From b62e3317b68d9c84301940ca8ca9c35a584111b2 Mon Sep 17 00:00:00 2001 From: Xiang wangx Date: Thu, 16 Dec 2021 23:19:16 +0800 Subject: net: fix typo in a comment The double 'as' in a comment is repeated, thus it should be removed. Signed-off-by: Xiang wangx Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be5cb3360b94..6aadcc0ecb5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1937,7 +1937,7 @@ enum netdev_ml_priv_type { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * - * @nested_level: Used as as a parameter of spin_lock_nested() of + * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. -- cgit v1.2.3 From ec624fe740b416fb68d536b37fb8eef46f90b5c2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 14 Dec 2021 19:24:33 +0200 Subject: net/sched: Extend qdisc control block with tc control block BPF layer extends the qdisc control block via struct bpf_skb_data_end and because of that there is no more room to add variables to the qdisc layer control block without going over the skb->cb size. Extend the qdisc control block with a tc control block, and move all tc related variables to there as a pre-step for extending the tc control block with additional members. Signed-off-by: Paul Blakey Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 15 +++++++++++++++ include/net/sch_generic.h | 2 -- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index bf79f3a890af..05f18e81f3e8 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -193,4 +193,19 @@ static inline void skb_txtime_consumed(struct sk_buff *skb) skb->tstamp = ktime_set(0, 0); } +struct tc_skb_cb { + struct qdisc_skb_cb qdisc_cb; + + u16 mru; + bool post_ct; +}; + +static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) +{ + struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; + + BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); + return cb; +} + #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 22179b2fda72..c70e6d2b2fdd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -447,8 +447,6 @@ struct qdisc_skb_cb { }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; - u16 mru; - bool post_ct; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); -- cgit v1.2.3 From 3849595866166b23bf6a0cb9ff87e06423167f67 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 14 Dec 2021 19:24:34 +0200 Subject: net/sched: flow_dissector: Fix matching on zone id for invalid conns If ct rejects a flow, it removes the conntrack info from the skb. act_ct sets the post_ct variable so the dissector will see this case as an +tracked +invalid state, but the zone id is lost with the conntrack info. To restore the zone id on such cases, set the last executed zone, via the tc control block, when passing ct, and read it back in the dissector if there is no ct info on the skb (invalid connection). Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Signed-off-by: Paul Blakey Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/net/pkt_sched.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c8cb7e697d47..2ecf8cfd2223 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1380,7 +1380,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, - bool post_ct); + bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 05f18e81f3e8..9e71691c491b 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -198,6 +198,7 @@ struct tc_skb_cb { u16 mru; bool post_ct; + u16 zone; /* Only valid if post_ct = true */ }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) -- cgit v1.2.3 From 635d448a1cce4b4ebee52b351052c70434fa90ea Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 14 Dec 2021 19:24:35 +0200 Subject: net: openvswitch: Fix matching zone id for invalid conns arriving from tc Zone id is not restored if we passed ct and ct rejected the connection, as there is no ct info on the skb. Save the zone from tc skb cb to tc skb extension and pass it on to ovs, use that info to restore the zone id for invalid connections. Fixes: d29334c15d33 ("net/sched: act_api: fix miss set post_ct for ovs after do conntrack in act_ct") Signed-off-by: Paul Blakey Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2ecf8cfd2223..4507d77d6941 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -286,6 +286,7 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; + __u16 zone; bool post_ct; }; #endif -- cgit v1.2.3 From 8f905c0e7354ef261360fb7535ea079b1082c105 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 20 Dec 2021 06:33:30 -0800 Subject: inet: fully convert sk->sk_rx_dst to RCU rules syzbot reported various issues around early demux, one being included in this changelog [1] sk->sk_rx_dst is using RCU protection without clearly documenting it. And following sequences in tcp_v4_do_rcv()/tcp_v6_do_rcv() are not following standard RCU rules. [a] dst_release(dst); [b] sk->sk_rx_dst = NULL; They look wrong because a delete operation of RCU protected pointer is supposed to clear the pointer before the