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/batman-adv/fragmentation.c | 562 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 562 insertions(+) create mode 100644 net/batman-adv/fragmentation.c (limited to 'net/batman-adv/fragmentation.c') diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c new file mode 100644 index 000000000..c120c7c6d --- /dev/null +++ b/net/batman-adv/fragmentation.c @@ -0,0 +1,562 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) B.A.T.M.A.N. contributors: + * + * Martin Hundebøll + */ + +#include "fragmentation.h" +#include "main.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hard-interface.h" +#include "originator.h" +#include "routing.h" +#include "send.h" + +/** + * batadv_frag_clear_chain() - delete entries in the fragment buffer chain + * @head: head of chain with entries. + * @dropped: whether the chain is cleared because all fragments are dropped + * + * Free fragments in the passed hlist. Should be called with appropriate lock. + */ +static void batadv_frag_clear_chain(struct hlist_head *head, bool dropped) +{ + struct batadv_frag_list_entry *entry; + struct hlist_node *node; + + hlist_for_each_entry_safe(entry, node, head, list) { + hlist_del(&entry->list); + + if (dropped) + kfree_skb(entry->skb); + else + consume_skb(entry->skb); + + kfree(entry); + } +} + +/** + * batadv_frag_purge_orig() - free fragments associated to an orig + * @orig_node: originator to free fragments from + * @check_cb: optional function to tell if an entry should be purged + */ +void batadv_frag_purge_orig(struct batadv_orig_node *orig_node, + bool (*check_cb)(struct batadv_frag_table_entry *)) +{ + struct batadv_frag_table_entry *chain; + u8 i; + + for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { + chain = &orig_node->fragments[i]; + spin_lock_bh(&chain->lock); + + if (!check_cb || check_cb(chain)) { + batadv_frag_clear_chain(&chain->fragment_list, true); + chain->size = 0; + } + + spin_unlock_bh(&chain->lock); + } +} + +/** + * batadv_frag_size_limit() - maximum possible size of packet to be fragmented + * + * Return: the maximum size of payload that can be fragmented. + */ +static int batadv_frag_size_limit(void) +{ + int limit = BATADV_FRAG_MAX_FRAG_SIZE; + + limit -= sizeof(struct batadv_frag_packet); + limit *= BATADV_FRAG_MAX_FRAGMENTS; + + return limit; +} + +/** + * batadv_frag_init_chain() - check and prepare fragment chain for new fragment + * @chain: chain in fragments table to init + * @seqno: sequence number of the received fragment + * + * Make chain ready for a fragment with sequence number "seqno". Delete existing + * entries if they have an "old" sequence number. + * + * Caller must hold chain->lock. + * + * Return: true if chain is empty and the caller can just insert the new + * fragment without searching for the right position. + */ +static bool batadv_frag_init_chain(struct batadv_frag_table_entry *chain, + u16 seqno) +{ + lockdep_assert_held(&chain->lock); + + if (chain->seqno == seqno) + return false; + + if (!hlist_empty(&chain->fragment_list)) + batadv_frag_clear_chain(&chain->fragment_list, true); + + chain->size = 0; + chain->seqno = seqno; + + return true; +} + +/** + * batadv_frag_insert_packet() - insert a fragment into a fragment chain + * @orig_node: originator that the fragment was received from + * @skb: skb to insert + * @chain_out: list head to attach complete chains of fragments to + * + * Insert a new fragment into the reverse ordered chain in the right table + * entry. The hash table entry is cleared if "old" fragments exist in it. + * + * Return: true if skb is buffered, false on error. If the chain has all the + * fragments needed to merge the packet, the chain is moved to the passed head + * to avoid locking the chain in the table. + */ +static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, + struct sk_buff *skb, + struct hlist_head *chain_out) +{ + struct batadv_frag_table_entry *chain; + struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr; + struct batadv_frag_list_entry *frag_entry_last = NULL; + struct batadv_frag_packet *frag_packet; + u8 bucket; + u16 seqno, hdr_size = sizeof(struct batadv_frag_packet); + bool