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, 619 insertions, 0 deletions

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
new file mode 100644
index 000000000..5cdbfbf9a
--- /dev/null
+++ b/net/core/dev_ioctl.c
@@ -0,0 +1,619 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kmod.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
+#include <linux/wireless.h>
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+#include <net/wext.h>
+
+#include "dev.h"
+
+/*
+ *	Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ *	We need this ioctl for efficient implementation of the
+ *	if_indextoname() function required by the IPv6 API.  Without
+ *	it, we would have to search all the interfaces to find a
+ *	match.  --pb
+ */
+
+static int dev_ifname(struct net *net, struct ifreq *ifr)
+{
+	ifr->ifr_name[IFNAMSIZ-1] = 0;
+	return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex);
+}
+
+/*
+ *	Perform a SIOCGIFCONF call. This structure will change
+ *	size eventually, and there is nothing I can do about it.
+ *	Thus we will need a 'compatibility mode'.
+ */
+int dev_ifconf(struct net *net, struct ifconf __user *uifc)
+{
+	struct net_device *dev;
+	void __user *pos;
+	size_t size;
+	int len, total = 0, done;
+
+	/* both the ifconf and the ifreq structures are slightly different */
+	if (in_compat_syscall()) {
+		struct compat_ifconf ifc32;
+
+		if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf)))
+			return -EFAULT;
+
+		pos = compat_ptr(ifc32.ifcbuf);
+		len = ifc32.ifc_len;
+		size = sizeof(struct compat_ifreq);
+	} else {
+		struct ifconf ifc;
+
+		if (copy_from_user(&ifc, uifc, sizeof(struct ifconf)))
+			return -EFAULT;
+
+		pos = ifc.ifc_buf;
+		len = ifc.ifc_len;
+		size = sizeof(struct ifreq);
+	}
+
+	/* Loop over the interfaces, and write an info block for each. */
+	rtnl_lock();
+	for_each_netdev(net, dev) {
+		if (!pos)
+			done = inet_gifconf(dev, NULL, 0, size);
+		else
+			done = inet_gifconf(dev, pos + total,
+					    len - total, size);
+		if (done < 0) {
+			rtnl_unlock();
+			return -EFAULT;
+		}
+		total += done;
+	}
+	rtnl_unlock();
+
+	return put_user(total, &uifc->ifc_len);
+}
+
+static int dev_getifmap(struct net_device *dev, struct ifreq *ifr)
+{
+	struct ifmap *ifmap = &ifr->ifr_map;
+
+	if (in_compat_syscall()) {
+		struct compat_ifmap *cifmap = (struct compat_ifmap *)ifmap;
+
+		cifmap->mem_start = dev->mem_start;
+		cifmap->mem_end   = dev->mem_end;
+		cifmap->base_addr = dev->base_addr;
+		cifmap->irq       = dev->irq;
+		cifmap->dma       = dev->dma;
+		cifmap->port      = dev->if_port;
+
+		return 0;
+	}
+
+	ifmap->mem_start  = dev->mem_start;
+	ifmap->mem_end    = dev->mem_end;
+	ifmap->base_addr  = dev->base_addr;
+	ifmap->irq        = dev->irq;
+	ifmap->dma        = dev->dma;
+	ifmap->port       = dev->if_port;
+
+	return 0;
+}
+
+static int dev_setifmap(struct net_device *dev, struct ifreq *ifr)
+{
+	struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map;
+
+	if (!dev->netdev_ops->ndo_set_config)
+		return -EOPNOTSUPP;
+
+	if (in_compat_syscall()) {
+		struct ifmap ifmap = {
+			.mem_start  = cifmap->mem_start,
+			.mem_end    = cifmap->mem_end,
+			.base_addr  = cifmap->base_addr,
+			.irq        = cifmap->irq,
+			.dma        = cifmap->dma,
+			.port       = cifmap->port,
+		};
+
+		return dev->netdev_ops->ndo_set_config(dev, &ifmap);
+	}
+
+	return dev->netdev_ops->ndo_set_config(dev, &ifr->ifr_map);
+}
+
+/*
+ *	Perform the SIOCxIFxxx calls, inside rcu_read_lock()
+ */
+static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+	int err;
+	struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
+
+	if (!dev)
