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, 344 insertions, 0 deletions

diff --git a/drivers/watchdog/shwdt.c b/drivers/watchdog/shwdt.c
new file mode 100644
index 000000000..f55533e0e
--- /dev/null
+++ b/drivers/watchdog/shwdt.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * drivers/watchdog/shwdt.c
+ *
+ * Watchdog driver for integrated watchdog in the SuperH processors.
+ *
+ * Copyright (C) 2001 - 2012  Paul Mundt <lethal@linux-sh.org>
+ *
+ * 14-Dec-2001 Matt Domsch <Matt_Domsch@dell.com>
+ *     Added nowayout module option to override CONFIG_WATCHDOG_NOWAYOUT
+ *
+ * 19-Apr-2002 Rob Radez <rob@osinvestor.com>
+ *     Added expect close support, made emulated timeout runtime changeable
+ *     general cleanups, add some ioctls
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/watchdog.h>
+#include <linux/pm_runtime.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <asm/watchdog.h>
+
+#define DRV_NAME "sh-wdt"
+
+/*
+ * Default clock division ratio is 5.25 msecs. For an additional table of
+ * values, consult the asm-sh/watchdog.h. Overload this at module load
+ * time.
+ *
+ * In order for this to work reliably we need to have HZ set to 1000 or
+ * something quite higher than 100 (or we need a proper high-res timer
+ * implementation that will deal with this properly), otherwise the 10ms
+ * resolution of a jiffy is enough to trigger the overflow. For things like
+ * the SH-4 and SH-5, this isn't necessarily that big of a problem, though
+ * for the SH-2 and SH-3, this isn't recommended unless the WDT is absolutely
+ * necssary.
+ *
+ * As a result of this timing problem, the only modes that are particularly
+ * feasible are the 4096 and the 2048 divisors, which yield 5.25 and 2.62ms
+ * overflow periods respectively.
+ *
+ * Also, since we can't really expect userspace to be responsive enough
+ * before the overflow happens, we maintain two separate timers .. One in
+ * the kernel for clearing out WOVF every 2ms or so (again, this depends on
+ * HZ == 1000), and another for monitoring userspace writes to the WDT device.
+ *
+ * As such, we currently use a configurable heartbeat interval which defaults
+ * to 30s. In this case, the userspace daemon is only responsible for periodic
+ * writes to the device before the next heartbeat is scheduled. If the daemon
+ * misses its deadline, the kernel timer will allow the WDT to overflow.
+ */
+static int clock_division_ratio = WTCSR_CKS_4096;
+#define next_ping_period(cks)	(jiffies + msecs_to_jiffies(cks - 4))
+
+#define WATCHDOG_HEARTBEAT 30			/* 30 sec default heartbeat */
+static int heartbeat = WATCHDOG_HEARTBEAT;	/* in seconds */
+static bool nowayout = WATCHDOG_NOWAYOUT;
+static unsigned long next_heartbeat;
+
+struct sh_wdt {
+	void __iomem		*base;
+	struct device		*dev;
+	struct clk		*clk;
+	spinlock_t		lock;
+
+	struct timer_list	timer;
+};
+
+static int sh_wdt_start(struct watchdog_device *wdt_dev)
+{
+	struct sh_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+	unsigned long flags;
+	u8 csr;
+
+	pm_runtime_get_sync(wdt->dev);
+	clk_enable(wdt->clk);
+
+	spin_lock_irqsave(&wdt->lock, flags);
+
+	next_heartbeat = jiffies + (heartbeat * HZ);
+	mod_timer(&wdt->timer, next_ping_period(clock_division_ratio));
+
+	csr = sh_wdt_read_csr();
+	csr |= WTCSR_WT | clock_division_ratio;
+	sh_wdt_write_csr(csr);
+
+	sh_wdt_write_cnt(0);
+
+	/*
+	 * These processors have a bit of an inconsistent initialization
+	 * process.. starting with SH-3, RSTS was moved to WTCSR, and the
+	 * RSTCSR register was removed.
