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, 249 insertions, 0 deletions

diff --git a/drivers/hwmon/sbtsi_temp.c b/drivers/hwmon/sbtsi_temp.c
new file mode 100644
index 000000000..4c37de846
--- /dev/null
+++ b/drivers/hwmon/sbtsi_temp.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sbtsi_temp.c - hwmon driver for a SBI Temperature Sensor Interface (SB-TSI)
+ *                compliant AMD SoC temperature device.
+ *
+ * Copyright (c) 2020, Google Inc.
+ * Copyright (c) 2020, Kun Yi <kunyi@google.com>
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+
+/*
+ * SB-TSI registers only support SMBus byte data access. "_INT" registers are
+ * the integer part of a temperature value or limit, and "_DEC" registers are
+ * corresponding decimal parts.
+ */
+#define SBTSI_REG_TEMP_INT		0x01 /* RO */
+#define SBTSI_REG_STATUS		0x02 /* RO */
+#define SBTSI_REG_CONFIG		0x03 /* RO */
+#define SBTSI_REG_TEMP_HIGH_INT		0x07 /* RW */
+#define SBTSI_REG_TEMP_LOW_INT		0x08 /* RW */
+#define SBTSI_REG_TEMP_DEC		0x10 /* RW */
+#define SBTSI_REG_TEMP_HIGH_DEC		0x13 /* RW */
+#define SBTSI_REG_TEMP_LOW_DEC		0x14 /* RW */
+
+#define SBTSI_CONFIG_READ_ORDER_SHIFT	5
+
+#define SBTSI_TEMP_MIN	0
+#define SBTSI_TEMP_MAX	255875
+
+/* Each client has this additional data */
+struct sbtsi_data {
+	struct i2c_client *client;
+	struct mutex lock;
+};
+
+/*
+ * From SB-TSI spec: CPU temperature readings and limit registers encode the
+ * temperature in increments of 0.125 from 0 to 255.875. The "high byte"
+ * register encodes the base-2 of the integer portion, and the upper 3 bits of
+ * the "low byte" encode in base-2 the decimal portion.
+ *
+ * e.g. INT=0x19, DEC=0x20 represents 25.125 degrees Celsius
+ *
+ * Therefore temperature in millidegree Celsius =
+ *   (INT + DEC / 256) * 1000 = (INT * 8 + DEC / 32) * 125
+ */
+static inline int sbtsi_reg_to_mc(s32 integer, s32 decimal)
+{
+	return ((integer << 3) + (decimal >> 5)) * 125;
+}
+
+/*
+ * Inversely, given temperature in millidegree Celsius
+ *   INT = (TEMP / 125) / 8
+ *   DEC = ((TEMP / 125) % 8) * 32
+ * Caller have to make sure temp doesn't exceed 255875, the max valid value.
+ */
+static inline void sbtsi_mc_to_reg(s32 temp, u8 *integer, u8 *decimal)
+{
+	temp /= 125;
+	*integer = temp >> 3;
+	*decimal = (temp & 0x7) << 5;
+}
+
+static int sbtsi_read(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long *val)
+{
+	struct sbtsi_data *data = dev_get_drvdata(dev);
+	s32 temp_int, temp_dec;
+	int err;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		/*
+		 * ReadOrder bit specifies the reading order of integer and
+		 * decimal part of CPU temp for atomic reads. If bit == 0,
+		 * reading integer part triggers latching of the decimal part,
+		 * so integer part should be read first. If bit == 1, read
+		 * order should be reversed.
+		 */
+		err = i2c_smbus_read_byte_data(data->client, SBTSI_REG_CONFIG);
+		if (err < 0)
+			return err;
+
+		mutex_lock(&data->lock);
+		if (err & BIT(SBTSI_CONFIG_READ_ORDER_SHIFT)) {
+			temp_dec = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_DEC);
+			temp_int = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_INT);
+		} else {
+			temp_int = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_INT);
+			temp_dec = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_DEC);
+		}
+		mutex_unlock(&data->lock);
+		break;
+	case hwmon_temp_max:
+		mutex_lock(&data->lock);
+		temp_int = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_HIGH_INT);
+		temp_dec = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_HIGH_DEC);
+		mutex_unlock(&data->lock);
+		break;
+	case hwmon_temp_min:
+		mutex_lock(&data->lock);
+		temp_int = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_LOW_INT);
+		temp_dec = i2c_smbus_read_byte_data(data->client, SBTSI_REG_TEMP_LOW_DEC);
+		mutex_unlock(&data->lock);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+
+	if (temp_int < 0)
+		return temp_int;
+	if (temp_dec < 0)
+		return temp_dec;
+
+	*val = sbtsi_reg_to_mc(temp_int, temp_dec);
+
+	return 0;
+}
+
+static int sbtsi_write(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel, long val)
+{
+	struct sbtsi_data *data = dev_get_drvdata(dev);
+	int reg_int, reg_dec, err;
+	u8 temp_int, temp_dec;
+
+	switch (attr) {
+	case hwmon_temp_max:
+		reg_int = SBTSI_REG_TEMP_HIGH_INT;
+		reg_dec = SBTSI_REG_TEMP_HIGH_DEC;
+		break;
+	case hwmon_temp_min:
+		reg_int = SBTSI_REG_TEMP_LOW_INT;
+		reg_dec = SBTSI_REG_TEMP_LOW_DEC;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	val = clamp_val(val, SBTSI_TEMP_MIN, SBTSI_TEMP_MAX);
+	sbtsi_mc_to_reg(val, &temp_int, &temp_dec);
+
+	mutex_lock(&data->lock);
+	err = i2c_smbus_write_byte_data(data->client, reg_int, temp_int);
+	if (err)
+		goto exit;
+
+	err = i2c_smbus_write_byte_data(data->client, reg_dec, temp_dec);
+exit:
+	mutex_unlock(&data->lock);
+	return err;
+}
+
+static umode_t sbtsi_is_visible(const void *data,
+				enum hwmon_sensor_types type,
+				u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+			return 0444;
+		case hwmon_temp_min:
+			return 0644;
+		case hwmon_temp_max:
+			return 0644;
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static const struct hwmon_channel_info *sbtsi_info[] = {
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX),
+	NULL
+};
+
+static const struct hwmon_ops sbtsi_hwmon_ops = {
+	.is_visible = sbtsi_is_visible,
+	.read = sbtsi_read,
+	.write = sbtsi_write,
+};
+
+static const struct hwmon_chip_info sbtsi_chip_info = {
+	.ops = &sbtsi_hwmon_ops,
+	.info = sbtsi_info,
+};
+
+static int sbtsi_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct device *hwmon_dev;
+	struct sbtsi_data *data;
+
+	data = devm_kzalloc(dev, sizeof(struct sbtsi_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &sbtsi_chip_info,
+							 NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id sbtsi_id[] = {
+	{"sbtsi", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, sbtsi_id);
+
+static const struct of_device_id __maybe_unused sbtsi_of_match[] = {
+	{
+		.compatible = "amd,sbtsi",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sbtsi_of_match);
+
+static struct i2c_driver sbtsi_driver = {
+	.class = I2C_CLASS_HWMON,
+	.driver = {
+		.name = "sbtsi",
+		.of_match_table = of_match_ptr(sbtsi_of_match),
+	},
+	.probe_new = sbtsi_probe,
+	.id_table = sbtsi_id,
+};
+
+module_i2c_driver(sbtsi_driver);
+
+MODULE_AUTHOR("Kun Yi <kunyi@google.com>");
+MODULE_DESCRIPTION("Hwmon driver for AMD SB-TSI emulated sensor");
+MODULE_LICENSE("GPL");