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, 340 insertions, 0 deletions

diff --git a/drivers/watchdog/mlx_wdt.c b/drivers/watchdog/mlx_wdt.c
new file mode 100644
index 000000000..9c5b6616f
--- /dev/null
+++ b/drivers/watchdog/mlx_wdt.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Mellanox watchdog driver
+ *
+ * Copyright (C) 2019 Mellanox Technologies
+ * Copyright (C) 2019 Michael Shych <mshych@mellanox.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/watchdog.h>
+
+#define MLXREG_WDT_CLOCK_SCALE		1000
+#define MLXREG_WDT_MAX_TIMEOUT_TYPE1	32
+#define MLXREG_WDT_MAX_TIMEOUT_TYPE2	255
+#define MLXREG_WDT_MAX_TIMEOUT_TYPE3	65535
+#define MLXREG_WDT_MIN_TIMEOUT		1
+#define MLXREG_WDT_OPTIONS_BASE (WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE | \
+				 WDIOF_SETTIMEOUT)
+
+/**
+ * struct mlxreg_wdt - wd private data:
+ *
+ * @wdd:	watchdog device;
+ * @device:	basic device;
+ * @pdata:	data received from platform driver;
+ * @regmap:	register map of parent device;
+ * @timeout:	defined timeout in sec.;
+ * @action_idx:	index for direct access to action register;
+ * @timeout_idx:index for direct access to TO register;
+ * @tleft_idx:	index for direct access to time left register;
+ * @ping_idx:	index for direct access to ping register;
+ * @reset_idx:	index for direct access to reset cause register;
+ * @wd_type:	watchdog HW type;
+ */
+struct mlxreg_wdt {
+	struct watchdog_device wdd;
+	struct mlxreg_core_platform_data *pdata;
+	void *regmap;
+	int action_idx;
+	int timeout_idx;
+	int tleft_idx;
+	int ping_idx;
+	int reset_idx;
+	int regmap_val_sz;
+	enum mlxreg_wdt_type wdt_type;
+};
+
+static void mlxreg_wdt_check_card_reset(struct mlxreg_wdt *wdt)
+{
+	struct mlxreg_core_data *reg_data;
+	u32 regval;
+	int rc;
+
+	if (wdt->reset_idx == -EINVAL)
+		return;
+
+	if (!(wdt->wdd.info->options & WDIOF_CARDRESET))
+		return;
+
+	reg_data = &wdt->pdata->data[wdt->reset_idx];
+	rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+	if (!rc) {
+		if (regval & ~reg_data->mask) {
+			wdt->wdd.bootstatus = WDIOF_CARDRESET;
+			dev_info(wdt->wdd.parent,
+				 "watchdog previously reset the CPU\n");
+		}
+	}
+}
+
+static int mlxreg_wdt_start(struct watchdog_device *wdd)
+{
+	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
+	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->action_idx];
+
+	return regmap_update_bits(wdt->regmap, reg_data->reg, ~reg_data->mask,
+				  BIT(reg_data->bit));
+}
+
+static int mlxreg_wdt_stop(struct watchdog_device *wdd)
+{
+	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
+	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->action_idx];
+
+	return regmap_update_bits(wdt->regmap, reg_data->reg, ~reg_data->mask,
+				  ~BIT(reg_data->bit));
+}
+
+static int mlxreg_wdt_ping(struct watchdog_device *wdd)
+{
+	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
+	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->ping_idx];
+
+	return regmap_write_bits(wdt->regmap, reg_data->reg, ~reg_data->mask,
+				 BIT(reg_data->bit));
+}
+
+static int mlxreg_wdt_set_timeout(struct watchdog_device *wdd,
+				  unsigned int timeout)
+{
+	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
+	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->timeout_idx];
+	u32 regval, set_time, hw_timeout;
+	int rc;
+
+	switch (wdt->wdt_type) {
+	case MLX_WDT_TYPE1:
+		rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+		if (rc)
+			return rc;
+
+		hw_timeout = order_base_2(timeout * MLXREG_WDT_CLOCK_SCALE);
+		regval = (regval & reg_data->mask) | hw_timeout;
+		/* Rowndown to actual closest number of sec. */
+		set_time = BIT(hw_timeout) / MLXREG_WDT_CLOCK_SCALE;
+		rc = regmap_write(wdt->regmap, reg_data->reg, regval);
+		break;
+	case MLX_WDT_TYPE2:
+		set_time = timeout;
+		rc = regmap_write(wdt->regmap, reg_data->reg, timeout);
+		break;
+	case MLX_WDT_TYPE3:
+		/* WD_TYPE3 has 2B set time register */
+		set_time = timeout;
+		if (wdt->regmap_val_sz == 1) {
+			regval = timeout & 0xff;
+			rc = regmap_write(wdt->regmap, reg_data->reg, regval);
+			if (!rc) {
+				regval = (timeout & 0xff00) >> 8;
+				rc = regmap_write(wdt->regmap,
+						reg_data->reg + 1, regval);
+			}
+		} else {
+			rc = regmap_write(wdt->regmap, reg_data->reg, timeout);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	wdd->timeout = set_time;
+	if (!rc) {
+		/*
+		 * Restart watchdog with new timeout period
+		 * if watchdog is already started.
+		 */
+		if (watchdog_active(wdd)) {
+			rc = mlxreg_wdt_stop(wdd);
+			if (!rc)
+				rc = mlxreg_wdt_start(wdd);
+		}
+	}
+
+	return rc;
+}
+
+static unsigned int mlxreg_wdt_get_timeleft(struct watchdog_device *wdd)
+{
+	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
+	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->tleft_idx];
+	u32 regval, msb, lsb;
+	int rc;
+
+	if (wdt->wdt_type == MLX_WDT_TYPE2) {
+		rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+	} else {
+		/* WD_TYPE3 has 2 byte timeleft register */
+		if (wdt->regmap_val_sz == 1) {
+			rc = regmap_read(wdt->regmap, reg_data->reg, &lsb);
+			if (!rc) {
+				rc = regmap_read(wdt->regmap,
+						reg_data->reg + 1, &msb);
+				regval = (msb & 0xff) << 8 | (lsb & 0xff);
+			}
+		} else {
+			rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+		}
+	}
+
+	/* Return 0 timeleft in case of failure register read. */
+	return rc == 0 ? regval : 0;
+}
+
+static const struct watchdog_ops mlxreg_wdt_ops_type1 = {
+	.start		= mlxreg_wdt_start,
+	.stop		= mlxreg_wdt_stop,
+	.ping		= mlxreg_wdt_ping,
+	.set_timeout	= mlxreg_wdt_set_timeout,
+	.owner		= THIS_MODULE,
+};
+
+static const struct watchdog_ops mlxreg_wdt_ops_type2 = {
+	.start		= mlxreg_wdt_start,
+	.stop		= mlxreg_wdt_stop,
+	.ping		= mlxreg_wdt_ping,
+	.set_timeout	= mlxreg_wdt_set_timeout,
+	.get_timeleft	= mlxreg_wdt_get_timeleft,
+	.owner		= THIS_MODULE,
+};
+
+static const struct watchdog_info mlxreg_wdt_main_info = {
+	.options	= MLXREG_WDT_OPTIONS_BASE
+			| WDIOF_CARDRESET,
+	.identity	= "mlx-wdt-main",
+};
+
+static const struct watchdog_info mlxreg_wdt_aux_info = {
+	.options	= MLXREG_WDT_OPTIONS_BASE
+			| WDIOF_ALARMONLY,
+	.identity	= "mlx-wdt-aux",
+};
+
+static void mlxreg_wdt_config(struct mlxreg_wdt *wdt,
+			      struct mlxreg_core_platform_data *pdata)
+{
+	struct mlxreg_core_data *data = pdata->data;
+	int i;
+
+	wdt->reset_idx = -EINVAL;
+	for (i = 0; i < pdata->counter; i++, data++) {
+		if (strnstr(data->label, "action", sizeof(data->label)))
+			wdt->action_idx = i;
+		else if (strnstr(data->label, "timeout", sizeof(data->label)))
+			wdt->timeout_idx = i;
+		else if (strnstr(data->label, "timeleft", sizeof(data->label)))
+			wdt->tleft_idx = i;
+		else if (strnstr(data->label, "ping", sizeof(data->label)))
+			wdt->ping_idx = i;
+		else if (strnstr(data->label, "reset", sizeof(data->label)))
+			wdt->reset_idx = i;
+	}
+
+	wdt->pdata = pdata;
+	if (strnstr(pdata->identity, mlxreg_wdt_main_info.identity,
+		    sizeof(mlxreg_wdt_main_info.identity)))
+		wdt->wdd.info = &mlxreg_wdt_main_info;
+	else
+		wdt->wdd.info = &mlxreg_wdt_aux_info;
+
+	wdt->wdt_type = pdata->version;
+	switch (wdt->wdt_type) {
+	case MLX_WDT_TYPE1:
+		wdt->wdd.ops = &mlxreg_wdt_ops_type1;
+		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE1;
+		break;
+	case MLX_WDT_TYPE2:
+		wdt->wdd.ops = &mlxreg_wdt_ops_type2;
+		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE2;
+		break;
+	case MLX_WDT_TYPE3:
+		wdt->wdd.ops = &mlxreg_wdt_ops_type2;
+		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE3;
+		break;
+	default:
+		break;
+	}
+
+	wdt->wdd.min_timeout = MLXREG_WDT_MIN_TIMEOUT;
+}
+
+static int mlxreg_wdt_init_timeout(struct mlxreg_wdt *wdt,
+				   struct mlxreg_core_platform_data *pdata)
+{
+	u32 timeout;
+
+	timeout = pdata->data[wdt->timeout_idx].health_cntr;
+	return mlxreg_wdt_set_timeout(&wdt->wdd, timeout);
+}
+
+static int mlxreg_wdt_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_wdt *wdt;
+	int rc;
+
+	pdata = dev_get_platdata(dev);
+	if (!pdata) {
+		dev_err(dev, "Failed to get platform data.\n");
+		return -EINVAL;
+	}
+	wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	wdt->wdd.parent = dev;
+	wdt->regmap = pdata->regmap;
+	rc = regmap_get_val_bytes(wdt->regmap);
+	if (rc < 0)
+		return -EINVAL;
+
+	wdt->regmap_val_sz = rc;
+	mlxreg_wdt_config(wdt, pdata);
+
+	if ((pdata->features & MLXREG_CORE_WD_FEATURE_NOWAYOUT))
+		watchdog_set_nowayout(&wdt->wdd, WATCHDOG_NOWAYOUT);
+	watchdog_stop_on_reboot(&wdt->wdd);
+	watchdog_stop_on_unregister(&wdt->wdd);
+	watchdog_set_drvdata(&wdt->wdd, wdt);
+	rc = mlxreg_wdt_init_timeout(wdt, pdata);
+	if (rc)
+		goto register_error;
+
+	if ((pdata->features & MLXREG_CORE_WD_FEATURE_START_AT_BOOT)) {
+		rc = mlxreg_wdt_start(&wdt->wdd);
+		if (rc)
+			goto register_error;
+		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
+	}
+	mlxreg_wdt_check_card_reset(wdt);
+	rc = devm_watchdog_register_device(dev, &wdt->wdd);
+
+register_error:
+	if (rc)
+		dev_err(dev, "Cannot register watchdog device (err=%d)\n", rc);
+	return rc;
+}
+
+static struct platform_driver mlxreg_wdt_driver = {
+	.probe	= mlxreg_wdt_probe,
+	.driver	= {
+			.name = "mlx-wdt",
+	},
+};
+
+module_platform_driver(mlxreg_wdt_driver);
+
+MODULE_AUTHOR("Michael Shych <michaelsh@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox watchdog driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlx-wdt");