kernel/linux.git/net/core/skbuff.c, branch v7.0-rc7

net: Drop the lock in skb_may_tx_timestamp()

2026-02-24T10:27:29+00:00

skb_may_tx_timestamp() may acquire sock::sk_callback_lock. The lock must not be taken in IRQ context, only softirq is okay. A few drivers receive the timestamp via a dedicated interrupt and complete the TX timestamp from that handler. This will lead to a deadlock if the lock is already write-locked on the same CPU. Taking the lock can be avoided. The socket (pointed by the skb) will remain valid until the skb is released. The ->sk_socket and ->file member will be set to NULL once the user closes the socket which may happen before the timestamp arrives. If we happen to observe the pointer while the socket is closing but before the pointer is set to NULL then we may use it because both pointer (and the file's cred member) are RCU freed. Drop the lock. Use READ_ONCE() to obtain the individual pointer. Add a matching WRITE_ONCE() where the pointer are cleared. Link: https://lore.kernel.org/all/20260205145104.iWinkXHv@linutronix.de Fixes: b245be1f4db1a ("net-timestamp: no-payload only sysctl") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Willem de Bruijn Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260220183858.N4ERjFW6@linutronix.de Signed-off-by: Paolo Abeni

net: do not delay zero-copy skbs in skb_attempt_defer_free()

2026-02-18T01:06:18+00:00

After the blamed commit, TCP tx zero copy notifications could be arbitrarily delayed and cause regressions in applications waiting for them. Signed-off-by: Eric Dumazet Fixes: e20dfbad8aab ("net: fix napi_consume_skb() with alien skbs") Reviewed-by: Jason Xing Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260216193653.627617-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net: skb: allow up to 8 skb extension ids

2026-02-07T04:07:24+00:00

The skb extension ids range from 0 .. 7 to fit their bits as flags into a single byte. The ids are automatically enumnerated in enum skb_ext_id in skbuff.h, where SKB_EXT_NUM is defined as the last value. When having 8 skb extension ids (0 .. 7), SKB_EXT_NUM becomes 8 which is a valid value for SKB_EXT_NUM. Fixes: 96ea3a1e2d31 ("can: add CAN skb extension infrastructure") Link: https://lore.kernel.org/netdev/aXoMqaA7b2CqJZNA@strlen.de/ Reviewed-by: Florian Westphal Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20260205-skb_ext-v1-1-9ba992ccee8b@hartkopp.net Signed-off-by: Jakub Kicinski

net: add vlan_get_protocol_offset_inline() helper

2026-02-05T15:33:52+00:00

skb_protocol() is bloated, and forces slow stack canaries in many fast paths. Add vlan_get_protocol_offset_inline() which deals with the non-vlan common cases. __vlan_get_protocol_offset() is now out of line. It returns a vlan_type_depth struct to avoid stack canaries in callers. struct vlan_type_depth { __be16 type; u16 depth; }; $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 0/2 grow/shrink: 0/22 up/down: 0/-6320 (-6320) Function old new delta vlan_get_protocol_dgram 61 59 -2 __pfx_skb_protocol 16 - -16 __vlan_get_protocol_offset 307 273 -34 tap_get_user 1374 1207 -167 ip_md_tunnel_xmit 1625 1452 -173 tap_sendmsg 940 753 -187 netif_skb_features 1079 866 -213 netem_enqueue 3017 2800 -217 vlan_parse_protocol 271 50 -221 tso_start 567 344 -223 fq_dequeue 1908 1685 -223 skb_network_protocol 434 205 -229 ip6_tnl_xmit 2639 2409 -230 br_dev_queue_push_xmit 474 236 -238 skb_protocol 258 - -258 packet_parse_headers 621 357 -264 __ip6_tnl_rcv 1306 1039 -267 skb_csum_hwoffload_help 515 224 -291 ip_tunnel_xmit 2635 2339 -296 sch_frag_xmit_hook 1582 1233 -349 bpf_skb_ecn_set_ce 868 457 -411 IP6_ECN_decapsulate 1297 768 -529 ip_tunnel_rcv 2121 1489 -632 ipip6_rcv 2572 1922 -650 Total: Before=24892803, After=24886483, chg -0.03% Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260204053023.1622775-1-edumazet@google.com Signed-off-by: Paolo Abeni

can: add CAN skb extension infrastructure

2026-02-05T10:58:39+00:00

To remove the private CAN bus skb headroom infrastructure 8 bytes need to be stored in the skb. The skb extensions are a common pattern and an easy and efficient way to hold private data travelling along with the skb. We only need the skb_ext_add() and skb_ext_find() functions to allocate and access CAN specific content as the skb helpers to copy/clone/free skbs automatically take care of skb extensions and their final removal. This patch introduces the complete CAN skb extensions infrastructure: - add struct can_skb_ext in new file include/net/can.h - add include/net/can.h in MAINTAINERS - add SKB_EXT_CAN to skbuff.c and skbuff.h - select SKB_EXTENSIONS in Kconfig when CONFIG_CAN is enabled - check for existing CAN skb extensions in can_rcv() in af_can.c - add CAN skb extensions allocation at every skb_alloc() location - duplicate the skb extensions if cloning outgoing skbs (framelen/gw_hops) - introduce can_skb_ext_add() and can_skb_ext_find() helpers The patch also corrects an indention issue in the original code from 2018: Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202602010426.PnGrYAk3-lkp@intel.com/ Signed-off-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20260201-can_skb_ext-v8-2-3635d790fe8b@hartkopp.net Signed-off-by: Paolo Abeni

net: inline get_netmem() and put_netmem()

