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, 749 insertions, 0 deletions

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
new file mode 100644
index 000000000..5a165286e
--- /dev/null
+++ b/net/core/sock_reuseport.c
@@ -0,0 +1,749 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * To speed up listener socket lookup, create an array to store all sockets
+ * listening on the same port.  This allows a decision to be made after finding
+ * the first socket.  An optional BPF program can also be configured for
+ * selecting the socket index from the array of available sockets.
+ */
+
+#include <net/ip.h>
+#include <net/sock_reuseport.h>
+#include <linux/bpf.h>
+#include <linux/idr.h>
+#include <linux/filter.h>
+#include <linux/rcupdate.h>
+
+#define INIT_SOCKS 128
+
+DEFINE_SPINLOCK(reuseport_lock);
+
+static DEFINE_IDA(reuseport_ida);
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany);
+
+void reuseport_has_conns_set(struct sock *sk)
+{
+	struct sock_reuseport *reuse;
+
+	if (!rcu_access_pointer(sk->sk_reuseport_cb))
+		return;
+
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	if (likely(reuse))
+		reuse->has_conns = 1;
+	spin_unlock_bh(&reuseport_lock);
+}
+EXPORT_SYMBOL(reuseport_has_conns_set);
+
+static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse)
+{
+	/* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */
+	WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1);
+}
+
+static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse)
+{
+	/* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */
+	WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1);
+}
+
+static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse)
+{
+	if (sk->sk_incoming_cpu >= 0)
+		__reuseport_get_incoming_cpu(reuse);
+}
+
+static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse)
+{
+	if (sk->sk_incoming_cpu >= 0)
+		__reuseport_put_incoming_cpu(reuse);
+}
+
+void reuseport_update_incoming_cpu(struct sock *sk, int val)
+{
+	struct sock_reuseport *reuse;
+	int old_sk_incoming_cpu;
+
+	if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) {
+		/* Paired with REAE_ONCE() in sk_incoming_cpu_update()
+		 * and compute_score().
+		 */
+		WRITE_ONCE(sk->sk_incoming_cpu, val);
+		return;
+	}
+
+	spin_lock_bh(&reuseport_lock);
+
+	/* This must be done under reuseport_lock to avoid a race with
+	 * reuseport_grow(), which accesses sk->sk_incoming_cpu without
+	 * lock_sock() when detaching a shutdown()ed sk.
+	 *
+	 * Paired with READ_ONCE() in reuseport_select_sock_by_hash().
+	 */
+	old_sk_incoming_cpu = sk->sk_incoming_cpu;
+	WRITE_ONCE(sk->sk_incoming_cpu, val);
+
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+
+	/* reuseport_grow() has detached a closed sk. */
+	if (!reuse)
+		goto out;
+
+	if (old_sk_incoming_cpu < 0 && val >= 0)
+		__reuseport_get_incoming_cpu(reuse);
+	else if (old_sk_incoming_cpu >= 0 && val < 0)
+		__reuseport_put_incoming_cpu(reuse);
+
+out:
+	spin_unlock_bh(&reuseport_lock);
+}
+
+static int reuseport_sock_index(struct sock *sk,
+				const struct sock_reuseport *reuse,
+				bool closed)
+{
+	int left, right;
+
+	if (!closed) {
+		left = 0;
+		right = reuse->num_socks;
+	} else {
+		left = reuse->max_socks - reuse->num_closed_socks;
+		right = reuse->max_socks;
+	}
+
+	for (; left < right; left++)
+		if (reuse->socks[left] == sk)
+			return left;
+	return -1;
+}
+
+static void __reuseport_add_sock(struct sock *sk,
+				 struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->num_socks] = sk;
+	/* paired with smp_rmb() in reuseport_(select|migrate)_sock() */
+	smp_wmb();
+	reuse->num_socks++;
+	reuseport_get_incoming_cpu(sk, reuse);
+}
+
+static bool __reuseport_detach_sock(struct sock *sk,
+				    struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, false);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
+	reuse->num_socks--;
+	reuseport_put_incoming_cpu(sk, reuse);
+
+	return true;
+}
+
+static void __reuseport_add_closed_sock(struct sock *sk,
+					struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk;
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1);
+	reuseport_get_incoming_cpu(sk, reuse);
+}
+
+static bool __reuseport_detach_closed_sock(struct sock *sk,
+					   struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, true);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1);
+	reuseport_put_incoming_cpu(sk, reuse);
+
+	return true;
+}
+
+static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
+{
+	unsigned int size = sizeof(struct sock_reuseport) +
+		      sizeof(struct sock *) * max_socks;
+	struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
+
+	if (!reuse)
+		return NULL;
+
+	reuse->max_socks = max_socks;
+
+	RCU_INIT_POINTER(reuse->prog, NULL);
+	return reuse;
+}
+
+int reuseport_alloc(struct sock *sk, bool bind_inany)
+{
+	struct sock_reuseport *reuse;
+	int id, ret = 0;
+
+	/* bh lock used since this function call may precede hlist lock in
+	 * soft irq of receive path or setsockopt from process context
+	 */
+	spin_lock_bh(&reuseport_lock);
+
+	/* Allocation attempts can occur concurrently via the setsockopt path
+	 * and the bind/hash path.  Nothing to do when we lose the race.
