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, 752 insertions, 0 deletions

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
new file mode 100644
index 000000000..74842b453
--- /dev/null
+++ b/net/core/sysctl_net_core.c
@@ -0,0 +1,752 @@
+// SPDX-License-Identifier: GPL-2.0
+/* -*- linux-c -*-
+ * sysctl_net_core.c: sysctl interface to net core subsystem.
+ *
+ * Begun April 1, 1996, Mike Shaver.
+ * Added /proc/sys/net/core directory entry (empty =) ). [MS]
+ */
+
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/sysctl.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/netdevice.h>
+#include <linux/ratelimit.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/sched/isolation.h>
+
+#include <net/ip.h>
+#include <net/sock.h>
+#include <net/net_ratelimit.h>
+#include <net/busy_poll.h>
+#include <net/pkt_sched.h>
+
+#include "dev.h"
+
+static int int_3600 = 3600;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
+
+static int net_msg_warn;	/* Unused, but still a sysctl */
+
+int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0;
+EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net);
+
+/* 0 - Keep current behavior:
+ *     IPv4: inherit all current settings from init_net
+ *     IPv6: reset all settings to default
+ * 1 - Both inherit all current settings from init_net
+ * 2 - Both reset all settings to default
+ * 3 - Both inherit all settings from current netns
+ */
+int sysctl_devconf_inherit_init_net __read_mostly;
+EXPORT_SYMBOL(sysctl_devconf_inherit_init_net);
+
+#if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS)
+static void dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos,
+			 struct cpumask *mask)
+{
+	char kbuf[128];
+	int len;
+
+	if (*ppos || !*lenp) {
+		*lenp = 0;
+		return;
+	}
+
+	len = min(sizeof(kbuf) - 1, *lenp);
+	len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask));
+	if (!len) {
+		*lenp = 0;
+		return;
+	}
+
+	if (len < *lenp)
+		kbuf[len++] = '\n';
+	memcpy(buffer, kbuf, len);
+	*lenp = len;
+	*ppos += len;
+}
+#endif
+
+#ifdef CONFIG_RPS
+
+static struct cpumask *rps_default_mask_cow_alloc(struct net *net)
+{
+	struct cpumask *rps_default_mask;
+
+	if (net->core.rps_default_mask)
+		return net->core.rps_default_mask;
+
+	rps_default_mask = kzalloc(cpumask_size(), GFP_KERNEL);
+	if (!rps_default_mask)
+		return NULL;
+
+	/* pairs with READ_ONCE in rx_queue_default_mask() */
+	WRITE_ONCE(net->core.rps_default_mask, rps_default_mask);
+	return rps_default_mask;
+}
+
+static int rps_default_mask_sysctl(struct ctl_table *table, int write,
+				   void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = (struct net *)table->data;
+	int err = 0;
+
+	rtnl_lock();
+	if (write) {
+		struct cpumask *rps_default_mask = rps_default_mask_cow_alloc(net);
+
+		err = -ENOMEM;
+		if (!rps_default_mask)
+			goto done;
+
+		err = cpumask_parse(buffer, rps_default_mask);
+		if (err)
+			goto done;
+
+		err = rps_cpumask_housekeeping(rps_default_mask);
+		if (err)
+			goto done;
+	} else {
+		dump_cpumask(buffer, lenp, ppos,
+			     net->core.rps_default_mask ? : cpu_none_mask);
+	}
+
+done:
+	rtnl_unlock();
+	return err;
+}
+
+static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned int orig_size, size;
+	int ret, i;
+	struct ctl_table tmp = {
+		.data = &size,
+		.maxlen = sizeof(size),
+		.mode = table->mode
+	};
+	struct rps_sock_flow_table *orig_sock_table, *sock_table;
+	static DEFINE_MUTEX(sock_flow_mutex);
+
+	mutex_lock(&sock_flow_mutex);
+
+	orig_sock_table = rcu_dereference_protected(rps_sock_flow_table,
+					lockdep_is_held(&sock_flow_mutex));
+	size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
+
+	ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+
+	if (write) {
+		if (size) {
+			if (size > 1<<29) {
+				/* Enforce limit to prevent overflow */
+				mutex_unlock(&sock_flow_mutex);
+				return -EINVAL;
+			}
+			size = roundup_pow_of_two(size);
+			if (size != orig_size) {
+				sock_table =
+				    vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size));
