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, 315 insertions, 0 deletions

diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c
new file mode 100644
index 000000000..898a0bdf8
--- /dev/null
+++ b/drivers/scsi/raid_class.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * raid_class.c - implementation of a simple raid visualisation class
+ *
+ * Copyright (c) 2005 - James Bottomley <James.Bottomley@steeleye.com>
+ *
+ * This class is designed to allow raid attributes to be visualised and
+ * manipulated in a form independent of the underlying raid.  Ultimately this
+ * should work for both hardware and software raids.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/raid_class.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_host.h>
+
+#define RAID_NUM_ATTRS	3
+
+struct raid_internal {
+	struct raid_template r;
+	struct raid_function_template *f;
+	/* The actual attributes */
+	struct device_attribute private_attrs[RAID_NUM_ATTRS];
+	/* The array of null terminated pointers to attributes 
+	 * needed by scsi_sysfs.c */
+	struct device_attribute *attrs[RAID_NUM_ATTRS + 1];
+};
+
+struct raid_component {
+	struct list_head node;
+	struct device dev;
+	int num;
+};
+
+#define to_raid_internal(tmpl)	container_of(tmpl, struct raid_internal, r)
+
+#define tc_to_raid_internal(tcont) ({					\
+	struct raid_template *r =					\
+		container_of(tcont, struct raid_template, raid_attrs);	\
+	to_raid_internal(r);						\
+})
+
+#define ac_to_raid_internal(acont) ({					\
+	struct transport_container *tc =				\
+		container_of(acont, struct transport_container, ac);	\
+	tc_to_raid_internal(tc);					\
+})
+
+#define device_to_raid_internal(dev) ({				\
+	struct attribute_container *ac =				\
+		attribute_container_classdev_to_container(dev);	\
+	ac_to_raid_internal(ac);					\
+})
+	
+
+static int raid_match(struct attribute_container *cont, struct device *dev)
+{
+	/* We have to look for every subsystem that could house
+	 * emulated RAID devices, so start with SCSI */
+	struct raid_internal *i = ac_to_raid_internal(cont);
+
+	if (IS_ENABLED(CONFIG_SCSI) && scsi_is_sdev_device(dev)) {
+		struct scsi_device *sdev = to_scsi_device(dev);
+
+		if (i->f->cookie != sdev->host->hostt)
+			return 0;
+
+		return i->f->is_raid(dev);
+	}
+	/* FIXME: look at other subsystems too */
+	return 0;
+}
+
+static int raid_setup(struct transport_container *tc, struct device *dev,
+		       struct device *cdev)
+{
+	struct raid_data *rd;
+
+	BUG_ON(dev_get_drvdata(cdev));
+
+	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&rd->component_list);
+	dev_set_drvdata(cdev, rd);
+		
+	return 0;
+}
+
+static int raid_remove(struct transport_container *tc, struct device *dev,
+		       struct device *cdev)
+{
+	struct raid_data *rd = dev_get_drvdata(cdev);
+	struct raid_component *rc, *next;
+	dev_printk(KERN_ERR, dev, "RAID REMOVE\n");
+	dev_set_drvdata(cdev, NULL);
+	list_for_each_entry_safe(rc, next, &rd->component_list, node) {
+		list_del(&rc->node);
+		dev_printk(KERN_ERR, rc->dev.parent, "RAID COMPONENT REMOVE\n");
+		device_unregister(&rc->dev);
+	}
+	dev_printk(KERN_ERR, dev, "RAID REMOVE DONE\n");
+	kfree(rd);
+	return 0;
+}
+
+static DECLARE_TRANSPORT_CLASS(raid_class,
+			       "raid_devices",
+			       raid_setup,
+			       raid_remove,
+			       NULL);
+
+static const struct {
+	enum raid_state	value;
+	char		*name;
+} raid_states[] = {
+	{ RAID_STATE_UNKNOWN, "unknown" },
+	{ RAID_STATE_ACTIVE, "active" },
+	{ RAID_STATE_DEGRADED, "degraded" },
+	{ RAID_STATE_RESYNCING, "resyncing" },
+	{ RAID_STATE_OFFLINE, "offline" },
+};
+
+static const char *raid_state_name(enum raid_state state)
+{
+	int i;
+	char *name = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(raid_states); i++) {
+		if (raid_states[i].value == state) {
+			name = raid_states[i].name;
+			break;
+		}
+	}
+	return name;
+}
+
+static struct {
+	enum raid_level value;
+	char *name;
+} raid_levels[] = {
+	{ RAID_LEVEL_UNKNOWN, "unknown" },
+	{ RAID_LEVEL_LINEAR, "linear" },
+	{ RAID_LEVEL_0, "raid0" },
+	{ RAID_LEVEL_1, "raid1" },
+	{ RAID_LEVEL_10, "raid10" },
+	{ RAID_LEVEL_1E, "raid1e" },
