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, 265 insertions, 0 deletions

diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c
new file mode 100644
index 000000000..1a5d1e8eb
--- /dev/null
+++ b/arch/m68k/emu/nfeth.c
@@ -0,0 +1,265 @@
+/*
+ * atari_nfeth.c - ARAnyM ethernet card driver for GNU/Linux
+ *
+ * Copyright (c) 2005 Milan Jurik, Petr Stehlik of ARAnyM dev team
+ *
+ * Based on ARAnyM driver for FreeMiNT written by Standa Opichal
+ *
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ */
+
+#define DRV_VERSION	"0.3"
+#define DRV_RELDATE	"10/12/2005"
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <asm/natfeat.h>
+#include <asm/virtconvert.h>
+
+enum {
+	GET_VERSION = 0,/* no parameters, return NFAPI_VERSION in d0 */
+	XIF_INTLEVEL,	/* no parameters, return Interrupt Level in d0 */
+	XIF_IRQ,	/* acknowledge interrupt from host */
+	XIF_START,	/* (ethX), called on 'ifup', start receiver thread */
+	XIF_STOP,	/* (ethX), called on 'ifdown', stop the thread */
+	XIF_READLENGTH,	/* (ethX), return size of network data block to read */
+	XIF_READBLOCK,	/* (ethX, buffer, size), read block of network data */
+	XIF_WRITEBLOCK,	/* (ethX, buffer, size), write block of network data */
+	XIF_GET_MAC,	/* (ethX, buffer, size), return MAC HW addr in buffer */
+	XIF_GET_IPHOST,	/* (ethX, buffer, size), return IP address of host */
+	XIF_GET_IPATARI,/* (ethX, buffer, size), return IP address of atari */
+	XIF_GET_NETMASK	/* (ethX, buffer, size), return IP netmask */
+};
+
+#define MAX_UNIT	8
+
+/* These identify the driver base version and may not be removed. */
+static const char version[] =
+	KERN_INFO KBUILD_MODNAME ".c:v" DRV_VERSION " " DRV_RELDATE
+	" S.Opichal, M.Jurik, P.Stehlik\n"
+	KERN_INFO " http://aranym.org/\n";
+
+MODULE_AUTHOR("Milan Jurik");
+MODULE_DESCRIPTION("Atari NFeth driver");
+MODULE_LICENSE("GPL");
+
+
+static long nfEtherID;
+static int nfEtherIRQ;
+
+struct nfeth_private {
+	int ethX;
+};
+
+static struct net_device *nfeth_dev[MAX_UNIT];
+
+static int nfeth_open(struct net_device *dev)
+{
+	struct nfeth_private *priv = netdev_priv(dev);
+	int res;
+
+	res = nf_call(nfEtherID + XIF_START, priv->ethX);
+	netdev_dbg(dev, "%s: %d\n", __func__, res);
+
+	/* Ready for data */
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+static int nfeth_stop(struct net_device *dev)
+{
+	struct nfeth_private *priv = netdev_priv(dev);
+
+	/* No more data */
+	netif_stop_queue(dev);
+
+	nf_call(nfEtherID + XIF_STOP, priv->ethX);
+
+	return 0;
+}
+
+/*
+ * Read a packet out of the adapter and pass it to the upper layers
+ */
+static inline void recv_packet(struct net_device *dev)
+{
+	struct nfeth_private *priv = netdev_priv(dev);
+	unsigned short pktlen;
+	struct sk_buff *skb;
+
+	/* read packet length (excluding 32 bit crc) */
+	pktlen = nf_call(nfEtherID + XIF_READLENGTH, priv->ethX);
+
+	netdev_dbg(dev, "%s: %u\n", __func__, pktlen);
+
+	if (!pktlen) {
+		netdev_dbg(dev, "%s: pktlen == 0\n", __func__);
+		dev->stats.rx_errors++;
+		return;
+	}
+
+	skb = dev_alloc_skb(pktlen + 2);
+	if (!skb) {
+		netdev_dbg(dev, "%s: out of mem (buf_alloc failed)\n",
+			   __func__);
+		dev->stats.rx_dropped++;
+		return;
+	}
+
+	skb->dev = dev;
+	skb_reserve(skb, 2);		/* 16 Byte align  */
+	skb_put(skb, pktlen);		/* make room */