+				if (!sock_table) {
+					mutex_unlock(&sock_flow_mutex);
+					return -ENOMEM;
+				}
+				rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1;
+				sock_table->mask = size - 1;
+			} else
+				sock_table = orig_sock_table;
+
+			for (i = 0; i < size; i++)
+				sock_table->ents[i] = RPS_NO_CPU;
+		} else
+			sock_table = NULL;
+
+		if (sock_table != orig_sock_table) {
+			rcu_assign_pointer(rps_sock_flow_table, sock_table);
+			if (sock_table) {
+				static_branch_inc(&rps_needed);
+				static_branch_inc(&rfs_needed);
+			}
+			if (orig_sock_table) {
+				static_branch_dec(&rps_needed);
+				static_branch_dec(&rfs_needed);
+				kvfree_rcu(orig_sock_table);
+			}
+		}
+	}
+
+	mutex_unlock(&sock_flow_mutex);
+
+	return ret;
+}
+#endif /* CONFIG_RPS */
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+static DEFINE_MUTEX(flow_limit_update_mutex);
+
+static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct sd_flow_limit *cur;
+	struct softnet_data *sd;
+	cpumask_var_t mask;
+	int i, len, ret = 0;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (write) {
+		ret = cpumask_parse(buffer, mask);
+		if (ret)
+			goto done;
+
+		mutex_lock(&flow_limit_update_mutex);
+		len = sizeof(*cur) + netdev_flow_limit_table_len;
+		for_each_possible_cpu(i) {
+			sd = &per_cpu(softnet_data, i);
+			cur = rcu_dereference_protected(sd->flow_limit,
+				     lockdep_is_held(&flow_limit_update_mutex));
+			if (cur && !cpumask_test_cpu(i, mask)) {
+				RCU_INIT_POINTER(sd->flow_limit, NULL);
+				kfree_rcu(cur);
+			} else if (!cur && cpumask_test_cpu(i, mask)) {
+				cur = kzalloc_node(len, GFP_KERNEL,
+						   cpu_to_node(i));
+				if (!cur) {
+					/* not unwinding previous changes */
+					ret = -ENOMEM;
+					goto write_unlock;
+				}
+				cur->num_buckets = netdev_flow_limit_table_len;
+				rcu_assign_pointer(sd->flow_limit, cur);
+			}
+		}
+write_unlock:
+		mutex_unlock(&flow_limit_update_mutex);
+	} else {
+		cpumask_clear(mask);
+		rcu_read_lock();
+		for_each_possible_cpu(i) {
+			sd = &per_cpu(softnet_data, i);
+			if (rcu_dereference(sd->flow_limit))
+				cpumask_set_cpu(i, mask);
+		}
+		rcu_read_unlock();
+
+		dump_cpumask(buffer, lenp, ppos, mask);
+	}
+
+done:
+	free_cpumask_var(mask);
+	return ret;
+}
+
+static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned int old, *ptr;
+	int ret;
+
+	mutex_lock(&flow_limit_update_mutex);
+
+	ptr = table->data;
+	old = *ptr;
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (!ret && write && !is_power_of_2(*ptr)) {
+		*ptr = old;
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&flow_limit_update_mutex);
+	return ret;
+}
+#endif /* CONFIG_NET_FLOW_LIMIT */
+
+#ifdef CONFIG_NET_SCHED
+static int set_default_qdisc(struct ctl_table *table, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	char id[IFNAMSIZ];
+	struct ctl_table tbl = {
+		.data = id,
+		.maxlen = IFNAMSIZ,
+	};
+	int ret;
+
+	qdisc_get_default(id, IFNAMSIZ);
+
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		ret = qdisc_set_default(id);
+	return ret;
+}
+#endif
+
+static int proc_do_dev_weight(struct ctl_table *table, int write,
+			   void *buffer, size_t *lenp, loff_t *ppos)
+{
+	static DEFINE_MUTEX(dev_weight_mutex);
+	int ret, weight;
+
+	mutex_lock(&dev_weight_mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (!ret && write) {
+		weight = READ_ONCE(weight_p);
+		WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+		WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+	}
+	mutex_unlock(&dev_weight_mutex);
+
+	return ret;
+}
+
+static int proc_do_rss_key(struct ctl_table *table, int write,
+			   void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table fake_table;
+	char buf[NETDEV_RSS_KEY_LEN * 3];
+
+	snprintf(buf, sizeof(buf), "%*phC", NETDEV_RSS_KEY_LEN, netdev_rss_key);
+	fake_table.data = buf;
+	fake_table.maxlen = sizeof(buf);
+	return proc_dostring(&fake_table, write, buffer, lenp, ppos);
+}
+
+#ifdef CONFIG_BPF_JIT
+static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
+					   void *buffer, size_t *lenp,
