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, 605 insertions, 0 deletions

diff --git a/mm/list_lru.c b/mm/list_lru.c
new file mode 100644
index 000000000..a05e5bef3
--- /dev/null
+++ b/mm/list_lru.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
+ * Authors: David Chinner and Glauber Costa
+ *
+ * Generic LRU infrastructure
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/list_lru.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/memcontrol.h>
+#include "slab.h"
+#include "internal.h"
+
+#ifdef CONFIG_MEMCG_KMEM
+static LIST_HEAD(memcg_list_lrus);
+static DEFINE_MUTEX(list_lrus_mutex);
+
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return lru->memcg_aware;
+}
+
+static void list_lru_register(struct list_lru *lru)
+{
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	mutex_lock(&list_lrus_mutex);
+	list_add(&lru->list, &memcg_list_lrus);
+	mutex_unlock(&list_lrus_mutex);
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	mutex_lock(&list_lrus_mutex);
+	list_del(&lru->list);
+	mutex_unlock(&list_lrus_mutex);
+}
+
+static int lru_shrinker_id(struct list_lru *lru)
+{
+	return lru->shrinker_id;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
+{
+	if (list_lru_memcg_aware(lru) && idx >= 0) {
+		struct list_lru_memcg *mlru = xa_load(&lru->xa, idx);
+
+		return mlru ? &mlru->node[nid] : NULL;
+	}
+	return &lru->node[nid].lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
+		   struct mem_cgroup **memcg_ptr)
+{
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l = &nlru->lru;
+	struct mem_cgroup *memcg = NULL;
+
+	if (!list_lru_memcg_aware(lru))
+		goto out;
+
+	memcg = mem_cgroup_from_slab_obj(ptr);
+	if (!memcg)
+		goto out;
+
+	l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+out:
+	if (memcg_ptr)
+		*memcg_ptr = memcg;
+	return l;
+}
+#else
+static void list_lru_register(struct list_lru *lru)
+{
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+}
+
+static int lru_shrinker_id(struct list_lru *lru)
+{
+	return -1;
+}
+
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return false;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
+{
+	return &lru->node[nid].lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
+		   struct mem_cgroup **memcg_ptr)
+{
+	if (memcg_ptr)
+		*memcg_ptr = NULL;
+	return &lru->node[nid].lru;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+bool list_lru_add(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct mem_cgroup *memcg;
+	struct list_lru_one *l;
+
+	spin_lock(&nlru->lock);
+	if (list_empty(item)) {
+		l = list_lru_from_kmem(lru, nid, item, &memcg);
+		list_add_tail(item, &l->list);
+		/* Set shrinker bit if the first element was added */
+		if (!l->nr_items++)
+			set_shrinker_bit(memcg, nid,
+					 lru_shrinker_id(lru));
+		nlru->nr_items++;
+		spin_unlock(&nlru->lock);
+		return true;
+	}
+	spin_unlock(&nlru->lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_add);
+
+bool list_lru_del(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
+
+	spin_lock(&nlru->lock);
+	if (!list_empty(item)) {
+		l = list_lru_from_kmem(lru, nid, item, NULL);
+		list_del_init(item);
+		l->nr_items--;
+		nlru->nr_items--;
+		spin_unlock(&nlru->lock);
+		return true;
+	}
+	spin_unlock(&nlru->lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_del);
+
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
+{
+	list_del_init(item);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate);
+
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+			   struct list_head *head)
+{
+	list_move(item, head);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate_move);
+
+unsigned long list_lru_count_one(struct list_lru *lru,
+				 int nid, struct mem_cgroup *memcg)
+{
+	struct list_lru_one *l;
+	long count;
+
+	rcu_read_lock();
+	l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+	count = l ? READ_ONCE(l->nr_items) : 0;
+	rcu_read_unlock();
+
+	if (unlikely(count < 0))
+		count = 0;
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count_one);
+
+unsigned long list_lru_count_node(struct list_lru *lru, int nid)
+{
+	struct list_lru_node *nlru;
+
+	nlru = &lru->node[nid];
+	return nlru->nr_items;
+}
+EXPORT_SYMBOL_GPL(list_lru_count_node);
+
+static unsigned long
+__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
+		    list_lru_walk_cb isolate, void *cb_arg,
+		    unsigned long *nr_to_walk)
+{
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
+	struct list_head *item, *n;
+	unsigned long isolated = 0;
+
+restart:
+	l = list_lru_from_memcg_idx(lru, nid, memcg_idx);
+	if (!l)
+		goto out;
+
+	list_for_each_safe(item, n, &l->list) {
+		enum lru_status ret;
+
+		/*
+		 * decrement nr_to_walk first so that we don't livelock if we
+		 * get stuck on large numbers of LRU_RETRY items
+		 */
+		if (!*nr_to_walk)
+			break;
+		--*nr_to_walk;
+
+		ret = isolate(item, l, &nlru->lock, cb_arg);
+		switch (ret) {
+		case LRU_REMOVED_RETRY:
+			assert_spin_locked(&nlru->lock);
+			fallthrough;
+		case LRU_REMOVED:
+			isolated++;
+			nlru->nr_items--;
+			/*
+			 * If the lru lock has been dropped, our list
+			 * traversal is now invalid and so we have to
+			 * restart from scratch.