+		return -ENODEV;
+
+	switch (cmd) {
+	case SIOCGIFFLAGS:	/* Get interface flags */
+		ifr->ifr_flags = (short) dev_get_flags(dev);
+		return 0;
+
+	case SIOCGIFMETRIC:	/* Get the metric on the interface
+				   (currently unused) */
+		ifr->ifr_metric = 0;
+		return 0;
+
+	case SIOCGIFMTU:	/* Get the MTU of a device */
+		ifr->ifr_mtu = dev->mtu;
+		return 0;
+
+	case SIOCGIFSLAVE:
+		err = -EINVAL;
+		break;
+
+	case SIOCGIFMAP:
+		return dev_getifmap(dev, ifr);
+
+	case SIOCGIFINDEX:
+		ifr->ifr_ifindex = dev->ifindex;
+		return 0;
+
+	case SIOCGIFTXQLEN:
+		ifr->ifr_qlen = dev->tx_queue_len;
+		return 0;
+
+	default:
+		/* dev_ioctl() should ensure this case
+		 * is never reached
+		 */
+		WARN_ON(1);
+		err = -ENOTTY;
+		break;
+
+	}
+	return err;
+}
+
+static int net_hwtstamp_validate(struct ifreq *ifr)
+{
+	struct hwtstamp_config cfg;
+	enum hwtstamp_tx_types tx_type;
+	enum hwtstamp_rx_filters rx_filter;
+	int tx_type_valid = 0;
+	int rx_filter_valid = 0;
+
+	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+		return -EFAULT;
+
+	if (cfg.flags & ~HWTSTAMP_FLAG_MASK)
+		return -EINVAL;
+
+	tx_type = cfg.tx_type;
+	rx_filter = cfg.rx_filter;
+
+	switch (tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+	case HWTSTAMP_TX_ONESTEP_P2P:
+		tx_type_valid = 1;
+		break;
+	case __HWTSTAMP_TX_CNT:
+		/* not a real value */
+		break;
+	}
+
+	switch (rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		rx_filter_valid = 1;
+		break;
+	case __HWTSTAMP_FILTER_CNT:
+		/* not a real value */
+		break;
+	}
+
+	if (!tx_type_valid || !rx_filter_valid)
+		return -ERANGE;
+
+	return 0;
+}
+
+static int dev_eth_ioctl(struct net_device *dev,
+			 struct ifreq *ifr, unsigned int cmd)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int err;
+
+	err = dsa_ndo_eth_ioctl(dev, ifr, cmd);
+	if (err == 0 || err != -EOPNOTSUPP)
+		return err;
+
+	if (ops->ndo_eth_ioctl) {
+		if (netif_device_present(dev))
+			err = ops->ndo_eth_ioctl(dev, ifr, cmd);
+		else
+			err = -ENODEV;
+	}
+
+	return err;
+}
+
+static int dev_siocbond(struct net_device *dev,
+			struct ifreq *ifr, unsigned int cmd)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (ops->ndo_siocbond) {
+		if (netif_device_present(dev))
+			return ops->ndo_siocbond(dev, ifr, cmd);
+		else
+			return -ENODEV;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, unsigned int cmd)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (ops->ndo_siocdevprivate) {
+		if (netif_device_present(dev))
+			return ops->ndo_siocdevprivate(dev, ifr, data, cmd);
+		else
+			return -ENODEV;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (ops->ndo_siocwandev) {
+		if (netif_device_present(dev))
+			return ops->ndo_siocwandev(dev, ifs);
+		else
+			return -ENODEV;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+/*
+ *	Perform the SIOCxIFxxx calls, inside rtnl_lock()
+ */
+static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
+		      unsigned int cmd)
+{
+	int err;
+	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+	const struct net_device_ops *ops;
+	netdevice_tracker dev_tracker;
+
+	if (!dev)
+		return -ENODEV;
+
+	ops = dev->netdev_ops;
+
+	switch (cmd) {
+	case SIOCSIFFLAGS:	/* Set interface flags */
+		return dev_change_flags(dev, ifr->ifr_flags, NULL);
+
+	case SIOCSIFMETRIC:	/* Set the metric on the interface
+				   (currently unused) */
+		return -EOPNOTSUPP;
+
+	case SIOCSIFMTU:	/* Set the MTU of a device */
+		return dev_set_mtu(dev, ifr->ifr_mtu);
+
+	case SIOCSIFHWADDR:
+		if (dev->addr_len > sizeof(struct sockaddr))
+			return -EINVAL;
+		return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL);
+
+	case SIOCSIFHWBROADCAST:
