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, 352 insertions, 0 deletions

diff --git a/drivers/net/mdio/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c
new file mode 100644
index 000000000..956d54846
--- /dev/null
+++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2016 Broadcom
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/iopoll.h>
+#include <linux/mdio-mux.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+
+#define MDIO_RATE_ADJ_EXT_OFFSET	0x000
+#define MDIO_RATE_ADJ_INT_OFFSET	0x004
+#define MDIO_RATE_ADJ_DIVIDENT_SHIFT	16
+
+#define MDIO_SCAN_CTRL_OFFSET		0x008
+#define MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR	28
+
+#define MDIO_PARAM_OFFSET		0x23c
+#define MDIO_PARAM_MIIM_CYCLE		29
+#define MDIO_PARAM_INTERNAL_SEL		25
+#define MDIO_PARAM_BUS_ID		22
+#define MDIO_PARAM_C45_SEL		21
+#define MDIO_PARAM_PHY_ID		16
+#define MDIO_PARAM_PHY_DATA		0
+
+#define MDIO_READ_OFFSET		0x240
+#define MDIO_READ_DATA_MASK		0xffff
+#define MDIO_ADDR_OFFSET		0x244
+
+#define MDIO_CTRL_OFFSET		0x248
+#define MDIO_CTRL_WRITE_OP		0x1
+#define MDIO_CTRL_READ_OP		0x2
+
+#define MDIO_STAT_OFFSET		0x24c
+#define MDIO_STAT_DONE			1
+
+#define BUS_MAX_ADDR			32
+#define EXT_BUS_START_ADDR		16
+
+#define MDIO_REG_ADDR_SPACE_SIZE	0x250
+
+#define MDIO_OPERATING_FREQUENCY	11000000
+#define MDIO_RATE_ADJ_DIVIDENT		1
+
+struct iproc_mdiomux_desc {
+	void *mux_handle;
+	void __iomem *base;
+	struct device *dev;
+	struct mii_bus *mii_bus;
+	struct clk *core_clk;
+};
+
+static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md)
+{
+	u32 divisor;
+	u32 val;
+
+	/* Disable external mdio master access */
+	val = readl(md->base + MDIO_SCAN_CTRL_OFFSET);
+	val |= BIT(MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR);
+	writel(val, md->base + MDIO_SCAN_CTRL_OFFSET);
+
+	if (md->core_clk) {
+		/* use rate adjust regs to derive the mdio's operating
+		 * frequency from the specified core clock
+		 */
+		divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY;
+		divisor = divisor / (MDIO_RATE_ADJ_DIVIDENT + 1);
+		val = divisor;
+		val |= MDIO_RATE_ADJ_DIVIDENT << MDIO_RATE_ADJ_DIVIDENT_SHIFT;
+		writel(val, md->base + MDIO_RATE_ADJ_EXT_OFFSET);
+		writel(val, md->base + MDIO_RATE_ADJ_INT_OFFSET);
+	}
+}
+
+static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
+{
+	u32 val;
+
+	return readl_poll_timeout(base + MDIO_STAT_OFFSET, val,
+				  (val & MDIO_STAT_DONE) == result,
+				  2000, 1000000);
+}
+
+/* start_miim_ops- Program and start MDIO transaction over mdio bus.
+ * @base: Base address
+ * @phyid: phyid of the selected bus.
+ * @reg: register offset to be read/written.
+ * @val :0 if read op else value to be written in @reg;
+ * @op: Operation that need to be carried out.
+ *      MDIO_CTRL_READ_OP: Read transaction.
+ *      MDIO_CTRL_WRITE_OP: Write transaction.
+ *
+ * Return value: Successful Read operation returns read reg values and write
+ *      operation returns 0. Failure operation returns negative error code.
+ */
+static int start_miim_ops(void __iomem *base, bool c45,
+			  u16 phyid, u32 reg, u16 val, u32 op)
+{
+	u32 param;
+	int ret;
+
+	writel(0, base + MDIO_CTRL_OFFSET);
+	ret = iproc_mdio_wait_for_idle(base, 0);
+	if (ret)
+		goto err;
+
+	param = readl(base + MDIO_PARAM_OFFSET);
+	param |= phyid << MDIO_PARAM_PHY_ID;
+	param |= val << MDIO_PARAM_PHY_DATA;
+	if (c45)
+		param |= BIT(MDIO_PARAM_C45_SEL);
+
+	writel(param, base + MDIO_PARAM_OFFSET);
+
+	writel(reg, base + MDIO_ADDR_OFFSET);
+
+	writel(op, base + MDIO_CTRL_OFFSET);
+
+	ret = iproc_mdio_wait_for_idle(base, 1);
+	if (ret)
+		goto err;
+
+	if (op == MDIO_CTRL_READ_OP)
+		ret = readl(base + MDIO_READ_OFFSET) & MDIO_READ_DATA_MASK;
+err:
+	return ret;
+}
+
+static int iproc_mdiomux_read_c22(struct mii_bus *bus, int phyid, int reg)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	ret = start_miim_ops(md->base, false, phyid, reg, 0, MDIO_CTRL_READ_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux c22 read operation failed!!!");
+
+	return ret;
+}
+
+static int iproc_mdiomux_read_c45(struct mii_bus *bus, int phyid, int devad,
+				  int reg)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	ret = start_miim_ops(md->base, true, phyid, reg | devad << 16, 0,
+			     MDIO_CTRL_READ_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux read c45 operation failed!!!");
+
+	return ret;
+}
+
+static int iproc_mdiomux_write_c22(struct mii_bus *bus,
+				   int phyid, int reg, u16 val)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	/* Write val at reg offset */