+					   loff_t *ppos)
+{
+	int ret, jit_enable = *(int *)table->data;
+	int min = *(int *)table->extra1;
+	int max = *(int *)table->extra2;
+	struct ctl_table tmp = *table;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	tmp.data = &jit_enable;
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret) {
+		if (jit_enable < 2 ||
+		    (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
+			*(int *)table->data = jit_enable;
+			if (jit_enable == 2)
+				pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
+		} else {
+			ret = -EPERM;
+		}
+	}
+
+	if (write && ret && min == max)
+		pr_info_once("CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1.\n");
+
+	return ret;
+}
+
+# ifdef CONFIG_HAVE_EBPF_JIT
+static int
+proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+				    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+# endif /* CONFIG_HAVE_EBPF_JIT */
+
+static int
+proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+				     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
+#endif
+
+static struct ctl_table net_core_table[] = {
+	{
+		.procname	= "wmem_max",
+		.data		= &sysctl_wmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_max",
+		.data		= &sysctl_rmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
+	{
+		.procname	= "wmem_default",
+		.data		= &sysctl_wmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_default",
+		.data		= &sysctl_rmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
+	{
+		.procname	= "dev_weight",
+		.data		= &weight_p,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_do_dev_weight,
+	},
+	{
+		.procname	= "dev_weight_rx_bias",
+		.data		= &dev_weight_rx_bias,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_do_dev_weight,
+	},
+	{
+		.procname	= "dev_weight_tx_bias",
+		.data		= &dev_weight_tx_bias,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_do_dev_weight,
+	},
+	{
+		.procname	= "netdev_max_backlog",
+		.data		= &netdev_max_backlog,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "netdev_rss_key",
+		.data		= &netdev_rss_key,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_do_rss_key,
+	},
+#ifdef CONFIG_BPF_JIT
+	{
+		.procname	= "bpf_jit_enable",
+		.data		= &bpf_jit_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax_bpf_enable,
+# ifdef CONFIG_BPF_JIT_ALWAYS_ON
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_ONE,
+# else
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+# endif
+	},
+# ifdef CONFIG_HAVE_EBPF_JIT
+	{
+		.procname	= "bpf_jit_harden",
+		.data		= &bpf_jit_harden,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax_bpf_restricted,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{
+		.procname	= "bpf_jit_kallsyms",
+		.data		= &bpf_jit_kallsyms,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax_bpf_restricted,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+# endif
+	{
+		.procname	= "bpf_jit_limit",
+		.data		= &bpf_jit_limit,
+		.maxlen		= sizeof(long),
+		.mode		= 0600,
+		.proc_handler	= proc_dolongvec_minmax_bpf_restricted,
+		.extra1		= SYSCTL_LONG_ONE,
+		.extra2		= &bpf_jit_limit_max,
+	},
+#endif
+	{
+		.procname	= "netdev_tstamp_prequeue",
+		.data		= &netdev_tstamp_prequeue,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "message_cost",
+		.data		= &net_ratelimit_state.interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "message_burst",
+		.data		= &net_ratelimit_state.burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "optmem_max",
+		.data		= &sysctl_optmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tstamp_allow_data",
+		.data		= &sysctl_tstamp_allow_data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
+	},
+#ifdef CONFIG_RPS
+	{
+		.procname	= "rps_sock_flow_entries",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= rps_sock_flow_sysctl
+	},
+#endif
+#ifdef CONFIG_NET_FLOW_LIMIT
+	{
+		.procname	= "flow_limit_cpu_bitmap",
+		.mode		= 0644,
+		.proc_handler	= flow_limit_cpu_sysctl
+	},
+	{
+		.procname	= "flow_limit_table_len",
