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, 250 insertions, 0 deletions

diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c
new file mode 100644
index 000000000..9717a1626
--- /dev/null
+++ b/drivers/net/phy/bcm84881.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+// Broadcom BCM84881 NBASE-T PHY driver, as found on a SFP+ module.
+// Copyright (C) 2019 Russell King, Deep Blue Solutions Ltd.
+//
+// Like the Marvell 88x3310, the Broadcom 84881 changes its host-side
+// interface according to the operating speed between 10GBASE-R,
+// 2500BASE-X and SGMII (but unlike the 88x3310, without the control
+// word).
+//
+// This driver only supports those aspects of the PHY that I'm able to
+// observe and test with the SFP+ module, which is an incomplete subset
+// of what this PHY is able to support. For example, I only assume it
+// supports a single lane Serdes connection, but it may be that the PHY
+// is able to support more than that.
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+enum {
+	MDIO_AN_C22 = 0xffe0,
+};
+
+static int bcm84881_wait_init(struct phy_device *phydev)
+{
+	int val;
+
+	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1,
+					 val, !(val & MDIO_CTRL1_RESET),
+					 100000, 2000000, false);
+}
+
+static int bcm84881_config_init(struct phy_device *phydev)
+{
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_2500BASEX:
+	case PHY_INTERFACE_MODE_10GBASER:
+		break;
+	default:
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int bcm84881_probe(struct phy_device *phydev)
+{
+	/* This driver requires PMAPMD and AN blocks */
+	const u32 mmd_mask = MDIO_DEVS_PMAPMD | MDIO_DEVS_AN;
+
+	if (!phydev->is_c45 ||
+	    (phydev->c45_ids.devices_in_package & mmd_mask) != mmd_mask)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int bcm84881_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_abilities(phydev);
+	if (ret)
+		return ret;
+
+	/* Although the PHY sets bit 1.11.8, it does not support 10M modes */
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+			   phydev->supported);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+			   phydev->supported);
+
+	return 0;
+}
+
+static int bcm84881_config_aneg(struct phy_device *phydev)
+{
+	bool changed = false;
+	u32 adv;
+	int ret;
+
+	/* Wait for the PHY to finish initialising, otherwise our
+	 * advertisement may be overwritten.
+	 */
+	ret = bcm84881_wait_init(phydev);
+	if (ret)
+		return ret;
+
+	/* We don't support manual MDI control */
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
+	/* disabled autoneg doesn't seem to work with this PHY */
+	if (phydev->autoneg == AUTONEG_DISABLE)
+		return -EINVAL;
+
+	ret = genphy_c45_an_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
+	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN,
+				     MDIO_AN_C22 + MII_CTRL1000,
+				     ADVERTISE_1000FULL | ADVERTISE_1000HALF,
+				     adv);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	return genphy_c45_check_and_restart_aneg(phydev, changed);
+}
+
+static int bcm84881_aneg_done(struct phy_device *phydev)
+{
+	int bmsr, val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+	if (val < 0)
+		return val;
+
+	bmsr = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_C22 + MII_BMSR);
+	if (bmsr < 0)
+		return val;
+
+	return !!(val & MDIO_AN_STAT1_COMPLETE) &&
+	       !!(bmsr & BMSR_ANEGCOMPLETE);
+}
+
+static int bcm84881_read_status(struct phy_device *phydev)
+{
+	unsigned int mode;
+	int bmsr, val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+	if (val < 0)
+		return val;
+
+	if (val & MDIO_AN_CTRL1_RESTART) {
+		phydev->link = 0;
+		return 0;
+	}
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+	if (val < 0)
+		return val;
+
+	bmsr = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_C22 + MII_BMSR);
+	if (bmsr < 0)
+		return val;
+
+	phydev->autoneg_complete = !!(val & MDIO_AN_STAT1_COMPLETE) &&
+				   !!(bmsr & BMSR_ANEGCOMPLETE);
+	phydev->link = !!(val & MDIO_STAT1_LSTATUS) &&
+		       !!(bmsr & BMSR_LSTATUS);
+	if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete)
+		phydev->link = false;
+
+	linkmode_zero(phydev->lp_advertising);
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+	phydev->mdix = 0;
+
+	if (!phydev->link)
+		return 0;
+
+	if (phydev->autoneg_complete) {
+		val = genphy_c45_read_lpa(phydev);
+		if (val < 0)
+			return val;
+
+		val = phy_read_mmd(phydev, MDIO_MMD_AN,
+				   MDIO_AN_C22 + MII_STAT1000);
+		if (val < 0)
+			return val;
+
+		mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val);
+
+		if (phydev->autoneg == AUTONEG_ENABLE)
+			phy_resolve_aneg_linkmode(phydev);
+	}
+
+	if (phydev->autoneg == AUTONEG_DISABLE) {
+		/* disabled autoneg doesn't seem to work, so force the link
+		 * down.
+		 */
+		phydev->link = 0;
+		return 0;
+	}
+
+	/* Set the host link mode - we set the phy interface mode and
+	 * the speed according to this register so that downshift works.
+	 * We leave the duplex setting as per the resolution from the
+	 * above.
+	 */
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND1, 0x4011);
+	mode = (val & 0x1e) >> 1;
+	if (mode == 1 || mode == 2)
+		phydev->interface = PHY_INTERFACE_MODE_SGMII;
+	else if (mode == 3)
+		phydev->interface = PHY_INTERFACE_MODE_10GBASER;
+	else if (mode == 4)
+		phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+	switch (mode & 7) {
+	case 1:
+		phydev->speed = SPEED_100;
+		break;
+	case 2:
+		phydev->speed = SPEED_1000;
+		break;
+	case 3:
+		phydev->speed = SPEED_10000;
+		break;
+	case 4:
+		phydev->speed = SPEED_2500;
+		break;
+	case 5:
+		phydev->speed = SPEED_5000;
+		break;
+	}
+
+	return genphy_c45_read_mdix(phydev);
+}
+
+static struct phy_driver bcm84881_drivers[] = {
+	{
+		.phy_id		= 0xae025150,
+		.phy_id_mask	= 0xfffffff0,
+		.name		= "Broadcom BCM84881",
+		.config_init	= bcm84881_config_init,
+		.probe		= bcm84881_probe,
+		.get_features	= bcm84881_get_features,
+		.config_aneg	= bcm84881_config_aneg,
+		.aneg_done	= bcm84881_aneg_done,
+		.read_status	= bcm84881_read_status,
+	},
+};
+
+module_phy_driver(bcm84881_drivers);
+
+/* FIXME: module auto-loading for Clause 45 PHYs seems non-functional */
+static struct mdio_device_id __maybe_unused bcm84881_tbl[] = {
+	{ 0xae025150, 0xfffffff0 },
+	{ },
+};
+MODULE_AUTHOR("Russell King");
+MODULE_DESCRIPTION("Broadcom BCM84881 PHY driver");
+MODULE_DEVICE_TABLE(mdio, bcm84881_tbl);
+MODULE_LICENSE("GPL");