May 2022 - Kernel - mailweb.openeuler.org

[PATCH openEuler-5.10-LTS 01/31] inet: fully convert sk->sk_rx_dst to RCU rules
by Zheng Zengkai 31 May '22

31 May '22

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v5.16-rc7 commit 8f905c0e7354ef261360fb7535ea079b1082c105 category: bugfix bugzilla: 186714 https://gitee.com/src-openeuler/kernel/issues/I57QUK -------------------------------- 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: <TASK> __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 </TASK> 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 <edumazet(a)google.com> Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Conflict: include/net/sock.h net/ipv4/tcp_ipv4.c net/ipv6/tcp_ipv6.c net/ipv6/udp.c Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/net/sock.h | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/tcp.c | 3 +-- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 11 +++++++---- net/ipv4/udp.c | 6 +++--- net/ipv6/tcp_ipv6.c | 11 +++++++---- net/ipv6/udp.c | 4 ++-- 8 files changed, 23 insertions(+), 18 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index c958be11d172..bd34faf53b1f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -428,7 +428,7 @@ 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; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8bf43ca7139a..911ad595dbb9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -158,7 +158,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); - dst_release(sk->sk_rx_dst); + dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fcd792816756..c19428e97876 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2814,8 +2814,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - dst_release(sk->sk_rx_dst); - sk->sk_rx_dst = NULL; + dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 11f3f8e23a8a..6f4ac0f10f57 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5744,7 +5744,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) trace_tcp_probe(sk, skb); tcp_mstamp_refresh(tp); - if (unlikely(!sk->sk_rx_dst)) + if (unlikely(!rcu_access_pointer(sk->sk_rx_dst))) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ebfeeeadd47c..078f3a5d65b3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1670,15 +1670,18 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } tcp_rcv_established(sk, skb); @@ -1753,7 +1756,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2160,7 +2163,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8cca8bda0612..121c08d4255c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2186,7 +2186,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg(&sk->sk_rx_dst, dst); + old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } @@ -2376,7 +2376,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); @@ -2535,7 +2535,7 @@ int udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index df33145b876c..b87b04526e65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -107,7 +107,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } @@ -1482,15 +1482,18 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } @@ -1842,7 +1845,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 503706397839..7022dcbb5a11 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -940,7 +940,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { @@ -1054,7 +1054,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); -- 2.20.1

