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, 240 insertions, 0 deletions

diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c
new file mode 100644
index 000000000..cb10e2806
--- /dev/null
+++ b/drivers/thermal/db8500_thermal.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * db8500_thermal.c - DB8500 Thermal Management Implementation
+ *
+ * Copyright (C) 2012 ST-Ericsson
+ * Copyright (C) 2012-2019 Linaro Ltd.
+ *
+ * Authors: Hongbo Zhang, Linus Walleij
+ */
+
+#include <linux/cpu_cooling.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/dbx500-prcmu.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define PRCMU_DEFAULT_MEASURE_TIME	0xFFF
+#define PRCMU_DEFAULT_LOW_TEMP		0
+
+/**
+ * db8500_thermal_points - the interpolation points that trigger
+ * interrupts
+ */
+static const unsigned long db8500_thermal_points[] = {
+	15000,
+	20000,
+	25000,
+	30000,
+	35000,
+	40000,
+	45000,
+	50000,
+	55000,
+	60000,
+	65000,
+	70000,
+	75000,
+	80000,
+	/*
+	 * This is where things start to get really bad for the
+	 * SoC and the thermal zones should be set up to trigger
+	 * critical temperature at 85000 mC so we don't get above
+	 * this point.
+	 */
+	85000,
+	90000,
+	95000,
+	100000,
+};
+
+struct db8500_thermal_zone {
+	struct thermal_zone_device *tz;
+	unsigned long interpolated_temp;
+	unsigned int cur_index;
+};
+
+/* Callback to get current temperature */
+static int db8500_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
+{
+	struct db8500_thermal_zone *th = tz->devdata;
+
+	/*
+	 * TODO: There is no PRCMU interface to get temperature data currently,
+	 * so a pseudo temperature is returned , it works for thermal framework
+	 * and this will be fixed when the PRCMU interface is available.
+	 */
+	*temp = th->interpolated_temp;
+
+	return 0;
+}
+
+static const struct thermal_zone_device_ops thdev_ops = {
+	.get_temp = db8500_thermal_get_temp,
+};
+
+static void db8500_thermal_update_config(struct db8500_thermal_zone *th,
+					 unsigned int idx,
+					 unsigned long next_low,
+					 unsigned long next_high)
+{
+	prcmu_stop_temp_sense();
+
+	th->cur_index = idx;
+	th->interpolated_temp = (next_low + next_high)/2;
+
+	/*
+	 * The PRCMU accept absolute temperatures in celsius so divide
+	 * down the millicelsius with 1000
+	 */
+	prcmu_config_hotmon((u8)(next_low/1000), (u8)(next_high/1000));
+	prcmu_start_temp_sense(PRCMU_DEFAULT_MEASURE_TIME);
+}
+
+static irqreturn_t prcmu_low_irq_handler(int irq, void *irq_data)
+{
+	struct db8500_thermal_zone *th = irq_data;
+	unsigned int idx = th->cur_index;
+	unsigned long next_low, next_high;
+
+	if (idx == 0)
+		/* Meaningless for thermal management, ignoring it */
+		return IRQ_HANDLED;
+
+	if (idx == 1) {
+		next_high = db8500_thermal_points[0];
+		next_low = PRCMU_DEFAULT_LOW_TEMP;
+	} else {
+		next_high = db8500_thermal_points[idx - 1];
+		next_low = db8500_thermal_points[idx - 2];
+	}
+	idx -= 1;
+
+	db8500_thermal_update_config(th, idx, next_low, next_high);
+	dev_dbg(&th->tz->device,
+		"PRCMU set max %ld, min %ld\n", next_high, next_low);
+
+	thermal_zone_device_update(th->tz, THERMAL_EVENT_UNSPECIFIED);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t prcmu_high_irq_handler(int irq, void *irq_data)
