From 0a4cc4accf00b49b4728bb7639cb90a6a5b674e2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 25 Nov 2024 09:30:39 +0000 Subject: tcp: populate XPS related fields of timewait sockets syzbot reported that netdev_core_pick_tx() was reading an uninitialized field [1]. This is indeed hapening for timewait sockets after recent commits. We can copy the original established socket sk_tx_queue_mapping and sk_rx_queue_mapping fields, instead of adding more checks in fast paths. As a bonus, packets will use the same transmit queue than prior ones, this potentially can avoid reordering. [1] BUG: KMSAN: uninit-value in netdev_pick_tx+0x5c7/0x1550 netdev_pick_tx+0x5c7/0x1550 netdev_core_pick_tx+0x1d2/0x4a0 net/core/dev.c:4312 __dev_queue_xmit+0x128a/0x57d0 net/core/dev.c:4394 dev_queue_xmit include/linux/netdevice.h:3168 [inline] neigh_hh_output include/net/neighbour.h:523 [inline] neigh_output include/net/neighbour.h:537 [inline] ip_finish_output2+0x187c/0x1b70 net/ipv4/ip_output.c:236 __ip_finish_output+0x287/0x810 ip_finish_output+0x4b/0x600 net/ipv4/ip_output.c:324 NF_HOOK_COND include/linux/netfilter.h:303 [inline] ip_output+0x15f/0x3f0 net/ipv4/ip_output.c:434 dst_output include/net/dst.h:450 [inline] ip_local_out net/ipv4/ip_output.c:130 [inline] ip_send_skb net/ipv4/ip_output.c:1505 [inline] ip_push_pending_frames+0x444/0x570 net/ipv4/ip_output.c:1525 ip_send_unicast_reply+0x18c1/0x1b30 net/ipv4/ip_output.c:1672 tcp_v4_send_reset+0x238d/0x2a40 net/ipv4/tcp_ipv4.c:910 tcp_v4_rcv+0x48f8/0x5750 net/ipv4/tcp_ipv4.c:2431 ip_protocol_deliver_rcu+0x2a3/0x13d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x336/0x500 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:314 [inline] ip_local_deliver+0x21f/0x490 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:460 [inline] ip_sublist_rcv_finish net/ipv4/ip_input.c:578 [inline] ip_list_rcv_finish net/ipv4/ip_input.c:628 [inline] ip_sublist_rcv+0x15f3/0x17f0 net/ipv4/ip_input.c:636 ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:670 __netif_receive_skb_list_ptype net/core/dev.c:5715 [inline] __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5762 __netif_receive_skb_list net/core/dev.c:5814 [inline] netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:5905 gro_normal_list include/net/gro.h:515 [inline] napi_complete_done+0x3d4/0x810 net/core/dev.c:6256 virtqueue_napi_complete drivers/net/virtio_net.c:758 [inline] virtnet_poll+0x5d80/0x6bf0 drivers/net/virtio_net.c:3013 __napi_poll+0xe7/0x980 net/core/dev.c:6877 napi_poll net/core/dev.c:6946 [inline] net_rx_action+0xa5a/0x19b0 net/core/dev.c:7068 handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0x68/0x180 kernel/softirq.c:655 irq_exit_rcu+0x12/0x20 kernel/softirq.c:671 common_interrupt+0x97/0xb0 arch/x86/kernel/irq.c:278 asm_common_interrupt+0x2b/0x40 arch/x86/include/asm/idtentry.h:693 __preempt_count_sub arch/x86/include/asm/preempt.h:84 [inline] kmsan_virt_addr_valid arch/x86/include/asm/kmsan.h:95 [inline] virt_to_page_or_null+0xfb/0x150 mm/kmsan/shadow.c:75 kmsan_get_metadata+0x13e/0x1c0 mm/kmsan/shadow.c:141 kmsan_get_shadow_origin_ptr+0x4d/0xb0 mm/kmsan/shadow.c:102 get_shadow_origin_ptr mm/kmsan/instrumentation.c:38 [inline] __msan_metadata_ptr_for_store_4+0x27/0x40 mm/kmsan/instrumentation.c:93 rcu_preempt_read_enter kernel/rcu/tree_plugin.h:390 [inline] __rcu_read_lock+0x46/0x70 kernel/rcu/tree_plugin.h:413 rcu_read_lock include/linux/rcupdate.h:847 [inline] batadv_nc_purge_orig_hash net/batman-adv/network-coding.c:408 [inline] batadv_nc_worker+0x114/0x19e0 net/batman-adv/network-coding.c:719 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xae0/0x1c40 kernel/workqueue.c:3310 worker_thread+0xea7/0x14f0 kernel/workqueue.c:3391 kthread+0x3e2/0x540 kernel/kthread.c:389 ret_from_fork+0x6d/0x90 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Uninit was created at: __alloc_pages_noprof+0x9a7/0xe00 mm/page_alloc.c:4774 alloc_pages_mpol_noprof+0x299/0x990 mm/mempolicy.c:2265 alloc_pages_noprof+0x1bf/0x1e0 mm/mempolicy.c:2344 alloc_slab_page mm/slub.c:2412 [inline] allocate_slab+0x320/0x12e0 mm/slub.c:2578 new_slab mm/slub.c:2631 [inline] ___slab_alloc+0x12ef/0x35e0 mm/slub.c:3818 __slab_alloc mm/slub.c:3908 [inline] __slab_alloc_node mm/slub.c:3961 [inline] slab_alloc_node mm/slub.c:4122 [inline] kmem_cache_alloc_noprof+0x57a/0xb20 mm/slub.c:4141 inet_twsk_alloc+0x11f/0x9d0 net/ipv4/inet_timewait_sock.c:188 tcp_time_wait+0x83/0xf50 net/ipv4/tcp_minisocks.c:309 tcp_rcv_state_process+0x145a/0x49d0 tcp_v4_do_rcv+0xbf9/0x11a0 net/ipv4/tcp_ipv4.c:1939 tcp_v4_rcv+0x51df/0x5750 net/ipv4/tcp_ipv4.c:2351 ip_protocol_deliver_rcu+0x2a3/0x13d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x336/0x500 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:314 [inline] ip_local_deliver+0x21f/0x490 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:460 [inline] ip_sublist_rcv_finish net/ipv4/ip_input.c:578 [inline] ip_list_rcv_finish net/ipv4/ip_input.c:628 [inline] ip_sublist_rcv+0x15f3/0x17f0 net/ipv4/ip_input.c:636 ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:670 __netif_receive_skb_list_ptype net/core/dev.c:5715 [inline] __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5762 __netif_receive_skb_list net/core/dev.c:5814 [inline] netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:5905 gro_normal_list include/net/gro.h:515 [inline] napi_complete_done+0x3d4/0x810 net/core/dev.c:6256 virtqueue_napi_complete drivers/net/virtio_net.c:758 [inline] virtnet_poll+0x5d80/0x6bf0 drivers/net/virtio_net.c:3013 __napi_poll+0xe7/0x980 net/core/dev.c:6877 napi_poll net/core/dev.c:6946 [inline] net_rx_action+0xa5a/0x19b0 net/core/dev.c:7068 handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0x68/0x180 kernel/softirq.c:655 irq_exit_rcu+0x12/0x20 kernel/softirq.c:671 common_interrupt+0x97/0xb0 arch/x86/kernel/irq.c:278 asm_common_interrupt+0x2b/0x40 arch/x86/include/asm/idtentry.h:693 CPU: 0 UID: 0 PID: 3962 Comm: kworker/u8:18 Not tainted 6.12.0-syzkaller-09073-g9f16d5e6f220 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: bat_events batadv_nc_worker Fixes: 79636038d37e ("ipv4: tcp: give socket pointer to control skbs") Fixes: 507a96737d99 ("ipv6: tcp: give socket pointer to control skbs") Reported-by: syzbot+8b0959fc16551d55896b@syzkaller.appspotmail.com Link: https://lore.kernel.org/netdev/674442bd.050a0220.1cc393.0072.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Reviewed-by: Brian Vazquez Link: https://patch.msgid.link/20241125093039.3095790-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/inet_timewait_sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index beb533a0e880..62c0a7e65d6b 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -45,6 +45,8 @@ struct inet_timewait_sock { #define tw_node __tw_common.skc_nulls_node #define tw_bind_node __tw_common.skc_bind_node #define tw_refcnt __tw_common.skc_refcnt +#define tw_tx_queue_mapping __tw_common.skc_tx_queue_mapping +#define tw_rx_queue_mapping __tw_common.skc_rx_queue_mapping #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net -- cgit v1.2.3 From 7b1d83da254be3bf054965c8f3b1ad976f460ae5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 27 Nov 2024 12:46:54 +0100 Subject: netfilter: nft_inner: incorrect percpu area handling under softirq Softirq can interrupt ongoing packet from process context that is walking over the percpu area that contains inner header offsets. Disable bh and perform three checks before restoring the percpu inner header offsets to validate that the percpu area is valid for this skbuff: 1) If the NFT_PKTINFO_INNER_FULL flag is set on, then this skbuff has already been parsed before for inner header fetching to register. 2) Validate that the percpu area refers to this skbuff using the skbuff pointer as a cookie. If there is a cookie mismatch, then this skbuff needs to be parsed again. 