+		if (ifr->ifr_hwaddr.sa_family != dev->type)
+			return -EINVAL;
+		memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+		       min(sizeof(ifr->ifr_hwaddr.sa_data_min),
+			   (size_t)dev->addr_len));
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+		return 0;
+
+	case SIOCSIFMAP:
+		return dev_setifmap(dev, ifr);
+
+	case SIOCADDMULTI:
+		if (!ops->ndo_set_rx_mode ||
+		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+			return -EINVAL;
+		if (!netif_device_present(dev))
+			return -ENODEV;
+		return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
+
+	case SIOCDELMULTI:
+		if (!ops->ndo_set_rx_mode ||
+		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+			return -EINVAL;
+		if (!netif_device_present(dev))
+			return -ENODEV;
+		return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
+
+	case SIOCSIFTXQLEN:
+		if (ifr->ifr_qlen < 0)
+			return -EINVAL;
+		return dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+
+	case SIOCSIFNAME:
+		ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+		return dev_change_name(dev, ifr->ifr_newname);
+
+	case SIOCWANDEV:
+		return dev_siocwandev(dev, &ifr->ifr_settings);
+
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
+		if (!netif_device_present(dev))
+			return -ENODEV;
+		if (!netif_is_bridge_master(dev))
+			return -EOPNOTSUPP;
+		netdev_hold(dev, &dev_tracker, GFP_KERNEL);
+		rtnl_unlock();
+		err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL);
+		netdev_put(dev, &dev_tracker);
+		rtnl_lock();
+		return err;
+
+	case SIOCSHWTSTAMP:
+		err = net_hwtstamp_validate(ifr);
+		if (err)
+			return err;
+		fallthrough;
+
+	/*
+	 *	Unknown or private ioctl
+	 */
+	default:
+		if (cmd >= SIOCDEVPRIVATE &&
+		    cmd <= SIOCDEVPRIVATE + 15)
+			return dev_siocdevprivate(dev, ifr, data, cmd);
+
+		if (cmd == SIOCGMIIPHY ||
+		    cmd == SIOCGMIIREG ||
+		    cmd == SIOCSMIIREG ||
+		    cmd == SIOCSHWTSTAMP ||
+		    cmd == SIOCGHWTSTAMP) {
+			err = dev_eth_ioctl(dev, ifr, cmd);
+		} else if (cmd == SIOCBONDENSLAVE ||
+		    cmd == SIOCBONDRELEASE ||
+		    cmd == SIOCBONDSETHWADDR ||
+		    cmd == SIOCBONDSLAVEINFOQUERY ||
+		    cmd == SIOCBONDINFOQUERY ||
+		    cmd == SIOCBONDCHANGEACTIVE) {
+			err = dev_siocbond(dev, ifr, cmd);
+		} else
+			err = -EINVAL;
+
+	}
+	return err;
+}
+
+/**
+ *	dev_load 	- load a network module
+ *	@net: the applicable net namespace
+ *	@name: name of interface
+ *
+ *	If a network interface is not present and the process has suitable
+ *	privileges this function loads the module. If module loading is not
+ *	available in this kernel then it becomes a nop.
+ */
+
+void dev_load(struct net *net, const char *name)
+{
+	struct net_device *dev;
+	int no_module;
+
+	rcu_read_lock();
+	dev = dev_get_by_name_rcu(net, name);
+	rcu_read_unlock();
+
+	no_module = !dev;
+	if (no_module && capable(CAP_NET_ADMIN))
+		no_module = request_module("netdev-%s", name);
+	if (no_module && capable(CAP_SYS_MODULE))
+		request_module("%s", name);
+}
+EXPORT_SYMBOL(dev_load);
+
+/*
+ *	This function handles all "interface"-type I/O control requests. The actual
+ *	'doing' part of this is dev_ifsioc above.
+ */
+
+/**
+ *	dev_ioctl	-	network device ioctl
+ *	@net: the applicable net namespace
+ *	@cmd: command to issue
+ *	@ifr: pointer to a struct ifreq in user space
+ *	@need_copyout: whether or not copy_to_user() should be called
+ *
+ *	Issue ioctl functions to devices. This is normally called by the
+ *	user space syscall interfaces but can sometimes be useful for
+ *	other purposes. The return value is the return from the syscall if
+ *	positive or a negative errno code on error.