+{
+	struct db8500_thermal_zone *th = irq_data;
+	unsigned int idx = th->cur_index;
+	unsigned long next_low, next_high;
+	int num_points = ARRAY_SIZE(db8500_thermal_points);
+
+	if (idx < num_points - 1) {
+		next_high = db8500_thermal_points[idx+1];
+		next_low = db8500_thermal_points[idx];
+		idx += 1;
+
+		db8500_thermal_update_config(th, idx, next_low, next_high);
+
+		dev_dbg(&th->tz->device,
+			"PRCMU set max %ld, min %ld\n", next_high, next_low);
+	} else if (idx == num_points - 1)
+		/* So we roof out 1 degree over the max point */
+		th->interpolated_temp = db8500_thermal_points[idx] + 1;
+
+	thermal_zone_device_update(th->tz, THERMAL_EVENT_UNSPECIFIED);
+
+	return IRQ_HANDLED;
+}
+
+static int db8500_thermal_probe(struct platform_device *pdev)
+{
+	struct db8500_thermal_zone *th = NULL;
+	struct device *dev = &pdev->dev;
+	int low_irq, high_irq, ret = 0;
+
+	th = devm_kzalloc(dev, sizeof(*th), GFP_KERNEL);
+	if (!th)
+		return -ENOMEM;
+
+	low_irq = platform_get_irq_byname(pdev, "IRQ_HOTMON_LOW");
+	if (low_irq < 0)
+		return low_irq;
+
+	ret = devm_request_threaded_irq(dev, low_irq, NULL,
+		prcmu_low_irq_handler, IRQF_NO_SUSPEND | IRQF_ONESHOT,
+		"dbx500_temp_low", th);
+	if (ret < 0) {
+		dev_err(dev, "failed to allocate temp low irq\n");
+		return ret;
+	}
+
+	high_irq = platform_get_irq_byname(pdev, "IRQ_HOTMON_HIGH");
+	if (high_irq < 0)
+		return high_irq;
+
+	ret = devm_request_threaded_irq(dev, high_irq, NULL,
+		prcmu_high_irq_handler, IRQF_NO_SUSPEND | IRQF_ONESHOT,
+		"dbx500_temp_high", th);
+	if (ret < 0) {
+		dev_err(dev, "failed to allocate temp high irq\n");
+		return ret;
+	}
+
+	/* register of thermal sensor and get info from DT */
+	th->tz = devm_thermal_of_zone_register(dev, 0, th, &thdev_ops);
+	if (IS_ERR(th->tz)) {
+		dev_err(dev, "register thermal zone sensor failed\n");
+		return PTR_ERR(th->tz);
+	}
+	dev_info(dev, "thermal zone sensor registered\n");
+
+	/* Start measuring at the lowest point */
+	db8500_thermal_update_config(th, 0, PRCMU_DEFAULT_LOW_TEMP,
+				     db8500_thermal_points[0]);
+
+	platform_set_drvdata(pdev, th);
+
+	return 0;
+}
+
+static int db8500_thermal_suspend(struct platform_device *pdev,
+		pm_message_t state)
+{
+	prcmu_stop_temp_sense();
+
+	return 0;
+}
+
+static int db8500_thermal_resume(struct platform_device *pdev)
+{
+	struct db8500_thermal_zone *th = platform_get_drvdata(pdev);
+
+	/* Resume and start measuring at the lowest point */
+	db8500_thermal_update_config(th, 0, PRCMU_DEFAULT_LOW_TEMP,
+				     db8500_thermal_points[0]);
+
+	return 0;
+}
+
+static const struct of_device_id db8500_thermal_match[] = {
+	{ .compatible = "stericsson,db8500-thermal" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, db8500_thermal_match);
+
+static struct platform_driver db8500_thermal_driver = {
+	.driver = {
+		.name = "db8500-thermal",
+		.of_match_table = of_match_ptr(db8500_thermal_match),
+	},
+	.probe = db8500_thermal_probe,
+	.suspend = db8500_thermal_suspend,
+	.resume = db8500_thermal_resume,
+};
+
+module_platform_driver(db8500_thermal_driver);
+
+MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
+MODULE_DESCRIPTION("DB8500 thermal driver");
+MODULE_LICENSE("GPL");