| Message ID | 20241031122344.2148586-1-wangliang74@huawei.com (mailing list archive) |
|---|---|
| State | RFC |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [RFC,net] net: fix data-races around sk->sk_forward_alloc | expand |
On Thu, Oct 31, 2024 at 1:06 PM Wang Liang <wangliang74@huawei.com> wrote: > > Syzkaller reported this warning: Was this a public report ? > [ 65.568203][ C0] ------------[ cut here ]------------ > [ 65.569339][ C0] WARNING: CPU: 0 PID: 16 at net/ipv4/af_inet.c:156 inet_sock_destruct+0x1c5/0x1e0 > [ 65.575017][ C0] Modules linked in: > [ 65.575699][ C0] CPU: 0 UID: 0 PID: 16 Comm: ksoftirqd/0 Not tainted 6.12.0-rc5 #26 > [ 65.577086][ C0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 > [ 65.577094][ C0] RIP: 0010:inet_sock_destruct+0x1c5/0x1e0 > [ 65.577100][ C0] Code: 24 12 4c 89 e2 5b 48 c7 c7 98 ec bb 82 41 5c e9 d1 18 17 ff 4c 89 e6 5b 48 c7 c7 d0 ec bb 82 41 5c e9 bf 18 17 ff 0f 0b eb 83 <0f> 0b eb 97 0f 0b eb 87 0f 0b e9 68 ff ff ff 66 66 2e 0f 1f 84 00 > [ 65.577107][ C0] RSP: 0018:ffffc9000008bd90 EFLAGS: 00010206 > [ 65.577113][ C0] RAX: 0000000000000300 RBX: ffff88810b172a90 RCX: 0000000000000007 > [ 65.577117][ C0] RDX: 0000000000000002 RSI: 0000000000000300 RDI: ffff88810b172a00 > [ 65.577120][ C0] RBP: ffff88810b172a00 R08: ffff888104273c00 R09: 0000000000100007 > [ 65.577123][ C0] R10: 0000000000020000 R11: 0000000000000006 R12: ffff88810b172a00 > [ 65.577125][ C0] R13: 0000000000000004 R14: 0000000000000000 R15: ffff888237c31f78 > [ 65.577131][ C0] FS: 0000000000000000(0000) GS:ffff888237c00000(0000) knlGS:0000000000000000 > [ 65.592485][ C0] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 65.592489][ C0] CR2: 00007ffc63fecac8 CR3: 000000000342e000 CR4: 00000000000006f0 > [ 65.592491][ C0] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 65.592492][ C0] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > [ 65.592495][ C0] Call Trace: > [ 65.596277][ C0] <TASK> > [ 65.598171][ C0] ? __warn+0x88/0x130 > [ 65.598874][ C0] ? inet_sock_destruct+0x1c5/0x1e0 > [ 65.598879][ C0] ? report_bug+0x18e/0x1a0 > [ 65.598883][ C0] ? handle_bug+0x53/0x90 > [ 65.598886][ C0] ? exc_invalid_op+0x18/0x70 > [ 65.598888][ C0] ? asm_exc_invalid_op+0x1a/0x20 > [ 65.598893][ C0] ? inet_sock_destruct+0x1c5/0x1e0 > [ 65.598897][ C0] __sk_destruct+0x2a/0x200 > [ 65.604664][ C0] rcu_do_batch+0x1aa/0x530 > [ 65.605450][ C0] ? rcu_do_batch+0x13b/0x530 > [ 65.605456][ C0] rcu_core+0x159/0x2f0 > [ 65.605466][ C0] handle_softirqs+0xd3/0x2b0 > [ 65.607689][ C0] ? __pfx_smpboot_thread_fn+0x10/0x10 > [ 65.607695][ C0] run_ksoftirqd+0x25/0x30 > [ 65.607699][ C0] smpboot_thread_fn+0xdd/0x1d0 > [ 65.610152][ C0] kthread+0xd3/0x100 > [ 65.610158][ C0] ? __pfx_kthread+0x10/0x10 > [ 65.610160][ C0] ret_from_fork+0x34/0x50 > [ 65.610170][ C0] ? __pfx_kthread+0x10/0x10 > [ 65.610172][ C0] ret_from_fork_asm+0x1a/0x30 > [ 65.610181][ C0] </TASK> > [ 65.610182][ C0] ---[ end trace 0000000000000000 ]--- > > Its possible that two threads call tcp_v6_do_rcv()/sk_forward_alloc_add() > concurrently when sk->sk_state == TCP_LISTEN with sk->sk_lock unlocked, > which triggers a data-race around sk->sk_forward_alloc: > tcp_v6_rcv > tcp_v6_do_rcv > skb_clone_and_charge_r > sk_rmem_schedule > __sk_mem_schedule > sk_forward_alloc_add() > skb_set_owner_r > sk_mem_charge > sk_forward_alloc_add() > __kfree_skb > skb_release_all > skb_release_head_state > sock_rfree > sk_mem_uncharge > sk_forward_alloc_add() > sk_mem_reclaim > // set local var reclaimable > __sk_mem_reclaim > sk_forward_alloc_add() > > In this syzkaller testcase, two threads call tcp_v6_do_rcv() with > skb->truesize=768, the sk_forward_alloc changes like this: > (cpu 1) | (cpu 2) | sk_forward_alloc > ... | ... | 0 > __sk_mem_schedule() | | +4096 = 4096 > | __sk_mem_schedule() | +4096 = 8192 > sk_mem_charge() | | -768 = 7424 > | sk_mem_charge() | -768 = 6656 > ... | ... | > sk_mem_uncharge() | | +768 = 7424 > reclaimable=7424 | | > | sk_mem_uncharge() | +768 = 8192 > | reclaimable=8192 | > __sk_mem_reclaim() | | -4096 = 4096 > | __sk_mem_reclaim() | -8192 = -4096 != 0 > > Add lock around tcp_v6_do_rcv() in tcp_v6_rcv() will have some the > performance impacts, only add lock when opt_skb clone occurs. In some > scenes, tcp_v6_do_rcv() is embraced by sk->sk_lock, add > TCP_SKB_CB(skb)->sk_lock_capability to avoid re-locking. > > Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") > Signed-off-by: Wang Liang <wangliang74@huawei.com> > --- > include/net/tcp.h | 3 ++- > net/ipv6/tcp_ipv6.c | 21 ++++++++++++++++----- > 2 files changed, 18 insertions(+), 6 deletions(-) > > diff --git a/include/net/tcp.h b/include/net/tcp.h > index d1948d357dad..110a23dda1eb 100644 > --- a/include/net/tcp.h > +++ b/include/net/tcp.h > @@ -961,7 +961,8 @@ struct tcp_skb_cb { > __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ > eor:1, /* Is skb MSG_EOR marked? */ > has_rxtstamp:1, /* SKB has a RX timestamp */ > - unused:5; > + sk_lock_capability:1, /* Avoid re-lock flag */ > + unused:4; > __u32 ack_seq; /* Sequence number ACK'd */ > union { > struct { Oh the horror, this is completely wrong and unsafe anyway. TCP listen path MUST be lockless, and stay lockless. Ask yourself : Why would a listener even hold a pktoptions in the first place ? Normally, each request socket can hold an ireq->pktopts (see in tcp_v6_init_req()) The skb_clone_and_charge_r() happen later in tcp_v6_syn_recv_sock() The correct fix is to _not_ call skb_clone_and_charge_r() for a listener socket, of course, this never made _any_ sense. The following patch should fix both TCP and DCCP, and as a bonus make TCP SYN processing faster for listeners requesting these IPV6_PKTOPTIONS things. diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index da5dba120bc9a55c5fd9d6feda791b0ffc887423..d6649246188d72b3df6c74750779b7aa5910dcb7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -618,7 +618,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) by tcp. Feel free to propose better solution. --ANK (980728) */ - if (np->rxopt.all) + if (np->rxopt.all && sk->sk_state != DCCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d71ab4e1efe1c6598cf3d3e4334adf0881064ce9..e643dbaec9ccc92eb2d9103baf185c957ad1dd2e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1605,25 +1605,12 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * is currently called with bh processing disabled. */ - /* Do Stevens' IPV6_PKTOPTIONS. - - Yes, guys, it is the only place in our code, where we - may make it not affecting IPv4. - The rest of code is protocol independent, - and I do not like idea to uglify IPv4. - - Actually, all the idea behind IPV6_PKTOPTIONS - looks not very well thought. For now we latch - options, received in the last packet, enqueued - by tcp. Feel free to propose