ret = false; + + /* Linearize packet to avoid linearizing 16 packets in a row when doing + * the later merge. Non-linear merge should be added to remove this + * linearization. + */ + if (skb_linearize(skb) < 0) + goto err; + + frag_packet = (struct batadv_frag_packet *)skb->data; + seqno = ntohs(frag_packet->seqno); + bucket = seqno % BATADV_FRAG_BUFFER_COUNT; + + frag_entry_new = kmalloc(sizeof(*frag_entry_new), GFP_ATOMIC); + if (!frag_entry_new) + goto err; + + frag_entry_new->skb = skb; + frag_entry_new->no = frag_packet->no; + + /* Select entry in the "chain table" and delete any prior fragments + * with another sequence number. batadv_frag_init_chain() returns true, + * if the list is empty at return. + */ + chain = &orig_node->fragments[bucket]; + spin_lock_bh(&chain->lock); + if (batadv_frag_init_chain(chain, seqno)) { + hlist_add_head(&frag_entry_new->list, &chain->fragment_list); + chain->size = skb->len - hdr_size; + chain->timestamp = jiffies; + chain->total_size = ntohs(frag_packet->total_size); + ret = true; + goto out; + } + + /* Find the position for the new fragment. */ + hlist_for_each_entry(frag_entry_curr, &chain->fragment_list, list) { + /* Drop packet if fragment already exists. */ + if (frag_entry_curr->no == frag_entry_new->no) + goto err_unlock; + + /* Order fragments from highest to lowest. */ + if (frag_entry_curr->no < frag_entry_new->no) { + hlist_add_before(&frag_entry_new->list, + &frag_entry_curr->list); + chain->size += skb->len - hdr_size; + chain->timestamp = jiffies; + ret = true; + goto out; + } + + /* store current entry because it could be the last in list */ + frag_entry_last = frag_entry_curr; + } + + /* Reached the end of the list, so insert after 'frag_entry_last'. */ + if (likely(frag_entry_last)) { + hlist_add_behind(&frag_entry_new->list, &frag_entry_last->list); + chain->size += skb->len - hdr_size; + chain->timestamp = jiffies; + ret = true; + } + +out: + if (chain->size > batadv_frag_size_limit() || + chain->total_size != ntohs(frag_packet->total_size) || + chain->total_size > batadv_frag_size_limit()) { + /* Clear chain if total size of either the list or the packet + * exceeds the maximum size of one merged packet. Don't allow + * packets to have different total_size. + */ + batadv_frag_clear_chain(&chain->fragment_list, true); + chain->size = 0; + } else if (ntohs(frag_packet->total_size) == chain->size) { + /* All fragments received. Hand over chain to caller. */ + hlist_move_list(&chain->fragment_list, chain_out); + chain->size = 0; + } + +err_unlock: + spin_unlock_bh(&chain->lock); + +err: + if (!ret) { + kfree(frag_entry_new); + kfree_skb(skb); + } + + return ret; +} + +/** + * batadv_frag_merge_packets() - merge a chain of fragments + * @chain: head of chain with fragments + * + * Expand the first skb in the chain and copy the content of the remaining + * skb's into the expanded one. After doing so, clear the chain. + * + * Return: the merged skb or NULL on error. + */ +static struct sk_buff * +batadv_frag_merge_packets(struct hlist_head *chain) +{ + struct batadv_frag_packet *packet; + struct batadv_frag_list_entry *entry; + struct sk_buff *skb_out; + int size, hdr_size = sizeof(struct batadv_frag_packet); + bool dropped = false; + + /* Remove first entry, as this is the destination for the rest of the + * fragments. + */ + entry = hlist_entry(chain->first, struct batadv_frag_list_entry, list); + hlist_del(&entry->list); + skb_out = entry->skb; + kfree(entry); + + packet = (struct batadv_frag_packet *)skb_out->data; + size = ntohs(packet->total_size) + hdr_size; + + /* Make room for the rest of the fragments. */ + if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { + kfree_skb(skb_out); + skb_out = NULL; + dropped = true; + goto free; + } + + /* Move the existing MAC header to just before the payload. (Override + * the fragment header.) + */ + skb_pull(skb_out, hdr_size); + skb_out->ip_summed = CHECKSUM_NONE; + memmove(skb_out->data - ETH_HLEN, skb_mac_header(skb_out), ETH_HLEN); + skb_set_mac_header(skb_out, -ETH_HLEN); + skb_reset_network_header(skb_out); + skb_reset_transport_header(skb_out); + + /* Copy the payload of the each