+	 */
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	if (reuse) {
+		if (reuse->num_closed_socks) {
+			/* sk was shutdown()ed before */
+			ret = reuseport_resurrect(sk, reuse, NULL, bind_inany);
+			goto out;
+		}
+
+		/* Only set reuse->bind_inany if the bind_inany is true.
+		 * Otherwise, it will overwrite the reuse->bind_inany
+		 * which was set by the bind/hash path.
+		 */
+		if (bind_inany)
+			reuse->bind_inany = bind_inany;
+		goto out;
+	}
+
+	reuse = __reuseport_alloc(INIT_SOCKS);
+	if (!reuse) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	id = ida_alloc(&reuseport_ida, GFP_ATOMIC);
+	if (id < 0) {
+		kfree(reuse);
+		ret = id;
+		goto out;
+	}
+
+	reuse->reuseport_id = id;
+	reuse->bind_inany = bind_inany;
+	reuse->socks[0] = sk;
+	reuse->num_socks = 1;
+	reuseport_get_incoming_cpu(sk, reuse);
+	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+
+out:
+	spin_unlock_bh(&reuseport_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(reuseport_alloc);
+
+static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
+{
+	struct sock_reuseport *more_reuse;
+	u32 more_socks_size, i;
+
+	more_socks_size = reuse->max_socks * 2U;
+	if (more_socks_size > U16_MAX) {
+		if (reuse->num_closed_socks) {
+			/* Make room by removing a closed sk.
+			 * The child has already been migrated.
+			 * Only reqsk left at this point.
+			 */
+			struct sock *sk;
+
+			sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+			RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL);
+			__reuseport_detach_closed_sock(sk, reuse);
+
+			return reuse;
+		}
+
+		return NULL;
+	}
+
+	more_reuse = __reuseport_alloc(more_socks_size);
+	if (!more_reuse)
+		return NULL;
+
+	more_reuse->num_socks = reuse->num_socks;
+	more_reuse->num_closed_socks = reuse->num_closed_socks;
+	more_reuse->prog = reuse->prog;
+	more_reuse->reuseport_id = reuse->reuseport_id;
+	more_reuse->bind_inany = reuse->bind_inany;
+	more_reuse->has_conns = reuse->has_conns;
+	more_reuse->incoming_cpu = reuse->incoming_cpu;
+
+	memcpy(more_reuse->socks, reuse->socks,
+	       reuse->num_socks * sizeof(struct sock *));
+	memcpy(more_reuse->socks +
+	       (more_reuse->max_socks - more_reuse->num_closed_socks),
+	       reuse->socks + (reuse->max_socks - reuse->num_closed_socks),
+	       reuse->num_closed_socks * sizeof(struct sock *));
+	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
+
+	for (i = 0; i < reuse->max_socks; ++i)
+		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
+				   more_reuse);
+
+	/* Note: we use kfree_rcu here instead of reuseport_free_rcu so
+	 * that reuse and more_reuse can temporarily share a reference
+	 * to prog.
