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, 360 insertions, 0 deletions

diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c
new file mode 100644
index 000000000..ebc4256a9
--- /dev/null
+++ b/drivers/macintosh/windfarm_smu_sat.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Windfarm PowerMac thermal control.  SMU "satellite" controller sensors.
+ *
+ * Copyright (C) 2005 Paul Mackerras, IBM Corp. <paulus@samba.org>
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/wait.h>
+#include <linux/i2c.h>
+#include <linux/mutex.h>
+
+#include <asm/smu.h>
+#include <asm/pmac_low_i2c.h>
+
+#include "windfarm.h"
+
+#define VERSION "1.0"
+
+/* If the cache is older than 800ms we'll refetch it */
+#define MAX_AGE		msecs_to_jiffies(800)
+
+struct wf_sat {
+	struct kref		ref;
+	int			nr;
+	struct mutex		mutex;
+	unsigned long		last_read; /* jiffies when cache last updated */
+	u8			cache[16];
+	struct list_head	sensors;
+	struct i2c_client	*i2c;
+	struct device_node	*node;
+};
+
+static struct wf_sat *sats[2];
+
+struct wf_sat_sensor {
+	struct list_head	link;
+	int			index;
+	int			index2;		/* used for power sensors */
+	int			shift;
+	struct wf_sat		*sat;
+	struct wf_sensor 	sens;
+};
+
+#define wf_to_sat(c)	container_of(c, struct wf_sat_sensor, sens)
+
+struct smu_sdbp_header *smu_sat_get_sdb_partition(unsigned int sat_id, int id,
+						  unsigned int *size)
+{
+	struct wf_sat *sat;
+	int err;
+	unsigned int i, len;
+	u8 *buf;
+	u8 data[4];
+
+	/* TODO: Add the resulting partition to the device-tree */
+
+	if (sat_id > 1 || (sat = sats[sat_id]) == NULL)
+		return NULL;
+
+	err = i2c_smbus_write_word_data(sat->i2c, 8, id << 8);
+	if (err) {
+		printk(KERN_ERR "smu_sat_get_sdb_part wr error %d\n", err);
+		return NULL;
+	}
+
+	err = i2c_smbus_read_word_data(sat->i2c, 9);
+	if (err < 0) {
+		printk(KERN_ERR "smu_sat_get_sdb_part rd len error\n");
+		return NULL;
+	}
+	len = err;
+	if (len == 0) {
+		printk(KERN_ERR "smu_sat_get_sdb_part no partition %x\n", id);
+		return NULL;
+	}
+
+	len = le16_to_cpu(len);
+	len = (len + 3) & ~3;
+	buf = kmalloc(len, GFP_KERNEL);
+	if (buf == NULL)
+		return NULL;
+
+	for (i = 0; i < len; i += 4) {
+		err = i2c_smbus_read_i2c_block_data(sat->i2c, 0xa, 4, data);
+		if (err < 0) {
+			printk(KERN_ERR "smu_sat_get_sdb_part rd err %d\n",
+			       err);
+			goto fail;
+		}
+		buf[i] = data[1];
+		buf[i+1] = data[0];
+		buf[i+2] = data[3];
+		buf[i+3] = data[2];
+	}
+
+	printk(KERN_DEBUG "sat %d partition %x:", sat_id, id);
+	print_hex_dump(KERN_DEBUG, "  ", DUMP_PREFIX_OFFSET,
+		       16, 1, buf, len, false);
+	if (size)
+		*size = len;
+	return (struct smu_sdbp_header *) buf;
+
+ fail:
+	kfree(buf);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(smu_sat_get_sdb_partition);
+
+/* refresh the cache */
+static int wf_sat_read_cache(struct wf_sat *sat)
+{
+	int err;
+
+	err = i2c_smbus_read_i2c_block_data(sat->i2c, 0x3f, 16, sat->cache);
+	if (err < 0)