fragment into the last skb */ + hlist_for_each_entry(entry, chain, list) { + size = entry->skb->len - hdr_size; + skb_put_data(skb_out, entry->skb->data + hdr_size, size); + } + +free: + /* Locking is not needed, because 'chain' is not part of any orig. */ + batadv_frag_clear_chain(chain, dropped); + return skb_out; +} + +/** + * batadv_frag_skb_buffer() - buffer fragment for later merge + * @skb: skb to buffer + * @orig_node_src: originator that the skb is received from + * + * Add fragment to buffer and merge fragments if possible. + * + * There are three possible outcomes: 1) Packet is merged: Return true and + * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb + * to NULL; 3) Error: Return false and free skb. + * + * Return: true when the packet is merged or buffered, false when skb is not + * used. + */ +bool batadv_frag_skb_buffer(struct sk_buff **skb, + struct batadv_orig_node *orig_node_src) +{ + struct sk_buff *skb_out = NULL; + struct hlist_head head = HLIST_HEAD_INIT; + bool ret = false; + + /* Add packet to buffer and table entry if merge is possible. */ + if (!batadv_frag_insert_packet(orig_node_src, *skb, &head)) + goto out_err; + + /* Leave if more fragments are needed to merge. */ + if (hlist_empty(&head)) + goto out; + + skb_out = batadv_frag_merge_packets(&head); + if (!skb_out) + goto out_err; + +out: + ret = true; +out_err: + *skb = skb_out; + return ret; +} + +/** + * batadv_frag_skb_fwd() - forward fragments that would exceed MTU when merged + * @skb: skb to forward + * @recv_if: interface that the skb is received on + * @orig_node_src: originator that the skb is received from + * + * Look up the next-hop of the fragments payload and check if the merged packet + * will exceed the MTU towards the next-hop. If so, the fragment is forwarded + * without merging it. + * + * Return: true if the fragment is consumed/forwarded, false otherwise. + */ +bool batadv_frag_skb_fwd(struct sk_buff *skb, + struct batadv_hard_iface *recv_if, + struct batadv_orig_node *orig_node_src) +{ + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_orig_node *orig_node_dst; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_frag_packet *packet; + u16 total_size; + bool ret = false; + + packet = (struct batadv_frag_packet *)skb->data; + orig_node_dst = batadv_orig_hash_find(bat_priv, packet->dest); + if (!orig_node_dst) + goto out; + + neigh_node = batadv_find_router(bat_priv, orig_node_dst, recv_if); + if (!neigh_node) + goto out; + + /* Forward the fragment, if the merged packet would be too big to + * be assembled. + */ + total_size = ntohs(packet->total_size); + if (total_size > neigh_node->if_incoming->net_dev->mtu) { + batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_FWD); + batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES, + skb->len + ETH_HLEN); + + packet->ttl--; + batadv_send_unicast_skb(skb, neigh_node); + ret = true; + } + +out: + batadv_orig_node_put(orig_node_dst); + batadv_neigh_node_put(neigh_node); + return ret; +} + +/** + * batadv_frag_create() - create a fragment from skb + * @net_dev: outgoing device for fragment + * @skb: skb to create fragment from + * @frag_head: header to use in new fragment + * @fragment_size: size of new fragment + * + * Split the passed skb into two fragments: A new one with size matching the + * passed mtu and the old one with the rest. The new skb contains data from the + * tail of the old skb. + * + * Return: the new fragment, NULL on error. + */ +static struct sk_buff *batadv_frag_create(struct net_device *net_dev, + struct sk_buff *skb, + struct batadv_frag_packet *frag_head, + unsigned int fragment_size) +{ + unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev); + unsigned int tailroom = net_dev->needed_tailroom; + struct sk_buff *skb_fragment; + unsigned int header_size = sizeof(*frag_head); + unsigned int mtu = fragment_size + header_size; + + skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom); + if (!skb_fragment) + goto err; + + skb_fragment->priority = skb->priority; + + /* Eat the last mtu-bytes of the skb */ + skb_reserve(skb_fragment, ll_reserved + header_size); + skb_split(skb, skb_fragment, skb->len - fragment_size); + + /* Add the header */ + skb_push(skb_fragment, header_size); + memcpy(skb_fragment->data, frag_head, header_size); + +err: + return skb_fragment; +} + +/** + * batadv_frag_send_packet() - create up to 16 fragments from the passed skb + * @skb: skb to create fragments from + * @orig_node: final destination of the created fragments + * @neigh_node: next-hop of the created fragments + * + * Return: the netdev tx status or a negative errno code on a failure + */ +int batadv_frag_send_packet(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node) +{ + struct net_device *net_dev = neigh_node->if_incoming->net_dev; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_frag_packet frag_header; + struct sk_buff *skb_fragment; + unsigned int mtu = net_dev->mtu; + unsigned int header_size = sizeof(frag_header); + unsigned int max_fragment_size, num_fragments; + int ret; + + /* To avoid merge and refragmentation at next-hops we never send + * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE + */ + mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE); + max_fragment_size = mtu - header_size; + + if (skb->len == 0 || max_fragment_size == 0) + return -EINVAL; + + num_fragments = (skb->len - 1) / max_fragment_size + 1; + max_fragment_size = (skb->len - 1) / num_fragments + 1; + + /* Don't even try to fragment, if we need more than 16 fragments */ + if (num_fragments > BATADV_FRAG_MAX_FRAGMENTS) { + ret = -EAGAIN; + goto free_skb; + } + + bat_priv = orig_node->bat_priv; + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = -EINVAL; + goto free_skb; + } + + /* GRO might have added fragments to the fragment list instead of + * frags[]. But this is not handled by skb_split and must be + * linearized to avoid incorrect length information after all + * batman-adv fragments were created and submitted to the + * hard-interface + */ + if (skb_has_frag_list(skb) && __skb_linearize(skb)) { + ret = -ENOMEM; + goto free_skb; + } + + /* Create one header to be copied to all fragments */ + frag_header.packet_type = BATADV_UNICAST_FRAG; + frag_header.version = BATADV_COMPAT_VERSION; + frag_header.ttl = BATADV_TTL; + frag_header.seqno = htons(atomic_inc_return(&bat_priv->frag_seqno)); + frag_header.reserved = 0; + frag_header.no = 0; + frag_header.total_size = htons(skb->len); + + /* skb->priority values from 256->263 are magic values to + * directly indicate a specific 802.1d priority. This is used + * to allow 802.1d priority to be passed directly in from VLAN + * tags, etc. + */ + if (skb->priority >= 256 && skb->priority <= 263) + frag_header.priority = skb->priority - 256; + else + frag_header.priority = 0; + + ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr); + ether_addr_copy(frag_header.dest, orig_node->orig); + + /* Eat and send fragments from the tail of skb */ + while (skb->len > max_fragment_size) { + /* The initial check in this function should cover this case */ + if (unlikely(frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1)) { + ret = -EINVAL; + goto put_primary_if; + } + + skb_fragment = batadv_frag_create(net_dev, skb, &frag_header, + max_fragment_size); + if (!skb_fragment) { + ret = -ENOMEM; + goto put_primary_if; + } + + batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX); + batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES, + skb_fragment->len + ETH_HLEN); + ret = batadv_send_unicast_skb(skb_fragment, neigh_node); + if (ret != NET_XMIT_SUCCESS) { + ret = NET_XMIT_DROP; + goto put_primary_if; + } + + frag_header.no++; + } + + /* make sure that there is at least enough head for the fragmentation + * and ethernet headers + */ + ret = skb_cow_head(skb, ETH_HLEN + header_size); + if (ret < 0) + goto put_primary_if; + + skb_push(skb, header_size); + memcpy(skb->data, &frag_header, header_size); + + /* Send the last fragment */ + batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX); + batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES, + skb->len + ETH_HLEN); + ret = batadv_send_unicast_skb(skb, neigh_node); + /* skb was consumed */ + skb = NULL; + +put_primary_if: + batadv_hardif_put(primary_if); +free_skb: + kfree_skb(skb); + + return ret; +} -- cgit v1.2.3