1 30

[PATCH openEuler-5.10-LTS 0/7] Backport 5.10.105 LTS
by Zheng Zengkai 31 May '22

31 May '22

Backport 5.10.105 LTS patches from upstream Revert "ACPI: PM: s2idle: Cancel wakeup before dispatching EC GPE" arm64: cpufeature: add HWCAP for FEAT_RPRES arm64: cpufeature: add HWCAP for FEAT_AFP arm64: Add Cortex-A510 CPU part definition arm64: Add Cortex-X2 CPU part definition arm64: Add Neoverse-N2, Cortex-A710 CPU part definition arm64: cputype: Add CPU implementor & types for the Apple M1 cores Conflicts: arm64: cpufeature: add HWCAP for FEAT_RPRES arm64: cpufeature: add HWCAP for FEAT_AFP arm64: Add Cortex-A510 CPU part definition arm64: Add Neoverse-N2, Cortex-A710 CPU part definition arm64: cputype: Add CPU implementor & types for the Apple M1 cores Already merged(51): xen/netfront: react properly to failing gnttab_end_foreign_access_ref() xen/gnttab: fix gnttab_end_foreign_access() without page specified xen/pvcalls: use alloc/free_pages_exact() xen/9p: use alloc/free_pages_exact() xen: remove gnttab_query_foreign_access() xen/gntalloc: don't use gnttab_query_foreign_access() xen/scsifront: don't use gnttab_query_foreign_access() for mapped status xen/netfront: don't use gnttab_query_foreign_access() for mapped status xen/blkfront: don't use gnttab_query_foreign_access() for mapped status xen/grant-table: add gnttab_try_end_foreign_access() xen/xenbus: don't let xenbus_grant_ring() remove grants in error case ARM: Do not use NOCROSSREFS directive with ld.lld arm64: proton-pack: Include unprivileged eBPF status in Spectre v2 mitigation reporting arm64: Use the clearbhb instruction in mitigations KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated arm64: Mitigate spectre style branch history side channels KVM: arm64: Allow indirect vectors to be used without SPECTRE_V3A arm64: proton-pack: Report Spectre-BHB vulnerabilities as part of Spectre-v2 arm64: Add percpu vectors for EL1 arm64: entry: Add macro for reading symbol addresses from the trampoline arm64: entry: Add vectors that have the bhb mitigation sequences arm64: entry: Add non-kpti __bp_harden_el1_vectors for mitigations arm64: entry: Allow the trampoline text to occupy multiple pages arm64: entry: Make the kpti trampoline's kpti sequence optional arm64: entry: Move trampoline macros out of ifdef'd section arm64: entry: Don't assume tramp_vectors is the start of the vectors arm64: entry: Allow tramp_alias to access symbols after the 4K boundary arm64: entry: Move the trampoline data page before the text page arm64: entry: Free up another register on kpti's tramp_exit path arm64: entry: Make the trampoline cleanup optional arm64: spectre: Rename spectre_v4_patch_fw_mitigation_conduit arm64: entry.S: Add ventry overflow sanity checks arm64: add ID_AA64ISAR2_EL1 sys register arm64: Add HWCAP for self-synchronising virtual counter ARM: include unprivileged BPF status in Spectre V2 reporting ARM: Spectre-BHB workaround ARM: use LOADADDR() to get load address of sections ARM: early traps initialisation ARM: report Spectre v2 status through sysfs x86/speculation: Warn about eIBRS + LFENCE + Unprivileged eBPF + SMT x86/speculation: Warn about Spectre v2 LFENCE mitigation x86/speculation: Update link to AMD speculation whitepaper x86/speculation: Use generic retpoline by default on AMD x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting Documentation/hw-vuln: Update spectre doc x86/speculation: Add eIBRS + Retpoline options x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE x86,bugs: Unconditionally allow spectre_v2=retpoline,amd ARM: fix build error when BPF_SYSCALL is disabled ARM: fix co-processor register typo ARM: fix build warning in proc-v7-bugs.c Total patches: 58 - 51 = 7 Anshuman Khandual (2): arm64: Add Cortex-X2 CPU part definition arm64: Add Cortex-A510 CPU part definition Greg Kroah-Hartman (1): Revert "ACPI: PM: s2idle: Cancel wakeup before dispatching EC GPE" Hector Martin (1): arm64: cputype: Add CPU implementor & types for the Apple M1 cores Joey Gouly (2): arm64: cpufeature: add HWCAP for FEAT_AFP arm64: cpufeature: add HWCAP for FEAT_RPRES Suzuki K Poulose (1): arm64: Add Neoverse-N2, Cortex-A710 CPU part definition Documentation/arm64/cpu-feature-registers.rst | 17 +++++++++++++++++ Documentation/arm64/elf_hwcaps.rst | 8 ++++++++ arch/arm64/include/asm/cputype.h | 14 ++++++++++++++ arch/arm64/include/asm/hwcap.h | 2 ++ arch/arm64/include/asm/sysreg.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 2 ++ arch/arm64/kernel/cpufeature.c | 4 ++++ arch/arm64/kernel/cpuinfo.c | 2 ++ drivers/acpi/ec.c | 10 ---------- drivers/acpi/sleep.c | 14 ++++++++++---- 10 files changed, 60 insertions(+), 14 deletions(-) -- 2.20.1

1 7

[PATCH openEuler-5.10 01/50] inet: fully convert sk->sk_rx_dst to RCU rules
by Zheng Zengkai 31 May '22

31 May '22

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v5.16-rc7 commit 8f905c0e7354ef261360fb7535ea079b1082c105 category: bugfix bugzilla: 186714 https://gitee.com/src-openeuler/kernel/issues/I57QUK -------------------------------- 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: <TASK> __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 </TASK> 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 <edumazet(a)google.com> Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Conflict: include/net/sock.h net/ipv4/tcp_ipv4.c net/ipv6/tcp_ipv6.c net/ipv6/udp.c Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/net/sock.h | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/tcp.c | 3 +-- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 11 +++++++---- net/ipv4/udp.c | 6 +++--- net/ipv6/tcp_ipv6.c | 11 +++++++---- net/ipv6/udp.c | 4 ++-- 8 files changed, 23 insertions(+), 18 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index af73dda0285b..7d068cf871a3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -429,7 +429,7 @@ 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; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8bf43ca7139a..911ad595dbb9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -158,7 +158,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); - dst_release(sk->sk_rx_dst); + dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fcd792816756..c19428e97876 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2814,8 +2814,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - dst_release(sk->sk_rx_dst); - sk->sk_rx_dst = NULL; + dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 11f3f8e23a8a..6f4ac0f10f57 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5744,7 +5744,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) trace_tcp_probe(sk, skb); tcp_mstamp_refresh(tp); - if (unlikely(!sk->sk_rx_dst)) + if (unlikely(!rcu_access_pointer(sk->sk_rx_dst))) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ebfeeeadd47c..078f3a5d65b3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1670,15 +1670,18 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } tcp_rcv_established(sk, skb); @@ -1753,7 +1756,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2160,7 +2163,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8cca8bda0612..121c08d4255c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2186,7 +2186,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg(&sk->sk_rx_dst, dst); + old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } @@ -2376,7 +2376,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); @@ -2535,7 +2535,7 @@ int udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index df33145b876c..b87b04526e65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -107,7 +107,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } @@ -1482,15 +1482,18 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } @@ -1842,7 +1845,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 503706397839..7022dcbb5a11 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -940,7 +940,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { @@ -1054,7 +1054,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); -- 2.20.1