call_rcu()/synchronize_rcu() guarding actual memory freeing. In some cases indeed, dst could be freed before [b] is done. We could cheat by clearing sk_rx_dst before calling dst_release(), but this seems the right time to stick to standard RCU annotations and debugging facilities. [1] BUG: KASAN: use-after-free in dst_check include/net/dst.h:470 [inline] BUG: KASAN: use-after-free in tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 Read of size 2 at addr ffff88807f1cb73a by task syz-executor.5/9204 CPU: 0 PID: 9204 Comm: syz-executor.5 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x320 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:450 dst_check include/net/dst.h:470 [inline] tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 ip_rcv_finish_core.constprop.0+0x15de/0x1e80 net/ipv4/ip_input.c:340 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 common_interrupt+0x52/0xc0 arch/x86/kernel/irq.c:240 asm_common_interrupt+0x1e/0x40 arch/x86/include/asm/idtentry.h:629 RIP: 0033:0x7f5e972bfd57 Code: 39 d1 73 14 0f 1f 80 00 00 00 00 48 8b 50 f8 48 83 e8 08 48 39 ca 77 f3 48 39 c3 73 3e 48 89 13 48 8b 50 f8 48 89 38 49 8b 0e <48> 8b 3e 48 83 c3 08 48 83 c6 08 eb bc 48 39 d1 72 9e 48 39 d0 73 RSP: 002b:00007fff8a413210 EFLAGS: 00000283 RAX: 00007f5e97108990 RBX: 00007f5e97108338 RCX: ffffffff81d3aa45 RDX: ffffffff81d3aa45 RSI: 00007f5e97108340 RDI: ffffffff81d3aa45 RBP: 00007f5e97107eb8 R08: 00007f5e97108d88 R09: 0000000093c2e8d9 R10: 0000000000000000 R11: 0000000000000000 R12: 00007f5e97107eb0 R13: 00007f5e97108338 R14: 00007f5e97107ea8 R15: 0000000000000019 Allocated by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x90/0xc0 mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x202/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 ip_route_input_slow+0x1817/0x3a20 net/ipv4/route.c:2340 ip_route_input_rcu net/ipv4/route.c:2470 [inline] ip_route_input_noref+0x116/0x2a0 net/ipv4/route.c:2415 ip_rcv_finish_core.constprop.0+0x288/0x1e80 net/ipv4/ip_input.c:354 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Freed by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xff/0x130 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1749 slab_free mm/slub.c:3513 [inline] kmem_cache_free+0xbd/0x5d0 mm/slub.c:3530 dst_destroy+0x2d6/0x3f0 net/core/dst.c:127 rcu_do_batch kernel/rcu/tree.c:2506 [inline] rcu_core+0x7ab/0x1470 kernel/rcu/tree.c:2741 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 __kasan_record_aux_stack+0xf5/0x120 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:2985 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3065 dst_release net/core/dst.c:177 [inline] dst_release+0x79/0xe0 net/core/dst.c:167 tcp_v4_do_rcv+0x612/0x8d0 net/ipv4/tcp_ipv4.c:1712 sk_backlog_rcv include/net/sock.h:1030 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2768 release_sock+0x54/0x1b0 net/core/sock.c:3300 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1441 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_write_iter+0x289/0x3c0 net/socket.c:1057 call_write_iter include/linux/fs.h:2162 [inline] new_sync_write+0x429/0x660 fs/read_write.c:503 vfs_write+0x7cd/0xae0 fs/read_write.c:590 ksys_write+0x1ee/0x250 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88807f1cb700 which belongs to the cache ip_dst_cache of size 176 The buggy address is located 58 bytes inside of 176-byte region [ffff88807f1cb700, ffff88807f1cb7b0) The buggy address belongs to the page: page:ffffea0001fc72c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x7f1cb flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 dead000000000100 dead000000000122 ffff8881413bb780 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL), pid 5, ts 108466983062, free_ts 108048976062 prep_new_page mm/page_alloc.c:2418 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4149 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5369 alloc_pages+0x1a7/0x300 mm/mempolicy.c:2191 alloc_slab_page mm/slub.c:1793 [inline] allocate_slab mm/slub.c:1930 [inline] new_slab+0x32d/0x4a0 mm/slub.c:1993 ___slab_alloc+0x918/0xfe0 mm/slub.c:3022 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3109 slab_alloc_node mm/slub.c:3200 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x35c/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 __mkroute_output net/ipv4/route.c:2564 [inline] ip_route_output_key_hash_rcu+0x921/0x2d00 net/ipv4/route.c:2791 ip_route_output_key_hash+0x18b/0x300 net/ipv4/route.c:2619 __ip_route_output_key include/net/route.h:126 [inline] ip_route_output_flow+0x23/0x150 net/ipv4/route.c:2850 ip_route_output_key include/net/route.h:142 [inline] geneve_get_v4_rt+0x3a6/0x830 drivers/net/geneve.c:809 geneve_xmit_skb drivers/net/geneve.c:899 [inline] geneve_xmit+0xc4a/0x3540 drivers/net/geneve.c:1082 __netdev_start_xmit include/linux/netdevice.h:4994 [inline] netdev_start_xmit include/linux/netdevice.h:5008 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x1eb/0x920 