kernel/git/stable/linux.git/net/ipv4/udp.c, branch master

ipv4: udp: Create exceptions before socket matching

2026-09-01T02:56:30+00:00

Currently, when ICMP Fragmentation Needed and Redirect Message packets are locally delivered and quote a UDP packet, a FIB nexthop exception (FNHE) is only created if the kernel can match the UDP packet to an existing socket. This behavior allows off-path attackers to conduct a side-channel attack on the FNHE cache in order to discover the ephemeral port used by a connected UDP socket. Commit 6457378fe796 ("ipv4: use siphash instead of Jenkins in fnhe_hashfun()") and commit 67d6d681e15b ("ipv4: make exception cache less predictible") tried to mitigate such attacks by making it harder for attackers to discover hash collisions in the FNHE cache and by randomizing the number of exceptions a hash bucket can hold, respectively. Unfortunately, both of the mitigations can be bypassed. Instead, mitigate such attacks by always creating a FNHE, even before trying to find a matching socket. Do that by calling ipv4_update_pmtu() and ipv4_redirect(), the helpers used when the quoted packet did not originate from a socket. This means that guesses (right or wrong) from an off-path attacker will always result in a FNHE being created or updated in the cache that the attacker can observe. Pass an oif of 0, in a similar fashion to icmp_err(). This is also the oif used by the socket path for sockets that are not bound to a device. Note that this does not allow attackers to create FNHEs that they could not create before, as both helpers can already be reached with little to no validation. For example, by sending an ICMP error that quotes an ICMP Echo Reply or one that quotes a UDP source port that matches a wildcard socket. Also note that in the good case (matched socket) the above scheme comes at the cost of an extra route lookup, as the no socket helpers perform their own lookup before the one performed by ipv4_sk_update_pmtu() / ipv4_sk_redirect(). When the two resolve to different nexthops, it also results in two exceptions being created for the same destination IP. One in the FNHE cache of the nexthop resolved by the no socket helpers and another in the FNHE cache of the nexthop used by the socket. Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions.") Cc: stable@vger.kernel.org Reported-by: Amit Klein Reported-by: Noam Caspi Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/20260828192344.2596928-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski

raw: annotate disconnect-side IPv4 match writers

2026-08-30T21:14:57+00:00

raw_v4_match() reads inet_daddr, inet_rcv_saddr and sk_bound_dev_if locklessly under RCU. Bind and connect writers are annotated, but __udp_disconnect() still clears the same fields using plain stores. Commit 18f116931f52e ("raw: annotate lockless match fields in raw_v4_match()") added the lockless readers and annotated the raw bind and datagram connect writers. Its v4 revision intentionally left the shared disconnect-side IPv4 writers for follow-up cleanup. Complete that follow-up by using WRITE_ONCE() for the disconnect-side stores, including the inet_rcv_saddr reset in inet_reset_saddr(), to pair with the lockless raw socket matcher. Fixes: 0daf07e52709 ("raw: convert raw sockets to RCU") Link: https://lore.kernel.org/netdev/20260716142958.3064224-1-runyu.xiao@seu.edu.cn/ Suggested-by: Runyu Xiao Signed-off-by: Jackie Liu Signed-off-by: Xuanqiang Luo Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260828012918.1461-1-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski

Merge branch 'big-tcp-for-udp-tunnels'

2026-07-22T11:49:03+00:00

Alice Mikityanska says: ==================== BIG TCP for UDP tunnels This series is a follow-up to "BIG TCP without HBH in IPv6", and it adds support for BIG TCP IPv4/IPv6 workloads in vxlan and geneve. Now that IPv6 BIG TCP doesn't require stripping the HBH in all various combinations in tunneled traffic, adding BIG TCP becomes feasible. Patch 01 adds accessors for the length field in the UDP header, as suggested by Paolo in review. The usage of udp_set_len is then added in the following patches that start using length=0 in BIG TCP UDP packets. Patches 02-04 close the gaps that prevent BIG TCP packets from going through UDP tunnel code. Patch 05 validates packets in udp_gro_receive to exclude packets with length=0 from GRO aggregation. Patch 06 is for proper formatting in tcpdump (set UDP len to 0 rather than a trimmed value on overflow). Patches 07-08 bump up tso_max_size for VXLAN and GENEVE. Patch 09 adds selftests. ====================$ Link: https://patch.msgid.link/20260710134242.216538-1-alice.kernel@fastmail.im Signed-off-by: Paolo Abeni

