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, 377 insertions, 0 deletions

diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
new file mode 100644
index 000000000..01b80331e
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* acpi_thermal_rel.c driver for exporting ACPI thermal relationship
+ *
+ * Copyright (c) 2014 Intel Corp
+ */
+
+/*
+ * Two functionalities included:
+ * 1. Export _TRT, _ART, via misc device interface to the userspace.
+ * 2. Provide parsing result to kernel drivers
+ *
+ */
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/acpi.h>
+#include <linux/uaccess.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include "acpi_thermal_rel.h"
+
+static acpi_handle acpi_thermal_rel_handle;
+static DEFINE_SPINLOCK(acpi_thermal_rel_chrdev_lock);
+static int acpi_thermal_rel_chrdev_count;	/* #times opened */
+static int acpi_thermal_rel_chrdev_exclu;	/* already open exclusive? */
+
+static int acpi_thermal_rel_open(struct inode *inode, struct file *file)
+{
+	spin_lock(&acpi_thermal_rel_chrdev_lock);
+	if (acpi_thermal_rel_chrdev_exclu ||
+	    (acpi_thermal_rel_chrdev_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&acpi_thermal_rel_chrdev_lock);
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		acpi_thermal_rel_chrdev_exclu = 1;
+	acpi_thermal_rel_chrdev_count++;
+
+	spin_unlock(&acpi_thermal_rel_chrdev_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int acpi_thermal_rel_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&acpi_thermal_rel_chrdev_lock);
+	acpi_thermal_rel_chrdev_count--;
+	acpi_thermal_rel_chrdev_exclu = 0;
+	spin_unlock(&acpi_thermal_rel_chrdev_lock);
+
+	return 0;
+}
+
+/**
+ * acpi_parse_trt - Thermal Relationship Table _TRT for passive cooling
+ *
+ * @handle: ACPI handle of the device contains _TRT
+ * @trt_count: the number of valid entries resulted from parsing _TRT
+ * @trtp: pointer to pointer of array of _TRT entries in parsing result
+ * @create_dev: whether to create platform devices for target and source
+ *
+ */
+int acpi_parse_trt(acpi_handle handle, int *trt_count, struct trt **trtp,
+		bool create_dev)
+{
+	acpi_status status;
+	int result = 0;
+	int i;
+	int nr_bad_entries = 0;
+	struct trt *trts;
+	union acpi_object *p;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer element = { 0, NULL };
+	struct acpi_buffer trt_format = { sizeof("RRNNNNNN"), "RRNNNNNN" };
+
+	status = acpi_evaluate_object(handle, "_TRT", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buffer.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		pr_err("Invalid _TRT data\n");
+		result = -EFAULT;
+		goto end;
+	}
+
+	*trt_count = p->package.count;
+	trts = kcalloc(*trt_count, sizeof(struct trt), GFP_KERNEL);
+	if (!trts) {
+		result = -ENOMEM;
+		goto end;
+	}
+
+	for (i = 0; i < *trt_count; i++) {
+		struct trt *trt = &trts[i - nr_bad_entries];
+
+		element.length = sizeof(struct trt);
+		element.pointer = trt;
+
+		status = acpi_extract_package(&(p->package.elements[i]),
+					      &trt_format, &element);
+		if (ACPI_FAILURE(status)) {
+			nr_bad_entries++;
+			pr_warn("_TRT package %d is invalid, ignored\n", i);
+			continue;
+		}
+		if (!create_dev)
+			continue;
+
+		if (!acpi_fetch_acpi_dev(trt->source))
+			pr_warn("Failed to get source ACPI device\n");
+
+		if (!acpi_fetch_acpi_dev(trt->target))
+			pr_warn("Failed to get target ACPI device\n");