+	 */
+	kfree_rcu(reuse, rcu);
+	return more_reuse;
+}
+
+static void reuseport_free_rcu(struct rcu_head *head)
+{
+	struct sock_reuseport *reuse;
+
+	reuse = container_of(head, struct sock_reuseport, rcu);
+	sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1));
+	ida_free(&reuseport_ida, reuse->reuseport_id);
+	kfree(reuse);
+}
+
+/**
+ *  reuseport_add_sock - Add a socket to the reuseport group of another.
+ *  @sk:  New socket to add to the group.
+ *  @sk2: Socket belonging to the existing reuseport group.
+ *  @bind_inany: Whether or not the group is bound to a local INANY address.
+ *
+ *  May return ENOMEM and not add socket to group under memory pressure.
+ */
+int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
+{
+	struct sock_reuseport *old_reuse, *reuse;
+
+	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
+		int err = reuseport_alloc(sk2, bind_inany);
+
+		if (err)
+			return err;
+	}
+
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					      lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_closed_socks) {
+		/* sk was shutdown()ed before */
+		int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany);
+
+		spin_unlock_bh(&reuseport_lock);
+		return err;
+	}
+
+	if (old_reuse && old_reuse->num_socks != 1) {
+		spin_unlock_bh(&reuseport_lock);
+		return -EBUSY;
+	}
+
+	if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
+		reuse = reuseport_grow(reuse);
+		if (!reuse) {
+			spin_unlock_bh(&reuseport_lock);
+			return -ENOMEM;
+		}
+	}
+
+	__reuseport_add_sock(sk, reuse);
+	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+
+	spin_unlock_bh(&reuseport_lock);
+
+	if (old_reuse)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
+	return 0;
+}
+EXPORT_SYMBOL(reuseport_add_sock);
+
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany)
+{
+	if (old_reuse == reuse) {
+		/* If sk was in the same reuseport group, just pop sk out of
+		 * the closed section and push sk into the listening section.
+		 */
+		__reuseport_detach_closed_sock(sk, old_reuse);
+		__reuseport_add_sock(sk, old_reuse);
+		return 0;
+	}
+
+	if (!reuse) {
+		/* In bind()/listen() path, we cannot carry over the eBPF prog
+		 * for the shutdown()ed socket. In setsockopt() path, we should
+		 * not change the eBPF prog of listening sockets by attaching a
+		 * prog to the shutdown()ed socket. Thus, we will allocate a new
+		 * reuseport group and detach sk from the old group.
+		 */
+		int id;
+
+		reuse = __reuseport_alloc(INIT_SOCKS);
+		if (!reuse)
+			return -ENOMEM;
+
+		id = ida_alloc(&reuseport_ida, GFP_ATOMIC);
+		if (id < 0) {
+			kfree(reuse);
+			return id;
+		}
+
+		reuse->reuseport_id = id;
+		reuse->bind_inany = bind_inany;
+	} else {
+		/* Move sk from the old group to the new one if
+		 * - all the other listeners in the old group were close()d or
+		 *   shutdown()ed, and then sk2 has listen()ed on the same port
+		 * OR
+		 * - sk listen()ed without bind() (or with autobind), was
+		 *   shutdown()ed, and then listen()s on another port which
+		 *   sk2 listen()s on.
+		 */
+		if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
+			reuse = reuseport_grow(reuse);
+			if (!reuse)
+				return -ENOMEM;
+		}
+	}
+
+	__reuseport_detach_closed_sock(sk, old_reuse);
+	__reuseport_add_sock(sk, reuse);
+	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+
+	if (old_reuse->num_socks + old_reuse->num_closed_socks == 0)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
+
+	return 0;
+}
+
+void reuseport_detach_sock(struct sock *sk)
+{
+	struct sock_reuseport *reuse;
+
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+
+	/* reuseport_grow() has detached a closed sk */
+	if (!reuse)
+		goto out;
+
+	/* Notify the bpf side. The sk may be added to a sockarray
+	 * map. If so, sockarray logic will remove it from the map.
+	 *
+	 * Other bpf map types that work with reuseport, like sockmap,
+	 * don't need an explicit callback from here. They override sk
+	 * unhash/close ops to remove the sk from the map before we
+	 * get to this point.
