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, 298 insertions, 0 deletions

diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c
new file mode 100644
index 000000000..19c995295
--- /dev/null
+++ b/drivers/net/fjes/fjes_ethtool.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  FUJITSU Extended Socket Network Device driver
+ *  Copyright (c) 2015 FUJITSU LIMITED
+ */
+
+/* ethtool support for fjes */
+
+#include <linux/vmalloc.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/platform_device.h>
+
+#include "fjes.h"
+
+struct fjes_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define FJES_STAT(name, stat) { \
+	.stat_string = name, \
+	.sizeof_stat = sizeof_field(struct fjes_adapter, stat), \
+	.stat_offset = offsetof(struct fjes_adapter, stat) \
+}
+
+static const struct fjes_stats fjes_gstrings_stats[] = {
+	FJES_STAT("rx_packets", stats64.rx_packets),
+	FJES_STAT("tx_packets", stats64.tx_packets),
+	FJES_STAT("rx_bytes", stats64.rx_bytes),
+	FJES_STAT("tx_bytes", stats64.rx_bytes),
+	FJES_STAT("rx_dropped", stats64.rx_dropped),
+	FJES_STAT("tx_dropped", stats64.tx_dropped),
+};
+
+#define FJES_EP_STATS_LEN 14
+#define FJES_STATS_LEN \
+	(ARRAY_SIZE(fjes_gstrings_stats) + \
+	 ((&((struct fjes_adapter *)netdev_priv(netdev))->hw)->max_epid - 1) * \
+	 FJES_EP_STATS_LEN)
+
+static void fjes_get_ethtool_stats(struct net_device *netdev,
+				   struct ethtool_stats *stats, u64 *data)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+	int epidx;
+	char *p;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(fjes_gstrings_stats); i++) {
+		p = (char *)adapter + fjes_gstrings_stats[i].stat_offset;
+		data[i] = (fjes_gstrings_stats[i].sizeof_stat == sizeof(u64))
+			? *(u64 *)p : *(u32 *)p;
+	}
+	for (epidx = 0; epidx < hw->max_epid; epidx++) {
+		if (epidx == hw->my_epid)
+			continue;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.com_regist_buf_exec;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.com_unregist_buf_exec;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.send_intr_rx;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.send_intr_unshare;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.send_intr_zoneupdate;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.recv_intr_rx;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.recv_intr_unshare;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.recv_intr_stop;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.recv_intr_zoneupdate;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats.tx_buffer_full;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.tx_dropped_not_shared;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.tx_dropped_ver_mismatch;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.tx_dropped_buf_size_mismatch;
+		data[i++] = hw->ep_shm_info[epidx].ep_stats
+				.tx_dropped_vlanid_mismatch;
+	}
+}
+
+static void fjes_get_strings(struct net_device *netdev,
+			     u32 stringset, u8 *data)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(fjes_gstrings_stats); i++) {
+			memcpy(p, fjes_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < hw->max_epid; i++) {
+			if (i == hw->my_epid)
+				continue;
+			sprintf(p, "ep%u_com_regist_buf_exec", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_com_unregist_buf_exec", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_send_intr_rx", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_send_intr_unshare", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_send_intr_zoneupdate", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_recv_intr_rx", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_recv_intr_unshare", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_recv_intr_stop", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_recv_intr_zoneupdate", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_tx_buffer_full", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_tx_dropped_not_shared", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_tx_dropped_ver_mismatch", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_tx_dropped_buf_size_mismatch", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "ep%u_tx_dropped_vlanid_mismatch", i);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	}
