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().
  ...

3 files changed, 370 insertions, 0 deletions

diff --git a/tools/thermal/thermal-engine/Build b/tools/thermal/thermal-engine/Build
new file mode 100644
index 000000000..20c3c478b
--- /dev/null
+++ b/tools/thermal/thermal-engine/Build
@@ -0,0 +1 @@
+thermal-engine-y += thermal-engine.o
diff --git a/tools/thermal/thermal-engine/Makefile b/tools/thermal/thermal-engine/Makefile
new file mode 100644
index 000000000..6bd05ff89
--- /dev/null
+++ b/tools/thermal/thermal-engine/Makefile
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for thermal tools
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+# $(info Determined 'srctree' to be $(srctree))
+endif
+
+CFLAGS = -Wall -Wextra
+CFLAGS += -I$(srctree)/tools/thermal/lib
+CFLAGS += -I$(srctree)/tools/lib/thermal/include
+
+LDFLAGS = -L$(srctree)/tools/thermal/lib
+LDFLAGS += -L$(srctree)/tools/lib/thermal
+LDFLAGS += -lthermal_tools
+LDFLAGS += -lthermal
+LDFLAGS += -lconfig
+LDFLAGS += -lnl-genl-3 -lnl-3
+
+VERSION = 0.0.1
+
+all: thermal-engine
+%: %.c
+	$(CC) $(CFLAGS) -D VERSION=\"$(VERSION)\" -o $@ $^ $(LDFLAGS)
+clean:
+	$(RM) thermal-engine
diff --git a/tools/thermal/thermal-engine/thermal-engine.c b/tools/thermal/thermal-engine/thermal-engine.c
new file mode 100644
index 000000000..9b1476a26
--- /dev/null
+++ b/tools/thermal/thermal-engine/thermal-engine.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Thermal monitoring tool based on the thermal netlink events.
+ *
+ * Copyright (C) 2022 Linaro Ltd.
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@kernel.org>
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <syslog.h>
+
+#include <sys/epoll.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <thermal.h>
+#include "thermal-tools.h"
+
+struct options {
+	int loglevel;
+	int logopt;
+	int interactive;
+	int daemonize;
+};
+
+struct thermal_data {
+	struct thermal_zone *tz;
+	struct thermal_handler *th;
+};
+
+static int show_trip(struct thermal_trip *tt, __maybe_unused void *arg)
+{
+	INFO("trip id=%d, type=%d, temp=%d, hyst=%d\n",
+	     tt->id, tt->type, tt->temp, tt->hyst);
+
+	return 0;
+}
+
+static int show_temp(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+	thermal_cmd_get_temp(arg, tz);
+
+	INFO("temperature: %d\n", tz->temp);
+
+	return 0;
+}
+
+static int show_governor(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+	thermal_cmd_get_governor(arg, tz);
+
+	INFO("governor: '%s'\n", tz->governor);
+
+	return 0;
+}
+
+static int show_tz(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+	INFO("thermal zone '%s', id=%d\n", tz->name, tz->id);
+
+	for_each_thermal_trip(tz->trip, show_trip, NULL);
+
+	show_temp(tz, arg);
+
+	show_governor(tz, arg);
+
+	return 0;
+}
+
+static int tz_create(const char *name, int tz_id, __maybe_unused void *arg)
+{
+	INFO("Thermal zone '%s'/%d created\n", name, tz_id);
+
+	return 0;
+}
+
+static int tz_delete(int tz_id, __maybe_unused void *arg)
+{
+	INFO("Thermal zone %d deleted\n", tz_id);
+
+	return 0;
+}
+
+static int tz_disable(int tz_id, void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("Thermal zone %d ('%s') disabled\n", tz_id, tz->name);
+
+	return 0;
+}
+
+static int tz_enable(int tz_id, void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("Thermal zone %d ('%s') enabled\n", tz_id, tz->name);
+
+	return 0;
+}
+
+static int trip_high(int tz_id, int trip_id, int temp, void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("Thermal zone %d ('%s'): trip point %d crossed way up with %d °C\n",
+	     tz_id, tz->name, trip_id, temp);
+
+	return 0;
+}
+
+static int trip_low(int tz_id, int trip_id, int temp, void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("Thermal zone %d ('%s'): trip point %d crossed way down with %d °C\n",
+	     tz_id, tz->name, trip_id, temp);
+
+	return 0;
+}
+
+static int trip_add(int tz_id, int trip_id, int type, int temp, int hyst, __maybe_unused void *arg)
+{
+	INFO("Trip point added %d: id=%d, type=%d, temp=%d, hyst=%d\n",
+	     tz_id, trip_id, type, temp, hyst);
+
+	return 0;
+}
+
+static int trip_delete(int tz_id, int trip_id, __maybe_unused void *arg)
+{
+	INFO("Trip point deleted %d: id=%d\n", tz_id, trip_id);
+
+	return 0;
+}
+
+static int trip_change(int tz_id, int trip_id, int type, int temp,
+		       int hyst, __maybe_unused void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("Trip point changed %d: id=%d, type=%d, temp=%d, hyst=%d\n",