1 49

[PATCH openEuler-5.10 0/7] Backport 5.10.105 LTS
by Zheng Zengkai 31 May '22

31 May '22

Backport 5.10.105 LTS patches from upstream Revert "ACPI: PM: s2idle: Cancel wakeup before dispatching EC GPE" arm64: cpufeature: add HWCAP for FEAT_RPRES arm64: cpufeature: add HWCAP for FEAT_AFP arm64: Add Cortex-A510 CPU part definition arm64: Add Cortex-X2 CPU part definition arm64: Add Neoverse-N2, Cortex-A710 CPU part definition arm64: cputype: Add CPU implementor & types for the Apple M1 cores Conflicts: Revert "ACPI: PM: s2idle: Cancel wakeup before dispatching EC GPE" arm64: Add Cortex-X2 CPU part definition Anshuman Khandual (2): arm64: Add Cortex-X2 CPU part definition arm64: Add Cortex-A510 CPU part definition Greg Kroah-Hartman (1): Revert "ACPI: PM: s2idle: Cancel wakeup before dispatching EC GPE" Hector Martin (1): arm64: cputype: Add CPU implementor & types for the Apple M1 cores Joey Gouly (2): arm64: cpufeature: add HWCAP for FEAT_AFP arm64: cpufeature: add HWCAP for FEAT_RPRES Suzuki K Poulose (1): arm64: Add Neoverse-N2, Cortex-A710 CPU part definition Documentation/arm64/cpu-feature-registers.rst | 17 +++++++++++++++++ Documentation/arm64/elf_hwcaps.rst | 8 ++++++++ arch/arm64/include/asm/cputype.h | 14 ++++++++++++++ arch/arm64/include/asm/hwcap.h | 2 ++ arch/arm64/include/asm/sysreg.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 2 ++ arch/arm64/kernel/cpufeature.c | 4 ++++ arch/arm64/kernel/cpuinfo.c | 2 ++ drivers/acpi/ec.c | 10 ---------- drivers/acpi/sleep.c | 14 ++++++++++---- 10 files changed, 60 insertions(+), 14 deletions(-) -- 2.20.1

1 7

Re:[PATCH OLK-5.10] config: change CONFIG_DMATEST from y to m
by 焦芬芳 30 May '22

30 May '22

hi, all      Reviewed-by, "jiaofenfang"<jiaofenfang(a)uniontech.com>     ------------------ Original ------------------ From:  "Chao Liu"<liuchao173(a)huawei.com>; Date:  Sat, May 28, 2022 03:47 PM To:  "kernel"<kernel(a)openeuler.org>; Cc:  "hewenliang4"<hewenliang4(a)huawei.com>; "fangchuangchuang"<fangchuangchuang(a)huawei.com>; "xiexiuqi"<xiexiuqi(a)huawei.com>; "zhengzengkai"<zhengzengkai(a)huawei.com>; "kai.liu"<kai.liu(a)suse.com>; "jiaofenfang"<jiaofenfang(a)uniontech.com>; "yinxiujiang"<yinxiujiang(a)kylinos.cn>; Subject:  [PATCH OLK-5.10] config: change CONFIG_DMATEST from y to m   euler inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I59Q07 CVE: NA -------------------------------- Simple DMA test client. Say N unless you're debugging a DMA Device driver. It doesn't need to be compiled into the vmlinux, change it to m. Signed-off-by: Chao Liu <liuchao173(a)huawei.com> ---  arch/x86/configs/openeuler_defconfig | 2 +-  1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 61c4be815462..f9c94b618ad4 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -6370,7 +6370,7 @@ CONFIG_HSU_DMA=y  # DMA Clients  #  CONFIG_ASYNC_TX_DMA=y -CONFIG_DMATEST=y +CONFIG_DMATEST=m  CONFIG_DMA_ENGINE_RAID=y    # -- 2.23.0

1 0

[PATCH OLK-5.10] config: change CONFIG_DMATEST from y to m
by Chao Liu 30 May '22

30 May '22

euler inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I59Q07 CVE: NA -------------------------------- Simple DMA test client. Say N unless you're debugging a DMA Device driver. It doesn't need to be compiled into the vmlinux, change it to m. Signed-off-by: Chao Liu <liuchao173(a)huawei.com> --- arch/x86/configs/openeuler_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 61c4be815462..f9c94b618ad4 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -6370,7 +6370,7 @@ CONFIG_HSU_DMA=y # DMA Clients # CONFIG_ASYNC_TX_DMA=y -CONFIG_DMATEST=y +CONFIG_DMATEST=m CONFIG_DMA_ENGINE_RAID=y # -- 2.23.0

3 2

[PATCH openEuler-5.10 1/8] Revert "audit: bugfix for infinite loop when flush the hold queue"
by Zheng Zengkai 28 May '22