+		return err;
+	sat->last_read = jiffies;
+
+#ifdef LOTSA_DEBUG
+	{
+		int i;
+		printk(KERN_DEBUG "wf_sat_get: data is");
+		print_hex_dump(KERN_DEBUG, "  ", DUMP_PREFIX_OFFSET,
+			       16, 1, sat->cache, 16, false);
+	}
+#endif
+	return 0;
+}
+
+static int wf_sat_sensor_get(struct wf_sensor *sr, s32 *value)
+{
+	struct wf_sat_sensor *sens = wf_to_sat(sr);
+	struct wf_sat *sat = sens->sat;
+	int i, err;
+	s32 val;
+
+	if (sat->i2c == NULL)
+		return -ENODEV;
+
+	mutex_lock(&sat->mutex);
+	if (time_after(jiffies, (sat->last_read + MAX_AGE))) {
+		err = wf_sat_read_cache(sat);
+		if (err)
+			goto fail;
+	}
+
+	i = sens->index * 2;
+	val = ((sat->cache[i] << 8) + sat->cache[i+1]) << sens->shift;
+	if (sens->index2 >= 0) {
+		i = sens->index2 * 2;
+		/* 4.12 * 8.8 -> 12.20; shift right 4 to get 16.16 */
+		val = (val * ((sat->cache[i] << 8) + sat->cache[i+1])) >> 4;
+	}
+
+	*value = val;
+	err = 0;
+
+ fail:
+	mutex_unlock(&sat->mutex);
+	return err;
+}
+
+static void wf_sat_release(struct kref *ref)
+{
+	struct wf_sat *sat = container_of(ref, struct wf_sat, ref);
+
+	if (sat->nr >= 0)
+		sats[sat->nr] = NULL;
+	kfree(sat);
+}
+
+static void wf_sat_sensor_release(struct wf_sensor *sr)
+{
+	struct wf_sat_sensor *sens = wf_to_sat(sr);
+	struct wf_sat *sat = sens->sat;
+
+	kfree(sens);
+	kref_put(&sat->ref, wf_sat_release);
+}
+
+static const struct wf_sensor_ops wf_sat_ops = {
+	.get_value	= wf_sat_sensor_get,
+	.release	= wf_sat_sensor_release,
+	.owner		= THIS_MODULE,
+};
+
+static int wf_sat_probe(struct i2c_client *client)
+{
+	struct device_node *dev = client->dev.of_node;
+	struct wf_sat *sat;
+	struct wf_sat_sensor *sens;
+	const u32 *reg;
+	const char *loc;
+	u8 chip, core;
+	struct device_node *child;
+	int shift, cpu, index;
+	char *name;
+	int vsens[2], isens[2];
+
+	sat = kzalloc(sizeof(struct wf_sat), GFP_KERNEL);
+	if (sat == NULL)
+		return -ENOMEM;
+	sat->nr = -1;
+	sat->node = of_node_get(dev);
+	kref_init(&sat->ref);
+	mutex_init(&sat->mutex);
+	sat->i2c = client;
+	INIT_LIST_HEAD(&sat->sensors);
+	i2c_set_clientdata(client, sat);
+
+	vsens[0] = vsens[1] = -1;
+	isens[0] = isens[1] = -1;
+	for_each_child_of_node(dev, child) {
+		reg = of_get_property(child, "reg", NULL);
+		loc = of_get_property(child, "location", NULL);
+		if (reg == NULL || loc == NULL)
+			continue;
+
+		/* the cooked sensors are between 0x30 and 0x37 */
+		if (*reg < 0x30 || *reg > 0x37)
+			continue;
+		index = *reg - 0x30;
+
+		/* expect location to be CPU [AB][01] ... */
+		if (strncmp(loc, "CPU ", 4) != 0)
+			continue;
+		chip = loc[4] - 'A';
+		core = loc[5] - '0';
+		if (chip > 1 || core > 1) {
+			printk(KERN_ERR "wf_sat_create: don't understand "
+			       "location %s for %pOF\n", loc, child);
+			continue;
+		}
+		cpu = 2 * chip + core;
+		if (sat->nr < 0)
+			sat->nr = chip;
+		else if (sat->nr != chip) {
+			printk(KERN_ERR "wf_sat_create: can't cope with "
+			       "multiple CPU chips on one SAT (%s)\n", loc);