+			 */
+			if (ret == LRU_REMOVED_RETRY)
+				goto restart;
+			break;
+		case LRU_ROTATE:
+			list_move_tail(item, &l->list);
+			break;
+		case LRU_SKIP:
+			break;
+		case LRU_RETRY:
+			/*
+			 * The lru lock has been dropped, our list traversal is
+			 * now invalid and so we have to restart from scratch.
+			 */
+			assert_spin_locked(&nlru->lock);
+			goto restart;
+		default:
+			BUG();
+		}
+	}
+out:
+	return isolated;
+}
+
+unsigned long
+list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		  list_lru_walk_cb isolate, void *cb_arg,
+		  unsigned long *nr_to_walk)
+{
+	struct list_lru_node *nlru = &lru->node[nid];
+	unsigned long ret;
+
+	spin_lock(&nlru->lock);
+	ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate,
+				  cb_arg, nr_to_walk);
+	spin_unlock(&nlru->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_one);
+
+unsigned long
+list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		      list_lru_walk_cb isolate, void *cb_arg,
+		      unsigned long *nr_to_walk)
+{
+	struct list_lru_node *nlru = &lru->node[nid];
+	unsigned long ret;
+
+	spin_lock_irq(&nlru->lock);
+	ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate,
+				  cb_arg, nr_to_walk);
+	spin_unlock_irq(&nlru->lock);
+	return ret;
+}
+
+unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
+				 list_lru_walk_cb isolate, void *cb_arg,
+				 unsigned long *nr_to_walk)
+{
+	long isolated = 0;
+
+	isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg,
+				      nr_to_walk);
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) {
+		struct list_lru_memcg *mlru;
+		unsigned long index;
+
+		xa_for_each(&lru->xa, index, mlru) {
+			struct list_lru_node *nlru = &lru->node[nid];
+
+			spin_lock(&nlru->lock);
+			isolated += __list_lru_walk_one(lru, nid, index,
+							isolate, cb_arg,
+							nr_to_walk);
+			spin_unlock(&nlru->lock);
+
+			if (*nr_to_walk <= 0)
+				break;
+		}
+	}
+#endif
+
+	return isolated;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_node);
+
+static void init_one_lru(struct list_lru_one *l)
+{
+	INIT_LIST_HEAD(&l->list);
+	l->nr_items = 0;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp)
+{
+	int nid;
+	struct list_lru_memcg *mlru;
+
+	mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp);
+	if (!mlru)
+		return NULL;
+
+	for_each_node(nid)
+		init_one_lru(&mlru->node[nid]);
+
+	return mlru;
+}
+
+static void memcg_list_lru_free(struct list_lru *lru, int src_idx)
+{
+	struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx);
+
+	/*
+	 * The __list_lru_walk_one() can walk the list of this node.
+	 * We need kvfree_rcu() here. And the walking of the list
+	 * is under lru->node[nid]->lock, which can serve as a RCU
+	 * read-side critical section.
+	 */
+	if (mlru)
+		kvfree_rcu(mlru, rcu);
+}
+
+static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+	if (memcg_aware)
+		xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ);
+	lru->memcg_aware = memcg_aware;
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+	XA_STATE(xas, &lru->xa, 0);
+	struct list_lru_memcg *mlru;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	xas_lock_irq(&xas);
+	xas_for_each(&xas, mlru, ULONG_MAX) {
+		kfree(mlru);
+		xas_store(&xas, NULL);
+	}
+	xas_unlock_irq(&xas);
+}
+
+static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid,
+					 int src_idx, struct mem_cgroup *dst_memcg)
+{
+	struct list_lru_node *nlru = &lru->node[nid];
+	int dst_idx = dst_memcg->kmemcg_id;
+	struct list_lru_one *src, *dst;
+
+	/*
+	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+	 * we have to use IRQ-safe primitives here to avoid deadlock.
+	 */
+	spin_lock_irq(&nlru->lock);
+
+	src = list_lru_from_memcg_idx(lru, nid, src_idx);
+	if (!src)
+		goto out;
+	dst = list_lru_from_memcg_idx(lru, nid, dst_idx);
+
+	list_splice_init(&src->list, &dst->list);
+
+	if (src->nr_items) {
+		dst->nr_items += src->nr_items;
+		set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
+		src->nr_items = 0;
+	}
+out:
+	spin_unlock_irq(&nlru->lock);
+}
+
+static void memcg_reparent_list_lru(struct list_lru *lru,
+				    int src_idx, struct mem_cgroup *dst_memcg)
+{
+	int i;
+
+	for_each_node(i)
+		memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg);
+
+	memcg_list_lru_free(lru, src_idx);
+}
+
+void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+	struct cgroup_subsys_state *css;
+	struct list_lru *lru;
+	int src_idx = memcg->kmemcg_id;
+
+	/*
+	 * Change kmemcg_id of this cgroup and all its descendants to the
+	 * parent's id, and then move all entries from this cgroup's list_lrus
+	 * to ones of the parent.