28 May '22

From: Cui GaoSheng <cuigaosheng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 186383 https://gitee.com/openeuler/kernel/issues/I4X1AI?from=project-issue CVE: NA backport: openEuler-22.03-LTS -------------------------------- This reverts commit fcfdde9cfc503cfd191b7286f9c48077fb5bf420. Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- kernel/audit.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/kernel/audit.c b/kernel/audit.c index 21be62bc8205..2a38cbaf3ddb 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -732,8 +732,6 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, if (!sk) { if (err_hook) (*err_hook)(skb); - if (queue == &audit_hold_queue) - goto out; continue; } @@ -750,8 +748,6 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, (*err_hook)(skb); if (rc == -EAGAIN) rc = 0; - if (queue == &audit_hold_queue) - goto out; /* continue to drain the queue */ continue; } else @@ -763,7 +759,6 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, } } -out: return (rc >= 0 ? 0 : rc); } -- 2.20.1

1 7

[PATCH openEuler-5.10 00/99] Backport 5.10.104 LTS
by Zheng Zengkai 28 May '22

28 May '22

Backport 5.10.104 LTS patches from upstream hamradio: fix macro redefine warning Revert "xfrm: xfrm_state_mtu should return at least 1280 for ipv6" btrfs: add missing run of delayed items after unlink during log replay btrfs: qgroup: fix deadlock between rescan worker and remove qgroup btrfs: fix lost prealloc extents beyond eof after full fsync tracing: Fix return value of setup handlers tracing/histogram: Fix sorting on old "cpu" value HID: add mapping for KEY_ALL_APPLICATIONS HID: add mapping for KEY_DICTATE Input: samsung-keypad - properly state IOMEM dependency Input: elan_i2c - fix regulator enable count imbalance after suspend/resume Input: elan_i2c - move regulator[en|dis]able() out of elan[en|dis]able_power() net: dcb: disable softirqs in dcbnl_flush_dev() drm/amdgpu: fix suspend/resume hang regression nl80211: Handle nla_memdup failures in handle_nan_filter iavf: Refactor iavf state machine tracking net: chelsio: cxgb3: check the return value of pci_find_capability() ibmvnic: complete init_done on transport events ARM: tegra: Move panels to AUX bus soc: fsl: qe: Check of ioremap return value soc: fsl: guts: Add a missing memory allocation failure check soc: fsl: guts: Revert commit 3c0d64e867ed ARM: dts: Use 32KiHz oscillator on devkit8000 ARM: dts: switch timer config to common devkit8000 devicetree s390/extable: fix exception table sorting memfd: fix F_SEAL_WRITE after shmem huge page allocated ibmvnic: free reset-work-item when flushing igc: igc_write_phy_reg_gpy: drop premature return pinctrl: sunxi: Use unique lockdep classes for IRQs selftests: mlxsw: tc_police_scale: Make test more robust ARM: 9182/1: mmu: fix returns from early_param() and __setup() functions ARM: Fix kgdb breakpoint for Thumb2 igc: igc_read_phy_reg_gpy: drop premature return arm64: dts: rockchip: Switch RK3399-Gru DP to SPDIF output can: gs_usb: change active_channels's type from atomic_t to u8 ASoC: cs4265: Fix the duplicated control name firmware: arm_scmi: Remove space in MODULE_ALIAS name efivars: Respect "block" flag in efivar_entry_set_safe() ixgbe: xsk: change !netif_carrier_ok() handling in ixgbe_xmit_zc() net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe() ibmvnic: register netdev after init of adapter net: sxgbe: fix return value of __setup handler iavf: Fix missing check for running netdev mac80211: treat some SAE auth steps as final net: stmmac: fix return value of __setup handler mac80211: fix forwarded mesh frames AC & queue selection ice: fix concurrent reset and removal of VFs ice: Fix race conditions between virtchnl handling and VF ndo ops net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error cause by server net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error generated by client net/smc: fix connection leak net: dcb: flush lingering app table entries for unregistered devices net: ipv6: ensure we call ipv6_mc_down() at most once batman-adv: Don't expect inter-netns unique iflink indices batman-adv: Request iflink once in batadv_get_real_netdevice batman-adv: Request iflink once in batadv-on-batadv check netfilter: nf_queue: handle socket prefetch netfilter: nf_queue: fix possible use-after-free netfilter: nf_queue: don't assume sk is full socket net: fix up