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, 358 insertions, 0 deletions

diff --git a/drivers/hwmon/sbrmi.c b/drivers/hwmon/sbrmi.c
new file mode 100644
index 000000000..8ea5a4d32
--- /dev/null
+++ b/drivers/hwmon/sbrmi.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sbrmi.c - hwmon driver for a SB-RMI mailbox
+ *           compliant AMD SoC device.
+ *
+ * Copyright (C) 2020-2021 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+
+/* Do not allow setting negative power limit */
+#define SBRMI_PWR_MIN	0
+/* Mask for Status Register bit[1] */
+#define SW_ALERT_MASK	0x2
+
+/* Software Interrupt for triggering */
+#define START_CMD	0x80
+#define TRIGGER_MAILBOX	0x01
+
+/*
+ * SB-RMI supports soft mailbox service request to MP1 (power management
+ * firmware) through SBRMI inbound/outbound message registers.
+ * SB-RMI message IDs
+ */
+enum sbrmi_msg_id {
+	SBRMI_READ_PKG_PWR_CONSUMPTION = 0x1,
+	SBRMI_WRITE_PKG_PWR_LIMIT,
+	SBRMI_READ_PKG_PWR_LIMIT,
+	SBRMI_READ_PKG_MAX_PWR_LIMIT,
+};
+
+/* SB-RMI registers */
+enum sbrmi_reg {
+	SBRMI_CTRL		= 0x01,
+	SBRMI_STATUS,
+	SBRMI_OUTBNDMSG0	= 0x30,
+	SBRMI_OUTBNDMSG1,
+	SBRMI_OUTBNDMSG2,
+	SBRMI_OUTBNDMSG3,
+	SBRMI_OUTBNDMSG4,
+	SBRMI_OUTBNDMSG5,
+	SBRMI_OUTBNDMSG6,
+	SBRMI_OUTBNDMSG7,
+	SBRMI_INBNDMSG0,
+	SBRMI_INBNDMSG1,
+	SBRMI_INBNDMSG2,
+	SBRMI_INBNDMSG3,
+	SBRMI_INBNDMSG4,
+	SBRMI_INBNDMSG5,
+	SBRMI_INBNDMSG6,
+	SBRMI_INBNDMSG7,
+	SBRMI_SW_INTERRUPT,
+};
+
+/* Each client has this additional data */
+struct sbrmi_data {
+	struct i2c_client *client;
+	struct mutex lock;
+	u32 pwr_limit_max;
+};
+
+struct sbrmi_mailbox_msg {
+	u8 cmd;
+	bool read;
+	u32 data_in;
+	u32 data_out;
+};
+
+static int sbrmi_enable_alert(struct i2c_client *client)
+{
+	int ctrl;
+
+	/*
+	 * Enable the SB-RMI Software alert status
+	 * by writing 0 to bit 4 of Control register(0x1)
+	 */
+	ctrl = i2c_smbus_read_byte_data(client, SBRMI_CTRL);
+	if (ctrl < 0)
+		return ctrl;
+
+	if (ctrl & 0x10) {
+		ctrl &= ~0x10;
+		return i2c_smbus_write_byte_data(client,
+						 SBRMI_CTRL, ctrl);
+	}
+
+	return 0;
+}
+
+static int rmi_mailbox_xfer(struct sbrmi_data *data,
+			    struct sbrmi_mailbox_msg *msg)
+{
+	int i, ret, retry = 10;
+	int sw_status;
+	u8 byte;
+
+	mutex_lock(&data->lock);
+
+	/* Indicate firmware a command is to be serviced */
+	ret = i2c_smbus_write_byte_data(data->client,
+					SBRMI_INBNDMSG7, START_CMD);
+	if (ret < 0)
+		goto exit_unlock;
+
+	/* Write the command to SBRMI::InBndMsg_inst0 */
+	ret = i2c_smbus_write_byte_data(data->client,
+					SBRMI_INBNDMSG0, msg->cmd);
+	if (ret < 0)
+		goto exit_unlock;
+
+	/*
+	 * For both read and write the initiator (BMC) writes
+	 * Command Data In[31:0] to SBRMI::InBndMsg_inst[4:1]
+	 * SBRMI_x3C(MSB):SBRMI_x39(LSB)
+	 */
+	for (i = 0; i < 4; i++) {
+		byte = (msg->data_in >> i * 8) & 0xff;
+		ret = i2c_smbus_write_byte_data(data->client,
+						SBRMI_INBNDMSG1 + i, byte);
+		if (ret < 0)
+			goto exit_unlock;
+	}
+
+	/*
+	 * Write 0x01 to SBRMI::SoftwareInterrupt to notify firmware to
+	 * perform the requested read or write command
+	 */
+	ret = i2c_smbus_write_byte_data(data->client,
+					SBRMI_SW_INTERRUPT, TRIGGER_MAILBOX);
+	if (ret < 0)
+		goto exit_unlock;
+
+	/*
+	 * Firmware will write SBRMI::Status[SwAlertSts]=1 to generate
+	 * an ALERT (if enabled) to initiator (BMC) to indicate completion
+	 * of the requested command
+	 */
+	do {
+		sw_status = i2c_smbus_read_byte_data(data->client,
+						     SBRMI_STATUS);
+		if (sw_status < 0) {
+			ret = sw_status;
+			goto exit_unlock;
+		}
+		if (sw_status & SW_ALERT_MASK)
+			break;
+		usleep_range(50, 100);
+	} while (retry--);
+
+	if (retry < 0) {
+		dev_err(&data->client->dev,
+			"Firmware fail to indicate command completion\n");
+		ret = -EIO;
+		goto exit_unlock;
+	}
+
+	/*
+	 * For a read operation, the initiator (BMC) reads the firmware
+	 * response Command Data Out[31:0] from SBRMI::OutBndMsg_inst[4:1]
+	 * {SBRMI_x34(MSB):SBRMI_x31(LSB)}.