+			continue;
+		}
+
+		if (of_node_is_type(child, "voltage-sensor")) {
+			name = "cpu-voltage";
+			shift = 4;
+			vsens[core] = index;
+		} else if (of_node_is_type(child, "current-sensor")) {
+			name = "cpu-current";
+			shift = 8;
+			isens[core] = index;
+		} else if (of_node_is_type(child, "temp-sensor")) {
+			name = "cpu-temp";
+			shift = 10;
+		} else
+			continue;	/* hmmm shouldn't happen */
+
+		/* the +16 is enough for "cpu-voltage-n" */
+		sens = kzalloc(sizeof(struct wf_sat_sensor) + 16, GFP_KERNEL);
+		if (sens == NULL) {
+			printk(KERN_ERR "wf_sat_create: couldn't create "
+			       "%s sensor %d (no memory)\n", name, cpu);
+			continue;
+		}
+		sens->index = index;
+		sens->index2 = -1;
+		sens->shift = shift;
+		sens->sat = sat;
+		sens->sens.ops = &wf_sat_ops;
+		sens->sens.name = (char *) (sens + 1);
+		snprintf((char *)sens->sens.name, 16, "%s-%d", name, cpu);
+
+		if (wf_register_sensor(&sens->sens))
+			kfree(sens);
+		else {
+			list_add(&sens->link, &sat->sensors);
+			kref_get(&sat->ref);
+		}
+	}
+
+	/* make the power sensors */
+	for (core = 0; core < 2; ++core) {
+		if (vsens[core] < 0 || isens[core] < 0)
+			continue;
+		cpu = 2 * sat->nr + core;
+		sens = kzalloc(sizeof(struct wf_sat_sensor) + 16, GFP_KERNEL);
+		if (sens == NULL) {
+			printk(KERN_ERR "wf_sat_create: couldn't create power "
+			       "sensor %d (no memory)\n", cpu);
+			continue;
+		}
+		sens->index = vsens[core];
+		sens->index2 = isens[core];
+		sens->shift = 0;
+		sens->sat = sat;
+		sens->sens.ops = &wf_sat_ops;
+		sens->sens.name = (char *) (sens + 1);
+		snprintf((char *)sens->sens.name, 16, "cpu-power-%d", cpu);
+
+		if (wf_register_sensor(&sens->sens))
+			kfree(sens);
+		else {
+			list_add(&sens->link, &sat->sensors);
+			kref_get(&sat->ref);
+		}
+	}
+
+	if (sat->nr >= 0)
+		sats[sat->nr] = sat;
+
+	return 0;
+}
+
+static void wf_sat_remove(struct i2c_client *client)
+{
+	struct wf_sat *sat = i2c_get_clientdata(client);
+	struct wf_sat_sensor *sens;
+
+	/* release sensors */
+	while(!list_empty(&sat->sensors)) {
+		sens = list_first_entry(&sat->sensors,
+					struct wf_sat_sensor, link);
+		list_del(&sens->link);
+		wf_unregister_sensor(&sens->sens);
+	}
+	sat->i2c = NULL;
+	kref_put(&sat->ref, wf_sat_release);
+}
+
+static const struct i2c_device_id wf_sat_id[] = {
+	{ "MAC,smu-sat", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, wf_sat_id);
+
+static const struct of_device_id wf_sat_of_id[] = {
+	{ .compatible = "smu-sat", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_sat_of_id);
+
+static struct i2c_driver wf_sat_driver = {
+	.driver = {
+		.name		= "wf_smu_sat",
+		.of_match_table = wf_sat_of_id,
+	},
+	.probe_new	= wf_sat_probe,
+	.remove		= wf_sat_remove,
+	.id_table	= wf_sat_id,
+};
+
+module_i2c_driver(wf_sat_driver);
+
+MODULE_AUTHOR("Paul Mackerras <paulus@samba.org>");
+MODULE_DESCRIPTION("SMU satellite sensors for PowerMac thermal control");
+MODULE_LICENSE("GPL");