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, 453 insertions, 0 deletions

diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c
new file mode 100644
index 000000000..73f2221f6
--- /dev/null
+++ b/drivers/watchdog/machzwd.c
@@ -0,0 +1,453 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  MachZ ZF-Logic Watchdog Timer driver for Linux
+ *
+ *  The author does NOT admit liability nor provide warranty for
+ *  any of this software. This material is provided "AS-IS" in
+ *  the hope that it may be useful for others.
+ *
+ *  Author: Fernando Fuganti <fuganti@conectiva.com.br>
+ *
+ *  Based on sbc60xxwdt.c by Jakob Oestergaard
+ *
+ *  We have two timers (wd#1, wd#2) driven by a 32 KHz clock with the
+ *  following periods:
+ *      wd#1 - 2 seconds;
+ *      wd#2 - 7.2 ms;
+ *  After the expiration of wd#1, it can generate a NMI, SCI, SMI, or
+ *  a system RESET and it starts wd#2 that unconditionally will RESET
+ *  the system when the counter reaches zero.
+ *
+ *  14-Dec-2001 Matt Domsch <Matt_Domsch@dell.com>
+ *      Added nowayout module option to override CONFIG_WATCHDOG_NOWAYOUT
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/jiffies.h>
+#include <linux/miscdevice.h>
+#include <linux/watchdog.h>
+#include <linux/fs.h>
+#include <linux/ioport.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+
+
+/* ports */
+#define ZF_IOBASE	0x218
+#define INDEX		0x218
+#define DATA_B		0x219
+#define DATA_W		0x21A
+#define DATA_D		0x21A
+
+/* indexes */			/* size */
+#define ZFL_VERSION	0x02	/* 16   */
+#define CONTROL		0x10	/* 16   */
+#define STATUS		0x12	/* 8    */
+#define COUNTER_1	0x0C	/* 16   */
+#define COUNTER_2	0x0E	/* 8    */
+#define PULSE_LEN	0x0F	/* 8    */
+
+/* controls */
+#define ENABLE_WD1	0x0001
+#define ENABLE_WD2	0x0002
+#define RESET_WD1	0x0010
+#define RESET_WD2	0x0020
+#define GEN_SCI		0x0100
+#define GEN_NMI		0x0200
+#define GEN_SMI		0x0400
+#define GEN_RESET	0x0800
+
+
+/* utilities */
+
+#define WD1	0
+#define WD2	1
+
+#define zf_writew(port, data)  { outb(port, INDEX); outw(data, DATA_W); }
+#define zf_writeb(port, data)  { outb(port, INDEX); outb(data, DATA_B); }
+#define zf_get_ZFL_version()   zf_readw(ZFL_VERSION)
+
+
+static unsigned short zf_readw(unsigned char port)
+{
+	outb(port, INDEX);
+	return inw(DATA_W);
+}
+
+
+MODULE_AUTHOR("Fernando Fuganti <fuganti@conectiva.com.br>");
+MODULE_DESCRIPTION("MachZ ZF-Logic Watchdog driver");
+MODULE_LICENSE("GPL");
+
+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) ")");
+
+#define PFX "machzwd"
+
+static const struct watchdog_info zf_info = {
+	.options		= WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+	.firmware_version	= 1,
+	.identity		= "ZF-Logic watchdog",
+};
+
+
+/*
+ * action refers to action taken when watchdog resets
+ * 0 = GEN_RESET
+ * 1 = GEN_SMI
+ * 2 = GEN_NMI
+ * 3 = GEN_SCI
+ * defaults to GEN_RESET (0)
+ */
+static int action;
+module_param(action, int, 0);
+MODULE_PARM_DESC(action, "after watchdog resets, generate: "
+				"0 = RESET(*)  1 = SMI  2 = NMI  3 = SCI");
+
+static void zf_ping(struct timer_list *unused);
+
+static int zf_action = GEN_RESET;
+static unsigned long zf_is_open;
+static char zf_expect_close;
+static DEFINE_SPINLOCK(zf_port_lock);
+static DEFINE_TIMER(zf_timer, zf_ping);
+static unsigned long next_heartbeat;
+
+
+/* timeout for user land heart beat (10 seconds) */
+#define ZF_USER_TIMEO (HZ*10)
+
+/* timeout for hardware watchdog (~500ms) */
+#define ZF_HW_TIMEO (HZ/2)
+
+/* number of ticks on WD#1 (driven by a 32KHz clock, 2s) */
+#define ZF_CTIMEOUT 0xffff
+
+#ifndef ZF_DEBUG
+#define dprintk(format, args...)