skbs delta_truesize in UDP GRO frag_list e1000e: Correct NVM checksum verification flow xfrm: enforce validity of offload input flags xfrm: fix the if_id check in changelink bpf, sockmap: Do not ignore orig_len parameter netfilter: fix use-after-free in __nf_register_net_hook() xfrm: fix MTU regression mm: Consider __GFP_NOWARN flag for oversized kvmalloc() calls ntb: intel: fix port config status offset for SPR thermal: core: Fix TZ_GET_TRIP NULL pointer dereference xen/netfront: destroy queues before real_num_tx_queues is zeroed drm/i915: s/JSP2/ICP2/ PCH iommu/amd: Recover from event log overflow ASoC: ops: Shift tested values in snd_soc_put_volsw() by +min riscv: Fix config KASAN && DEBUG_VIRTUAL riscv: Fix config KASAN && SPARSEMEM && !SPARSE_VMEMMAP riscv/efi_stub: Fix get_boot_hartid_from_fdt() return value ALSA: intel_hdmi: Fix reference to PCM buffer address tracing: Add ustring operation to filtering string pointers drm/amdgpu: check vm ready by amdgpu_vm->evicting flag ata: pata_hpt37x: fix PCI clock detection serial: stm32: prevent TDR register overwrite when sending x_char tracing: Add test for user space strings when filtering on string pointers exfat: fix i_blocks for files truncated over 4 GiB exfat: reuse exfat_inode_info variable instead of calling EXFAT_I() net: usb: cdc_mbim: avoid altsetting toggling for Telit FN990 i2c: qup: allow COMPILE_TEST i2c: cadence: allow COMPILE_TEST dmaengine: shdma: Fix runtime PM imbalance on error selftests/seccomp: Fix seccomp failure by adding missing headers cifs: fix double free race when mount fails in cifs_get_root() tipc: fix a bit overflow in tipc_crypto_key_rcv() KVM: arm64: vgic: Read HW interrupt pending state from the HW Input: clear BTN_RIGHT/MIDDLE on buttonpads regulator: core: fix false positive in regulator_late_cleanup() ASoC: rt5682: do not block workqueue if card is unbound ASoC: rt5668: do not block workqueue if card is unbound i2c: bcm2835: Avoid clock stretching timeouts mac80211_hwsim: initialize ieee80211_tx_info at hw_scan_work mac80211_hwsim: report NOACK frames in tx_status already merged: usb: gadget: don't release an existing dev->buf usb: gadget: clear related members when goto fail rcu/nocb: Fix missed nocb_timer requeue sched/topology: Make sched_init_numa() use a set for the deduplicating sort sched/topology: Fix sched_domain_topology_level alloc in sched_init_numa() ia64: ensure proper NUMA distance and possible map initialization Total patches: 105 - 6 = 99 Alexandre Ghiti (2): riscv: Fix config KASAN && SPARSEMEM && !SPARSE_VMEMMAP riscv: Fix config KASAN && DEBUG_VIRTUAL Alyssa Ross (1): firmware: arm_scmi: Remove space in MODULE_ALIAS name Amit Cohen (1): selftests: mlxsw: tc_police_scale: Make test more robust Anthoine Bourgeois (2): ARM: dts: switch timer config to common devkit8000 devicetree ARM: dts: Use 32KiHz oscillator on devkit8000 Antony Antony (1): xfrm: fix the if_id check in changelink Benjamin Beichler (1): mac80211_hwsim: report NOACK frames in tx_status Brett Creeley (1): ice: Fix race conditions between virtchnl handling and VF ndo ops Brian Norris (1): arm64: dts: rockchip: Switch RK3399-Gru DP to SPDIF output Christophe JAILLET (2): soc: fsl: guts: Revert commit 3c0d64e867ed soc: fsl: guts: Add a missing memory allocation failure check Christophe Vu-Brugier (2): exfat: reuse exfat_inode_info variable instead of calling EXFAT_I() exfat: fix i_blocks for files truncated over 4 GiB Corinna Vinschen (1): igc: igc_read_phy_reg_gpy: drop premature return D. Wythe (3): net/smc: fix connection leak net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error generated by client net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error cause by server Daniel Borkmann (1): mm: Consider __GFP_NOWARN flag for oversized kvmalloc() calls Daniele Palmas (1): net: usb: cdc_mbim: avoid altsetting toggling for Telit FN990 Dave Jiang (1): ntb: intel: fix port config status offset for SPR David Gow (1): Input: samsung-keypad - properly state IOMEM dependency Eric Anholt (1): i2c: bcm2835: Avoid clock stretching timeouts Eric Dumazet (2): netfilter: fix use-after-free in __nf_register_net_hook() bpf, sockmap: Do not ignore orig_len parameter Fabio Estevam (1): ASoC: cs4265: Fix the duplicated control name Filipe Manana (2): btrfs: fix lost prealloc extents beyond eof after full fsync btrfs: add missing run of delayed