3) Finally, validate if the percpu area refers to this tunnel type. Only after these three checks the percpu area is restored to a on-stack copy and bh is enabled again. After inner header fetching, the on-stack copy is stored back to the percpu area. Fixes: 3a07327d10a0 ("netfilter: nft_inner: support for inner tunnel header matching") Reported-by: syzbot+84d0441b9860f0d63285@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index ff27cb2e1662..03b6165756fc 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -161,6 +161,7 @@ enum { }; struct nft_inner_tun_ctx { + unsigned long cookie; u16 type; u16 inner_tunoff; u16 inner_lloff; -- cgit v1.2.3 From 50b94204446e1215af081fd713d7d566d9258e35 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 3 Dec 2024 10:48:15 +0100 Subject: ipmr: tune the ipmr_can_free_table() checks. Eric reported a syzkaller-triggered splat caused by recent ipmr changes: WARNING: CPU: 2 PID: 6041 at net/ipv6/ip6mr.c:419 ip6mr_free_table+0xbd/0x120 net/ipv6/ip6mr.c:419 Modules linked in: CPU: 2 UID: 0 PID: 6041 Comm: syz-executor183 Not tainted 6.12.0-syzkaller-10681-g65ae975e97d5 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:ip6mr_free_table+0xbd/0x120 net/ipv6/ip6mr.c:419 Code: 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 58 49 83 bc 24 c0 0e 00 00 00 74 09 e8 44 ef a9 f7 90 <0f> 0b 90 e8 3b ef a9 f7 48 8d 7b 38 e8 12 a3 96 f7 48 89 df be 0f RSP: 0018:ffffc90004267bd8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff88803c710000 RCX: ffffffff89e4d844 RDX: ffff88803c52c880 RSI: ffffffff89e4d87c RDI: ffff88803c578ec0 RBP: 0000000000000001 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88803c578000 R13: ffff88803c710000 R14: ffff88803c710008 R15: dead000000000100 FS: 00007f7a855ee6c0(0000) GS:ffff88806a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7a85689938 CR3: 000000003c492000 CR4: 0000000000352ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ip6mr_rules_exit+0x176/0x2d0 net/ipv6/ip6mr.c:283 ip6mr_net_exit_batch+0x53/0xa0 net/ipv6/ip6mr.c:1388 ops_exit_list+0x128/0x180 net/core/net_namespace.c:177 setup_net+0x4fe/0x860 net/core/net_namespace.c:394 copy_net_ns+0x2b4/0x6b0 net/core/net_namespace.c:500 create_new_namespaces+0x3ea/0xad0 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc0/0x1f0 kernel/nsproxy.c:228 ksys_unshare+0x45d/0xa40 kernel/fork.c:3334 __do_sys_unshare kernel/fork.c:3405 [inline] __se_sys_unshare kernel/fork.c:3403 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:3403 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7a856332d9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f7a855ee238 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007f7a856bd308 RCX: 00007f7a856332d9 RDX: 00007f7a8560f8c6 RSI: 0000000000000000 RDI: 0000000062040200 RBP: 00007f7a856bd300 R08: 00007fff932160a7 R09: 00007f7a855ee6c0 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f7a856bd30c R13: 0000000000000000 R14: 00007fff93215fc0 R15: 00007fff932160a8 The root cause is a network namespace creation failing after successful initialization of the ipmr subsystem. Such a case is not currently matched by the ipmr_can_free_table() helper. New namespaces are zeroed on allocation and inserted into net ns list only after successful creation; when deleting an ipmr table, the list next pointer can be NULL only on netns initialization failure. Update the ipmr_can_free_table() checks leveraging such condition. Reported-by: Eric Dumazet Reported-by: syzbot+6e8cb445d4b43d006e0c@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6e8cb445d4b43d006e0c Fixes: 11b6e701bce9 ("ipmr: add debug check for mr table cleanup") Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/8bde975e21bbca9d9c27e36209b2dd4f1d7a3f00.1733212078.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/net/net_namespace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 873c0f9fdac6..f943bd79ef03 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -325,6 +325,11 @@ static inline int check_net(const struct net *net) #define net_drop_ns NULL #endif +/* Returns true if the netns initialization is completed successfully */ +static inline bool net_initialized(const struct net *net) +{ + return READ_ONCE(net->list.next); +} static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, -- cgit v1.2.3