+	ret = start_miim_ops(md->base, false, phyid, reg, val,
+			     MDIO_CTRL_WRITE_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux write c22 operation failed!!!");
+
+	return ret;
+}
+
+static int iproc_mdiomux_write_c45(struct mii_bus *bus,
+				   int phyid, int devad, int reg, u16 val)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	/* Write val at reg offset */
+	ret = start_miim_ops(md->base, true, phyid, reg | devad << 16, val,
+			     MDIO_CTRL_WRITE_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux write c45 operation failed!!!");
+
+	return ret;
+}
+
+static int mdio_mux_iproc_switch_fn(int current_child, int desired_child,
+				    void *data)
+{
+	struct iproc_mdiomux_desc *md = data;
+	u32 param, bus_id;
+	bool bus_dir;
+
+	/* select bus and its properties */
+	bus_dir = (desired_child < EXT_BUS_START_ADDR);
+	bus_id = bus_dir ? desired_child : (desired_child - EXT_BUS_START_ADDR);
+
+	param = (bus_dir ? 1 : 0) << MDIO_PARAM_INTERNAL_SEL;
+	param |= (bus_id << MDIO_PARAM_BUS_ID);
+
+	writel(param, md->base + MDIO_PARAM_OFFSET);
+	return 0;
+}
+
+static int mdio_mux_iproc_probe(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md;
+	struct mii_bus *bus;
+	struct resource *res;
+	int rc;
+
+	md = devm_kzalloc(&pdev->dev, sizeof(*md), GFP_KERNEL);
+	if (!md)
+		return -ENOMEM;
+	md->dev = &pdev->dev;
+
+	md->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(md->base))
+		return PTR_ERR(md->base);
+	if (res->start & 0xfff) {
+		/* For backward compatibility in case the
+		 * base address is specified with an offset.
+		 */
+		dev_info(&pdev->dev, "fix base address in dt-blob\n");
+		res->start &= ~0xfff;
+		res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1;
+	}
+
+	md->mii_bus = devm_mdiobus_alloc(&pdev->dev);
+	if (!md->mii_bus) {
+		dev_err(&pdev->dev, "mdiomux bus alloc failed\n");
+		return -ENOMEM;
+	}
+
+	md->core_clk = devm_clk_get(&pdev->dev, NULL);
+	if (md->core_clk == ERR_PTR(-ENOENT) ||
+	    md->core_clk == ERR_PTR(-EINVAL))
+		md->core_clk = NULL;
+	else if (IS_ERR(md->core_clk))
+		return PTR_ERR(md->core_clk);
+
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to enable core clk\n");
+		return rc;
+	}
+
+	bus = md->mii_bus;
+	bus->priv = md;
+	bus->name = "iProc MDIO mux bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id);
+	bus->parent = &pdev->dev;
+	bus->read = iproc_mdiomux_read_c22;
+	bus->write = iproc_mdiomux_write_c22;
+	bus->read_c45 = iproc_mdiomux_read_c45;
+	bus->write_c45 = iproc_mdiomux_write_c45;
+
+	bus->phy_mask = ~0;
+	bus->dev.of_node = pdev->dev.of_node;
+	rc = mdiobus_register(bus);
+	if (rc) {
+		dev_err(&pdev->dev, "mdiomux registration failed\n");
+		goto out_clk;
+	}
+
+	platform_set_drvdata(pdev, md);
+
+	rc = mdio_mux_init(md->dev, md->dev->of_node, mdio_mux_iproc_switch_fn,
+			   &md->mux_handle, md, md->mii_bus);
+	if (rc) {
+		dev_info(md->dev, "mdiomux initialization failed\n");
+		goto out_register;
+	}
+
+	mdio_mux_iproc_config(md);
+
+	dev_info(md->dev, "iProc mdiomux registered\n");
+	return 0;
+
+out_register:
+	mdiobus_unregister(bus);
+out_clk:
+	clk_disable_unprepare(md->core_clk);
+	return rc;
+}
+
+static int mdio_mux_iproc_remove(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+
+	mdio_mux_uninit(md->mux_handle);
+	mdiobus_unregister(md->mii_bus);
+	clk_disable_unprepare(md->core_clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mdio_mux_iproc_suspend(struct device *dev)
+{
+	struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(md->core_clk);
+
+	return 0;
+}
+
+static int mdio_mux_iproc_resume(struct device *dev)
+{
+	struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
+	int rc;
+
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(md->dev, "failed to enable core clk\n");
+		return rc;
+	}
+	mdio_mux_iproc_config(md);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mdio_mux_iproc_pm_ops,
+			 mdio_mux_iproc_suspend, mdio_mux_iproc_resume);
+
+static const struct of_device_id mdio_mux_iproc_match[] = {
+	{
+		.compatible = "brcm,mdio-mux-iproc",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mdio_mux_iproc_match);
+
+static struct platform_driver mdiomux_iproc_driver = {
+	.driver = {
+		.name		= "mdio-mux-iproc",
+		.of_match_table = mdio_mux_iproc_match,
+		.pm		= &mdio_mux_iproc_pm_ops,
+	},
+	.probe		= mdio_mux_iproc_probe,
+	.remove		= mdio_mux_iproc_remove,
+};
+
+module_platform_driver(mdiomux_iproc_driver);
+
+MODULE_DESCRIPTION("iProc MDIO Mux Bus Driver");
+MODULE_AUTHOR("Pramod Kumar <pramod.kumar@broadcom.com>");
+MODULE_LICENSE("GPL v2");