From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- net/ieee802154/6lowpan/reassembly.c | 551 ++++++++++++++++++++++++++++++++++++ 1 file changed, 551 insertions(+) create mode 100644 net/ieee802154/6lowpan/reassembly.c (limited to 'net/ieee802154/6lowpan/reassembly.c') diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c new file mode 100644 index 000000000..a91283d1e --- /dev/null +++ b/net/ieee802154/6lowpan/reassembly.c @@ -0,0 +1,551 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* 6LoWPAN fragment reassembly + * + * Authors: + * Alexander Aring + * + * Based on: net/ipv6/reassembly.c + */ + +#define pr_fmt(fmt) "6LoWPAN: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "6lowpan_i.h" + +static const char lowpan_frags_cache_name[] = "lowpan-frags"; + +static struct inet_frags lowpan_frags; + +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev, struct net_device *ldev); + +static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) +{ + const struct frag_lowpan_compare_key *key = a; + + BUILD_BUG_ON(sizeof(*key) > sizeof(q->key)); + memcpy(&q->key, key, sizeof(*key)); +} + +static void lowpan_frag_expire(struct timer_list *t) +{ + struct inet_frag_queue *frag = from_timer(frag, t, timer); + struct frag_queue *fq; + + fq = container_of(frag, struct frag_queue, q); + + spin_lock(&fq->q.lock); + + if (fq->q.flags & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q); +out: + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q); +} + +static inline struct lowpan_frag_queue * +fq_find(struct net *net, const struct lowpan_802154_cb *cb, + const struct ieee802154_addr *src, + const struct ieee802154_addr *dst) +{ + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + struct frag_lowpan_compare_key key = {}; + struct inet_frag_queue *q; + + key.tag = cb->d_tag; + key.d_size = cb->d_size; + key.src = *src; + key.dst = *dst; + + q = inet_frag_find(ieee802154_lowpan->fqdir, &key); + if (!q) + return NULL; + + return container_of(q, struct lowpan_frag_queue, q); +} + +static int lowpan_frag_queue(struct lowpan_frag_queue *fq, + struct sk_buff *skb, u8 frag_type) +{ + struct sk_buff *prev_tail; + struct net_device *ldev; + int end, offset, err; + + /* inet_frag_queue_* functions use skb->cb; see struct ipfrag_skb_cb + * in inet_fragment.c + */ + BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet_skb_parm)); + BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet6_skb_parm)); + + if (fq->q.flags & INET_FRAG_COMPLETE) + goto err; + + offset = lowpan_802154_cb(skb)->d_offset << 3; + end = lowpan_802154_cb(skb)->d_size; + + /* Is this the final fragment? */ + if (offset + skb->len == end) { + /* If we already have some bits beyond end + * or have different end, the segment is corrupted. + */ + if (end < fq->q.len || + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) + goto err; + fq->q.flags |= INET_FRAG_LAST_IN; + fq->q.len = end; + } else { + if (end > fq->q.len) { + /* Some bits beyond end -> corruption. */ + if (fq->q.flags & INET_FRAG_LAST_IN) + goto err; + fq->q.len = end; + } + } + + ldev = skb->dev; + if (ldev) + skb->dev = NULL; + barrier(); + + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto err; + + fq->q.stamp = skb->tstamp; + fq->q.mono_delivery_time = skb->mono_delivery_time; + if (frag_type == LOWPAN_DISPATCH_FRAG1) + fq->q.flags |= INET_FRAG_FIRST_IN; + + fq->q.meat += skb->len; + add_frag_mem_limit(fq->q.fqdir, skb->truesize); + + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = lowpan_frag_reasm(fq, skb, prev_tail, ldev); + skb->_skb_refdst = orefdst; + return res; + } + skb_dst_drop(skb); + + return -1; +err: + kfree_skb(skb); + return -1; +} + +/* Check if this packet is complete. + * + * It is called with locked fq, and caller must check that + * queue is eligible for reassembly i.e. it is not COMPLETE, + * the last and the first frames arrived and all the bits are here. + */ +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *ldev) +{ + void *reasm_data; + + inet_frag_kill(&fq->q); + + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom; + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); + + skb->dev = ldev; + skb->tstamp = fq->q.stamp; + fq->q.rb_fragments = RB_ROOT; + fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; + + return 1; +out_oom: + net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); + return -1; +} + +static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, + lowpan_rx_result res) +{ + switch (res) { + case RX_QUEUED: + return NET_RX_SUCCESS; + case RX_CONTINUE: + /* nobody cared about this packet */ + net_warn_ratelimited("%s: received unknown dispatch\n", + __func__); + + fallthrough; + default: + /* all others failure */ + return NET_RX_DROP; + } +} + +static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) +{ + int ret; + + if (!lowpan_is_iphc(*skb_network_header(skb))) + return RX_CONTINUE; + + ret = lowpan_iphc_decompress(skb); + if (ret < 0) + return RX_DROP; + + return RX_QUEUED; +} + +static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) +{ + lowpan_rx_result res; + +#define CALL_RXH(rxh) \ + do { \ + res = rxh(skb); \ + if (res != RX_CONTINUE) \ + goto rxh_next; \ + } while (0) + + /* likely at first */ + CALL_RXH(lowpan_frag_rx_h_iphc); + CALL_RXH(lowpan_rx_h_ipv6); + +rxh_next: + return lowpan_frag_rx_handlers_result(skb, res); +#undef CALL_RXH +} + +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 + +static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, + struct lowpan_802154_cb *cb) +{ + bool fail; + u8 high = 0, low = 0; + __be16 d_tag = 0; + + fail = lowpan_fetch_skb(skb, &high, 1); + fail |= lowpan_fetch_skb(skb, &low, 1); + /* remove the dispatch value and use first three bits as high value + * for the datagram size + */ + cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << + LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; + fail |= lowpan_fetch_skb(skb, &d_tag, 2); + cb->d_tag = ntohs(d_tag); + + if (frag_type == LOWPAN_DISPATCH_FRAGN) { + fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); + } else { + skb_reset_network_header(skb); + cb->d_offset = 0; + /* check if datagram_size has ipv6hdr on FRAG1 */ + fail |= cb->d_size < sizeof(struct ipv6hdr); + /* check if we can dereference the dispatch value */ + fail |= !skb->len; + } + + if (unlikely(fail)) + return -EIO; + + return 0; +} + +int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) +{ + struct lowpan_frag_queue *fq; + struct net *net = dev_net(skb->dev); + struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); + struct ieee802154_hdr hdr = {}; + int err; + + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + goto err; + + err = lowpan_get_cb(skb, frag_type, cb); + if (err < 0) + goto err; + + if (frag_type == LOWPAN_DISPATCH_FRAG1) { + err = lowpan_invoke_frag_rx_handlers(skb); + if (err == NET_RX_DROP) + goto err; + } + + if (cb->d_size > IPV6_MIN_MTU) { + net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); + goto err; + } + + fq = fq_find(net, cb, &hdr.source, &hdr.dest); + if (fq != NULL) { + int ret; + + spin_lock(&fq->q.lock); + ret = lowpan_frag_queue(fq, skb, frag_type); + spin_unlock(&fq->q.lock); + + inet_frag_put(&fq->q); + return ret; + } + +err: + kfree_skb(skb); + return -1; +} + +#ifdef CONFIG_SYSCTL + +static struct ctl_table lowpan_frags_ns_ctl_table[] = { + { + .procname = "6lowpanfrag_high_thresh", + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "6lowpanfrag_low_thresh", + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "6lowpanfrag_time", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +/* secret interval has been deprecated */ +static int lowpan_frags_secret_interval_unused; +static struct ctl_table lowpan_frags_ctl_table[] = { + { + .procname = "6lowpanfrag_secret_interval", + .data = &lowpan_frags_secret_interval_unused, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + + table = lowpan_frags_ns_ctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + } + + table[0].data = &ieee802154_lowpan->fqdir->high_thresh; + table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; + table[1].data = &ieee802154_lowpan->fqdir->low_thresh; + table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; + table[2].data = &ieee802154_lowpan->fqdir->timeout; + + hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); + if (hdr == NULL) + goto err_reg; + + ieee802154_lowpan->sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) +{ + struct ctl_table *table; + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + + table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct ctl_table_header *lowpan_ctl_header; + +static int __init lowpan_frags_sysctl_register(void) +{ + lowpan_ctl_header = register_net_sysctl(&init_net, + "net/ieee802154/6lowpan", + lowpan_frags_ctl_table); + return lowpan_ctl_header == NULL ? -ENOMEM : 0; +} + +static void lowpan_frags_sysctl_unregister(void) +{ + unregister_net_sysctl_table(lowpan_ctl_header); +} +#else +static inline int lowpan_frags_ns_sysctl_register(struct net *net) +{ + return 0; +} + +static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) +{ +} + +static inline int __init lowpan_frags_sysctl_register(void) +{ + return 0; +} + +static inline void lowpan_frags_sysctl_unregister(void) +{ +} +#endif + +static int __net_init lowpan_frags_init_net(struct net *net) +{ + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + int res; + + + res = fqdir_init(&ieee802154_lowpan->fqdir, &lowpan_frags, net); + if (res < 0) + return res; + + ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; + ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; + + res = lowpan_frags_ns_sysctl_register(net); + if (res < 0) + fqdir_exit(ieee802154_lowpan->fqdir); + return res; +} + +static void __net_exit lowpan_frags_pre_exit_net(struct net *net) +{ + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + + fqdir_pre_exit(ieee802154_lowpan->fqdir); +} + +static void __net_exit lowpan_frags_exit_net(struct net *net) +{ + struct netns_ieee802154_lowpan *ieee802154_lowpan = + net_ieee802154_lowpan(net); + + lowpan_frags_ns_sysctl_unregister(net); + fqdir_exit(ieee802154_lowpan->fqdir); +} + +static struct pernet_operations lowpan_frags_ops = { + .init = lowpan_frags_init_net, + .pre_exit = lowpan_frags_pre_exit_net, + .exit = lowpan_frags_exit_net, +}; + +static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); +} + +static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key, + sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); +} + +static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_lowpan_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static const struct rhashtable_params lowpan_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = lowpan_key_hashfn, + .obj_hashfn = lowpan_obj_hashfn, + .obj_cmpfn = lowpan_obj_cmpfn, + .automatic_shrinking = true, +}; + +int __init lowpan_net_frag_init(void) +{ + int ret; + + lowpan_frags.constructor = lowpan_frag_init; + lowpan_frags.destructor = NULL; + lowpan_frags.qsize = sizeof(struct frag_queue); + lowpan_frags.frag_expire = lowpan_frag_expire; + lowpan_frags.frags_cache_name = lowpan_frags_cache_name; + lowpan_frags.rhash_params = lowpan_rhash_params; + ret = inet_frags_init(&lowpan_frags); + if (ret) + goto out; + + ret = lowpan_frags_sysctl_register(); + if (ret) + goto err_sysctl; + + ret = register_pernet_subsys(&lowpan_frags_ops); + if (ret) + goto err_pernet; +out: + return ret; +err_pernet: + lowpan_frags_sysctl_unregister(); +err_sysctl: + inet_frags_fini(&lowpan_frags); + return ret; +} + +void lowpan_net_frag_exit(void) +{ + lowpan_frags_sysctl_unregister(); + unregister_pernet_subsys(&lowpan_frags_ops); + inet_frags_fini(&lowpan_frags); +} -- cgit v1.2.3