+}
+
+static int fjes_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return FJES_STATS_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void fjes_get_drvinfo(struct net_device *netdev,
+			     struct ethtool_drvinfo *drvinfo)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct platform_device *plat_dev;
+
+	plat_dev = adapter->plat_dev;
+
+	strscpy(drvinfo->driver, fjes_driver_name, sizeof(drvinfo->driver));
+	strscpy(drvinfo->version, fjes_driver_version,
+		sizeof(drvinfo->version));
+
+	strscpy(drvinfo->fw_version, "none", sizeof(drvinfo->fw_version));
+	snprintf(drvinfo->bus_info, sizeof(drvinfo->bus_info),
+		 "platform:%s", plat_dev->name);
+}
+
+static int fjes_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *ecmd)
+{
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ecmd->base.duplex = DUPLEX_FULL;
+	ecmd->base.autoneg = AUTONEG_DISABLE;
+	ecmd->base.port = PORT_NONE;
+	ecmd->base.speed = 20000;	/* 20Gb/s */
+
+	return 0;
+}
+
+static int fjes_get_regs_len(struct net_device *netdev)
+{
+#define FJES_REGS_LEN	37
+	return FJES_REGS_LEN * sizeof(u32);
+}
+
+static void fjes_get_regs(struct net_device *netdev,
+			  struct ethtool_regs *regs, void *p)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+
+	memset(p, 0, FJES_REGS_LEN * sizeof(u32));
+
+	regs->version = 1;
+
+	/* Information registers */
+	regs_buff[0] = rd32(XSCT_OWNER_EPID);
+	regs_buff[1] = rd32(XSCT_MAX_EP);
+
+	/* Device Control registers */
+	regs_buff[4] = rd32(XSCT_DCTL);
+
+	/* Command Control registers */
+	regs_buff[8] = rd32(XSCT_CR);
+	regs_buff[9] = rd32(XSCT_CS);
+	regs_buff[10] = rd32(XSCT_SHSTSAL);
+	regs_buff[11] = rd32(XSCT_SHSTSAH);
+
+	regs_buff[13] = rd32(XSCT_REQBL);
+	regs_buff[14] = rd32(XSCT_REQBAL);
+	regs_buff[15] = rd32(XSCT_REQBAH);
+
+	regs_buff[17] = rd32(XSCT_RESPBL);
+	regs_buff[18] = rd32(XSCT_RESPBAL);
+	regs_buff[19] = rd32(XSCT_RESPBAH);
+
+	/* Interrupt Control registers */
+	regs_buff[32] = rd32(XSCT_IS);
+	regs_buff[33] = rd32(XSCT_IMS);
+	regs_buff[34] = rd32(XSCT_IMC);
+	regs_buff[35] = rd32(XSCT_IG);
+	regs_buff[36] = rd32(XSCT_ICTL);
+}
+
+static int fjes_set_dump(struct net_device *netdev, struct ethtool_dump *dump)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+	int ret = 0;
+
+	if (dump->flag) {
+		if (hw->debug_mode)
+			return -EPERM;
+
+		hw->debug_mode = dump->flag;
+
+		/* enable debug mode */
+		mutex_lock(&hw->hw_info.lock);
+		ret = fjes_hw_start_debug(hw);
+		mutex_unlock(&hw->hw_info.lock);
+
+		if (ret)
+			hw->debug_mode = 0;
+	} else {
+		if (!hw->debug_mode)
+			return -EPERM;
+
+		/* disable debug mode */
+		mutex_lock(&hw->hw_info.lock);
+		ret = fjes_hw_stop_debug(hw);
+		mutex_unlock(&hw->hw_info.lock);
+	}
+
+	return ret;
+}
+
+static int fjes_get_dump_flag(struct net_device *netdev,
+			      struct ethtool_dump *dump)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+
+	dump->len = hw->hw_info.trace_size;
+	dump->version = 1;
+	dump->flag = hw->debug_mode;
+
+	return 0;
+}
+
+static int fjes_get_dump_data(struct net_device *netdev,
+			      struct ethtool_dump *dump, void *buf)
+{
+	struct fjes_adapter *adapter = netdev_priv(netdev);
+	struct fjes_hw *hw = &adapter->hw;
+	int ret = 0;
+
+	if (hw->hw_info.trace)
+		memcpy(buf, hw->hw_info.trace, hw->hw_info.trace_size);
+	else
+		ret = -EPERM;
+
+	return ret;
+}
+
+static const struct ethtool_ops fjes_ethtool_ops = {
+		.get_drvinfo		= fjes_get_drvinfo,
+		.get_ethtool_stats = fjes_get_ethtool_stats,
+		.get_strings      = fjes_get_strings,
+		.get_sset_count   = fjes_get_sset_count,
+		.get_regs		= fjes_get_regs,
+		.get_regs_len		= fjes_get_regs_len,
+		.set_dump		= fjes_set_dump,
+		.get_dump_flag		= fjes_get_dump_flag,
+		.get_dump_data		= fjes_get_dump_data,
+		.get_link_ksettings	= fjes_get_link_ksettings,
+};
+
+void fjes_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &fjes_ethtool_ops;
+}