udp: Support gro_ipv4_max_size > 65536

2026-07-22T11:47:02+00:00

Currently, gro_max_size and gro_ipv4_max_size can be set to values bigger than 65536, and GRO will happily aggregate UDP to the configured size (for example, with TCP traffic in VXLAN tunnels). However, udp_gro_complete uses the 16-bit length field in the UDP header to store the length of the aggregated packet. It leads to the packet truncation later in udp_rcv. Fix this by storing 0 to the UDP length field and by restoring the real length from skb->len in udp_rcv. IP GRO already can store 0 to the IP length field, and iph_totlen()/ipv6_payload_len() are capable of restoring the real length, because the relevant packets (BIG TCP tunneled in UDP tunnels) will have skb_is_gso_tcp == true. Additionally, restrict handling uh->len=0 in udpv6_rcv to BIG TCP and jumbograms only by using the udp_get_len helper. Signed-off-by: Alice Mikityanska Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260710134242.216538-5-alice.kernel@fastmail.im Reviewed-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni

net: Use helpers to get/set UDP len tree-wide

2026-07-22T11:47:02+00:00

Since BIG TCP for UDP tunnels will start using len=0 in the UDP header as an indicator of a GSO packet bigger than 65535 bytes, this commit introduces the following getter and setters to use tree-wide, in order to explicitly mark places where len=0 may be expected, and handle them properly: 1. udp_set_len() sets uh->len to its real value if it's not bigger than 65535, and to 0 otherwise: to be used in GSO context with aggregated packets. 2. udp_set_len_short() is to be used when the length is known to fit 16 bits. It WARNs when the caller tries to assign a bigger value if CONFIG_DEBUG_NET=y. 3. udp_get_len_short() returns len in host byte order: to be used on the RX side to deal with non-aggregated packets, or to access the raw value of the len field. 4. udp_get_len() decodes uh->len set by udp_set_len(). It checks whether the packet is GSO to guard from malformed packets. At the moment udp_set_len() is not used, a following commit will start using it after enabling len>65535 for GSO. Raw uh->len (in network byte order) is still accessed in a few places for checksum calculation purposes, and to decode len=0 in udpv6_rcv for jumbograms. udp_rcv and udpv6_rcv will be addressed by the commit that starts using udp_set_len() to set UDP len=0 for BIG TCP packets in UDP tunnels. Signed-off-by: Alice Mikityanska Reviewed-by: Willem de Bruijn Acked-by: Jason A. Donenfeld Link: https://patch.msgid.link/20260710134242.216538-2-alice.kernel@fastmail.im Reviewed-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni

udp: fix encapsulation packet resubmit in multicast deliver

2026-07-21T09:09:02+00:00

When a UDP encapsulation socket (e.g., FOU) receives a multicast packet, __udp4_lib_mcast_deliver() and __udp6_lib_mcast_deliver() call consume_skb() when udp_queue_rcv_skb() returns a positive value. A positive return value from udp_queue_rcv_skb() indicates that the encap_rcv handler (e.g., fou_udp_recv) has consumed the UDP header and wants the packet to be resubmitted to the IP protocol handler for further processing (e.g., as a GRE packet). The unicast paths handle this correctly by propagating the return value up to ip_protocol_deliver_rcu() / ip6_protocol_deliver_rcu() for resubmission. However, the multicast paths destroy the packet via consume_skb() instead of resubmitting it, causing silent packet loss. This affects any UDP encapsulation (FOU, GUE) combined with multicast destination addresses. Fix this by returning the value from udp_queue_rcv_skb() when it is positive, matching the behavior of the corresponding unicast paths. Note the sign difference between IPv4 and IPv6: - IPv4: udp_unicast_rcv_skb() returns -ret, and ip_protocol_deliver_rcu() resubmits when ret < 0 (using -ret as the protocol number). - IPv6: udp6_unicast_rcv_skb() returns ret, and ip6_protocol_deliver_rcu() resubmits when ret > 0 (using ret as the nexthdr). Both mcast paths now follow the same convention as their respective unicast paths. Suggested-by: Kuniyuki Iwashima Signed-off-by: Anton Danilov Assisted-by: Claude:claude-opus-4-6 Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/5372ccac062193147e02b991d5328a5c3fa3a85a.1783372173.git.littlesmilingcloud@gmail.com Signed-off-by: Paolo Abeni

