_ksettings(struct net_device *ndev,
+			    const struct ethtool_link_ksettings *ecmd)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (!cpsw->slaves[slave_no].phy)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_ksettings_set(cpsw->slaves[slave_no].phy, ecmd);
+}
+
+int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_get_eee(cpsw->slaves[slave_no].phy, edata);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_set_eee(cpsw->slaves[slave_no].phy, edata);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_nway_reset(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return genphy_restart_aneg(cpsw->slaves[slave_no].phy);
+	else
+		return -EOPNOTSUPP;
+}
+
+static void cpsw_suspend_data_pass(struct net_device *ndev)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	int i;
+
+	/* Disable NAPI scheduling */
+	cpsw_intr_disable(cpsw);
+
+	/* Stop all transmit queues for every network device.
+	 */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		netif_tx_stop_all_queues(ndev);
+
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+	}
+
+	/* Handle rest of tx packets and stop cpdma channels */
+	cpdma_ctlr_stop(cpsw->dma);
+}
+
+static int cpsw_resume_data_pass(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int i, ret;
+
+	/* After this receive is started */
+	if (cpsw->usage_count) {
+		ret = cpsw_fill_rx_channels(priv);
+		if (ret)
+			return ret;
+
+		cpdma_ctlr_start(cpsw->dma);
+		cpsw_intr_enable(cpsw);
+	}
+
+	/* Resume transmit for every affected interface */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev && netif_running(ndev))
+			netif_tx_start_all_queues(ndev);
+	}
+
+	return 0;
+}
+
+static int cpsw_check_ch_settings(struct cpsw_common *cpsw,
+				  struct ethtool_channels *ch)
+{
+	if (cpsw->quirk_irq) {
+		dev_err(cpsw->dev, "Maximum one tx/rx queue is allowed");
+		return -EOPNOTSUPP;
+	}
+
+	if (ch->combined_count)
+		return -EINVAL;
+
+	/* verify we have at least one channel in each direction */
+	if (!ch->rx_count || !ch->tx_count)
+		return -EINVAL;
+
+	if (ch->rx_count > cpsw->data.channels ||
+	    ch->tx_count > cpsw->data.channels)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
+				    cpdma_handler_fn rx_handler)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	void (*handler)(void *, int, int);
+	struct netdev_queue *queue;
+	struct cpsw_vector *vec;
+	int ret, *ch, vch;
+
+	if (rx) {
+		ch = &cpsw->rx_ch_num;
+		vec = cpsw->rxv;
+		handler = rx_handler;
+	} else {
+		ch = &cpsw->tx_ch_num;
+		vec = cpsw->txv;
+		handler = cpsw_tx_handler;
+	}
+
+	while (*ch < ch_num) {
+		vch = rx ? *ch : 7 - *ch;
+		vec[*ch].ch = cpdma_chan_create(cpsw->dma, vch, handler, rx);
+		queue = netdev_get_tx_queue(priv->ndev, *ch);
+		queue->tx_maxrate = 0;
+
+		if (IS_ERR(vec[*ch].ch))
+			return PTR_ERR(vec[*ch].ch);
+
+		if (!vec[*ch].ch)
+			return -EINVAL;
+
+		cpsw_info(priv, ifup, "created new %d %s channel\n", *ch,
+			  (rx ? "rx" : "tx"));
+		(*ch)++;
+	}
+
+	while (*ch > ch_num) {
+		(*ch)--;
+
+		ret = cpdma_chan_destroy(vec[*ch].ch);
+		if (ret)
+			return ret;
+
+		cpsw_info(priv, ifup, "destroyed %d %s channel\n", *ch,
+			  (rx ? "rx" : "tx"));
+	}
+
+	return 0;
+}
+
+static void cpsw_fail(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev)
+			dev_close(ndev);
+	}
+}
+
+int cpsw_set_channels_common(struct net_device *ndev,
+			     struct ethtool_channels *chs,
+			     cpdma_handler_fn rx_handler)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct net_device *sl_ndev;
+	int i, new_pools, ret;
+
+	ret = cpsw_check_ch_settings(cpsw, chs);
+	if (ret < 0)
+		return ret;
+
+	cpsw_suspend_data_pass(ndev);
+
+	new_pools = (chs->rx_count != cpsw->rx_ch_num) && cpsw->usage_count;
+
+	ret = cpsw_update_channels_res(priv, chs->rx_count, 1, rx_handler);
+	if (ret)
+		goto err;
+
+	ret = cpsw_update_channels_res(priv, chs->tx_count, 0, rx_handler);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		sl_ndev = cpsw->slaves[i].ndev;
+		if (!(sl_ndev && netif_running(sl_ndev)))
+			continue;
+
+		/* Inform stack about new count of queues */
+		ret = netif_set_real_num_tx_queues(sl_ndev, cpsw->tx_ch_num);
+		if (ret) {
+			dev_err(priv->dev, "cannot set real number of tx queues\n");
+			goto err;
+		}
+
+		ret = netif_set_real_num_rx_queues(sl_ndev, cpsw->rx_ch_num);
+		if (ret) {
+			dev_err(priv->dev, "cannot set real number of rx queues\n");
+			goto err;
+		}
+	}
+
+	cpsw_split_res(cpsw);
+
+	if (new_pools) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
+
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
+err:
+	dev_err(priv->dev, "cannot update channels number, closing device\n");
+	cpsw_fail(cpsw);
+	return ret;
+}
+
+void cpsw_get_ringparam(struct net_device *ndev,
+			struct ethtool_ringparam *ering,
+			struct kernel_ethtool_ringparam *kernel_ering,
+			struct netlink_ext_ack *extack)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	/* not supported */
+	ering->tx_max_pending = cpsw->descs_pool_size - CPSW_MAX_QUEUES;
+	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
+	ering->rx_max_pending = cpsw->descs_pool_size - CPSW_MAX_QUEUES;
+	ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma);
+}
+
+int cpsw_set_ringparam(struct net_device *ndev,
+		       struct ethtool_ringparam *ering,
+		       struct kernel_ethtool_ringparam *kernel_ering,
+		       struct netlink_ext_ack *extack)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	int descs_num, ret;
+
+	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
+
+	if (ering->rx_mini_pending || ering->rx_jumbo_pending ||
+	    ering->rx_pending < CPSW_MAX_QUEUES ||
+	    ering->rx_pending > (cpsw->descs_pool_size - CPSW_MAX_QUEUES))
+		return -EINVAL;
+
+	descs_num = cpdma_get_num_rx_descs(cpsw->dma);
+	if (ering->rx_pending == descs_num)
+		return 0;
+
+	cpsw_suspend_data_pass(ndev);
+
+	ret = cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+	if (ret) {
+		if (cpsw_resume_data_pass(ndev))
+			goto err;
+
+		return ret;
+	}
+
+	if (cpsw->usage_count) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
+
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
+err:
+	cpdma_set_num_rx_descs(cpsw->dma, descs_num);
+	dev_err(cpsw->dev, "cannot set ring params, closing device\n");
+	cpsw_fail(cpsw);
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_TI_CPTS)
+int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->phc_index = cpsw->cpts->phc_index;
+	info->tx_types =
+		(1 << HWTSTAMP_TX_OFF) |
+		(1 << HWTSTAMP_TX_ON);
+	info->rx_filters =
+		(1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
+	return 0;
+}
+#else
+int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info)
+{
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE;
+	info->phc_index = -1;
+	info->tx_types = 0;
+	info->rx_filters = 0;
+	return 0;
+}
+#endif