net/core/dev.c:3606 __dev_queue_xmit+0x299a/0x3650 net/core/dev.c:4229 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1338 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1389 free_unref_page_prepare mm/page_alloc.c:3309 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3388 qlink_free mm/kasan/quarantine.c:146 [inline] qlist_free_all+0x5a/0xc0 mm/kasan/quarantine.c:165 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:272 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:444 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] kmem_cache_alloc_node+0x255/0x3f0 mm/slub.c:3270 __alloc_skb+0x215/0x340 net/core/skbuff.c:414 alloc_skb include/linux/skbuff.h:1126 [inline] alloc_skb_with_frags+0x93/0x620 net/core/skbuff.c:6078 sock_alloc_send_pskb+0x783/0x910 net/core/sock.c:2575 mld_newpack+0x1df/0x770 net/ipv6/mcast.c:1754 add_grhead+0x265/0x330 net/ipv6/mcast.c:1857 add_grec+0x1053/0x14e0 net/ipv6/mcast.c:1995 mld_send_initial_cr.part.0+0xf6/0x230 net/ipv6/mcast.c:2242 mld_send_initial_cr net/ipv6/mcast.c:1232 [inline] mld_dad_work+0x1d3/0x690 net/ipv6/mcast.c:2268 process_one_work+0x9b2/0x1690 kernel/workqueue.c:2298 worker_thread+0x658/0x11f0 kernel/workqueue.c:2445 Memory state around the buggy address: ffff88807f1cb600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807f1cb680: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff88807f1cb700: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88807f1cb780: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ffff88807f1cb800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index bea21ff70e74..d47e9658da28 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -431,7 +431,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry *sk_rx_dst; + struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; -- cgit v1.2.3 From 7e5cced9ca84df52d874aca6b632f930b3dc5bc6 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 20 Dec 2021 09:49:01 -0500 Subject: net: accept UFOv6 packages in virtio_net_hdr_to_skb Skb with skb->protocol 0 at the time of virtio_net_hdr_to_skb may have a protocol inferred from virtio_net_hdr with virtio_net_hdr_set_proto. Unlike TCP, UDP does not have separate types for IPv4 and IPv6. Type VIRTIO_NET_HDR_GSO_UDP is guessed to be IPv4/UDP. As of the below commit, UFOv6 packets are dropped due to not matching the protocol as obtained from dev_parse_header_protocol. Invert the test to take that L2 protocol field as starting point and pass both UFOv4 and UFOv6 for VIRTIO_NET_HDR_GSO_UDP. Fixes: 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct") Link: https://lore.kernel.org/netdev/CABcq3pG9GRCYqFDBAJ48H1vpnnX=41u+MhQnayF1ztLH4WX0Fw@mail.gmail.com/ Reported-by: Andrew Melnichenko Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20211220144901.2784030-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 04e87f4b9417..22dd48c82560 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -7,6 +7,21 @@ #include #include +static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) +{ + switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + return protocol == cpu_to_be16(ETH_P_IP); + case VIRTIO_NET_HDR_GSO_TCPV6: + return protocol == cpu_to_be16(ETH_P_IPV6); + case VIRTIO_NET_HDR_GSO_UDP: + return protocol == cpu_to_be16(ETH_P_IP) || + protocol == cpu_to_be16(ETH_P_IPV6); + default: + return false; + } +} + static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { @@ -88,9 +103,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); - virtio_net_hdr_set_proto(skb, hdr); - if (protocol && protocol != skb->protocol) + if (!protocol) + virtio_net_hdr_set_proto(skb, hdr); + else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; + else + skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, -- cgit v1.2.3 From 1ed1d592113959f00cc552c3b9f47ca2d157768f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 20 Dec 2021 09:50:27 -0500 Subject: net: skip virtio_net_hdr_set_proto if protocol already set virtio_net_hdr_set_proto infers skb->protocol from the virtio_net_hdr gso_type, to avoid packets getting dropped for lack of a proto type. Its protocol choice is a guess, especially in the case of UFO, where the single VIRTIO_NET_HDR_GSO_UDP label covers both UFOv4 and UFOv6. Skip this best effort if the field is already initialized. Whether explicitly from userspace, or implicitly based on an earlier call to dev_parse_header_protocol (which is more robust, but was introduced after this patch). Fixes: 9d2f67e43b73 ("net/packet: fix packet drop as of virtio gso") Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20211220145027.2784293-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 22dd48c82560..a960de68ac69 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -25,6 +25,9 @@ static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { + if (skb->protocol) + return 0; + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: -- cgit v1.2.3