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, 326 insertions, 0 deletions

diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c
new file mode 100644
index 000000000..e74802f3a
--- /dev/null
+++ b/drivers/watchdog/rc32434_wdt.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  IDT Interprise 79RC32434 watchdog driver
+ *
+ *  Copyright (C) 2006, Ondrej Zajicek <santiago@crfreenet.org>
+ *  Copyright (C) 2008, Florian Fainelli <florian@openwrt.org>
+ *
+ *  based on
+ *  SoftDog 0.05:	A Software Watchdog Device
+ *
+ *  (c) Copyright 1996 Alan Cox <alan@lxorguk.ukuu.org.uk>,
+ *					All Rights Reserved.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>		/* For module specific items */
+#include <linux/moduleparam.h>		/* For new moduleparam's */
+#include <linux/types.h>		/* For standard types (like size_t) */
+#include <linux/errno.h>		/* For the -ENODEV/... values */
+#include <linux/kernel.h>		/* For printk/panic/... */
+#include <linux/fs.h>			/* For file operations */
+#include <linux/miscdevice.h>		/* For struct miscdevice */
+#include <linux/watchdog.h>		/* For the watchdog specific items */
+#include <linux/init.h>			/* For __init/__exit/... */
+#include <linux/platform_device.h>	/* For platform_driver framework */
+#include <linux/spinlock.h>		/* For spin_lock/spin_unlock/... */
+#include <linux/uaccess.h>		/* For copy_to_user/put_user/... */
+#include <linux/io.h>			/* For devm_ioremap */
+
+#include <asm/mach-rc32434/integ.h>	/* For the Watchdog registers */
+
+#define VERSION "1.0"
+
+static struct {
+	unsigned long inuse;
+	spinlock_t io_lock;
+} rc32434_wdt_device;
+
+static struct integ __iomem *wdt_reg;
+
+static int expect_close;
+
+/* Board internal clock speed in Hz,
+ * the watchdog timer ticks at. */
+extern unsigned int idt_cpu_freq;
+
+/* translate wtcompare value to seconds and vice versa */
+#define WTCOMP2SEC(x)	(x / idt_cpu_freq)
+#define SEC2WTCOMP(x)	(x * idt_cpu_freq)
+
+/* Use a default timeout of 20s. This should be
+ * safe for CPU clock speeds up to 400MHz, as
+ * ((2 ^ 32) - 1) / (400MHz / 2) = 21s.  */
+#define WATCHDOG_TIMEOUT 20
+
+static int timeout = WATCHDOG_TIMEOUT;
+module_param(timeout, int, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout value, in seconds (default="
+		__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+/* apply or and nand masks to data read from addr and write back */
+#define SET_BITS(addr, or, nand) \
+	writel((readl(&addr) | or) & ~nand, &addr)
+
+static int rc32434_wdt_set(int new_timeout)
+{
+	int max_to = WTCOMP2SEC((u32)-1);
+
+	if (new_timeout < 0 || new_timeout > max_to) {
+		pr_err("timeout value must be between 0 and %d\n", max_to);
+		return -EINVAL;
+	}
+	timeout = new_timeout;
+	spin_lock(&rc32434_wdt_device.io_lock);
+	writel(SEC2WTCOMP(timeout), &wdt_reg->wtcompare);
+	spin_unlock(&rc32434_wdt_device.io_lock);
+
+	return 0;
+}
+
+static void rc32434_wdt_start(void)
+{
+	u32 or, nand;
+
+	spin_lock(&rc32434_wdt_device.io_lock);
+
+	/* zero the counter before enabling */
+	writel(0, &wdt_reg->wtcount);
+
+	/* don't generate a non-maskable interrupt,
+	 * do a warm reset instead */
+	nand = 1 << RC32434_ERR_WNE;
+	or = 1 << RC32434_ERR_WRE;
+
+	/* reset the ERRCS timeout bit in case it's set */
+	nand |= 1 << RC32434_ERR_WTO;
+
+	SET_BITS(wdt_reg->errcs, or, nand);
+
+	/* set the timeout (either default or based on module param) */
+	rc32434_wdt_set(timeout);
+
+	/* reset WTC timeout bit and enable WDT */
+	nand = 1 << RC32434_WTC_TO;
+	or = 1 << RC32434_WTC_EN;
+
+	SET_BITS(wdt_reg->wtc, or, nand);
+
+	spin_unlock(&rc32434_wdt_device.io_lock);
+	pr_info("Started watchdog timer\n");
+}
+
+static void rc32434_wdt_stop(void)
+{
+	spin_lock(&rc32434_wdt_device.io_lock);
+
+	/* Disable WDT */
+	SET_BITS(wdt_reg->wtc, 0, 1 << RC32434_WTC_EN);
+
+	spin_unlock(&rc32434_wdt_device.io_lock);
+	pr_info("Stopped watchdog timer\n");
+}
+
+static void rc32434_wdt_ping(void)
+{
+	spin_lock(&rc32434_wdt_device.io_lock);
+	writel(0, &wdt_reg->wtcount);
+	spin_unlock(&rc32434_wdt_device.io_lock);
+}
+
+static int rc32434_wdt_open(struct inode *inode, struct file *file)
+{
+	if (test_and_set_bit(0, &rc32434_wdt_device.inuse))