udp: convert udp_lib_getsockopt to sockopt_t

2026-07-02T10:29:06+00:00

In preparation for converting the proto-layer getsockopt callbacks to the sockopt_t interface, switch udp_lib_getsockopt() to take a sockopt_t. The thin udp_getsockopt()/udpv6_getsockopt() wrappers keep their __user signature for now: they build a user-backed sockopt_t with sockopt_init_user(), call the helper, and write the returned length back to optlen. The helper uses copy_to_iter() instead of copy_to_user(). No functional change. Signed-off-by: Breno Leitao Acked-by: Stanislav Fomichev Acked-by: Willem de Bruijn Link: https://patch.msgid.link/20260630-getsockopt_phase2-v2-2-193335f3d4d1@debian.org Signed-off-by: Paolo Abeni

udp: clear skb->dev before running a sockmap verdict

2026-06-04T16:01:51+00:00

On the UDP receive path skb->dev is repurposed as dev_scratch (the truesize/state cache set by udp_set_dev_scratch()), through the union { struct net_device *dev; unsigned long dev_scratch; } in sk_buff. When a UDP socket is in a sockmap, sk_data_ready is sk_psock_verdict_data_ready(), which calls udp_read_skb() -> recv_actor() (sk_psock_verdict_recv) to run the attached SK_SKB verdict program in softirq. If that program calls a socket-lookup helper (bpf_sk_lookup_tcp/udp, bpf_skc_lookup_tcp), bpf_skc_lookup() does: if (skb->dev) caller_net = dev_net(skb->dev); skb->dev still holds the dev_scratch value (a non-NULL integer), so dev_net() dereferences it as a struct net_device * and the kernel takes a general protection fault on a non-canonical address in softirq: Oops: general protection fault, probably for non-canonical address 0x1010000800004a0 CPU: 1 UID: 0 PID: 1406 Comm: syz.2.19 Not tainted 7.1.0-rc6 #1 PREEMPT(full) RIP: 0010:bpf_skc_lookup net/core/filter.c:7033 [inline] RIP: 0010:bpf_sk_lookup+0x45/0x160 net/core/filter.c:7047 Call Trace: bpf_prog_4675cb904b7071f8+0x12e/0x14e bpf_prog_run_pin_on_cpu+0xc6/0x1f0 sk_psock_verdict_recv+0x1ba/0x350 udp_read_skb+0x31a/0x370 sk_psock_verdict_data_ready+0x2e3/0x600 __udp_enqueue_schedule_skb+0x4c8/0x650 udpv6_queue_rcv_one_skb+0x3ec/0x740 udp6_unicast_rcv_skb+0x11d/0x140 ip6_protocol_deliver_rcu+0x61e/0x950 ip6_input_finish+0xa9/0x150 NF_HOOK+0x286/0x2f0 ip6_input+0x117/0x220 NF_HOOK+0x286/0x2f0 __netif_receive_skb+0x85/0x200 process_backlog+0x374/0x9a0 __napi_poll+0x4f/0x1c0 net_rx_action+0x3b0/0x770 handle_softirqs+0x15a/0x460 do_softirq+0x57/0x80 The rmem charge that dev_scratch accounted for is released by skb_recv_udp() on dequeue, just above, so the scratch is dead by the time recv_actor() runs. Clear skb->dev so bpf_skc_lookup() falls back to sock_net(skb->sk), which skb_set_owner_sk_safe() set just above. Fixes: 965b57b469a5 ("net: Introduce a new proto_ops ->read_skb()") Cc: stable@vger.kernel.org Signed-off-by: Sechang Lim Reviewed-by: Jiayuan Chen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260603162737.697215-1-rhkrqnwk98@gmail.com Signed-off-by: Jakub Kicinski