items after unlink during log replay Florian Westphal (3): netfilter: nf_queue: don't assume sk is full socket netfilter: nf_queue: fix possible use-after-free netfilter: nf_queue: handle socket prefetch Hangyu Hua (1): tipc: fix a bit overflow in tipc_crypto_key_rcv() Hans de Goede (2): Input: elan_i2c - move regulator_[en|dis]able() out of elan_[en|dis]able_power() Input: elan_i2c - fix regulator enable count imbalance after suspend/resume Heiko Carstens (1): s390/extable: fix exception table sorting Huang Pei (1): hamradio: fix macro redefine warning Hugh Dickins (1): memfd: fix F_SEAL_WRITE after shmem huge page allocated Jacob Keller (1): ice: fix concurrent reset and removal of VFs JaeMan Park (1): mac80211_hwsim: initialize ieee80211_tx_info at hw_scan_work Jann Horn (1): efivars: Respect "block" flag in efivar_entry_set_safe() Jia-Ju Bai (1): net: chelsio: cxgb3: check the return value of pci_find_capability() Jiasheng Jiang (2): soc: fsl: qe: Check of ioremap return value nl80211: Handle nla_memdup failures in handle_nan_filter Jiri Bohac (2): xfrm: fix MTU regression Revert "xfrm: xfrm_state_mtu should return at least 1280 for ipv6" Johannes Berg (1): mac80211: treat some SAE auth steps as final José Expósito (1): Input: clear BTN_RIGHT/MIDDLE on buttonpads Kai Vehmanen (2): ASoC: rt5668: do not block workqueue if card is unbound ASoC: rt5682: do not block workqueue if card is unbound Lennert Buytenhek (1): iommu/amd: Recover from event log overflow Leon Romanovsky (1): xfrm: enforce validity of offload input flags Maciej Fijalkowski (1): ixgbe: xsk: change !netif_carrier_ok() handling in ixgbe_xmit_zc() Marc Zyngier (1): KVM: arm64: vgic: Read HW interrupt pending state from the HW Marek Marczykowski-Górecki (1): xen/netfront: destroy queues before real_num_tx_queues is zeroed Marek Vasut (1): ASoC: ops: Shift tested values in snd_soc_put_volsw() by +min Mateusz Palczewski (1): iavf: Refactor iavf state machine tracking Nicolas Cavallari (1): thermal: core: Fix TZ_GET_TRIP NULL pointer dereference Nicolas Escande (1): mac80211: fix forwarded mesh frames AC & queue selection Oliver Barta (1): regulator: core: fix false positive in regulator_late_cleanup() Qiang Yu (2): drm/amdgpu: check vm ready by amdgpu_vm->evicting flag drm/amdgpu: fix suspend/resume hang regression Randy Dunlap (4): net: stmmac: fix return value of __setup handler net: sxgbe: fix return value of __setup handler ARM: 9182/1: mmu: fix returns from early_param() and __setup() functions tracing: Fix return value of __setup handlers Ronnie Sahlberg (1): cifs: fix double free race when mount fails in cifs_get_root() Russell King (Oracle) (1): ARM: Fix kgdb breakpoint for Thumb2 Samuel Holland (1): pinctrl: sunxi: Use unique lockdep classes for IRQs Sasha Neftin (2): e1000e: Correct NVM checksum verification flow igc: igc_write_phy_reg_gpy: drop premature return Sergey Shtylyov (1): ata: pata_hpt37x: fix PCI clock detection Sherry Yang (1): selftests/seccomp: Fix seccomp failure by adding missing headers Sidong Yang (1): btrfs: qgroup: fix deadlock between rescan worker and remove qgroup Slawomir Laba (1): iavf: Fix missing check for running netdev Steven Rostedt (2): tracing: Add test for user space strings when filtering on string pointers tracing: Add ustring operation to filtering string pointers Steven Rostedt (Google) (1): tracing/histogram: Fix sorting on old "cpu" value Sukadev Bhattiprolu (3): ibmvnic: register netdev after init of adapter ibmvnic: free reset-work-item when flushing ibmvnic: complete init_done on transport events Sunil V L (1): riscv/efi_stub: Fix get_boot_hartid_from_fdt() return value Sven Eckelmann (3): batman-adv: Request iflink once in batadv-on-batadv check batman-adv: Request iflink once in batadv_get_real_netdevice batman-adv: Don't expect inter-netns unique iflink indices Thierry Reding (1): ARM: tegra: Move panels to AUX bus Valentin Caron (1): serial: stm32: prevent TDR register overwrite when sending x_char Ville Syrjälä (1): drm/i915: s/JSP2/ICP2/ PCH Vincent Mailhol (1): can: gs_usb: change active_channels's type from atomic_t to u8 Vladimir Oltean (2): net: dcb: flush lingering app table entries for unregistered devices net: dcb: disable softirqs in dcbnl_flush_dev() William Mahon (2): HID: add mapping for KEY_DICTATE HID: add mapping for KEY_ALL_APPLICATIONS Wolfram Sang (2): i2c: cadence: allow