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, 317 insertions, 0 deletions

diff --git a/drivers/watchdog/ie6xx_wdt.c b/drivers/watchdog/ie6xx_wdt.c
new file mode 100644
index 000000000..8f28993fa
--- /dev/null
+++ b/drivers/watchdog/ie6xx_wdt.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *      Intel Atom E6xx Watchdog driver
+ *
+ *      Copyright (C) 2011 Alexander Stein
+ *                <alexander.stein@systec-electronic.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/watchdog.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/spinlock.h>
+
+#define DRIVER_NAME "ie6xx_wdt"
+
+#define PV1	0x00
+#define PV2	0x04
+
+#define RR0	0x0c
+#define RR1	0x0d
+#define WDT_RELOAD	0x01
+#define WDT_TOUT	0x02
+
+#define WDTCR	0x10
+#define WDT_PRE_SEL	0x04
+#define WDT_RESET_SEL	0x08
+#define WDT_RESET_EN	0x10
+#define WDT_TOUT_EN	0x20
+
+#define DCR	0x14
+
+#define WDTLR	0x18
+#define WDT_LOCK	0x01
+#define WDT_ENABLE	0x02
+#define WDT_TOUT_CNF	0x03
+
+#define MIN_TIME	1
+#define MAX_TIME	(10 * 60) /* 10 minutes */
+#define DEFAULT_TIME	60
+
+static unsigned int timeout = DEFAULT_TIME;
+module_param(timeout, uint, 0);
+MODULE_PARM_DESC(timeout,
+		"Default Watchdog timer setting ("
+		__MODULE_STRING(DEFAULT_TIME) "s)."
+		"The range is from 1 to 600");
+
+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 u8 resetmode = 0x10;
+module_param(resetmode, byte, 0);
+MODULE_PARM_DESC(resetmode,
+	"Resetmode bits: 0x08 warm reset (cold reset otherwise), "
+	"0x10 reset enable, 0x20 disable toggle GPIO[4] (default=0x10)");
+
+static struct {
+	unsigned short sch_wdtba;
+	spinlock_t unlock_sequence;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs;
+#endif
+} ie6xx_wdt_data;
+
+/*
+ * This is needed to write to preload and reload registers
+ * struct ie6xx_wdt_data.unlock_sequence must be used
+ * to prevent sequence interrupts
+ */
+static void ie6xx_wdt_unlock_registers(void)
+{
+	outb(0x80, ie6xx_wdt_data.sch_wdtba + RR0);
+	outb(0x86, ie6xx_wdt_data.sch_wdtba + RR0);
+}
+
+static int ie6xx_wdt_ping(struct watchdog_device *wdd)
+{
+	spin_lock(&ie6xx_wdt_data.unlock_sequence);
+	ie6xx_wdt_unlock_registers();
+	outb(WDT_RELOAD, ie6xx_wdt_data.sch_wdtba + RR1);
+	spin_unlock(&ie6xx_wdt_data.unlock_sequence);
+	return 0;
+}
+
+static int ie6xx_wdt_set_timeout(struct watchdog_device *wdd, unsigned int t)
+{
+	u32 preload;
+	u64 clock;
+	u8 wdtcr;
+
+	/* Watchdog clock is PCI Clock (33MHz) */
+	clock = 33000000;
+	/* and the preload value is loaded into [34:15] of the down counter */
+	preload = (t * clock) >> 15;
+	/*
+	 * Manual states preload must be one less.
+	 * Does not wrap as t is at least 1
+	 */
+	preload -= 1;
+
+	spin_lock(&ie6xx_wdt_data.unlock_sequence);
+
+	/* Set ResetMode & Enable prescaler for range 10ms to 10 min */
+	wdtcr = resetmode & 0x38;
+	outb(wdtcr, ie6xx_wdt_data.sch_wdtba + WDTCR);
+
+	ie6xx_wdt_unlock_registers();
+	outl(0, ie6xx_wdt_data.sch_wdtba + PV1);
+
+	ie6xx_wdt_unlock_registers();
+	outl(preload, ie6xx_wdt_data.sch_wdtba + PV2);
+
+	ie6xx_wdt_unlock_registers();
+	outb(WDT_RELOAD | WDT_TOUT, ie6xx_wdt_data.sch_wdtba + RR1);
+
+	spin_unlock(&ie6xx_wdt_data.unlock_sequence);
+
+	wdd->timeout = t;
+	return 0;
+}
+
+static int ie6xx_wdt_start(struct watchdog_device *wdd)
+{
+	ie6xx_wdt_set_timeout(wdd, wdd->timeout);
+
+	/* Enable the watchdog timer */
+	spin_lock(&ie6xx_wdt_data.unlock_sequence);
+	outb(WDT_ENABLE, ie6xx_wdt_data.sch_wdtba + WDTLR);
+	spin_unlock(&ie6xx_wdt_data.unlock_sequence);
+
+	return 0;
+}
+
+static int ie6xx_wdt_stop(struct watchdog_device *wdd)
+{
+	if (inb(ie6xx_wdt_data.sch_wdtba + WDTLR) & WDT_LOCK)
+		return -1;
+
+	/* Disable the watchdog timer */
+	spin_lock(&ie6xx_wdt_data.unlock_sequence);
+	outb(0, ie6xx_wdt_data.sch_wdtba + WDTLR);
+	spin_unlock(&ie6xx_wdt_data.unlock_sequence);
+
+	return 0;
+}
+