Merge tag 'net-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

2026-04-15T01:36:10+00:00

Pull networking updates from Jakub Kicinski: "Core & protocols: - Support HW queue leasing, allowing containers to be granted access to HW queues for zero-copy operations and AF_XDP - Number of code moves to help the compiler with inlining. Avoid output arguments for returning drop reason where possible - Rework drop handling within qdiscs to include more metadata about the reason and dropping qdisc in the tracepoints - Remove the rtnl_lock use from IP Multicast Routing - Pack size information into the Rx Flow Steering table pointer itself. This allows making the table itself a flat array of u32s, thus making the table allocation size a power of two - Report TCP delayed ack timer information via socket diag - Add ip_local_port_step_width sysctl to allow distributing the randomly selected ports more evenly throughout the allowed space - Add support for per-route tunsrc in IPv6 segment routing - Start work of switching sockopt handling to iov_iter - Improve dynamic recvbuf sizing in MPTCP, limit burstiness and avoid buffer size drifting up - Support MSG_EOR in MPTCP - Add stp_mode attribute to the bridge driver for STP mode selection. This addresses concerns about call_usermodehelper() usage - Remove UDP-Lite support (as announced in 2023) - Remove support for building IPv6 as a module. Remove the now unnecessary function calling indirection Cross-tree stuff: - Move Michael MIC code from generic crypto into wireless, it's considered insecure but some WiFi networks still need it Netfilter: - Switch nft_fib_ipv6 module to no longer need temporary dst_entry object allocations by using fib6_lookup() + RCU. Florian W reports this gets us ~13% higher packet rate - Convert IPVS's global __ip_vs_mutex to per-net service_mutex and switch the service tables to be per-net. Convert some code that walks the service lists to use RCU instead of the service_mutex - Add more opinionated input validation to lower security exposure - Make IPVS hash tables to be per-netns and resizable Wireless: - Finished assoc frame encryption/EPPKE/802.1X-over-auth - Radar detection improvements - Add 6 GHz incumbent signal detection APIs - Multi-link support for FILS, probe response templates and client probing - New APIs and mac80211 support for NAN (Neighbor Aware Networking, aka Wi-Fi Aware) so less work must be in firmware Driver API: - Add numerical ID for devlink instances (to avoid having to create fake bus/device pairs just to have an ID). Support shared devlink instances which span multiple PFs - Add standard counters for reporting pause storm events (implement in mlx5 and fbnic) - Add configuration API for completion writeback buffering (implement in mana) - Support driver-initiated change of RSS context sizes - Support DPLL monitoring input frequency (implement in zl3073x) - Support per-port resources in devlink (implement in mlx5) Misc: - Expand the YAML spec for Netfilter Drivers - Software: - macvlan: support multicast rx for bridge ports with shared source MAC address - team: decouple receive and transmit enablement for IEEE 802.3ad LACP "independent control" - Ethernet high-speed NICs: - nVidia/Mellanox: - support high order pages in zero-copy mode (for payload coalescing) - support multiple packets in a page (for systems with 64kB pages) - Broadcom 25-400GE (bnxt): - implement XDP RSS hash metadata extraction - add software fallback for UDP GSO, lowering the IOMMU cost - Broadcom 800GE (bnge): - add link status and configuration handling - add various HW and SW statistics - Marvell/Cavium: - NPC HW block support for cn20k - Huawei (hinic3): - add mailbox / control queue - add rx VLAN offload - add driver info and link management - Ethernet NICs: - Marvell/Aquantia: - support reading SFP module info on some AQC100 cards - Realtek PCI (r8169): - add support for RTL8125cp - Realtek USB (r8152): - support for the RTL8157 5Gbit chip - add 2500baseT EEE status/configuration support - Ethernet NICs embedded and off-the-shelf IP: - Synopsys (stmmac): - cleanup and reorganize SerDes handling and PCS support - cleanup descriptor handling and per-platform data - cleanup and consolidate MDIO defines and handling - shrink driver memory use for internal structures - improve Tx IRQ coalescing - improve TCP segmentation handling - add support for Spacemit K3 - Cadence (macb): - support PHYs that have inband autoneg disabled with GEM - support IEEE 802.3az EEE - rework usrio capabilities and handling - AMD (xgbe): - improve power management for S0i3 - improve TX resilience for link-down handling - Virtual: - Google cloud vNIC: - support larger ring sizes in DQO-QPL mode - improve HW-GRO handling - support UDP GSO for DQO format - PCIe NTB: - support queue count configuration - Ethernet PHYs: - automatically disable PHY autonomous EEE if MAC is in charge - Broadcom: - add BCM84891/BCM84892 support - Micrel: - support for LAN9645X internal PHY - Realtek: - add RTL8224 pair order support - support PHY LEDs on RTL8211F-VD - support spread spectrum clocking (SSC) - Maxlinear: - add PHY-level statistics via ethtool - Ethernet switches: - Maxlinear (mxl862xx): - support for bridge offloading - support for VLANs - support driver statistics - Bluetooth: - large number of fixes and new device IDs - Mediatek: - support MT6639 (MT7927) - support MT7902 SDIO - WiFi: - Intel (iwlwifi): - UNII-9 and continuing UHR work - MediaTek (mt76): - mt7996/mt7925 MLO fixes/improvements - mt7996 NPU support (HW eth/wifi traffic offload) - Qualcomm (ath12k): - monitor mode support on IPQ5332 - basic hwmon temperature reporting - support IPQ5424 - Realtek: - add USB RX aggregation to improve performance - add USB TX flow control by tracking in-flight URBs - Cellular: - IPA v5.2 support" * tag 'net-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1561 commits) net: pse-pd: fix kernel-doc function name for pse_control_find_by_id() wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wireguard: allowedips: remove redundant space tools: ynl: add sample for wireguard wireguard: allowedips: Use kfree_rcu() instead of call_rcu() MAINTAINERS: Add netkit selftest files selftests/net: Add additional test coverage in nk_qlease selftests/net: Split netdevsim tests from HW tests in nk_qlease tools/ynl: Make YnlFamily closeable as a context manager net: airoha: Add missing PPE configurations in airoha_ppe_hw_init() net: airoha: Fix VIP configuration for AN7583 SoC net: caif: clear client service pointer on teardown net: strparser: fix skb_head leak in strp_abort_strp() net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() selftests/bpf: add test for xdp_master_redirect with bond not up net, bpf: fix null-ptr-deref in xdp_master_redirect() for down master net: airoha: Remove PCE_MC_EN_MASK bit in REG_FE_PCE_CFG configuration sctp: disable BH before calling udp_tunnel_xmit_skb() sctp: fix missing encap_port propagation for GSO fragments net: airoha: Rely on net_device pointer in ETS callbacks ...