better solution. - --ANK (980728) - */ - if (np->rxopt.all) - opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; + if (np->rxopt.all) + opt_skb = skb_clone_and_charge_r(skb, sk); dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); @@ -1656,13 +1643,13 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (reason) goto reset; } - if (opt_skb) - __kfree_skb(opt_skb); return 0; } } else sock_rps_save_rxhash(sk, skb); + if (np->rxopt.all) + opt_skb = skb_clone_and_charge_r(skb, sk); reason = tcp_rcv_state_process(sk, skb); if (reason) goto reset;
diff --git a/include/net/tcp.h b/include/net/tcp.h index d1948d357dad..110a23dda1eb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -961,7 +961,8 @@ struct tcp_skb_cb { __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + sk_lock_capability:1, /* Avoid re-lock flag */ + unused:4; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d71ab4e1efe1..a1166035fbce 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1588,6 +1588,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) struct sk_buff *opt_skb = NULL; enum skb_drop_reason reason; struct tcp_sock *tp; + bool sk_lock_flag = false; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. @@ -1618,8 +1619,13 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) by tcp. Feel free to propose better solution. --ANK (980728) */ - if (np->rxopt.all) + if (np->rxopt.all) { + if (TCP_SKB_CB(skb)->sk_lock_capability) { + sk_lock_flag = true; + bh_lock_sock_nested(sk); + } opt_skb = skb_clone_and_charge_r(skb, sk); + } if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1641,7 +1647,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; - return 0; + goto unlock; } if (tcp_checksum_complete(skb)) @@ -1658,7 +1664,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } if (opt_skb) __kfree_skb(opt_skb); - return 0; + goto unlock; } } else sock_rps_save_rxhash(sk, skb); @@ -1668,7 +1674,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) goto reset; if (opt_skb) goto ipv6_pktoptions; - return 0; + goto unlock; reset: tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); @@ -1676,7 +1682,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (opt_skb) __kfree_skb(opt_skb); sk_skb_reason_drop(sk, skb, reason); - return 0; + goto unlock; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); @@ -1715,6 +1721,9 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } consume_skb(opt_skb); +unlock: + if (sk_lock_flag) + bh_unlock_sock(sk); return 0; } @@ -1900,7 +1909,9 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { + TCP_SKB_CB(skb)->sk_lock_capability = true; ret = tcp_v6_do_rcv(sk, skb); + TCP_SKB_CB(skb)->sk_lock_capability = false; goto put_and_return; }
Syzkaller reported this warning: [ 65.568203][ C0] ------------[ cut here ]------------ [ 65.569339][ C0] WARNING: CPU: 0 PID: 16 at net/ipv4/af_inet.c:156 inet_sock_destruct+0x1c5/0x1e0 [ 65.575017][ C0] Modules linked in: [ 65.575699][ C0] CPU: 0 UID: 0 PID: 16 Comm: ksoftirqd/0 Not tainted 6.12.0-rc5 #26 [ 65.577086][ C0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 65.577094][ C0] RIP: 0010:inet_sock_destruct+0x1c5/0x1e0 [ 65.577100][ C0] Code: 24 12 4c 89 e2 5b 48 c7 c7 98 ec bb 82 41 5c e9 d1 18 17 ff 4c 89 e6 5b 48 c7 c7 d0 ec bb 82 41 5c e9 bf 18 17 ff 0f 0b eb 83 <0f> 0b eb 97 0f 0b eb 87 0f 0b e9 68 ff ff ff 66 66 2e 0f 1f 84 00 [ 65.577107][ C0] RSP: 