+static const struct watchdog_info ie6xx_wdt_info = {
+	.identity =	"Intel Atom E6xx Watchdog",
+	.options =	WDIOF_SETTIMEOUT |
+			WDIOF_MAGICCLOSE |
+			WDIOF_KEEPALIVEPING,
+};
+
+static const struct watchdog_ops ie6xx_wdt_ops = {
+	.owner =	THIS_MODULE,
+	.start =	ie6xx_wdt_start,
+	.stop =		ie6xx_wdt_stop,
+	.ping =		ie6xx_wdt_ping,
+	.set_timeout =	ie6xx_wdt_set_timeout,
+};
+
+static struct watchdog_device ie6xx_wdt_dev = {
+	.info =		&ie6xx_wdt_info,
+	.ops =		&ie6xx_wdt_ops,
+	.min_timeout =	MIN_TIME,
+	.max_timeout =	MAX_TIME,
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+static int ie6xx_wdt_show(struct seq_file *s, void *unused)
+{
+	seq_printf(s, "PV1   = 0x%08x\n",
+		inl(ie6xx_wdt_data.sch_wdtba + PV1));
+	seq_printf(s, "PV2   = 0x%08x\n",
+		inl(ie6xx_wdt_data.sch_wdtba + PV2));
+	seq_printf(s, "RR    = 0x%08x\n",
+		inw(ie6xx_wdt_data.sch_wdtba + RR0));
+	seq_printf(s, "WDTCR = 0x%08x\n",
+		inw(ie6xx_wdt_data.sch_wdtba + WDTCR));
+	seq_printf(s, "DCR   = 0x%08x\n",
+		inl(ie6xx_wdt_data.sch_wdtba + DCR));
+	seq_printf(s, "WDTLR = 0x%08x\n",
+		inw(ie6xx_wdt_data.sch_wdtba + WDTLR));
+
+	seq_printf(s, "\n");
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ie6xx_wdt);
+
+static void ie6xx_wdt_debugfs_init(void)
+{
+	/* /sys/kernel/debug/ie6xx_wdt */
+	ie6xx_wdt_data.debugfs = debugfs_create_file("ie6xx_wdt",
+		S_IFREG | S_IRUGO, NULL, NULL, &ie6xx_wdt_fops);
+}
+
+static void ie6xx_wdt_debugfs_exit(void)
+{
+	debugfs_remove(ie6xx_wdt_data.debugfs);
+}
+
+#else
+static void ie6xx_wdt_debugfs_init(void)
+{
+}
+
+static void ie6xx_wdt_debugfs_exit(void)
+{
+}
+#endif
+
+static int ie6xx_wdt_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	u8 wdtlr;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (!res)
+		return -ENODEV;
+
+	if (!request_region(res->start, resource_size(res), pdev->name)) {
+		dev_err(&pdev->dev, "Watchdog region 0x%llx already in use!\n",
+			(u64)res->start);
+		return -EBUSY;
+	}
+
+	ie6xx_wdt_data.sch_wdtba = res->start;
+	dev_dbg(&pdev->dev, "WDT = 0x%X\n", ie6xx_wdt_data.sch_wdtba);
+
+	ie6xx_wdt_dev.timeout = timeout;
+	watchdog_set_nowayout(&ie6xx_wdt_dev, nowayout);
+	ie6xx_wdt_dev.parent = &pdev->dev;
+
+	spin_lock_init(&ie6xx_wdt_data.unlock_sequence);
+
+	wdtlr = inb(ie6xx_wdt_data.sch_wdtba + WDTLR);
+	if (wdtlr & WDT_LOCK)
+		dev_warn(&pdev->dev,
+			"Watchdog Timer is Locked (Reg=0x%x)\n", wdtlr);
+
+	ie6xx_wdt_debugfs_init();
+
+	ret = watchdog_register_device(&ie6xx_wdt_dev);
+	if (ret)
+		goto misc_register_error;
+
+	return 0;
+
+misc_register_error:
+	ie6xx_wdt_debugfs_exit();
+	release_region(res->start, resource_size(res));
+	ie6xx_wdt_data.sch_wdtba = 0;
+	return ret;
+}
+
+static int ie6xx_wdt_remove(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	ie6xx_wdt_stop(NULL);
+	watchdog_unregister_device(&ie6xx_wdt_dev);
+	ie6xx_wdt_debugfs_exit();
+	release_region(res->start, resource_size(res));
+	ie6xx_wdt_data.sch_wdtba = 0;
+
+	return 0;
+}
+
+static struct platform_driver ie6xx_wdt_driver = {
+	.probe		= ie6xx_wdt_probe,
+	.remove		= ie6xx_wdt_remove,
+	.driver		= {
+		.name	= DRIVER_NAME,
+	},
+};
+
+static int __init ie6xx_wdt_init(void)
+{
+	/* Check boot parameters to verify that their initial values */
+	/* are in range. */
+	if ((timeout < MIN_TIME) ||
+	    (timeout > MAX_TIME)) {
+		pr_err("Watchdog timer: value of timeout %d (dec) "
+		  "is out of range from %d to %d (dec)\n",
+		  timeout, MIN_TIME, MAX_TIME);
+		return -EINVAL;
+	}
+
+	return platform_driver_register(&ie6xx_wdt_driver);
+}
+
+static void __exit ie6xx_wdt_exit(void)
+{
+	platform_driver_unregister(&ie6xx_wdt_driver);
+}
+
+late_initcall(ie6xx_wdt_init);
+module_exit(ie6xx_wdt_exit);
+
+MODULE_AUTHOR("Alexander Stein <alexander.stein@systec-electronic.com>");
+MODULE_DESCRIPTION("Intel Atom E6xx Watchdog Device Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRIVER_NAME);