udp: Force compute_score to always inline

2026-04-13T22:44:42+00:00

Back in 2024 I reported a 7-12% regression on an iperf3 UDP loopback thoughput test that we traced to the extra overhead of calling compute_score on two places, introduced by commit f0ea27e7bfe1 ("udp: re-score reuseport groups when connected sockets are present"). At the time, I pointed out the overhead was caused by the multiple calls, associated with cpu-specific mitigations, and merged commit 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites") to jump back explicitly, to force the rescore call in a single place. Recently though, we got another regression report against a newer distro version, which a team colleague traced back to the same root-cause. Turns out that once we updated to gcc-13, the compiler got smart enough to unroll the loop, undoing my previous mitigation. Let's bite the bullet and __always_inline compute_score on both ipv4 and ipv6 to prevent gcc from de-optimizing it again in the future. These functions are only called in two places each, udpX_lib_lookup1 and udpX_lib_lookup2, so the extra size shouldn't be a problem and it is hot enough to be very visible in profilings. In fact, with gcc13, forcing the inline will prevent gcc from unrolling the fix from commit 50aee97d1511, so we don't end up increasing udpX_lib_lookup2 at all. I haven't recollected the results myself, as I don't have access to the machine at the moment. But the same colleague reported 4.67% inprovement with this patch in the loopback benchmark, solving the regression report within noise margins. Eric Dumazet reported no size change to vmlinux when built with clang. I report the same also with gcc-13: scripts/bloat-o-meter vmlinux vmlinux-inline add/remove: 0/2 grow/shrink: 4/0 up/down: 616/-416 (200) Function old new delta udp6_lib_lookup2 762 949 +187 __udp6_lib_lookup 810 975 +165 udp4_lib_lookup2 757 906 +149 __udp4_lib_lookup 871 986 +115 __pfx_compute_score 32 - -32 compute_score 384 - -384 Total: Before=35011784, After=35011984, chg +0.00% Fixes: 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites") Reviewed-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: Gabriel Krisman Bertazi Link: https://patch.msgid.link/20260410155936.654915-1-krisman@suse.de Signed-off-by: Jakub Kicinski