0018:ffffc9000008bd90 EFLAGS: 00010206 [ 65.577113][ C0] RAX: 0000000000000300 RBX: ffff88810b172a90 RCX: 0000000000000007 [ 65.577117][ C0] RDX: 0000000000000002 RSI: 0000000000000300 RDI: ffff88810b172a00 [ 65.577120][ C0] RBP: ffff88810b172a00 R08: ffff888104273c00 R09: 0000000000100007 [ 65.577123][ C0] R10: 0000000000020000 R11: 0000000000000006 R12: ffff88810b172a00 [ 65.577125][ C0] R13: 0000000000000004 R14: 0000000000000000 R15: ffff888237c31f78 [ 65.577131][ C0] FS: 0000000000000000(0000) GS:ffff888237c00000(0000) knlGS:0000000000000000 [ 65.592485][ C0] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.592489][ C0] CR2: 00007ffc63fecac8 CR3: 000000000342e000 CR4: 00000000000006f0 [ 65.592491][ C0] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 65.592492][ C0] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 65.592495][ C0] Call Trace: [ 65.596277][ C0] <TASK> [ 65.598171][ C0] ? __warn+0x88/0x130 [ 65.598874][ C0] ? inet_sock_destruct+0x1c5/0x1e0 [ 65.598879][ C0] ? report_bug+0x18e/0x1a0 [ 65.598883][ C0] ? handle_bug+0x53/0x90 [ 65.598886][ C0] ? exc_invalid_op+0x18/0x70 [ 65.598888][ C0] ? asm_exc_invalid_op+0x1a/0x20 [ 65.598893][ C0] ? inet_sock_destruct+0x1c5/0x1e0 [ 65.598897][ C0] __sk_destruct+0x2a/0x200 [ 65.604664][ C0] rcu_do_batch+0x1aa/0x530 [ 65.605450][ C0] ? rcu_do_batch+0x13b/0x530 [ 65.605456][ C0] rcu_core+0x159/0x2f0 [ 65.605466][ C0] handle_softirqs+0xd3/0x2b0 [ 65.607689][ C0] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 65.607695][ C0] run_ksoftirqd+0x25/0x30 [ 65.607699][ C0] smpboot_thread_fn+0xdd/0x1d0 [ 65.610152][ C0] kthread+0xd3/0x100 [ 65.610158][ C0] ? __pfx_kthread+0x10/0x10 [ 65.610160][ C0] ret_from_fork+0x34/0x50 [ 65.610170][ C0] ? __pfx_kthread+0x10/0x10 [ 65.610172][ C0] ret_from_fork_asm+0x1a/0x30 [ 65.610181][ C0] </TASK> [ 65.610182][ C0] ---[ end trace 0000000000000000 ]--- Its possible that two threads call tcp_v6_do_rcv()/sk_forward_alloc_add() concurrently when sk->sk_state == TCP_LISTEN with sk->sk_lock unlocked, which triggers a data-race around sk->sk_forward_alloc: tcp_v6_rcv tcp_v6_do_rcv skb_clone_and_charge_r sk_rmem_schedule __sk_mem_schedule sk_forward_alloc_add() skb_set_owner_r sk_mem_charge sk_forward_alloc_add() __kfree_skb skb_release_all skb_release_head_state sock_rfree sk_mem_uncharge sk_forward_alloc_add() sk_mem_reclaim // set local var reclaimable __sk_mem_reclaim sk_forward_alloc_add() In this syzkaller testcase, two threads call tcp_v6_do_rcv() with skb->truesize=768, the sk_forward_alloc changes like this: (cpu 1) | (cpu 2) | sk_forward_alloc ... | ... | 0 __sk_mem_schedule() | | +4096 = 4096 | __sk_mem_schedule() | +4096 = 8192 sk_mem_charge() | | -768 = 7424 | sk_mem_charge() | -768 = 6656 ... | ... | sk_mem_uncharge() | | +768 = 7424 reclaimable=7424 | | | sk_mem_uncharge() | +768 = 8192 | reclaimable=8192 | __sk_mem_reclaim() | | -4096 = 4096 | __sk_mem_reclaim() | -8192 = -4096 != 0 Add lock around tcp_v6_do_rcv() in tcp_v6_rcv() will have some the performance impacts, only add lock when opt_skb clone occurs. In some scenes, tcp_v6_do_rcv() is embraced by sk->sk_lock, add TCP_SKB_CB(skb)->sk_lock_capability to avoid re-locking. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Signed-off-by: Wang Liang <wangliang74@huawei.com> --- include/net/tcp.h | 3 ++- net/ipv6/tcp_ipv6.c | 21 ++++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-)