+		return -EBUSY;
+
+	if (nowayout)
+		__module_get(THIS_MODULE);
+
+	rc32434_wdt_start();
+	rc32434_wdt_ping();
+
+	return stream_open(inode, file);
+}
+
+static int rc32434_wdt_release(struct inode *inode, struct file *file)
+{
+	if (expect_close == 42) {
+		rc32434_wdt_stop();
+		module_put(THIS_MODULE);
+	} else {
+		pr_crit("device closed unexpectedly. WDT will not stop!\n");
+		rc32434_wdt_ping();
+	}
+	clear_bit(0, &rc32434_wdt_device.inuse);
+	return 0;
+}
+
+static ssize_t rc32434_wdt_write(struct file *file, const char *data,
+				size_t len, loff_t *ppos)
+{
+	if (len) {
+		if (!nowayout) {
+			size_t i;
+
+			/* In case it was set long ago */
+			expect_close = 0;
+
+			for (i = 0; i != len; i++) {
+				char c;
+				if (get_user(c, data + i))
+					return -EFAULT;
+				if (c == 'V')
+					expect_close = 42;
+			}
+		}
+		rc32434_wdt_ping();
+		return len;
+	}
+	return 0;
+}
+
+static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	int new_timeout;
+	unsigned int value;
+	static const struct watchdog_info ident = {
+		.options =		WDIOF_SETTIMEOUT |
+					WDIOF_KEEPALIVEPING |
+					WDIOF_MAGICCLOSE,
+		.identity =		"RC32434_WDT Watchdog",
+	};
+	switch (cmd) {
+	case WDIOC_GETSUPPORT:
+		if (copy_to_user(argp, &ident, sizeof(ident)))
+			return -EFAULT;
+		break;
+	case WDIOC_GETSTATUS:
+	case WDIOC_GETBOOTSTATUS:
+		value = 0;
+		if (copy_to_user(argp, &value, sizeof(int)))
+			return -EFAULT;
+		break;
+	case WDIOC_SETOPTIONS:
+		if (copy_from_user(&value, argp, sizeof(int)))
+			return -EFAULT;
+		switch (value) {
+		case WDIOS_ENABLECARD:
+			rc32434_wdt_start();
+			break;
+		case WDIOS_DISABLECARD:
+			rc32434_wdt_stop();
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case WDIOC_KEEPALIVE:
+		rc32434_wdt_ping();
+		break;
+	case WDIOC_SETTIMEOUT:
+		if (copy_from_user(&new_timeout, argp, sizeof(int)))
+			return -EFAULT;
+		if (rc32434_wdt_set(new_timeout))
+			return -EINVAL;
+		fallthrough;
+	case WDIOC_GETTIMEOUT:
+		return copy_to_user(argp, &timeout, sizeof(int)) ? -EFAULT : 0;
+	default:
+		return -ENOTTY;
+	}
+
+	return 0;
+}
+
+static const struct file_operations rc32434_wdt_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.write		= rc32434_wdt_write,
+	.unlocked_ioctl	= rc32434_wdt_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.open		= rc32434_wdt_open,
+	.release	= rc32434_wdt_release,
+};
+
+static struct miscdevice rc32434_wdt_miscdev = {
+	.minor	= WATCHDOG_MINOR,
+	.name	= "watchdog",
+	.fops	= &rc32434_wdt_fops,
+};
+
+static int rc32434_wdt_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct resource *r;
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rb532_wdt_res");
+	if (!r) {
+		pr_err("failed to retrieve resources\n");
+		return -ENODEV;
+	}
+
+	wdt_reg = devm_ioremap(&pdev->dev, r->start, resource_size(r));
+	if (!wdt_reg) {
+		pr_err("failed to remap I/O resources\n");
+		return -ENXIO;
+	}
+
+	spin_lock_init(&rc32434_wdt_device.io_lock);
+
+	/* Make sure the watchdog is not running */
+	rc32434_wdt_stop();
+
+	/* Check that the heartbeat value is within it's range;
+	 * if not reset to the default */
+	if (rc32434_wdt_set(timeout)) {
+		rc32434_wdt_set(WATCHDOG_TIMEOUT);
+		pr_info("timeout value must be between 0 and %d\n",
+			WTCOMP2SEC((u32)-1));
+	}
+
+	ret = misc_register(&rc32434_wdt_miscdev);
+	if (ret < 0) {
+		pr_err("failed to register watchdog device\n");
+		return ret;
+	}
+
+	pr_info("Watchdog Timer version " VERSION ", timer margin: %d sec\n",
+		timeout);
+
+	return 0;
+}
+
+static int rc32434_wdt_remove(struct platform_device *pdev)
+{
+	misc_deregister(&rc32434_wdt_miscdev);
+	return 0;
+}
+
+static void rc32434_wdt_shutdown(struct platform_device *pdev)
+{
+	rc32434_wdt_stop();
+}
+
+static struct platform_driver rc32434_wdt_driver = {
+	.probe		= rc32434_wdt_probe,
+	.remove		= rc32434_wdt_remove,
+	.shutdown	= rc32434_wdt_shutdown,
+	.driver		= {
+			.name = "rc32434_wdt",
+	}
+};
+
+module_platform_driver(rc32434_wdt_driver);
+
+MODULE_AUTHOR("Ondrej Zajicek <santiago@crfreenet.org>,"
+		"Florian Fainelli <florian@openwrt.org>");
+MODULE_DESCRIPTION("Driver for the IDT RC32434 SoC watchdog");
+MODULE_LICENSE("GPL");