+	 *
+	 * On the SH-2 however, in addition with bits being in different
+	 * locations, we must deal with RSTCSR outright..
+	 */
+	csr = sh_wdt_read_csr();
+	csr |= WTCSR_TME;
+	csr &= ~WTCSR_RSTS;
+	sh_wdt_write_csr(csr);
+
+#ifdef CONFIG_CPU_SH2
+	csr = sh_wdt_read_rstcsr();
+	csr &= ~RSTCSR_RSTS;
+	sh_wdt_write_rstcsr(csr);
+#endif
+	spin_unlock_irqrestore(&wdt->lock, flags);
+
+	return 0;
+}
+
+static int sh_wdt_stop(struct watchdog_device *wdt_dev)
+{
+	struct sh_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+	unsigned long flags;
+	u8 csr;
+
+	spin_lock_irqsave(&wdt->lock, flags);
+
+	del_timer(&wdt->timer);
+
+	csr = sh_wdt_read_csr();
+	csr &= ~WTCSR_TME;
+	sh_wdt_write_csr(csr);
+
+	spin_unlock_irqrestore(&wdt->lock, flags);
+
+	clk_disable(wdt->clk);
+	pm_runtime_put_sync(wdt->dev);
+
+	return 0;
+}
+
+static int sh_wdt_keepalive(struct watchdog_device *wdt_dev)
+{
+	struct sh_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&wdt->lock, flags);
+	next_heartbeat = jiffies + (heartbeat * HZ);
+	spin_unlock_irqrestore(&wdt->lock, flags);
+
+	return 0;
+}
+
+static int sh_wdt_set_heartbeat(struct watchdog_device *wdt_dev, unsigned t)
+{
+	struct sh_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+	unsigned long flags;
+
+	if (unlikely(t < 1 || t > 3600)) /* arbitrary upper limit */
+		return -EINVAL;
+
+	spin_lock_irqsave(&wdt->lock, flags);
+	heartbeat = t;
+	wdt_dev->timeout = t;
+	spin_unlock_irqrestore(&wdt->lock, flags);
+
+	return 0;
+}
+
+static void sh_wdt_ping(struct timer_list *t)
+{
+	struct sh_wdt *wdt = from_timer(wdt, t, timer);
+	unsigned long flags;
+
+	spin_lock_irqsave(&wdt->lock, flags);
+	if (time_before(jiffies, next_heartbeat)) {
+		u8 csr;
+
+		csr = sh_wdt_read_csr();
+		csr &= ~WTCSR_IOVF;
+		sh_wdt_write_csr(csr);
+
+		sh_wdt_write_cnt(0);
+
+		mod_timer(&wdt->timer, next_ping_period(clock_division_ratio));
+	} else
+		dev_warn(wdt->dev, "Heartbeat lost! Will not ping "
+		         "the watchdog\n");
+	spin_unlock_irqrestore(&wdt->lock, flags);
+}
+
+static const struct watchdog_info sh_wdt_info = {
+	.options		= WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+				  WDIOF_MAGICCLOSE,
+	.firmware_version	= 1,
+	.identity		= "SH WDT",
+};
+
+static const struct watchdog_ops sh_wdt_ops = {
+	.owner		= THIS_MODULE,
+	.start		= sh_wdt_start,
+	.stop		= sh_wdt_stop,
+	.ping		= sh_wdt_keepalive,
+	.set_timeout	= sh_wdt_set_heartbeat,
+};
+
+static struct watchdog_device sh_wdt_dev = {
+	.info	= &sh_wdt_info,
+	.ops	= &sh_wdt_ops,
+};
+
+static int sh_wdt_probe(struct platform_device *pdev)
+{
+	struct sh_wdt *wdt;
+	int rc;
+
+	/*
+	 * As this driver only covers the global watchdog case, reject
+	 * any attempts to register per-CPU watchdogs.