+	nf_call(nfEtherID + XIF_READBLOCK, priv->ethX, virt_to_phys(skb->data),
+		pktlen);
+
+	skb->protocol = eth_type_trans(skb, dev);
+	netif_rx(skb);
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += pktlen;
+
+	/* and enqueue packet */
+	return;
+}
+
+static irqreturn_t nfeth_interrupt(int irq, void *dev_id)
+{
+	int i, m, mask;
+
+	mask = nf_call(nfEtherID + XIF_IRQ, 0);
+	for (i = 0, m = 1; i < MAX_UNIT; m <<= 1, i++) {
+		if (mask & m && nfeth_dev[i]) {
+			recv_packet(nfeth_dev[i]);
+			nf_call(nfEtherID + XIF_IRQ, m);
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static int nfeth_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	unsigned int len;
+	char *data, shortpkt[ETH_ZLEN];
+	struct nfeth_private *priv = netdev_priv(dev);
+
+	data = skb->data;
+	len = skb->len;
+	if (len < ETH_ZLEN) {
+		memset(shortpkt, 0, ETH_ZLEN);
+		memcpy(shortpkt, data, len);
+		data = shortpkt;
+		len = ETH_ZLEN;
+	}
+
+	netdev_dbg(dev, "%s: send %u bytes\n", __func__, len);
+	nf_call(nfEtherID + XIF_WRITEBLOCK, priv->ethX, virt_to_phys(data),
+		len);
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += len;
+
+	dev_kfree_skb(skb);
+	return 0;
+}
+
+static void nfeth_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	dev->stats.tx_errors++;
+	netif_wake_queue(dev);
+}
+
+static const struct net_device_ops nfeth_netdev_ops = {
+	.ndo_open		= nfeth_open,
+	.ndo_stop		= nfeth_stop,
+	.ndo_start_xmit		= nfeth_xmit,
+	.ndo_tx_timeout		= nfeth_tx_timeout,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
+};
+
+static struct net_device * __init nfeth_probe(int unit)
+{
+	struct net_device *dev;
+	struct nfeth_private *priv;
+	char mac[ETH_ALEN], host_ip[32], local_ip[32];
+	int err;
+
+	if (!nf_call(nfEtherID + XIF_GET_MAC, unit, virt_to_phys(mac),
+		     ETH_ALEN))
+		return NULL;
+
+	dev = alloc_etherdev(sizeof(struct nfeth_private));
+	if (!dev)
+		return NULL;
+
+	dev->irq = nfEtherIRQ;
+	dev->netdev_ops = &nfeth_netdev_ops;
+
+	eth_hw_addr_set(dev, mac);
+
+	priv = netdev_priv(dev);
+	priv->ethX = unit;
+
+	err = register_netdev(dev);
+	if (err) {
+		free_netdev(dev);
+		return NULL;
+	}
+
+	nf_call(nfEtherID + XIF_GET_IPHOST, unit,
+		virt_to_phys(host_ip), sizeof(host_ip));
+	nf_call(nfEtherID + XIF_GET_IPATARI, unit,
+		virt_to_phys(local_ip), sizeof(local_ip));
+
+	netdev_info(dev, KBUILD_MODNAME " addr:%s (%s) HWaddr:%pM\n", host_ip,
+		    local_ip, mac);
+
+	return dev;
+}
+
+static int __init nfeth_init(void)
+{
+	long ver;
+	int error, i;
+
+	nfEtherID = nf_get_id("ETHERNET");
+	if (!nfEtherID)
+		return -ENODEV;
+
+	ver = nf_call(nfEtherID + GET_VERSION);
+	pr_info("API %lu\n", ver);
+
+	nfEtherIRQ = nf_call(nfEtherID + XIF_INTLEVEL);
+	error = request_irq(nfEtherIRQ, nfeth_interrupt, IRQF_SHARED,
+			    "eth emu", nfeth_interrupt);
+	if (error) {
+		pr_err("request for irq %d failed %d", nfEtherIRQ, error);
+		return error;
+	}
+
+	for (i = 0; i < MAX_UNIT; i++)
+		nfeth_dev[i] = nfeth_probe(i);
+
+	return 0;
+}
+
+static void __exit nfeth_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_UNIT; i++) {
+		if (nfeth_dev[i]) {
+			unregister_netdev(nfeth_dev[i]);
+			free_netdev(nfeth_dev[i]);
+		}
+	}
+	free_irq(nfEtherIRQ, nfeth_interrupt);
+}
+
+module_init(nfeth_init);
+module_exit(nfeth_cleanup);