+	 *
+	 * After we have finished, all list_lrus corresponding to this cgroup
+	 * are guaranteed to remain empty. So we can safely free this cgroup's
+	 * list lrus in memcg_list_lru_free().
+	 *
+	 * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc()
+	 * from allocating list lrus for this cgroup after memcg_list_lru_free()
+	 * call.
+	 */
+	rcu_read_lock();
+	css_for_each_descendant_pre(css, &memcg->css) {
+		struct mem_cgroup *child;
+
+		child = mem_cgroup_from_css(css);
+		WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id);
+	}
+	rcu_read_unlock();
+
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &memcg_list_lrus, list)
+		memcg_reparent_list_lru(lru, src_idx, parent);
+	mutex_unlock(&list_lrus_mutex);
+}
+
+static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg,
+					    struct list_lru *lru)
+{
+	int idx = memcg->kmemcg_id;
+
+	return idx < 0 || xa_load(&lru->xa, idx);
+}
+
+int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
+			 gfp_t gfp)
+{
+	int i;
+	unsigned long flags;
+	struct list_lru_memcg_table {
+		struct list_lru_memcg *mlru;
+		struct mem_cgroup *memcg;
+	} *table;
+	XA_STATE(xas, &lru->xa, 0);
+
+	if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru))
+		return 0;
+
+	gfp &= GFP_RECLAIM_MASK;
+	table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp);
+	if (!table)
+		return -ENOMEM;
+
+	/*
+	 * Because the list_lru can be reparented to the parent cgroup's
+	 * list_lru, we should make sure that this cgroup and all its
+	 * ancestors have allocated list_lru_memcg.
+	 */
+	for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) {
+		if (memcg_list_lru_allocated(memcg, lru))
+			break;
+
+		table[i].memcg = memcg;
+		table[i].mlru = memcg_init_list_lru_one(gfp);
+		if (!table[i].mlru) {
+			while (i--)
+				kfree(table[i].mlru);
+			kfree(table);
+			return -ENOMEM;
+		}
+	}
+
+	xas_lock_irqsave(&xas, flags);
+	while (i--) {
+		int index = READ_ONCE(table[i].memcg->kmemcg_id);
+		struct list_lru_memcg *mlru = table[i].mlru;
+
+		xas_set(&xas, index);
+retry:
+		if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) {
+			kfree(mlru);
+		} else {
+			xas_store(&xas, mlru);
+			if (xas_error(&xas) == -ENOMEM) {
+				xas_unlock_irqrestore(&xas, flags);
+				if (xas_nomem(&xas, gfp))
+					xas_set_err(&xas, 0);
+				xas_lock_irqsave(&xas, flags);
+				/*
+				 * The xas lock has been released, this memcg
+				 * can be reparented before us. So reload
+				 * memcg id. More details see the comments
+				 * in memcg_reparent_list_lrus().
+				 */
+				index = READ_ONCE(table[i].memcg->kmemcg_id);
+				if (index < 0)
+					xas_set_err(&xas, 0);
+				else if (!xas_error(&xas) && index != xas.xa_index)
+					xas_set(&xas, index);
+				goto retry;
+			}
+		}
+	}
+	/* xas_nomem() is used to free memory instead of memory allocation. */
+	if (xas.xa_alloc)
+		xas_nomem(&xas, gfp);
+	xas_unlock_irqrestore(&xas, flags);
+	kfree(table);
+
+	return xas_error(&xas);
+}
+#else
+static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+		    struct lock_class_key *key, struct shrinker *shrinker)
+{
+	int i;
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (shrinker)
+		lru->shrinker_id = shrinker->id;
+	else
+		lru->shrinker_id = -1;
+#endif
+
+	lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL);
+	if (!lru->node)
+		return -ENOMEM;
+
+	for_each_node(i) {
+		spin_lock_init(&lru->node[i].lock);
+		if (key)
+			lockdep_set_class(&lru->node[i].lock, key);
+		init_one_lru(&lru->node[i].lru);
+	}
+
+	memcg_init_list_lru(lru, memcg_aware);
+	list_lru_register(lru);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__list_lru_init);
+
+void list_lru_destroy(struct list_lru *lru)
+{
+	/* Already destroyed or not yet initialized? */
+	if (!lru->node)
+		return;
+
+	list_lru_unregister(lru);
+
+	memcg_destroy_list_lru(lru);
+	kfree(lru->node);
+	lru->node = NULL;
+
+#ifdef CONFIG_MEMCG_KMEM
+	lru->shrinker_id = -1;
+#endif
+}
+EXPORT_SYMBOL_GPL(list_lru_destroy);