+	}
+
+	result = 0;
+
+	*trtp = trts;
+	/* don't count bad entries */
+	*trt_count -= nr_bad_entries;
+end:
+	kfree(buffer.pointer);
+	return result;
+}
+EXPORT_SYMBOL(acpi_parse_trt);
+
+/**
+ * acpi_parse_art - Parse Active Relationship Table _ART
+ *
+ * @handle: ACPI handle of the device contains _ART
+ * @art_count: the number of valid entries resulted from parsing _ART
+ * @artp: pointer to pointer of array of art entries in parsing result
+ * @create_dev: whether to create platform devices for target and source
+ *
+ */
+int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp,
+		bool create_dev)
+{
+	acpi_status status;
+	int result = 0;
+	int i;
+	int nr_bad_entries = 0;
+	struct art *arts;
+	union acpi_object *p;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer element = { 0, NULL };
+	struct acpi_buffer art_format =	{
+		sizeof("RRNNNNNNNNNNN"), "RRNNNNNNNNNNN" };
+
+	status = acpi_evaluate_object(handle, "_ART", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buffer.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		pr_err("Invalid _ART data\n");
+		result = -EFAULT;
+		goto end;
+	}
+
+	/* ignore p->package.elements[0], as this is _ART Revision field */
+	*art_count = p->package.count - 1;
+	arts = kcalloc(*art_count, sizeof(struct art), GFP_KERNEL);
+	if (!arts) {
+		result = -ENOMEM;
+		goto end;
+	}
+
+	for (i = 0; i < *art_count; i++) {
+		struct art *art = &arts[i - nr_bad_entries];
+
+		element.length = sizeof(struct art);
+		element.pointer = art;
+
+		status = acpi_extract_package(&(p->package.elements[i + 1]),
+					      &art_format, &element);
+		if (ACPI_FAILURE(status)) {
+			pr_warn("_ART package %d is invalid, ignored", i);
+			nr_bad_entries++;
+			continue;
+		}
+		if (!create_dev)
+			continue;
+
+		if (!acpi_fetch_acpi_dev(art->source))
+			pr_warn("Failed to get source ACPI device\n");
+
+		if (!acpi_fetch_acpi_dev(art->target))
+			pr_warn("Failed to get target ACPI device\n");
+	}
+
+	*artp = arts;
+	/* don't count bad entries */
+	*art_count -= nr_bad_entries;
+end:
+	kfree(buffer.pointer);
+	return result;
+}
+EXPORT_SYMBOL(acpi_parse_art);
+
+
+/* get device name from acpi handle */
+static void get_single_name(acpi_handle handle, char *name)
+{
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER};
+
+	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer)))
+		pr_warn("Failed to get device name from acpi handle\n");
+	else {
+		memcpy(name, buffer.pointer, ACPI_NAMESEG_SIZE);
+		kfree(buffer.pointer);
+	}
+}
+
+static int fill_art(char __user *ubuf)
+{
+	int i;
+	int ret;
+	int count;
+	int art_len;
+	struct art *arts = NULL;
+	union art_object *art_user;
+
+	ret = acpi_parse_art(acpi_thermal_rel_handle, &count, &arts, false);
+	if (ret)
+		goto free_art;
+	art_len = count * sizeof(union art_object);
+	art_user = kzalloc(art_len, GFP_KERNEL);
+	if (!art_user) {
+		ret = -ENOMEM;
+		goto free_art;
+	}
+	/* now fill in user art data */
+	for (i = 0; i < count; i++) {
+		/* userspace art needs device name instead of acpi reference */
+		get_single_name(arts[i].source, art_user[i].source_device);
+		get_single_name(arts[i].target, art_user[i].target_device);
+		/* copy the rest int data in addition to source and target */
+		BUILD_BUG_ON(sizeof(art_user[i].data) !=
+			     sizeof(u64) * (ACPI_NR_ART_ELEMENTS - 2));