2026-01-25T21:18:53+00:00

These helpers are used in network fast paths. Only call out-of-line helpers for netmem case. We might consider inlining __get_netmem() and __put_netmem() in the future. $ scripts/bloat-o-meter -t vmlinux.3 vmlinux.4 add/remove: 6/6 grow/shrink: 22/1 up/down: 2614/-646 (1968) Function old new delta pskb_carve 1669 1894 +225 gro_pull_from_frag0 - 206 +206 get_page 190 380 +190 skb_segment 3561 3747 +186 put_page 595 765 +170 skb_copy_ubufs 1683 1822 +139 __pskb_trim_head 276 401 +125 __pskb_copy_fclone 734 858 +124 skb_zerocopy 1092 1215 +123 pskb_expand_head 892 1008 +116 skb_split 828 940 +112 skb_release_data 297 409 +112 ___pskb_trim 829 941 +112 __skb_zcopy_downgrade_managed 120 226 +106 tcp_clone_payload 530 634 +104 esp_ssg_unref 191 294 +103 dev_gro_receive 1464 1514 +50 __put_netmem - 41 +41 __get_netmem - 41 +41 skb_shift 1139 1175 +36 skb_try_coalesce 681 714 +33 __pfx_put_page 112 144 +32 __pfx_get_page 32 64 +32 __pskb_pull_tail 1137 1168 +31 veth_xdp_get 250 267 +17 __pfx_gro_pull_from_frag0 - 16 +16 __pfx___put_netmem - 16 +16 __pfx___get_netmem - 16 +16 __pfx_put_netmem 16 - -16 __pfx_gro_try_pull_from_frag0 16 - -16 __pfx_get_netmem 16 - -16 put_netmem 114 - -114 get_netmem 130 - -130 napi_gro_frags 929 771 -158 gro_try_pull_from_frag0 196 - -196 Total: Before=22565857, After=22567825, chg +0.01% Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260122045720.1221017-5-edumazet@google.com Signed-off-by: Jakub Kicinski

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2026-01-23T04:14:36+00:00

Cross-merge networking fixes after downstream PR (net-6.19-rc7). Conflicts: drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b35a6fd37a00 ("hinic3: Add adaptive IRQ coalescing with DIM") fb2bb2a1ebf7 ("hinic3: Fix netif_queue_set_napi queue_index input parameter error") https://lore.kernel.org/fc0a7fdf08789a52653e8ad05281a0a849e79206.1768915707.git.zhuyikai1@h-partners.com drivers/net/wireless/ath/ath12k/mac.c drivers/net/wireless/ath/ath12k/wifi7/hw.c 31707572108d ("wifi: ath12k: Fix wrong P2P device link id issue") c26f294fef2a ("wifi: ath12k: Move ieee80211_ops callback to the arch specific module") https://lore.kernel.org/20260114123751.6a208818@canb.auug.org.au Adjacent changes: drivers/net/wireless/ath/ath12k/mac.c 8b8d6ee53dfd ("wifi: ath12k: Fix scan state stuck in ABORTING after cancel_remain_on_channel") 914c890d3b90 ("wifi: ath12k: Add framework for hardware specific ieee80211_ops registration") Signed-off-by: Jakub Kicinski

net: add kdoc for napi_consume_skb()

2026-01-21T02:27:50+00:00

Looks like AI reviewers miss that napi_consume_skb() must have a real budget passed to it. Let's see if adding a real kdoc will help them figure this out. Reviewed-by: Jason Xing Link: https://patch.msgid.link/20260119224140.1362729-1-kuba@kernel.org Signed-off-by: Jakub Kicinski

net: fclone allocation small optimization

2026-01-21T02:25:33+00:00

After skb allocation, initial skb->fclone value is 0 (SKB_FCLONE_UNAVAILABLE) We can replace one RMW sequence with a single OR instruction. movzbl 0x7e(%r13),%eax // skb->fclone = SKB_FCLONE_ORIG; and $0xf3,%al or $0x4,%al mov %al,0x7e(%r13) -> or $0x4,0x7e(%r13) // skb->fclone |= SKB_FCLONE_ORIG; Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260116164402.1872649-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net: split kmalloc_reserve() to allow inlining

2026-01-21T02:19:18+00:00

kmalloc_reserve() is too big to be inlined. Put the slow path in a new out-of-line function : kmalloc_pfmemalloc() Then let kmalloc_reserve() set skb->pfmemalloc only when/if the slow path is taken. This makes __alloc_skb() faster : - kmalloc_reserve() is now automatically inlined by both gcc and clang. - No more expensive RMW (skb->pfmemalloc = pfmemalloc). - No more expensive stack canary (for CONFIG_STACKPROTECTOR_STRONG=y). - Removal of two prefetches that were coming too late for modern cpus. Text size increase is quite small compared to the cpu savings (~0.7 %) $ size net/core/skbuff.clang.before.o net/core/skbuff.clang.after.o text data bss dec hex filename 72507 5897 0 78404 13244 net/core/skbuff.clang.before.o 72681 5897 0 78578 132f2 net/core/skbuff.clang.after.o Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260116041359.181104-1-edumazet@google.com Signed-off-by: Jakub Kicinski