+	{ RAID_LEVEL_3, "raid3" },
+	{ RAID_LEVEL_4, "raid4" },
+	{ RAID_LEVEL_5, "raid5" },
+	{ RAID_LEVEL_50, "raid50" },
+	{ RAID_LEVEL_6, "raid6" },
+	{ RAID_LEVEL_JBOD, "jbod" },
+};
+
+static const char *raid_level_name(enum raid_level level)
+{
+	int i;
+	char *name = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(raid_levels); i++) {
+		if (raid_levels[i].value == level) {
+			name = raid_levels[i].name;
+			break;
+		}
+	}
+	return name;
+}
+
+#define raid_attr_show_internal(attr, fmt, var, code)			\
+static ssize_t raid_show_##attr(struct device *dev, 			\
+				struct device_attribute *attr, 		\
+				char *buf)				\
+{									\
+	struct raid_data *rd = dev_get_drvdata(dev);			\
+	code								\
+	return snprintf(buf, 20, #fmt "\n", var);			\
+}
+
+#define raid_attr_ro_states(attr, states, code)				\
+raid_attr_show_internal(attr, %s, name,					\
+	const char *name;						\
+	code								\
+	name = raid_##states##_name(rd->attr);				\
+)									\
+static DEVICE_ATTR(attr, S_IRUGO, raid_show_##attr, NULL)
+
+
+#define raid_attr_ro_internal(attr, code)				\
+raid_attr_show_internal(attr, %d, rd->attr, code)			\
+static DEVICE_ATTR(attr, S_IRUGO, raid_show_##attr, NULL)
+
+#define ATTR_CODE(attr)							\
+	struct raid_internal *i = device_to_raid_internal(dev);		\
+	if (i->f->get_##attr)						\
+		i->f->get_##attr(dev->parent);
+
+#define raid_attr_ro(attr)	raid_attr_ro_internal(attr, )
+#define raid_attr_ro_fn(attr)	raid_attr_ro_internal(attr, ATTR_CODE(attr))
+#define raid_attr_ro_state(attr)	raid_attr_ro_states(attr, attr, )
+#define raid_attr_ro_state_fn(attr)	raid_attr_ro_states(attr, attr, ATTR_CODE(attr))
+
+
+raid_attr_ro_state(level);
+raid_attr_ro_fn(resync);
+raid_attr_ro_state_fn(state);
+
+static void raid_component_release(struct device *dev)
+{
+	struct raid_component *rc =
+		container_of(dev, struct raid_component, dev);
+	dev_printk(KERN_ERR, rc->dev.parent, "COMPONENT RELEASE\n");
+	put_device(rc->dev.parent);
+	kfree(rc);
+}
+
+int raid_component_add(struct raid_template *r,struct device *raid_dev,
+		       struct device *component_dev)
+{
+	struct device *cdev =
+		attribute_container_find_class_device(&r->raid_attrs.ac,
+						      raid_dev);
+	struct raid_component *rc;
+	struct raid_data *rd = dev_get_drvdata(cdev);
+	int err;
+
+	rc = kzalloc(sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&rc->node);
+	device_initialize(&rc->dev);
+	rc->dev.release = raid_component_release;
+	rc->dev.parent = get_device(component_dev);
+	rc->num = rd->component_count++;
+
+	dev_set_name(&rc->dev, "component-%d", rc->num);
+	list_add_tail(&rc->node, &rd->component_list);
+	rc->dev.class = &raid_class.class;
+	err = device_add(&rc->dev);
+	if (err)
+		goto err_out;
+
+	return 0;
+
+err_out:
+	list_del(&rc->node);
+	rd->component_count--;
+	put_device(component_dev);
+	kfree(rc);
+	return err;
+}
+EXPORT_SYMBOL(raid_component_add);
+
+struct raid_template *
+raid_class_attach(struct raid_function_template *ft)
+{
+	struct raid_internal *i = kzalloc(sizeof(struct raid_internal),
+					  GFP_KERNEL);
+	int count = 0;
+
+	if (unlikely(!i))
+		return NULL;
+
+	i->f = ft;
+
+	i->r.raid_attrs.ac.class = &raid_class.class;
+	i->r.raid_attrs.ac.match = raid_match;
+	i->r.raid_attrs.ac.attrs = &i->attrs[0];
+
+	attribute_container_register(&i->r.raid_attrs.ac);
+
+	i->attrs[count++] = &dev_attr_level;
+	i->attrs[count++] = &dev_attr_resync;
+	i->attrs[count++] = &dev_attr_state;
+
+	i->attrs[count] = NULL;
+	BUG_ON(count > RAID_NUM_ATTRS);
+
+	return &i->r;
+}
+EXPORT_SYMBOL(raid_class_attach);
+
+void
+raid_class_release(struct raid_template *r)
+{
+	struct raid_internal *i = to_raid_internal(r);
+
+	BUG_ON(attribute_container_unregister(&i->r.raid_attrs.ac));
+
+	kfree(i);
+}
+EXPORT_SYMBOL(raid_class_release);
+
+static __init int raid_init(void)
+{
+	return transport_class_register(&raid_class);
+}
+
+static __exit void raid_exit(void)
+{
+	transport_class_unregister(&raid_class);
+}
+
+MODULE_AUTHOR("James Bottomley");
+MODULE_DESCRIPTION("RAID device class");
+MODULE_LICENSE("GPL");
+
+module_init(raid_init);
+module_exit(raid_exit);
+