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, 274 insertions, 0 deletions

diff --git a/drivers/watchdog/tegra_wdt.c b/drivers/watchdog/tegra_wdt.c
new file mode 100644
index 000000000..d5de6c065
--- /dev/null
+++ b/drivers/watchdog/tegra_wdt.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/watchdog.h>
+
+/* minimum and maximum watchdog trigger timeout, in seconds */
+#define MIN_WDT_TIMEOUT			1
+#define MAX_WDT_TIMEOUT			255
+
+/*
+ * Base of the WDT registers, from the timer base address.  There are
+ * actually 5 watchdogs that can be configured (by pairing with an available
+ * timer), at bases 0x100 + (WDT ID) * 0x20, where WDT ID is 0 through 4.
+ * This driver only configures the first watchdog (WDT ID 0).
+ */
+#define WDT_BASE			0x100
+#define WDT_ID				0
+
+/*
+ * Register base of the timer that's selected for pairing with the watchdog.
+ * This driver arbitrarily uses timer 5, which is currently unused by
+ * other drivers (in particular, the Tegra clocksource driver).  If this
+ * needs to change, take care that the new timer is not used by the
+ * clocksource driver.
+ */
+#define WDT_TIMER_BASE			0x60
+#define WDT_TIMER_ID			5
+
+/* WDT registers */
+#define WDT_CFG				0x0
+#define WDT_CFG_PERIOD_SHIFT		4
+#define WDT_CFG_PERIOD_MASK		0xff
+#define WDT_CFG_INT_EN			(1 << 12)
+#define WDT_CFG_PMC2CAR_RST_EN		(1 << 15)
+#define WDT_STS				0x4
+#define WDT_STS_COUNT_SHIFT		4
+#define WDT_STS_COUNT_MASK		0xff
+#define WDT_STS_EXP_SHIFT		12
+#define WDT_STS_EXP_MASK		0x3
+#define WDT_CMD				0x8
+#define WDT_CMD_START_COUNTER		(1 << 0)
+#define WDT_CMD_DISABLE_COUNTER		(1 << 1)
+#define WDT_UNLOCK			(0xc)
+#define WDT_UNLOCK_PATTERN		(0xc45a << 0)
+
+/* Timer registers */
+#define TIMER_PTV			0x0
+#define TIMER_EN			(1 << 31)
+#define TIMER_PERIODIC			(1 << 30)
+
+struct tegra_wdt {
+	struct watchdog_device	wdd;
+	void __iomem		*wdt_regs;
+	void __iomem		*tmr_regs;
+};
+
+#define WDT_HEARTBEAT 120
+static int heartbeat = WDT_HEARTBEAT;
+module_param(heartbeat, int, 0);
+MODULE_PARM_DESC(heartbeat,
+	"Watchdog heartbeats in seconds. (default = "
+	__MODULE_STRING(WDT_HEARTBEAT) ")");
+
+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) ")");
+
+static int tegra_wdt_start(struct watchdog_device *wdd)
+{
+	struct tegra_wdt *wdt = watchdog_get_drvdata(wdd);
+	u32 val;
+
+	/*
+	 * This thing has a fixed 1MHz clock.  Normally, we would set the
+	 * period to 1 second by writing 1000000ul, but the watchdog system
+	 * reset actually occurs on the 4th expiration of this counter,
+	 * so we set the period to 1/4 of this amount.
+	 */
+	val = 1000000ul / 4;
+	val |= (TIMER_EN | TIMER_PERIODIC);
+	writel(val, wdt->tmr_regs + TIMER_PTV);
+
+	/*
+	 * Set number of periods and start counter.
+	 *
+	 * Interrupt handler is not required for user space
+	 * WDT accesses, since the caller is responsible to ping the
+	 * WDT to reset the counter before expiration, through ioctls.
