diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-22 05:24:12 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-22 05:24:12 +0300 |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /tools/testing/selftests/net/nat6to4.c | |
parent | 36289a03bcd3aabdf66de75cb6d1b4ee15726438 (diff) | |
parent | d1fabc68f8e0541d41657096dc713cb01775652d (diff) | |
download | linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.xz |
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().
...
Diffstat (limited to 'tools/testing/selftests/net/nat6to4.c')
-rw-r--r-- | tools/testing/selftests/net/nat6to4.c | 285 |
1 files changed, 285 insertions, 0 deletions
diff --git a/tools/testing/selftests/net/nat6to4.c b/tools/testing/selftests/net/nat6to4.c new file mode 100644 index 000000000000..ac54c36b25fc --- /dev/null +++ b/tools/testing/selftests/net/nat6to4.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code is taken from the Android Open Source Project and the author + * (Maciej Żenczykowski) has gave permission to relicense it under the + * GPLv2. Therefore this program is free software; + * You can redistribute it and/or modify it under the terms of the GNU + * General Public License version 2 as published by the Free Software + * Foundation + + * The original headers, including the original license headers, are + * included below for completeness. + * + * Copyright (C) 2019 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +#include <linux/bpf.h> +#include <linux/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/swab.h> +#include <stdbool.h> +#include <stdint.h> + + +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IP_DF 0x4000 // Flag: "Don't Fragment" + +SEC("schedcls/ingress6/nat_6") +int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr * const eth = data; // used iff is_ethernet + const struct ipv6hdr * const ip6 = (void *)(eth + 1); + + // Require ethernet dst mac address to be our unicast address. + if (skb->pkt_type != PACKET_HOST) + return TC_ACT_OK; + + // Must be meta-ethernet IPv6 frame + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // Must have (ethernet and) ipv6 header + if (data + l2_header_size + sizeof(*ip6) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv6 + if (eth->h_proto != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // IP version must be 6 + if (ip6->version != 6) + return TC_ACT_OK; + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr)) + return TC_ACT_OK; + switch (ip6->nexthdr) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_UDP: // address means there is no need to update their checksums. + case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers, + case IPPROTO_ESP: // since there is never a checksum to update. + break; + default: // do not know how to handle anything else + return TC_ACT_OK; + } + + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype + + struct iphdr ip = { + .version = 4, // u4 + .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4 + .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8 + .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16 + .id = 0, // u16 + .frag_off = bpf_htons(IP_DF), // u16 + .ttl = ip6->hop_limit, // u8 + .protocol = ip6->nexthdr, // u8 + .check = 0, // u16 + .saddr = 0x0201a8c0, // u32 + .daddr = 0x0101a8c0, // u32 + }; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i) + sum4 += ((__u16 *)&ip)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF + + // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits) + for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i) + sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation + + // Note that there is no L4 checksum update: we are relying on the checksum neutrality + // of the ipv6 address chosen by netd's ClatdController. + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0)) + return TC_ACT_OK; + bpf_csum_update(skb, sum6); + + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + if (data + l2_header_size + sizeof(struct iphdr) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + + // Copy over the new ipv4 header. + *(struct iphdr *)(new_eth + 1) = ip; + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +SEC("schedcls/egress4/snat4") +int sched_cls_egress4_snat4_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr *const eth = data; // used iff is_ethernet + const struct iphdr *const ip4 = (void *)(eth + 1); + + // Must be meta-ethernet IPv4 frame + if (skb->protocol != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // Must have ipv4 header + if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv4 + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // IP version must be 4 + if (ip4->version != 4) + return TC_ACT_OK; + + // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header + if (ip4->ihl != 5) + return TC_ACT_OK; + + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr)) + return TC_ACT_OK; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i) + sum4 += ((__u16 *)ip4)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF + if (sum4 != 0xFFFF) + return TC_ACT_OK; + + // Minimum IPv4 total length is the size of the header + if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4)) + return TC_ACT_OK; + + // We are incapable of dealing with IPv4 fragments + if (ip4->frag_off & ~bpf_htons(IP_DF)) + return TC_ACT_OK; + + switch (ip4->protocol) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_GRE: // address means there is no need to update their checksums. + case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers, + break; // since there is never a checksum to update. + + case IPPROTO_UDP: // See above comment, but must also have UDP header... + if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end) + return TC_ACT_OK; + const struct udphdr *uh = (const struct udphdr *)(ip4 + 1); + // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the + // checksum. Otherwise the network or more likely the NAT64 gateway might + // drop the packet because in most cases IPv6/UDP packets with a zero checksum + // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff() + if (!uh->check) + return TC_ACT_OK; + break; + + default: // do not know how to handle anything else + return TC_ACT_OK; + } + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype + + struct ipv6hdr ip6 = { + .version = 6, // __u8:4 + .priority = ip4->tos >> 4, // __u8:4 + .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3] + .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16 + .nexthdr = ip4->protocol, // __u8 + .hop_limit = ip4->ttl, // __u8 + }; + ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.saddr.in6_u.u6_addr32[1] = 0; + ip6.saddr.in6_u.u6_addr32[2] = 0; + ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1); + ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.daddr.in6_u.u6_addr32[1] = 0; + ip6.daddr.in6_u.u6_addr32[2] = 0; + ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2); + + // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6.version == 6 + for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i) + sum6 += ((__u16 *)&ip6)[i]; + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0)) + return TC_ACT_OK; + + // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet. + // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload, + // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum. + // However, we've already verified the ipv4 checksum is correct and thus 0. + // Thus we only need to add the ipv6 header's sum. + // + // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error + // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details). + bpf_csum_update(skb, sum6); + + // bpf_skb_change_proto() invalidates all pointers - reload them. + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + // I cannot think of any valid way for this error condition to trigger, however I do + // believe the explicit check is required to keep the in kernel ebpf verifier happy. + if (data + l2_header_size + sizeof(ip6) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + // Copy over the new ipv4 header. + *(struct ipv6hdr *)(new_eth + 1) = ip6; + return TC_ACT_OK; +} + +char _license[] SEC("license") = ("GPL"); |