+	 */
+	if (pdev->id != -1)
+		return -EINVAL;
+
+	wdt = devm_kzalloc(&pdev->dev, sizeof(struct sh_wdt), GFP_KERNEL);
+	if (unlikely(!wdt))
+		return -ENOMEM;
+
+	wdt->dev = &pdev->dev;
+
+	wdt->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(wdt->clk)) {
+		/*
+		 * Clock framework support is optional, continue on
+		 * anyways if we don't find a matching clock.
+		 */
+		wdt->clk = NULL;
+	}
+
+	wdt->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(wdt->base))
+		return PTR_ERR(wdt->base);
+
+	watchdog_set_nowayout(&sh_wdt_dev, nowayout);
+	watchdog_set_drvdata(&sh_wdt_dev, wdt);
+	sh_wdt_dev.parent = &pdev->dev;
+
+	spin_lock_init(&wdt->lock);
+
+	rc = sh_wdt_set_heartbeat(&sh_wdt_dev, heartbeat);
+	if (unlikely(rc)) {
+		/* Default timeout if invalid */
+		sh_wdt_set_heartbeat(&sh_wdt_dev, WATCHDOG_HEARTBEAT);
+
+		dev_warn(&pdev->dev,
+			 "heartbeat value must be 1<=x<=3600, using %d\n",
+			 sh_wdt_dev.timeout);
+	}
+
+	dev_info(&pdev->dev, "configured with heartbeat=%d sec (nowayout=%d)\n",
+		 sh_wdt_dev.timeout, nowayout);
+
+	rc = watchdog_register_device(&sh_wdt_dev);
+	if (unlikely(rc)) {
+		dev_err(&pdev->dev, "Can't register watchdog (err=%d)\n", rc);
+		return rc;
+	}
+
+	timer_setup(&wdt->timer, sh_wdt_ping, 0);
+	wdt->timer.expires	= next_ping_period(clock_division_ratio);
+
+	dev_info(&pdev->dev, "initialized.\n");
+
+	pm_runtime_enable(&pdev->dev);
+
+	return 0;
+}
+
+static int sh_wdt_remove(struct platform_device *pdev)
+{
+	watchdog_unregister_device(&sh_wdt_dev);
+
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static void sh_wdt_shutdown(struct platform_device *pdev)
+{
+	sh_wdt_stop(&sh_wdt_dev);
+}
+
+static struct platform_driver sh_wdt_driver = {
+	.driver		= {
+		.name	= DRV_NAME,
+	},
+
+	.probe		= sh_wdt_probe,
+	.remove		= sh_wdt_remove,
+	.shutdown	= sh_wdt_shutdown,
+};
+
+static int __init sh_wdt_init(void)
+{
+	if (unlikely(clock_division_ratio < 0x5 ||
+		     clock_division_ratio > 0x7)) {
+		clock_division_ratio = WTCSR_CKS_4096;
+
+		pr_info("divisor must be 0x5<=x<=0x7, using %d\n",
+			clock_division_ratio);
+	}
+
+	return platform_driver_register(&sh_wdt_driver);
+}
+
+static void __exit sh_wdt_exit(void)
+{
+	platform_driver_unregister(&sh_wdt_driver);
+}
+module_init(sh_wdt_init);
+module_exit(sh_wdt_exit);
+
+MODULE_AUTHOR("Paul Mundt <lethal@linux-sh.org>");
+MODULE_DESCRIPTION("SuperH watchdog driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRV_NAME);
+
+module_param(clock_division_ratio, int, 0);
+MODULE_PARM_DESC(clock_division_ratio,
+	"Clock division ratio. Valid ranges are from 0x5 (1.31ms) "
+	"to 0x7 (5.25ms). (default=" __MODULE_STRING(WTCSR_CKS_4096) ")");
+
+module_param(heartbeat, int, 0);
+MODULE_PARM_DESC(heartbeat,
+	"Watchdog heartbeat in seconds. (1 <= heartbeat <= 3600, default="
+				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
+
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout,
+	"Watchdog cannot be stopped once started (default="
+				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");