+	 */
+	val = WDT_TIMER_ID |
+	      (wdd->timeout << WDT_CFG_PERIOD_SHIFT) |
+	      WDT_CFG_PMC2CAR_RST_EN;
+	writel(val, wdt->wdt_regs + WDT_CFG);
+
+	writel(WDT_CMD_START_COUNTER, wdt->wdt_regs + WDT_CMD);
+
+	return 0;
+}
+
+static int tegra_wdt_stop(struct watchdog_device *wdd)
+{
+	struct tegra_wdt *wdt = watchdog_get_drvdata(wdd);
+
+	writel(WDT_UNLOCK_PATTERN, wdt->wdt_regs + WDT_UNLOCK);
+	writel(WDT_CMD_DISABLE_COUNTER, wdt->wdt_regs + WDT_CMD);
+	writel(0, wdt->tmr_regs + TIMER_PTV);
+
+	return 0;
+}
+
+static int tegra_wdt_ping(struct watchdog_device *wdd)
+{
+	struct tegra_wdt *wdt = watchdog_get_drvdata(wdd);
+
+	writel(WDT_CMD_START_COUNTER, wdt->wdt_regs + WDT_CMD);
+
+	return 0;
+}
+
+static int tegra_wdt_set_timeout(struct watchdog_device *wdd,
+				 unsigned int timeout)
+{
+	wdd->timeout = timeout;
+
+	if (watchdog_active(wdd)) {
+		tegra_wdt_stop(wdd);
+		return tegra_wdt_start(wdd);
+	}
+
+	return 0;
+}
+
+static unsigned int tegra_wdt_get_timeleft(struct watchdog_device *wdd)
+{
+	struct tegra_wdt *wdt = watchdog_get_drvdata(wdd);
+	u32 val;
+	int count;
+	int exp;
+
+	val = readl(wdt->wdt_regs + WDT_STS);
+
+	/* Current countdown (from timeout) */
+	count = (val >> WDT_STS_COUNT_SHIFT) & WDT_STS_COUNT_MASK;
+
+	/* Number of expirations (we are waiting for the 4th expiration) */
+	exp = (val >> WDT_STS_EXP_SHIFT) & WDT_STS_EXP_MASK;
+
+	/*
+	 * The entire thing is divided by 4 because we are ticking down 4 times
+	 * faster due to needing to wait for the 4th expiration.
+	 */
+	return (((3 - exp) * wdd->timeout) + count) / 4;
+}
+
+static const struct watchdog_info tegra_wdt_info = {
+	.options	= WDIOF_SETTIMEOUT |
+			  WDIOF_MAGICCLOSE |
+			  WDIOF_KEEPALIVEPING,
+	.firmware_version = 0,
+	.identity	= "Tegra Watchdog",
+};
+
+static const struct watchdog_ops tegra_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = tegra_wdt_start,
+	.stop = tegra_wdt_stop,
+	.ping = tegra_wdt_ping,
+	.set_timeout = tegra_wdt_set_timeout,
+	.get_timeleft = tegra_wdt_get_timeleft,
+};
+
+static int tegra_wdt_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct watchdog_device *wdd;
+	struct tegra_wdt *wdt;
+	void __iomem *regs;
+	int ret;
+
+	/* This is the timer base. */
+	regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	/*
+	 * Allocate our watchdog driver data, which has the
+	 * struct watchdog_device nested within it.
+	 */
+	wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	/* Initialize struct tegra_wdt. */
+	wdt->wdt_regs = regs + WDT_BASE;
+	wdt->tmr_regs = regs + WDT_TIMER_BASE;
+
+	/* Initialize struct watchdog_device. */
+	wdd = &wdt->wdd;
+	wdd->timeout = heartbeat;
+	wdd->info = &tegra_wdt_info;
+	wdd->ops = &tegra_wdt_ops;
+	wdd->min_timeout = MIN_WDT_TIMEOUT;
+	wdd->max_timeout = MAX_WDT_TIMEOUT;
+	wdd->parent = dev;
+
+	watchdog_set_drvdata(wdd, wdt);
+
+	watchdog_set_nowayout(wdd, nowayout);
+
+	watchdog_stop_on_unregister(wdd);
+	ret = devm_watchdog_register_device(dev, wdd);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, wdt);
+
+	dev_info(dev, "initialized (heartbeat = %d sec, nowayout = %d)\n",
+		 heartbeat, nowayout);
+
+	return 0;
+}
+
+static int tegra_wdt_suspend(struct device *dev)
+{
+	struct tegra_wdt *wdt = dev_get_drvdata(dev);
+
+	if (watchdog_active(&wdt->wdd))
+		tegra_wdt_stop(&wdt->wdd);
+
+	return 0;
+}
+
+static int tegra_wdt_resume(struct device *dev)
+{
+	struct tegra_wdt *wdt = dev_get_drvdata(dev);
+
+	if (watchdog_active(&wdt->wdd))
+		tegra_wdt_start(&wdt->wdd);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_wdt_of_match[] = {
+	{ .compatible = "nvidia,tegra30-timer", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra_wdt_of_match);
+
+static DEFINE_SIMPLE_DEV_PM_OPS(tegra_wdt_pm_ops,
+				tegra_wdt_suspend, tegra_wdt_resume);
+
+static struct platform_driver tegra_wdt_driver = {
+	.probe		= tegra_wdt_probe,
+	.driver		= {
+		.name	= "tegra-wdt",
+		.pm	= pm_sleep_ptr(&tegra_wdt_pm_ops),
+		.of_match_table = tegra_wdt_of_match,
+	},
+};
+module_platform_driver(tegra_wdt_driver);
+
+MODULE_AUTHOR("NVIDIA Corporation");
+MODULE_DESCRIPTION("Tegra Watchdog Driver");
+MODULE_LICENSE("GPL v2");