+	 */
+	bpf_sk_reuseport_detach(sk);
+
+	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
+
+	if (!__reuseport_detach_closed_sock(sk, reuse))
+		__reuseport_detach_sock(sk, reuse);
+
+	if (reuse->num_socks + reuse->num_closed_socks == 0)
+		call_rcu(&reuse->rcu, reuseport_free_rcu);
+
+out:
+	spin_unlock_bh(&reuseport_lock);
+}
+EXPORT_SYMBOL(reuseport_detach_sock);
+
+void reuseport_stop_listen_sock(struct sock *sk)
+{
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		struct sock_reuseport *reuse;
+		struct bpf_prog *prog;
+
+		spin_lock_bh(&reuseport_lock);
+
+		reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+						  lockdep_is_held(&reuseport_lock));
+		prog = rcu_dereference_protected(reuse->prog,
+						 lockdep_is_held(&reuseport_lock));
+
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) ||
+		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
+			/* Migration capable, move sk from the listening section
+			 * to the closed section.
+			 */
+			bpf_sk_reuseport_detach(sk);
+
+			__reuseport_detach_sock(sk, reuse);
+			__reuseport_add_closed_sock(sk, reuse);
+
+			spin_unlock_bh(&reuseport_lock);
+			return;
+		}
+
+		spin_unlock_bh(&reuseport_lock);
+	}
+
+	/* Not capable to do migration, detach immediately */
+	reuseport_detach_sock(sk);
+}
+EXPORT_SYMBOL(reuseport_stop_listen_sock);
+
+static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
+				   struct bpf_prog *prog, struct sk_buff *skb,
+				   int hdr_len)
+{
+	struct sk_buff *nskb = NULL;
+	u32 index;
+
+	if (skb_shared(skb)) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			return NULL;
+		skb = nskb;
+	}
+
+	/* temporarily advance data past protocol header */
+	if (!pskb_pull(skb, hdr_len)) {
+		kfree_skb(nskb);
+		return NULL;
+	}
+	index = bpf_prog_run_save_cb(prog, skb);
+	__skb_push(skb, hdr_len);
+
+	consume_skb(nskb);
+
+	if (index >= socks)
+		return NULL;
+
+	return reuse->socks[index];
+}
+
+static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse,
+						  u32 hash, u16 num_socks)
+{
+	struct sock *first_valid_sk = NULL;
+	int i, j;
+
+	i = j = reciprocal_scale(hash, num_socks);
+	do {
+		struct sock *sk = reuse->socks[i];
+
+		if (sk->sk_state != TCP_ESTABLISHED) {
+			/* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */
+			if (!READ_ONCE(reuse->incoming_cpu))
+				return sk;
+
+			/* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */
+			if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
+				return sk;
+
+			if (!first_valid_sk)
+				first_valid_sk = sk;
+		}
+
+		i++;
+		if (i >= num_socks)
+			i = 0;
+	} while (i != j);
+
+	return first_valid_sk;
+}
+
+/**
+ *  reuseport_select_sock - Select a socket from an SO_REUSEPORT group.
+ *  @sk: First socket in the group.
+ *  @hash: When no BPF filter is available, use this hash to select.
+ *  @skb: skb to run through BPF filter.
+ *  @hdr_len: BPF filter expects skb data pointer at payload data.  If
+ *    the skb does not yet point at the payload, this parameter represents
+ *    how far the pointer needs to advance to reach the payload.
+ *  Returns a socket that should receive the packet (or NULL on error).
+ */
+struct sock *reuseport_select_sock(struct sock *sk,
+				   u32 hash,
+				   struct sk_buff *skb,
+				   int hdr_len)
+{
+	struct sock_reuseport *reuse;
+	struct bpf_prog *prog;
+	struct sock *sk2 = NULL;
+	u16 socks;
+
+	rcu_read_lock();
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+
+	/* if memory allocation failed or add call is not yet complete */
+	if (!reuse)
+		goto out;
+
+	prog = rcu_dereference(reuse->prog);
+	socks = READ_ONCE(reuse->num_socks);
+	if (likely(socks)) {
+		/* paired with smp_wmb() in __reuseport_add_sock() */
+		smp_rmb();
+
+		if (!prog || !skb)
+			goto select_by_hash;
+
+		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash);
+		else
+			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
+
+select_by_hash:
+		/* no bpf or invalid bpf result: fall back to hash usage */
+		if (!sk2)
+			sk2 = reuseport_select_sock_by_hash(reuse, hash, socks);
+	}
+
+out:
+	rcu_read_unlock();
+	return sk2;
+}
+EXPORT_SYMBOL(reuseport_select_sock);
+
+/**
+ *  reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group.