+	 */
+	if (msg->read) {
+		for (i = 0; i < 4; i++) {
+			ret = i2c_smbus_read_byte_data(data->client,
+						       SBRMI_OUTBNDMSG1 + i);
+			if (ret < 0)
+				goto exit_unlock;
+			msg->data_out |= ret << i * 8;
+		}
+	}
+
+	/*
+	 * BMC must write 1'b1 to SBRMI::Status[SwAlertSts] to clear the
+	 * ALERT to initiator
+	 */
+	ret = i2c_smbus_write_byte_data(data->client, SBRMI_STATUS,
+					sw_status | SW_ALERT_MASK);
+
+exit_unlock:
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
+static int sbrmi_read(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long *val)
+{
+	struct sbrmi_data *data = dev_get_drvdata(dev);
+	struct sbrmi_mailbox_msg msg = { 0 };
+	int ret;
+
+	if (type != hwmon_power)
+		return -EINVAL;
+
+	msg.read = true;
+	switch (attr) {
+	case hwmon_power_input:
+		msg.cmd = SBRMI_READ_PKG_PWR_CONSUMPTION;
+		ret = rmi_mailbox_xfer(data, &msg);
+		break;
+	case hwmon_power_cap:
+		msg.cmd = SBRMI_READ_PKG_PWR_LIMIT;
+		ret = rmi_mailbox_xfer(data, &msg);
+		break;
+	case hwmon_power_cap_max:
+		msg.data_out = data->pwr_limit_max;
+		ret = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (ret < 0)
+		return ret;
+	/* hwmon power attributes are in microWatt */
+	*val = (long)msg.data_out * 1000;
+	return ret;
+}
+
+static int sbrmi_write(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel, long val)
+{
+	struct sbrmi_data *data = dev_get_drvdata(dev);
+	struct sbrmi_mailbox_msg msg = { 0 };
+
+	if (type != hwmon_power && attr != hwmon_power_cap)
+		return -EINVAL;
+	/*
+	 * hwmon power attributes are in microWatt
+	 * mailbox read/write is in mWatt
+	 */
+	val /= 1000;
+
+	val = clamp_val(val, SBRMI_PWR_MIN, data->pwr_limit_max);
+
+	msg.cmd = SBRMI_WRITE_PKG_PWR_LIMIT;
+	msg.data_in = val;
+	msg.read = false;
+
+	return rmi_mailbox_xfer(data, &msg);
+}
+
+static umode_t sbrmi_is_visible(const void *data,
+				enum hwmon_sensor_types type,
+				u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_input:
+		case hwmon_power_cap_max:
+			return 0444;
+		case hwmon_power_cap:
+			return 0644;
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static const struct hwmon_channel_info *sbrmi_info[] = {
+	HWMON_CHANNEL_INFO(power,
+			   HWMON_P_INPUT | HWMON_P_CAP | HWMON_P_CAP_MAX),
+	NULL
+};
+
+static const struct hwmon_ops sbrmi_hwmon_ops = {
+	.is_visible = sbrmi_is_visible,
+	.read = sbrmi_read,
+	.write = sbrmi_write,
+};
+
+static const struct hwmon_chip_info sbrmi_chip_info = {
+	.ops = &sbrmi_hwmon_ops,
+	.info = sbrmi_info,
+};
+
+static int sbrmi_get_max_pwr_limit(struct sbrmi_data *data)
+{
+	struct sbrmi_mailbox_msg msg = { 0 };
+	int ret;
+
+	msg.cmd = SBRMI_READ_PKG_MAX_PWR_LIMIT;
+	msg.read = true;
+	ret = rmi_mailbox_xfer(data, &msg);
+	if (ret < 0)
+		return ret;
+	data->pwr_limit_max = msg.data_out;
+
+	return ret;
+}
+
+static int sbrmi_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct device *hwmon_dev;
+	struct sbrmi_data *data;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(struct sbrmi_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	/* Enable alert for SB-RMI sequence */
+	ret = sbrmi_enable_alert(client);
+	if (ret < 0)
+		return ret;
+
+	/* Cache maximum power limit */
+	ret = sbrmi_get_max_pwr_limit(data);
+	if (ret < 0)
+		return ret;
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data,
+							 &sbrmi_chip_info, NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id sbrmi_id[] = {
+	{"sbrmi", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, sbrmi_id);
+
+static const struct of_device_id __maybe_unused sbrmi_of_match[] = {
+	{
+		.compatible = "amd,sbrmi",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sbrmi_of_match);
+
+static struct i2c_driver sbrmi_driver = {
+	.class = I2C_CLASS_HWMON,
+	.driver = {
+		.name = "sbrmi",
+		.of_match_table = of_match_ptr(sbrmi_of_match),
+	},
+	.probe_new = sbrmi_probe,
+	.id_table = sbrmi_id,
+};
+
+module_i2c_driver(sbrmi_driver);
+
+MODULE_AUTHOR("Akshay Gupta <akshay.gupta@amd.com>");
+MODULE_DESCRIPTION("Hwmon driver for AMD SB-RMI emulated sensor");
+MODULE_LICENSE("GPL");