+		memcpy(&art_user[i].data, &arts[i].data, sizeof(art_user[i].data));
+	}
+
+	if (copy_to_user(ubuf, art_user, art_len))
+		ret = -EFAULT;
+	kfree(art_user);
+free_art:
+	kfree(arts);
+	return ret;
+}
+
+static int fill_trt(char __user *ubuf)
+{
+	int i;
+	int ret;
+	int count;
+	int trt_len;
+	struct trt *trts = NULL;
+	union trt_object *trt_user;
+
+	ret = acpi_parse_trt(acpi_thermal_rel_handle, &count, &trts, false);
+	if (ret)
+		goto free_trt;
+	trt_len = count * sizeof(union trt_object);
+	trt_user = kzalloc(trt_len, GFP_KERNEL);
+	if (!trt_user) {
+		ret = -ENOMEM;
+		goto free_trt;
+	}
+	/* now fill in user trt data */
+	for (i = 0; i < count; i++) {
+		/* userspace trt needs device name instead of acpi reference */
+		get_single_name(trts[i].source, trt_user[i].source_device);
+		get_single_name(trts[i].target, trt_user[i].target_device);
+		trt_user[i].sample_period = trts[i].sample_period;
+		trt_user[i].influence = trts[i].influence;
+	}
+
+	if (copy_to_user(ubuf, trt_user, trt_len))
+		ret = -EFAULT;
+	kfree(trt_user);
+free_trt:
+	kfree(trts);
+	return ret;
+}
+
+static long acpi_thermal_rel_ioctl(struct file *f, unsigned int cmd,
+				   unsigned long __arg)
+{
+	int ret = 0;
+	unsigned long length = 0;
+	int count = 0;
+	char __user *arg = (void __user *)__arg;
+	struct trt *trts = NULL;
+	struct art *arts = NULL;
+
+	switch (cmd) {
+	case ACPI_THERMAL_GET_TRT_COUNT:
+		ret = acpi_parse_trt(acpi_thermal_rel_handle, &count,
+				&trts, false);
+		kfree(trts);
+		if (!ret)
+			return put_user(count, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_TRT_LEN:
+		ret = acpi_parse_trt(acpi_thermal_rel_handle, &count,
+				&trts, false);
+		kfree(trts);
+		length = count * sizeof(union trt_object);
+		if (!ret)
+			return put_user(length, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_TRT:
+		return fill_trt(arg);
+	case ACPI_THERMAL_GET_ART_COUNT:
+		ret = acpi_parse_art(acpi_thermal_rel_handle, &count,
+				&arts, false);
+		kfree(arts);
+		if (!ret)
+			return put_user(count, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_ART_LEN:
+		ret = acpi_parse_art(acpi_thermal_rel_handle, &count,
+				&arts, false);
+		kfree(arts);
+		length = count * sizeof(union art_object);
+		if (!ret)
+			return put_user(length, (unsigned long __user *)__arg);
+		return ret;
+
+	case ACPI_THERMAL_GET_ART:
+		return fill_art(arg);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations acpi_thermal_rel_fops = {
+	.owner		= THIS_MODULE,
+	.open		= acpi_thermal_rel_open,
+	.release	= acpi_thermal_rel_release,
+	.unlocked_ioctl	= acpi_thermal_rel_ioctl,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice acpi_thermal_rel_misc_device = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	"acpi_thermal_rel",
+	&acpi_thermal_rel_fops
+};
+
+int acpi_thermal_rel_misc_device_add(acpi_handle handle)
+{
+	acpi_thermal_rel_handle = handle;
+
+	return misc_register(&acpi_thermal_rel_misc_device);
+}
+EXPORT_SYMBOL(acpi_thermal_rel_misc_device_add);
+
+int acpi_thermal_rel_misc_device_remove(acpi_handle handle)
+{
+	misc_deregister(&acpi_thermal_rel_misc_device);
+
+	return 0;
+}
+EXPORT_SYMBOL(acpi_thermal_rel_misc_device_remove);
+
+MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>");
+MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@intel.com");
+MODULE_DESCRIPTION("Intel acpi thermal rel misc dev driver");
+MODULE_LICENSE("GPL v2");