From ca43ccf41224b023fc290073d5603a755fd12eed Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 9 Feb 2023 16:22:01 -0800 Subject: [PATCH 1/2] dccp/tcp: Avoid negative sk_forward_alloc by ipv6_pinfo.pktoptions. Eric Dumazet pointed out [0] that when we call skb_set_owner_r() for ipv6_pinfo.pktoptions, sk_rmem_schedule() has not been called, resulting in a negative sk_forward_alloc. We add a new helper which clones a skb and sets its owner only when sk_rmem_schedule() succeeds. Note that we move skb_set_owner_r() forward in (dccp|tcp)_v6_do_rcv() because tcp_send_synack() can make sk_forward_alloc negative before ipv6_opt_accepted() in the crossed SYN-ACK or self-connect() cases. [0]: https://lore.kernel.org/netdev/CANn89iK9oc20Jdi_41jb9URdF210r7d1Y-+uypbMSbOfY6jqrg@mail.gmail.com/ Fixes: 323fbd0edf3f ("net: dccp: Add handling of IPV6_PKTOPTIONS to dccp_v6_do_rcv()") Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/sock.h | 13 +++++++++++++ net/dccp/ipv6.c | 7 ++----- net/ipv6/tcp_ipv6.c | 10 +++------- 3 files changed, 18 insertions(+), 12 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index dcd72e6285b23..5562097276336 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2434,6 +2434,19 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) +{ + skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + if (skb) { + if (sk_rmem_schedule(sk, skb, skb->truesize)) { + skb_set_owner_r(skb, sk); + return skb; + } + __kfree_skb(skb); + } + return NULL; +} + static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4260fe4669939..b9d7c3dd1cb39 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -551,11 +551,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); } return newsk; @@ -615,7 +613,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) @@ -679,7 +677,6 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0d25e813288db..a52a4f12f1467 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1388,14 +1388,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_mask(sk, GFP_ATOMIC)); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) { + if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); - skb_set_owner_r(newnp->pktoptions, newsk); - } } } else { if (!req_unhash && found_dup_sk) { @@ -1467,7 +1464,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + opt_skb = skb_clone_and_charge_r(skb, sk); reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ @@ -1553,7 +1550,6 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { From 62ec33b44e0f7168ff2886520fec6fb62d03b5a3 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 9 Feb 2023 16:22:02 -0800 Subject: [PATCH 2/2] net: Remove WARN_ON_ONCE(sk->sk_forward_alloc) from sk_stream_kill_queues(). Christoph Paasch reported that commit b5fc29233d28 ("inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy().") started triggering WARN_ON_ONCE(sk->sk_forward_alloc) in sk_stream_kill_queues(). [0 - 2] Also, we can reproduce it by a program in [3]. In the commit, we delay freeing ipv6_pinfo.pktoptions from sk->destroy() to sk->sk_destruct(), so sk->sk_forward_alloc is no longer zero in inet_csk_destroy_sock(). The same check has been in inet_sock_destruct() from at least v2.6, we can just remove the WARN_ON_ONCE(). However, among the users of sk_stream_kill_queues(), only CAIF is not calling inet_sock_destruct(). Thus, we add the same WARN_ON_ONCE() to caif_sock_destructor(). [0]: https://lore.kernel.org/netdev/39725AB4-88F1-41B3-B07F-949C5CAEFF4F@icloud.com/ [1]: https://github.com/multipath-tcp/mptcp_net-next/issues/341 [2]: WARNING: CPU: 0 PID: 3232 at net/core/stream.c:212 sk_stream_kill_queues+0x2f9/0x3e0 Modules linked in: CPU: 0 PID: 3232 Comm: syz-executor.0 Not tainted 6.2.0-rc5ab24eb4698afbe147b424149c529e2a43ec24eb5 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_stream_kill_queues+0x2f9/0x3e0 Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ec 00 00 00 8b ab 08 01 00 00 e9 60 ff ff ff e8 d0 5f b6 fe 0f 0b eb 97 e8 c7 5f b6 fe <0f> 0b eb a0 e8 be 5f b6 fe 0f 0b e9 6a fe ff ff e8 02 07 e3 fe e9 RSP: 0018:ffff88810570fc68 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff888101f38f40 RSI: ffffffff8285e529 RDI: 0000000000000005 RBP: 0000000000000ce0 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000ce0 R11: 0000000000000001 R12: ffff8881009e9488 R13: ffffffff84af2cc0 R14: 0000000000000000 R15: ffff8881009e9458 FS: 00007f7fdfbd5800(0000) GS:ffff88811b600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32923000 CR3: 00000001062fc006 CR4: 0000000000170ef0 Call Trace: inet_csk_destroy_sock+0x1a1/0x320 __tcp_close+0xab6/0xe90 tcp_close+0x30/0xc0 inet_release+0xe9/0x1f0 inet6_release+0x4c/0x70 __sock_release+0xd2/0x280 sock_close+0x15/0x20 __fput+0x252/0xa20 task_work_run+0x169/0x250 exit_to_user_mode_prepare+0x113/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f7fdf7ae28d Code: c1 20 00 00 75 10 b8 03 00 00 00 0f 05 48 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ee fb ff ff 48 89 04 24 b8 03 00 00 00 0f 05 <48> 8b 3c 24 48 89 c2 e8 37 fc ff ff 48 89 d0 48 83 c4 08 48 3d 01 RSP: 002b:00000000007dfbb0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000004 RCX: 00007f7fdf7ae28d RDX: 0000000000000000 RSI: ffffffffffffffff RDI: 0000000000000003 RBP: 0000000000000000 R08: 000000007f338e0f R09: 0000000000000e0f R10: 000000007f338e13 R11: 0000000000000293 R12: 00007f7fdefff000 R13: 00007f7fdefffcd8 R14: 00007f7fdefffce0 R15: 00007f7fdefffcd8 [3]: https://lore.kernel.org/netdev/20230208004245.83497-1-kuniyu@amazon.com/ Fixes: b5fc29233d28 ("inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy().") Reported-by: syzbot Reported-by: Christoph Paasch Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/caif/caif_socket.c | 1 + net/core/stream.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 748be72532485..78c9729a6057d 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1015,6 +1015,7 @@ static void caif_sock_destructor(struct sock *sk) return; } sk_stream_kill_queues(&cf_sk->sk); + WARN_ON_ONCE(sk->sk_forward_alloc); caif_free_client(&cf_sk->layer); } diff --git a/net/core/stream.c b/net/core/stream.c index cd06750dd3297..434446ab14c57 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -209,7 +209,6 @@ void sk_stream_kill_queues(struct sock *sk) sk_mem_reclaim_final(sk); WARN_ON_ONCE(sk->sk_wmem_queued); - WARN_ON_ONCE(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket