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, 329 insertions, 0 deletions

diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c
new file mode 100644
index 000000000..e5d18dac8
--- /dev/null
+++ b/drivers/hwmon/via-cputemp.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * via-cputemp.c - Driver for VIA CPU core temperature monitoring
+ * Copyright (C) 2009 VIA Technologies, Inc.
+ *
+ * based on existing coretemp.c, which is
+ *
+ * Copyright (C) 2007 Rudolf Marek <r.marek@assembler.cz>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-vid.h>
+#include <linux/sysfs.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/cpu.h>
+#include <asm/msr.h>
+#include <asm/processor.h>
+#include <asm/cpu_device_id.h>
+
+#define DRVNAME	"via_cputemp"
+
+enum { SHOW_TEMP, SHOW_LABEL, SHOW_NAME };
+
+/*
+ * Functions declaration
+ */
+
+struct via_cputemp_data {
+	struct device *hwmon_dev;
+	const char *name;
+	u8 vrm;
+	u32 id;
+	u32 msr_temp;
+	u32 msr_vid;
+};
+
+/*
+ * Sysfs stuff
+ */
+
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
+			 char *buf)
+{
+	int ret;
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct via_cputemp_data *data = dev_get_drvdata(dev);
+
+	if (attr->index == SHOW_NAME)
+		ret = sprintf(buf, "%s\n", data->name);
+	else	/* show label */
+		ret = sprintf(buf, "Core %d\n", data->id);
+	return ret;
+}
+
+static ssize_t temp_show(struct device *dev, struct device_attribute *devattr,
+			 char *buf)
+{
+	struct via_cputemp_data *data = dev_get_drvdata(dev);
+	u32 eax, edx;
+	int err;
+
+	err = rdmsr_safe_on_cpu(data->id, data->msr_temp, &eax, &edx);
+	if (err)
+		return -EAGAIN;
+
+	return sprintf(buf, "%lu\n", ((unsigned long)eax & 0xffffff) * 1000);
+}
+
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *devattr, char *buf)
+{
+	struct via_cputemp_data *data = dev_get_drvdata(dev);
+	u32 eax, edx;
+	int err;
+
+	err = rdmsr_safe_on_cpu(data->id, data->msr_vid, &eax, &edx);
+	if (err)
+		return -EAGAIN;
+
+	return sprintf(buf, "%d\n", vid_from_reg(~edx & 0x7f, data->vrm));
+}
+
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, SHOW_TEMP);
+static SENSOR_DEVICE_ATTR_RO(temp1_label, name, SHOW_LABEL);
+static SENSOR_DEVICE_ATTR_RO(name, name, SHOW_NAME);
+
+static struct attribute *via_cputemp_attributes[] = {
+	&sensor_dev_attr_name.dev_attr.attr,
+	&sensor_dev_attr_temp1_label.dev_attr.attr,
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group via_cputemp_group = {
+	.attrs = via_cputemp_attributes,
+};
+
+/* Optional attributes */
+static DEVICE_ATTR_RO(cpu0_vid);
+
+static int via_cputemp_probe(struct platform_device *pdev)
+{
+	struct via_cputemp_data *data;
+	struct cpuinfo_x86 *c = &cpu_data(pdev->id);
+	int err;
+	u32 eax, edx;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(struct via_cputemp_data),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->id = pdev->id;
+	data->name = "via_cputemp";
+
+	if (c->x86 == 7) {
+		data->msr_temp = 0x1423;
+	} else {
+		switch (c->x86_model) {
+		case 0xA:
+			/* C7 A */
+		case 0xD:
+			/* C7 D */
+			data->msr_temp = 0x1169;
+			data->msr_vid = 0x198;
+			break;
+		case 0xF:
+			/* Nano */
+			data->msr_temp = 0x1423;
+			break;
+		default:
+			return -ENODEV;
+		}
+	}
+
+	/* test if we can access the TEMPERATURE MSR */
+	err = rdmsr_safe_on_cpu(data->id, data->msr_temp, &eax, &edx);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Unable to access TEMPERATURE MSR, giving up\n");
+		return err;
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	err = sysfs_create_group(&pdev->dev.kobj, &via_cputemp_group);
+	if (err)
+		return err;
+
+	if (data->msr_vid)
+		data->vrm = vid_which_vrm();
+
+	if (data->vrm) {
+		err = device_create_file(&pdev->dev, &dev_attr_cpu0_vid);
+		if (err)
+			goto exit_remove;
+	}
+
+	data->hwmon_dev = hwmon_device_register(&pdev->dev);
+	if (IS_ERR(data->hwmon_dev)) {
+		err = PTR_ERR(data->hwmon_dev);
+		dev_err(&pdev->dev, "Class registration failed (%d)\n",
+			err);
+		goto exit_remove;
+	}
+
+	return 0;
+
+exit_remove:
+	if (data->vrm)
+		device_remove_file(&pdev->dev, &dev_attr_cpu0_vid);
+	sysfs_remove_group(&pdev->dev.kobj, &via_cputemp_group);
+	return err;
+}
+
+static int via_cputemp_remove(struct platform_device *pdev)
+{
+	struct via_cputemp_data *data = platform_get_drvdata(pdev);
+
+	hwmon_device_unregister(data->hwmon_dev);
+	if (data->vrm)
+		device_remove_file(&pdev->dev, &dev_attr_cpu0_vid);
+	sysfs_remove_group(&pdev->dev.kobj, &via_cputemp_group);
+	return 0;
+}
+
+static struct platform_driver via_cputemp_driver = {
+	.driver = {
+		.name = DRVNAME,
+	},
+	.probe = via_cputemp_probe,
+	.remove = via_cputemp_remove,
+};
+
+struct pdev_entry {
+	struct list_head list;
+	struct platform_device *pdev;
+	unsigned int cpu;
+};
+
+static LIST_HEAD(pdev_list);
+static DEFINE_MUTEX(pdev_list_mutex);
+
+static int via_cputemp_online(unsigned int cpu)
+{
+	int err;
+	struct platform_device *pdev;
+	struct pdev_entry *pdev_entry;
+
+	pdev = platform_device_alloc(DRVNAME, cpu);
+	if (!pdev) {
+		err = -ENOMEM;
+		pr_err("Device allocation failed\n");
+		goto exit;
+	}
+
+	pdev_entry = kzalloc(sizeof(struct pdev_entry), GFP_KERNEL);
+	if (!pdev_entry) {
+		err = -ENOMEM;
+		goto exit_device_put;
+	}
+
+	err = platform_device_add(pdev);
+	if (err) {
+		pr_err("Device addition failed (%d)\n", err);
+		goto exit_device_free;
+	}
+
+	pdev_entry->pdev = pdev;
+	pdev_entry->cpu = cpu;
+	mutex_lock(&pdev_list_mutex);
+	list_add_tail(&pdev_entry->list, &pdev_list);
+	mutex_unlock(&pdev_list_mutex);
+
+	return 0;
+
+exit_device_free:
+	kfree(pdev_entry);
+exit_device_put:
+	platform_device_put(pdev);
+exit:
+	return err;
+}
+
+static int via_cputemp_down_prep(unsigned int cpu)
+{
+	struct pdev_entry *p;
+
+	mutex_lock(&pdev_list_mutex);
+	list_for_each_entry(p, &pdev_list, list) {
+		if (p->cpu == cpu) {
+			platform_device_unregister(p->pdev);
+			list_del(&p->list);
+			mutex_unlock(&pdev_list_mutex);
+			kfree(p);
+			return 0;
+		}
+	}
+	mutex_unlock(&pdev_list_mutex);
+	return 0;
+}
+
+static const struct x86_cpu_id __initconst cputemp_ids[] = {
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_A,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_D,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_NANO,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, X86_MODEL_ANY,		NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, cputemp_ids);
+
+static enum cpuhp_state via_temp_online;
+
+static int __init via_cputemp_init(void)
+{
+	int err;
+
+	if (!x86_match_cpu(cputemp_ids))
+		return -ENODEV;
+
+	err = platform_driver_register(&via_cputemp_driver);
+	if (err)
+		goto exit;
+
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hwmon/via:online",
+				via_cputemp_online, via_cputemp_down_prep);
+	if (err < 0)
+		goto exit_driver_unreg;
+	via_temp_online = err;
+
+#ifndef CONFIG_HOTPLUG_CPU
+	if (list_empty(&pdev_list)) {
+		err = -ENODEV;
+		goto exit_hp_unreg;
+	}
+#endif
+	return 0;
+
+#ifndef CONFIG_HOTPLUG_CPU
+exit_hp_unreg:
+	cpuhp_remove_state_nocalls(via_temp_online);
+#endif
+exit_driver_unreg:
+	platform_driver_unregister(&via_cputemp_driver);
+exit:
+	return err;
+}
+
+static void __exit via_cputemp_exit(void)
+{
+	cpuhp_remove_state(via_temp_online);
+	platform_driver_unregister(&via_cputemp_driver);
+}
+
+MODULE_AUTHOR("Harald Welte <HaraldWelte@viatech.com>");
+MODULE_DESCRIPTION("VIA CPU temperature monitor");
+MODULE_LICENSE("GPL");
+
+module_init(via_cputemp_init)
+module_exit(via_cputemp_exit)