+	     tz_id, trip_id, type, temp, hyst);
+
+	tz->trip[trip_id].type = type;
+	tz->trip[trip_id].temp = temp;
+	tz->trip[trip_id].hyst = hyst;
+
+	return 0;
+}
+
+static int cdev_add(const char *name, int cdev_id, int max_state, __maybe_unused void *arg)
+{
+	INFO("Cooling device '%s'/%d (max state=%d) added\n", name, cdev_id, max_state);
+
+	return 0;
+}
+
+static int cdev_delete(int cdev_id, __maybe_unused void *arg)
+{
+	INFO("Cooling device %d deleted", cdev_id);
+
+	return 0;
+}
+
+static int cdev_update(int cdev_id, int cur_state, __maybe_unused void *arg)
+{
+	INFO("cdev:%d state:%d\n", cdev_id, cur_state);
+
+	return 0;
+}
+
+static int gov_change(int tz_id, const char *name, __maybe_unused void *arg)
+{
+	struct thermal_data *td = arg;
+	struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+	INFO("%s: governor changed %s -> %s\n", tz->name, tz->governor, name);
+
+	strcpy(tz->governor, name);
+
+	return 0;
+}
+
+static struct thermal_ops ops = {
+	.events.tz_create	= tz_create,
+	.events.tz_delete	= tz_delete,
+	.events.tz_disable	= tz_disable,
+	.events.tz_enable	= tz_enable,
+	.events.trip_high	= trip_high,
+	.events.trip_low	= trip_low,
+	.events.trip_add	= trip_add,
+	.events.trip_delete	= trip_delete,
+	.events.trip_change	= trip_change,
+	.events.cdev_add	= cdev_add,
+	.events.cdev_delete	= cdev_delete,
+	.events.cdev_update	= cdev_update,
+	.events.gov_change	= gov_change
+};
+
+static int thermal_event(__maybe_unused int fd, __maybe_unused void *arg)
+{
+	struct thermal_data *td = arg;
+
+	return thermal_events_handle(td->th, td);
+}
+
+static void usage(const char *cmd)
+{
+	printf("%s : A thermal monitoring engine based on notifications\n", cmd);
+	printf("Usage: %s [options]\n", cmd);
+	printf("\t-h, --help\t\tthis help\n");
+	printf("\t-d, --daemonize\n");
+	printf("\t-l <level>, --loglevel <level>\tlog level: ");
+	printf("DEBUG, INFO, NOTICE, WARN, ERROR\n");
+	printf("\t-s, --syslog\t\toutput to syslog\n");
+	printf("\n");
+	exit(0);
+}
+
+static int options_init(int argc, char *argv[], struct options *options)
+{
+	int opt;
+
+	struct option long_options[] = {
+		{ "help",	no_argument, NULL, 'h' },
+		{ "daemonize",	no_argument, NULL, 'd' },
+		{ "syslog",	no_argument, NULL, 's' },
+		{ "loglevel",	required_argument, NULL, 'l' },
+		{ 0, 0, 0, 0 }
+	};
+
+	while (1) {
+
+		int optindex = 0;
+
+		opt = getopt_long(argc, argv, "l:dhs", long_options, &optindex);
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'l':
+			options->loglevel = log_str2level(optarg);
+			break;
+		case 'd':
+			options->daemonize = 1;
+			break;
+		case 's':
+			options->logopt = TO_SYSLOG;
+			break;
+		case 'h':
+			usage(basename(argv[0]));
+			break;
+		default: /* '?' */
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+enum {
+	THERMAL_ENGINE_SUCCESS = 0,
+	THERMAL_ENGINE_OPTION_ERROR,
+	THERMAL_ENGINE_DAEMON_ERROR,
+	THERMAL_ENGINE_LOG_ERROR,
+	THERMAL_ENGINE_THERMAL_ERROR,
+	THERMAL_ENGINE_MAINLOOP_ERROR,
+};
+
+int main(int argc, char *argv[])
+{
+	struct thermal_data td;
+	struct options options = {
+		.loglevel = LOG_INFO,
+		.logopt = TO_STDOUT,
+	};
+
+	if (options_init(argc, argv, &options)) {
+		ERROR("Usage: %s --help\n", argv[0]);
+		return THERMAL_ENGINE_OPTION_ERROR;
+	}
+
+	if (options.daemonize && daemon(0, 0)) {
+		ERROR("Failed to daemonize: %p\n");
+		return THERMAL_ENGINE_DAEMON_ERROR;
+	}
+
+	if (log_init(options.loglevel, basename(argv[0]), options.logopt)) {
+		ERROR("Failed to initialize logging facility\n");
+		return THERMAL_ENGINE_LOG_ERROR;
+	}
+
+	td.th = thermal_init(&ops);
+	if (!td.th) {
+		ERROR("Failed to initialize the thermal library\n");
+		return THERMAL_ENGINE_THERMAL_ERROR;
+	}
+
+	td.tz = thermal_zone_discover(td.th);
+	if (!td.tz) {
+		ERROR("No thermal zone available\n");
+		return THERMAL_ENGINE_THERMAL_ERROR;
+	}
+
+	for_each_thermal_zone(td.tz, show_tz, td.th);
+
+	if (mainloop_init()) {
+		ERROR("Failed to initialize the mainloop\n");
+		return THERMAL_ENGINE_MAINLOOP_ERROR;
+	}
+
+	if (mainloop_add(thermal_events_fd(td.th), thermal_event, &td)) {
+		ERROR("Failed to setup the mainloop\n");
+		return THERMAL_ENGINE_MAINLOOP_ERROR;
+	}
+
+	INFO("Waiting for thermal events ...\n");
+
+	if (mainloop(-1)) {
+		ERROR("Mainloop failed\n");
+		return THERMAL_ENGINE_MAINLOOP_ERROR;
+	}
+
+	return THERMAL_ENGINE_SUCCESS;
+}