+ */
+
+int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
+	      void __user *data, bool *need_copyout)
+{
+	int ret;
+	char *colon;
+
+	if (need_copyout)
+		*need_copyout = true;
+	if (cmd == SIOCGIFNAME)
+		return dev_ifname(net, ifr);
+
+	ifr->ifr_name[IFNAMSIZ-1] = 0;
+
+	colon = strchr(ifr->ifr_name, ':');
+	if (colon)
+		*colon = 0;
+
+	/*
+	 *	See which interface the caller is talking about.
+	 */
+
+	switch (cmd) {
+	case SIOCGIFHWADDR:
+		dev_load(net, ifr->ifr_name);
+		ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name);
+		if (colon)
+			*colon = ':';
+		return ret;
+	/*
+	 *	These ioctl calls:
+	 *	- can be done by all.
+	 *	- atomic and do not require locking.
+	 *	- return a value
+	 */
+	case SIOCGIFFLAGS:
+	case SIOCGIFMETRIC:
+	case SIOCGIFMTU:
+	case SIOCGIFSLAVE:
+	case SIOCGIFMAP:
+	case SIOCGIFINDEX:
+	case SIOCGIFTXQLEN:
+		dev_load(net, ifr->ifr_name);
+		rcu_read_lock();
+		ret = dev_ifsioc_locked(net, ifr, cmd);
+		rcu_read_unlock();
+		if (colon)
+			*colon = ':';
+		return ret;
+
+	case SIOCETHTOOL:
+		dev_load(net, ifr->ifr_name);
+		ret = dev_ethtool(net, ifr, data);
+		if (colon)
+			*colon = ':';
+		return ret;
+
+	/*
+	 *	These ioctl calls:
+	 *	- require superuser power.
+	 *	- require strict serialization.
+	 *	- return a value
+	 */
+	case SIOCGMIIPHY:
+	case SIOCGMIIREG:
+	case SIOCSIFNAME:
+		dev_load(net, ifr->ifr_name);
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		rtnl_lock();
+		ret = dev_ifsioc(net, ifr, data, cmd);
+		rtnl_unlock();
+		if (colon)
+			*colon = ':';
+		return ret;
+
+	/*
+	 *	These ioctl calls:
+	 *	- require superuser power.
+	 *	- require strict serialization.
+	 *	- do not return a value
+	 */
+	case SIOCSIFMAP:
+	case SIOCSIFTXQLEN:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		fallthrough;
+	/*
+	 *	These ioctl calls:
+	 *	- require local superuser power.
+	 *	- require strict serialization.
+	 *	- do not return a value
+	 */
+	case SIOCSIFFLAGS:
+	case SIOCSIFMETRIC:
+	case SIOCSIFMTU:
+	case SIOCSIFHWADDR:
+	case SIOCSIFSLAVE:
+	case SIOCADDMULTI:
+	case SIOCDELMULTI:
+	case SIOCSIFHWBROADCAST:
+	case SIOCSMIIREG:
+	case SIOCBONDENSLAVE:
+	case SIOCBONDRELEASE:
+	case SIOCBONDSETHWADDR:
+	case SIOCBONDCHANGEACTIVE:
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
+	case SIOCSHWTSTAMP:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		fallthrough;
+	case SIOCBONDSLAVEINFOQUERY:
+	case SIOCBONDINFOQUERY:
+		dev_load(net, ifr->ifr_name);
+		rtnl_lock();
+		ret = dev_ifsioc(net, ifr, data, cmd);
+		rtnl_unlock();
+		if (need_copyout)
+			*need_copyout = false;
+		return ret;
+
+	case SIOCGIFMEM:
+		/* Get the per device memory space. We can add this but
+		 * currently do not support it */
+	case SIOCSIFMEM:
+		/* Set the per device memory buffer space.
+		 * Not applicable in our case */
+	case SIOCSIFLINK:
+		return -ENOTTY;
+
+	/*
+	 *	Unknown or private ioctl.
+	 */
+	default:
+		if (cmd == SIOCWANDEV ||
+		    cmd == SIOCGHWTSTAMP ||
+		    (cmd >= SIOCDEVPRIVATE &&
+		     cmd <= SIOCDEVPRIVATE + 15)) {
+			dev_load(net, ifr->ifr_name);
+			rtnl_lock();
+			ret = dev_ifsioc(net, ifr, data, cmd);
+			rtnl_unlock();
+			return ret;
+		}
+		return -ENOTTY;
+	}
+}