+ *  @sk: close()ed or shutdown()ed socket in the group.
+ *  @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or
+ *    NEW_SYN_RECV request socket during 3WHS.
+ *  @skb: skb to run through BPF filter.
+ *  Returns a socket (with sk_refcnt +1) that should accept the child socket
+ *  (or NULL on error).
+ */
+struct sock *reuseport_migrate_sock(struct sock *sk,
+				    struct sock *migrating_sk,
+				    struct sk_buff *skb)
+{
+	struct sock_reuseport *reuse;
+	struct sock *nsk = NULL;
+	bool allocated = false;
+	struct bpf_prog *prog;
+	u16 socks;
+	u32 hash;
+
+	rcu_read_lock();
+
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (!reuse)
+		goto out;
+
+	socks = READ_ONCE(reuse->num_socks);
+	if (unlikely(!socks))
+		goto failure;
+
+	/* paired with smp_wmb() in __reuseport_add_sock() */
+	smp_rmb();
+
+	hash = migrating_sk->sk_hash;
+	prog = rcu_dereference(reuse->prog);
+	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req))
+			goto select_by_hash;
+		goto failure;
+	}
+
+	if (!skb) {
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			goto failure;
+		allocated = true;
+	}
+
+	nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash);
+
+	if (allocated)
+		kfree_skb(skb);
+
+select_by_hash:
+	if (!nsk)
+		nsk = reuseport_select_sock_by_hash(reuse, hash, socks);
+
+	if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) {
+		nsk = NULL;
+		goto failure;
+	}
+
+out:
+	rcu_read_unlock();
+	return nsk;
+
+failure:
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
+	goto out;
+}
+EXPORT_SYMBOL(reuseport_migrate_sock);
+
+int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
+{
+	struct sock_reuseport *reuse;
+	struct bpf_prog *old_prog;
+
+	if (sk_unhashed(sk)) {
+		int err;
+
+		if (!sk->sk_reuseport)
+			return -EINVAL;
+
+		err = reuseport_alloc(sk, false);
+		if (err)
+			return err;
+	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
+		/* The socket wasn't bound with SO_REUSEPORT */
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	old_prog = rcu_dereference_protected(reuse->prog,
+					     lockdep_is_held(&reuseport_lock));
+	rcu_assign_pointer(reuse->prog, prog);
+	spin_unlock_bh(&reuseport_lock);
+
+	sk_reuseport_prog_free(old_prog);
+	return 0;
+}
+EXPORT_SYMBOL(reuseport_attach_prog);
+
+int reuseport_detach_prog(struct sock *sk)
+{
+	struct sock_reuseport *reuse;
+	struct bpf_prog *old_prog;
+
+	old_prog = NULL;
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+
+	/* reuse must be checked after acquiring the reuseport_lock
+	 * because reuseport_grow() can detach a closed sk.
+	 */
+	if (!reuse) {
+		spin_unlock_bh(&reuseport_lock);
+		return sk->sk_reuseport ? -ENOENT : -EINVAL;
+	}
+
+	if (sk_unhashed(sk) && reuse->num_closed_socks) {
+		spin_unlock_bh(&reuseport_lock);
+		return -ENOENT;
+	}
+
+	old_prog = rcu_replace_pointer(reuse->prog, old_prog,
+				       lockdep_is_held(&reuseport_lock));
+	spin_unlock_bh(&reuseport_lock);
+
+	if (!old_prog)
+		return -ENOENT;
+
+	sk_reuseport_prog_free(old_prog);
+	return 0;
+}
+EXPORT_SYMBOL(reuseport_detach_prog);