+#else
+#define dprintk(format, args...)					\
+	pr_debug(":%s:%d: " format, __func__, __LINE__ , ## args)
+#endif
+
+
+static inline void zf_set_status(unsigned char new)
+{
+	zf_writeb(STATUS, new);
+}
+
+
+/* CONTROL register functions */
+
+static inline unsigned short zf_get_control(void)
+{
+	return zf_readw(CONTROL);
+}
+
+static inline void zf_set_control(unsigned short new)
+{
+	zf_writew(CONTROL, new);
+}
+
+
+/* WD#? counter functions */
+/*
+ *	Just set counter value
+ */
+
+static inline void zf_set_timer(unsigned short new, unsigned char n)
+{
+	switch (n) {
+	case WD1:
+		zf_writew(COUNTER_1, new);
+		fallthrough;
+	case WD2:
+		zf_writeb(COUNTER_2, new > 0xff ? 0xff : new);
+		fallthrough;
+	default:
+		return;
+	}
+}
+
+/*
+ * stop hardware timer
+ */
+static void zf_timer_off(void)
+{
+	unsigned int ctrl_reg = 0;
+	unsigned long flags;
+
+	/* stop internal ping */
+	del_timer_sync(&zf_timer);
+
+	spin_lock_irqsave(&zf_port_lock, flags);
+	/* stop watchdog timer */
+	ctrl_reg = zf_get_control();
+	ctrl_reg |= (ENABLE_WD1|ENABLE_WD2);	/* disable wd1 and wd2 */
+	ctrl_reg &= ~(ENABLE_WD1|ENABLE_WD2);
+	zf_set_control(ctrl_reg);
+	spin_unlock_irqrestore(&zf_port_lock, flags);
+
+	pr_info("Watchdog timer is now disabled\n");
+}
+
+
+/*
+ * start hardware timer
+ */
+static void zf_timer_on(void)
+{
+	unsigned int ctrl_reg = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&zf_port_lock, flags);
+
+	zf_writeb(PULSE_LEN, 0xff);
+
+	zf_set_timer(ZF_CTIMEOUT, WD1);
+
+	/* user land ping */
+	next_heartbeat = jiffies + ZF_USER_TIMEO;
+
+	/* start the timer for internal ping */
+	mod_timer(&zf_timer, jiffies + ZF_HW_TIMEO);
+
+	/* start watchdog timer */
+	ctrl_reg = zf_get_control();
+	ctrl_reg |= (ENABLE_WD1|zf_action);
+	zf_set_control(ctrl_reg);
+	spin_unlock_irqrestore(&zf_port_lock, flags);
+
+	pr_info("Watchdog timer is now enabled\n");
+}
+
+
+static void zf_ping(struct timer_list *unused)
+{
+	unsigned int ctrl_reg = 0;
+	unsigned long flags;
+
+	zf_writeb(COUNTER_2, 0xff);
+
+	if (time_before(jiffies, next_heartbeat)) {
+		dprintk("time_before: %ld\n", next_heartbeat - jiffies);
+		/*
+		 * reset event is activated by transition from 0 to 1 on
+		 * RESET_WD1 bit and we assume that it is already zero...
+		 */
+
+		spin_lock_irqsave(&zf_port_lock, flags);
+		ctrl_reg = zf_get_control();
+		ctrl_reg |= RESET_WD1;
+		zf_set_control(ctrl_reg);
+
+		/* ...and nothing changes until here */
+		ctrl_reg &= ~(RESET_WD1);
+		zf_set_control(ctrl_reg);
+		spin_unlock_irqrestore(&zf_port_lock, flags);
+
+		mod_timer(&zf_timer, jiffies + ZF_HW_TIMEO);
+	} else
+		pr_crit("I will reset your machine\n");
+}
+
+static ssize_t zf_write(struct file *file, const char __user *buf, size_t count,
+								loff_t *ppos)
+{
+	/* See if we got the magic character */
+	if (count) {
+		/*
+		 * no need to check for close confirmation
+		 * no way to disable watchdog ;)
+		 */
+		if (!nowayout) {
+			size_t ofs;
+			/*
+			 * note: just in case someone wrote the magic character
+			 * five months ago...