COMPILE_TEST i2c: qup: allow COMPILE_TEST Yongzhi Liu (1): dmaengine: shdma: Fix runtime PM imbalance on error Zhen Ni (1): ALSA: intel_hdmi: Fix reference to PCM buffer address Zheyu Ma (1): net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe() j.nixdorf(a)avm.de (1): net: ipv6: ensure we call ipv6_mc_down() at most once lena wang (1): net: fix up skbs delta_truesize in UDP GRO frag_list Documentation/trace/events.rst | 19 ++++ .../arm/boot/dts/omap3-devkit8000-common.dtsi | 18 +++ arch/arm/boot/dts/omap3-devkit8000.dts | 33 ------ arch/arm/boot/dts/tegra124-nyan-big.dts | 15 ++- arch/arm/boot/dts/tegra124-nyan-blaze.dts | 15 ++- arch/arm/boot/dts/tegra124-venice2.dts | 14 +-- arch/arm/kernel/kgdb.c | 36 ++++-- arch/arm/mm/mmu.c | 2 + arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi | 17 ++- arch/arm64/kvm/vgic/vgic-mmio.c | 2 + arch/riscv/mm/Makefile | 3 + arch/riscv/mm/kasan_init.c | 3 +- arch/s390/include/asm/extable.h | 9 +- drivers/ata/pata_hpt37x.c | 4 +- drivers/clocksource/timer-ti-dm-systimer.c | 3 +- drivers/dma/sh/shdma-base.c | 4 +- drivers/firmware/arm_scmi/driver.c | 2 +- drivers/firmware/efi/libstub/riscv-stub.c | 17 +-- drivers/firmware/efi/vars.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +- drivers/gpu/drm/i915/intel_pch.c | 2 +- drivers/gpu/drm/i915/intel_pch.h | 2 +- drivers/hid/hid-debug.c | 5 +- drivers/hid/hid-input.c | 3 + drivers/i2c/busses/Kconfig | 4 +- drivers/i2c/busses/i2c-bcm2835.c | 11 ++ drivers/input/input.c | 6 + drivers/input/keyboard/Kconfig | 2 +- drivers/input/mouse/elan_i2c_core.c | 64 ++++------- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/init.c | 10 ++ drivers/iommu/amd/iommu.c | 10 +- drivers/net/arcnet/com20020-pci.c | 3 + drivers/net/can/usb/gs_usb.c | 10 +- drivers/net/ethernet/chelsio/cxgb3/t3_hw.c | 2 + drivers/net/ethernet/ibm/ibmvnic.c | 21 +++- drivers/net/ethernet/intel/e1000e/ich8lan.c | 4 +- drivers/net/ethernet/intel/iavf/iavf.h | 10 ++ drivers/net/ethernet/intel/iavf/iavf_main.c | 44 +++---- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 2 +- drivers/net/ethernet/intel/ice/ice_main.c | 2 + .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 58 ++++++++-- .../net/ethernet/intel/ice/ice_virtchnl_pf.h | 5 + drivers/net/ethernet/intel/igc/igc_phy.c | 4 - drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 6 +- .../net/ethernet/samsung/sxgbe/sxgbe_main.c | 6 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +- drivers/net/hamradio/mkiss.c | 2 + drivers/net/usb/cdc_mbim.c | 5 + drivers/net/wireless/mac80211_hwsim.c | 13 +++ drivers/net/xen-netfront.c | 39 ++++--- drivers/ntb/hw/intel/ntb_hw_gen4.c | 17 ++- drivers/ntb/hw/intel/ntb_hw_gen4.h | 16 +++ drivers/pinctrl/sunxi/pinctrl-sunxi.c | 9 ++ drivers/regulator/core.c | 13 +-- drivers/soc/fsl/guts.c | 14 ++- drivers/soc/fsl/qe/qe_io.c | 2 + drivers/thermal/thermal_netlink.c | 5 +- drivers/tty/serial/stm32-usart.c | 12 ++ fs/btrfs/qgroup.c | 9 +- fs/btrfs/tree-log.c | 61 ++++++++-- fs/cifs/cifsfs.c | 1 + fs/exfat/file.c | 18 +-- fs/exfat/inode.c | 13 +-- fs/exfat/namei.c | 6 +- fs/exfat/super.c | 10 +- include/net/netfilter/nf_queue.h | 2 +- include/net/xfrm.h | 1 - include/uapi/linux/input-event-codes.h | 4 +- include/uapi/linux/xfrm.h | 6 + kernel/trace/trace.c | 4 +- kernel/trace/trace_events_filter.c | 107 ++++++++++++++++-- kernel/trace/trace_events_hist.c | 6 +- kernel/trace/trace_kprobe.c | 2 +- mm/memfd.c | 40 +++++-- mm/util.c | 4 +- net/batman-adv/hard-interface.c | 29 +++-- net/core/skbuff.c | 2 +- net/core/skmsg.c | 2 +- net/dcb/dcbnl.c | 44 +++++++ net/ipv4/esp4.c | 2 +- net/ipv6/addrconf.c | 8 +- net/ipv6/esp6.c | 2 +- net/ipv6/ip6_output.c | 11 +- net/mac80211/ieee80211_i.h | 2 +- net/mac80211/mlme.c | 16 ++- net/mac80211/rx.c | 4 +- net/netfilter/core.c | 5 +- net/netfilter/nf_queue.c | 36 +++++- net/netfilter/nfnetlink_queue.c | 12 +- net/smc/af_smc.c | 10 +- net/smc/smc_core.c | 5 +- net/tipc/crypto.c | 2 +- net/wireless/nl80211.c | 12 ++ net/xfrm/xfrm_device.c | 6 +- net/xfrm/xfrm_interface.c | 2 +- net/xfrm/xfrm_state.c | 14 +-- sound/soc/codecs/cs4265.c | 3 +- sound/soc/codecs/rt5668.c | 12 +- sound/soc/codecs/rt5682.c | 12 +- sound/soc/soc-ops.c | 4 +- sound/x86/intel_hdmi_audio.c | 2 +- .../drivers/net/mlxsw/tc_police_scale.sh | 3 +- tools/testing/selftests/seccomp/Makefile | 2 +- 105 files changed, 881 insertions(+), 359 deletions(-) -- 2.20.1

