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, 347 insertions, 0 deletions

diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
new file mode 100644
index 000000000..513a07184
--- /dev/null
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Power Interface (SCMI) based CPUFreq Interface driver
+ *
+ * Copyright (C) 2018-2021 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk-provider.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/energy_model.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/scmi_protocol.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+struct scmi_data {
+	int domain_id;
+	int nr_opp;
+	struct device *cpu_dev;
+	cpumask_var_t opp_shared_cpus;
+};
+
+static struct scmi_protocol_handle *ph;
+static const struct scmi_perf_proto_ops *perf_ops;
+
+static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+	struct scmi_data *priv = policy->driver_data;
+	unsigned long rate;
+	int ret;
+
+	ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
+	if (ret)
+		return 0;
+	return rate / 1000;
+}
+
+/*
+ * perf_ops->freq_set is not a synchronous, the actual OPP change will
+ * happen asynchronously and can get notified if the events are
+ * subscribed for by the SCMI firmware
+ */
+static int
+scmi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
+{
+	struct scmi_data *priv = policy->driver_data;
+	u64 freq = policy->freq_table[index].frequency;
+
+	return perf_ops->freq_set(ph, priv->domain_id, freq * 1000, false);
+}
+
+static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
+					     unsigned int target_freq)
+{
+	struct scmi_data *priv = policy->driver_data;
+
+	if (!perf_ops->freq_set(ph, priv->domain_id,
+				target_freq * 1000, true))
+		return target_freq;
+
+	return 0;
+}
+
+static int
+scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
+{
+	int cpu, domain, tdomain;
+	struct device *tcpu_dev;
+
+	domain = perf_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev)
+			continue;
+
+		tdomain = perf_ops->device_domain_id(tcpu_dev);
+		if (tdomain == domain)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused
+scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power,
+		   unsigned long *KHz)
+{
+	enum scmi_power_scale power_scale = perf_ops->power_scale_get(ph);
+	unsigned long Hz;
+	int ret, domain;
+
+	domain = perf_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	/* Get the power cost of the performance domain. */
+	Hz = *KHz * 1000;
+	ret = perf_ops->est_power_get(ph, domain, &Hz, power);
+	if (ret)
+		return ret;
+
+	/* Convert the power to uW if it is mW (ignore bogoW) */
+	if (power_scale == SCMI_POWER_MILLIWATTS)
+		*power *= MICROWATT_PER_MILLIWATT;
+
+	/* The EM framework specifies the frequency in KHz. */
+	*KHz = Hz / 1000;
+
+	return 0;
+}
+
+static int scmi_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret, nr_opp;
+	unsigned int latency;
+	struct device *cpu_dev;
+	struct scmi_data *priv;
+	struct cpufreq_frequency_table *freq_table;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", policy->cpu);
+		return -ENODEV;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	if (!zalloc_cpumask_var(&priv->opp_shared_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_free_priv;
+	}
+
+	/* Obtain CPUs that share SCMI performance controls */
+	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
+		dev_warn(cpu_dev, "failed to get sharing cpumask\n");
+		goto out_free_cpumask;
+	}
+
+	/*
+	 * Obtain CPUs that share performance levels.
+	 * The OPP 'sharing cpus' info may come from DT through an empty opp
+	 * table and opp-shared.
+	 */
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
+	if (ret || cpumask_empty(priv->opp_shared_cpus)) {
+		/*
+		 * Either opp-table is not set or no opp-shared was found.
+		 * Use the CPU mask from SCMI to designate CPUs sharing an OPP
+		 * table.
+		 */
+		cpumask_copy(priv->opp_shared_cpus, policy->cpus);
+	}
+
+	 /*
+	  * A previous CPU may have marked OPPs as shared for a few CPUs, based on
+	  * what OPP core provided. If the current CPU is part of those few, then
+	  * there is no need to add OPPs again.