+			 */
+			zf_expect_close = 0;
+
+			/* now scan */
+			for (ofs = 0; ofs != count; ofs++) {
+				char c;
+				if (get_user(c, buf + ofs))
+					return -EFAULT;
+				if (c == 'V') {
+					zf_expect_close = 42;
+					dprintk("zf_expect_close = 42\n");
+				}
+			}
+		}
+
+		/*
+		 * Well, anyhow someone wrote to us,
+		 * we should return that favour
+		 */
+		next_heartbeat = jiffies + ZF_USER_TIMEO;
+		dprintk("user ping at %ld\n", jiffies);
+	}
+	return count;
+}
+
+static long zf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	int __user *p = argp;
+	switch (cmd) {
+	case WDIOC_GETSUPPORT:
+		if (copy_to_user(argp, &zf_info, sizeof(zf_info)))
+			return -EFAULT;
+		break;
+	case WDIOC_GETSTATUS:
+	case WDIOC_GETBOOTSTATUS:
+		return put_user(0, p);
+	case WDIOC_KEEPALIVE:
+		zf_ping(NULL);
+		break;
+	default:
+		return -ENOTTY;
+	}
+	return 0;
+}
+
+static int zf_open(struct inode *inode, struct file *file)
+{
+	if (test_and_set_bit(0, &zf_is_open))
+		return -EBUSY;
+	if (nowayout)
+		__module_get(THIS_MODULE);
+	zf_timer_on();
+	return stream_open(inode, file);
+}
+
+static int zf_close(struct inode *inode, struct file *file)
+{
+	if (zf_expect_close == 42)
+		zf_timer_off();
+	else {
+		del_timer(&zf_timer);
+		pr_err("device file closed unexpectedly. Will not stop the WDT!\n");
+	}
+	clear_bit(0, &zf_is_open);
+	zf_expect_close = 0;
+	return 0;
+}
+
+/*
+ * Notifier for system down
+ */
+
+static int zf_notify_sys(struct notifier_block *this, unsigned long code,
+								void *unused)
+{
+	if (code == SYS_DOWN || code == SYS_HALT)
+		zf_timer_off();
+	return NOTIFY_DONE;
+}
+
+static const struct file_operations zf_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.write		= zf_write,
+	.unlocked_ioctl = zf_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.open		= zf_open,
+	.release	= zf_close,
+};
+
+static struct miscdevice zf_miscdev = {
+	.minor = WATCHDOG_MINOR,
+	.name = "watchdog",
+	.fops = &zf_fops,
+};
+
+
+/*
+ * The device needs to learn about soft shutdowns in order to
+ * turn the timebomb registers off.
+ */
+static struct notifier_block zf_notifier = {
+	.notifier_call = zf_notify_sys,
+};
+
+static void __init zf_show_action(int act)
+{
+	static const char * const str[] = { "RESET", "SMI", "NMI", "SCI" };
+
+	pr_info("Watchdog using action = %s\n", str[act]);
+}
+
+static int __init zf_init(void)
+{
+	int ret;
+
+	pr_info("MachZ ZF-Logic Watchdog driver initializing\n");
+
+	ret = zf_get_ZFL_version();
+	if (!ret || ret == 0xffff) {
+		pr_warn("no ZF-Logic found\n");
+		return -ENODEV;
+	}
+
+	if (action <= 3 && action >= 0)
+		zf_action = zf_action >> action;
+	else
+		action = 0;
+
+	zf_show_action(action);
+
+	if (!request_region(ZF_IOBASE, 3, "MachZ ZFL WDT")) {
+		pr_err("cannot reserve I/O ports at %d\n", ZF_IOBASE);
+		ret = -EBUSY;
+		goto no_region;
+	}
+
+	ret = register_reboot_notifier(&zf_notifier);
+	if (ret) {
+		pr_err("can't register reboot notifier (err=%d)\n", ret);
+		goto no_reboot;
+	}
+
+	ret = misc_register(&zf_miscdev);
+	if (ret) {
+		pr_err("can't misc_register on minor=%d\n", WATCHDOG_MINOR);
+		goto no_misc;
+	}
+
+	zf_set_status(0);
+	zf_set_control(0);
+
+	return 0;
+
+no_misc:
+	unregister_reboot_notifier(&zf_notifier);
+no_reboot:
+	release_region(ZF_IOBASE, 3);
+no_region:
+	return ret;
+}
+
+
+static void __exit zf_exit(void)
+{
+	zf_timer_off();
+
+	misc_deregister(&zf_miscdev);
+	unregister_reboot_notifier(&zf_notifier);
+	release_region(ZF_IOBASE, 3);
+}
+
+module_init(zf_init);
+module_exit(zf_exit);