1 99

[PATCH openEuler-5.10 1/6] slub: add back check for free nonslab objects
by Zheng Zengkai 28 May '22

28 May '22

From: Kefeng Wang <wangkefeng.wang(a)huawei.com> mainline inclusion from mainline-v5.16-rc1 commit d0fe47c64152a63ceed4b9f29ac56371407fa7b4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I57LS2 CVE: NA backport: openEuler-22.03-LTS -------------------------------- After commit f227f0faf63b ("slub: fix unreclaimable slab stat for bulk free"), the check for free nonslab page is replaced by VM_BUG_ON_PAGE, which only check with CONFIG_DEBUG_VM enabled, but this config may impact performance, so it only for debug. Commit 0937502af7c9 ("slub: Add check for kfree() of non slab objects.") add the ability, which should be needed in any configs to catch the invalid free, they even could be potential issue, eg, memory corruption, use after free and double free, so replace VM_BUG_ON_PAGE to WARN_ON_ONCE, add object address printing to help use to debug the issue. Link: https://lkml.kernel.org/r/20210930070214.61499-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Christoph Lameter <cl(a)linux.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: David Rienjes <rientjes(a)google.com> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/slub.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/slub.c b/mm/slub.c index 7a7b0bf82b8e..98452815a066 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3209,7 +3209,9 @@ static inline void free_nonslab_page(struct page *page, void *object) { unsigned int order = compound_order(page); - VM_BUG_ON_PAGE(!PageCompound(page), page); + if (WARN_ON_ONCE(!PageCompound(page))) + pr_warn_once("object pointer: 0x%p\n", object); + kfree_hook(object); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(page, order); -- 2.20.1

1 5

[PATCH openEuler-5.10 v2 1/4] ipv6: per-netns exclusive flowlabel checks
by Zheng Zengkai 28 May '22

28 May '22

From: Willem de Bruijn <willemb(a)google.com> stable inclusion from stable-v5.10.102 commit 4f523f15e5d753ac055302bc29ca9677d6692eed bugzilla: https://gitee.com/openeuler/kernel/issues/I575QT Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0b0dff5b3b98c5c7ce848151df9da0b3cdf0cc8b upstream. Ipv6 flowlabels historically require a reservation before use. Optionally in exclusive mode (e.g., user-private). Commit 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") introduced a fastpath that avoids this check when no exclusive leases exist in the system, and thus any flowlabel use will be granted. That allows skipping the control operation to reserve a flowlabel entirely. Though with a warning if the fast path fails: This is an optimization. Robust applications still have to revert to requesting leases if the fast path fails due to an exclusive lease. Still, this is subtle. Better isolate network namespaces from each other. Flowlabels are per-netns. Also record per-netns whether exclusive leases are in use. Then behavior does not change based on activity in other netns. Changes v2 - wrap in IS_ENABLED(CONFIG_IPV6) to avoid breakage if disabled Fixes: 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") Link: https://lore.kernel.org/netdev/MWHPR2201MB1072BCCCFCE779E4094837ACD0329@MWH… Reported-by: Congyu Liu <liu3101(a)purdue.edu> Signed-off-by: Willem de Bruijn <willemb(a)google.com> Tested-by: Congyu Liu <liu3101(a)purdue.edu> Link: https://lore.kernel.org/r/20220215160037.1976072-1-willemdebruijn.kernel@gm… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/net/ipv6.h | 5 ++++- include/net/netns/ipv6.h | 5 +++++ net/ipv6/ip6_flowlabel.c | 4 +++- 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index c0273ae50296..9392a81a3ae4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -390,17 +390,20 @@ static inline void txopt_put(struct ipv6_txoptions *opt) kfree_rcu(opt, rcu); } +#if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { - if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) + if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && + READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } +#endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index ce5ed87accda..b2a28201f4fd 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -83,6 +83,11 @@ struct netns_ipv6 { unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES unsigned int fib6_rules_require_fldissect; +#endif +#ifndef __GENKSYMS__ + unsigned char flowlabel_has_excl; +#endif +#ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; #ifdef CONFIG_IPV6_SUBTREES unsigned int fib6_routes_require_src; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index aa673a6a7e43..ceb85c67ce39 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -450,8 +450,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -EINVAL; goto done; } - if (fl_shared_exclusive(fl) || fl->opt) + if (fl_shared_exclusive(fl) || fl->opt) { + WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1); static_branch_deferred_inc(&ipv6_flowlabel_exclusive); + } return fl; done: -- 2.20.1

1 3