+	  */
+	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+	if (nr_opp <= 0) {
+		ret = perf_ops->device_opps_add(ph, cpu_dev);
+		if (ret) {
+			dev_warn(cpu_dev, "failed to add opps to the device\n");
+			goto out_free_cpumask;
+		}
+
+		nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+		if (nr_opp <= 0) {
+			dev_err(cpu_dev, "%s: No OPPs for this device: %d\n",
+				__func__, nr_opp);
+
+			ret = -ENODEV;
+			goto out_free_opp;
+		}
+
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
+		if (ret) {
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
+
+			goto out_free_opp;
+		}
+
+		priv->nr_opp = nr_opp;
+	}
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+		goto out_free_opp;
+	}
+
+	priv->cpu_dev = cpu_dev;
+	priv->domain_id = perf_ops->device_domain_id(cpu_dev);
+
+	policy->driver_data = priv;
+	policy->freq_table = freq_table;
+
+	/* SCMI allows DVFS request for any domain from any CPU */
+	policy->dvfs_possible_from_any_cpu = true;
+
+	latency = perf_ops->transition_latency_get(ph, cpu_dev);
+	if (!latency)
+		latency = CPUFREQ_ETERNAL;
+
+	policy->cpuinfo.transition_latency = latency;
+
+	policy->fast_switch_possible =
+		perf_ops->fast_switch_possible(ph, cpu_dev);
+
+	return 0;
+
+out_free_opp:
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
+
+out_free_cpumask:
+	free_cpumask_var(priv->opp_shared_cpus);
+
+out_free_priv:
+	kfree(priv);
+
+	return ret;
+}
+
+static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct scmi_data *priv = policy->driver_data;
+
+	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
+	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	free_cpumask_var(priv->opp_shared_cpus);
+	kfree(priv);
+
+	return 0;
+}
+
+static void scmi_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
+	enum scmi_power_scale power_scale = perf_ops->power_scale_get(ph);
+	struct scmi_data *priv = policy->driver_data;
+	bool em_power_scale = false;
+
+	/*
+	 * This callback will be called for each policy, but we don't need to
+	 * register with EM every time. Despite not being part of the same
+	 * policy, some CPUs may still share their perf-domains, and a CPU from
+	 * another policy may already have registered with EM on behalf of CPUs
+	 * of this policy.
+	 */
+	if (!priv->nr_opp)
+		return;
+
+	if (power_scale == SCMI_POWER_MILLIWATTS
+	    || power_scale == SCMI_POWER_MICROWATTS)
+		em_power_scale = true;
+
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu), priv->nr_opp,
+				    &em_cb, priv->opp_shared_cpus,
+				    em_power_scale);
+}
+
+static struct cpufreq_driver scmi_cpufreq_driver = {
+	.name	= "scmi",
+	.flags	= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+		  CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		  CPUFREQ_IS_COOLING_DEV,
+	.verify	= cpufreq_generic_frequency_table_verify,
+	.attr	= cpufreq_generic_attr,
+	.target_index	= scmi_cpufreq_set_target,
+	.fast_switch	= scmi_cpufreq_fast_switch,
+	.get	= scmi_cpufreq_get_rate,
+	.init	= scmi_cpufreq_init,
+	.exit	= scmi_cpufreq_exit,
+	.register_em	= scmi_cpufreq_register_em,
+};
+
+static int scmi_cpufreq_probe(struct scmi_device *sdev)
+{
+	int ret;
+	struct device *dev = &sdev->dev;
+	const struct scmi_handle *handle;
+
+	handle = sdev->handle;
+
+	if (!handle)
+		return -ENODEV;
+
+	perf_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_PERF, &ph);
+	if (IS_ERR(perf_ops))
+		return PTR_ERR(perf_ops);
+
+#ifdef CONFIG_COMMON_CLK
+	/* dummy clock provider as needed by OPP if clocks property is used */
+	if (of_find_property(dev->of_node, "#clock-cells", NULL))
+		devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+#endif
+
+	ret = cpufreq_register_driver(&scmi_cpufreq_driver);
+	if (ret) {
+		dev_err(dev, "%s: registering cpufreq failed, err: %d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+static void scmi_cpufreq_remove(struct scmi_device *sdev)
+{
+	cpufreq_unregister_driver(&scmi_cpufreq_driver);
+}
+
+static const struct scmi_device_id scmi_id_table[] = {
+	{ SCMI_PROTOCOL_PERF, "cpufreq" },
+	{ },
+};
+MODULE_DEVICE_TABLE(scmi, scmi_id_table);
+
+static struct scmi_driver scmi_cpufreq_drv = {
+	.name		= "scmi-cpufreq",
+	.probe		= scmi_cpufreq_probe,
+	.remove		= scmi_cpufreq_remove,
+	.id_table	= scmi_id_table,
+};
+module_scmi_driver(scmi_cpufreq_drv);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCMI CPUFreq interface driver");
+MODULE_LICENSE("GPL v2");