+		.data		= &netdev_flow_limit_table_len,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= flow_limit_table_len_sysctl
+	},
+#endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	{
+		.procname	= "busy_poll",
+		.data		= &sysctl_net_busy_poll,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+	{
+		.procname	= "busy_read",
+		.data		= &sysctl_net_busy_read,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+#endif
+#ifdef CONFIG_NET_SCHED
+	{
+		.procname	= "default_qdisc",
+		.mode		= 0644,
+		.maxlen		= IFNAMSIZ,
+		.proc_handler	= set_default_qdisc
+	},
+#endif
+	{
+		.procname	= "netdev_budget",
+		.data		= &netdev_budget,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "warnings",
+		.data		= &net_msg_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &max_skb_frags,
+	},
+	{
+		.procname	= "netdev_budget_usecs",
+		.data		= &netdev_budget_usecs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+	{
+		.procname	= "fb_tunnels_only_for_init_net",
+		.data		= &sysctl_fb_tunnels_only_for_init_net,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{
+		.procname	= "devconf_inherit_init_net",
+		.data		= &sysctl_devconf_inherit_init_net,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_THREE,
+	},
+	{
+		.procname	= "high_order_alloc_disable",
+		.data		= &net_high_order_alloc_disable_key.key,
+		.maxlen         = sizeof(net_high_order_alloc_disable_key),
+		.mode		= 0644,
+		.proc_handler	= proc_do_static_key,
+	},
+	{
+		.procname	= "gro_normal_batch",
+		.data		= &gro_normal_batch,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "netdev_unregister_timeout_secs",
+		.data		= &netdev_unregister_timeout_secs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &int_3600,
+	},
+	{
+		.procname	= "skb_defer_max",
+		.data		= &sysctl_skb_defer_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+	{ }
+};
+
+static struct ctl_table netns_core_table[] = {
+#if IS_ENABLED(CONFIG_RPS)
+	{
+		.procname	= "rps_default_mask",
+		.data		= &init_net,
+		.mode		= 0644,
+		.proc_handler	= rps_default_mask_sysctl
+	},
+#endif
+	{
+		.procname	= "somaxconn",
+		.data		= &init_net.core.sysctl_somaxconn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.extra1		= SYSCTL_ZERO,
+		.proc_handler	= proc_dointvec_minmax
+	},
+	{
+		.procname	= "txrehash",
+		.data		= &init_net.core.sysctl_txrehash,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+		.proc_handler	= proc_dou8vec_minmax,
+	},
+	{ }
+};
+
+static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
+{
+	/* fallback tunnels for initns only */
+	if (!strncmp(str, "initns", 6))
+		sysctl_fb_tunnels_only_for_init_net = 1;
+	/* no fallback tunnels anywhere */
+	else if (!strncmp(str, "none", 4))
+		sysctl_fb_tunnels_only_for_init_net = 2;
+
+	return 1;
+}
+__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup);
+
+static __net_init int sysctl_core_net_init(struct net *net)
+{
+	struct ctl_table *tbl, *tmp;
+
+	tbl = netns_core_table;
+	if (!net_eq(net, &init_net)) {
+		tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);
+		if (tbl == NULL)
+			goto err_dup;
+
+		for (tmp = tbl; tmp->procname; tmp++)
+			tmp->data += (char *)net - (char *)&init_net;
+	}
+
+	net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl);
+	if (net->core.sysctl_hdr == NULL)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	if (tbl != netns_core_table)
+		kfree(tbl);
+err_dup:
+	return -ENOMEM;
+}
+
+static __net_exit void sysctl_core_net_exit(struct net *net)
+{
+	struct ctl_table *tbl;
+
+	tbl = net->core.sysctl_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->core.sysctl_hdr);
+	BUG_ON(tbl == netns_core_table);
+#if IS_ENABLED(CONFIG_RPS)
+	kfree(net->core.rps_default_mask);
+#endif
+	kfree(tbl);
+}
+
+static __net_initdata struct pernet_operations sysctl_core_ops = {
+	.init = sysctl_core_net_init,
+	.exit = sysctl_core_net_exit,
+};
+
+static __init int sysctl_core_init(void)
+{
+	register_net_sysctl(&init_net, "net/core", net_core_table);
+	return register_pernet_subsys(&sysctl_core_ops);
+}
+
+fs_initcall(sysctl_core_init);