On Wednesday 11 January 2012 15:56:52 Eric Dumazet wrote: > Le mercredi 11 janvier 2012 à 14:33 +0100, Eric Dumazet a écrit : > > Le mercredi 11 janvier 2012 à 14:24 +0100, Hans Schillstrom a écrit : > > > On Wednesday 11 January 2012 11:01:51 Eric Dumazet wrote: > > > > > > Hmm, we either need to take rcu_read_lock() while calling > > > > __nf_ct_l3proto_find(), or define a variant using > > > > rcu_dereference_protected() in places we hold nf_conntrack_lock > > > > > > > I made a qick test with locks /unlocks in > > > __nf_ct_l3proto_find() and __nf_ct_l4proto_find() > > > > > > rcu_read_lock(); > > > ... > > > rcu_read_unlock(); > > > return retp; > > > > > > It seems to help, I cant see the dump anymore and everything else that I run works ... > > > > > > > > > > You cant do that, its just a brown paper bag :) > > > > If "retp" is returned, then the caller must handle the rcu_read_unlock() > > itself, after all possible "retp" dereferences. > > > > But really adding rcu_read_lock() should not be necessary on paths we > > own the conntrack lock. We should use rcu_dereference_protected() > > instead. > > > > Well, __nf_ct_l4proto_find() being out of line and the way we already > use rcu_read_lock() in this code, it seems following patch is > the most natural way to cope with these lockdep warnings. > > Thanks > > [PATCH] netfilter: ctnetlink: fix lockep splats > > net/netfilter/nf_conntrack_proto.c:70 suspicious rcu_dereference_check() usage! > > other info that might help us debug this: > > > rcu_scheduler_active = 1, debug_locks = 0 > 3 locks held by conntrack/3235: > #0: (nfnl_mutex){+.+.+.}, at: [<ffffffff81603537>] > nfnl_lock+0x17/0x20 > #1: (nlk->cb_mutex){+.+.+.}, at: [<ffffffff815fbd72>] > netlink_dump+0x32/0x240 > #2: (nf_conntrack_lock){+.-...}, at: [<ffffffffa0115d2e>] > ctnetlink_dump_table+0x3e/0x170 [nf_conntrack_netlink] > > stack backtrace: > Pid: 3235, comm: conntrack Tainted: G W 3.2.0+ #511 > Call Trace: > [<ffffffff8108ce45>] lockdep_rcu_suspicious+0xe5/0x100 > [<ffffffffa00ec6e1>] __nf_ct_l4proto_find+0x81/0xb0 [nf_conntrack] > [<ffffffffa0115675>] ctnetlink_fill_info+0x215/0x5f0 [nf_conntrack_netlink] > [<ffffffffa0115dc1>] ctnetlink_dump_table+0xd1/0x170 [nf_conntrack_netlink] > [<ffffffff815fbdbf>] netlink_dump+0x7f/0x240 > [<ffffffff81090f9d>] ? trace_hardirqs_on+0xd/0x10 > [<ffffffff815fd34f>] netlink_dump_start+0xdf/0x190 > [<ffffffffa0111490>] ? ctnetlink_change_nat_seq_adj+0x160/0x160 [nf_conntrack_netlink] > [<ffffffffa0115cf0>] ? ctnetlink_get_conntrack+0x2a0/0x2a0 [nf_conntrack_netlink] > [<ffffffffa0115ad9>] ctnetlink_get_conntrack+0x89/0x2a0 [nf_conntrack_netlink] > [<ffffffff81603a47>] nfnetlink_rcv_msg+0x467/0x5f0 > [<ffffffff81603a7c>] ? nfnetlink_rcv_msg+0x49c/0x5f0 > [<ffffffff81603922>] ? nfnetlink_rcv_msg+0x342/0x5f0 > [<ffffffff81071b21>] ? get_parent_ip+0x11/0x50 > [<ffffffff816035e0>] ? nfnetlink_subsys_register+0x60/0x60 > [<ffffffff815fed49>] netlink_rcv_skb+0xa9/0xd0 > [<ffffffff81603475>] nfnetlink_rcv+0x15/0x20 > [<ffffffff815fe70e>] netlink_unicast+0x1ae/0x1f0 > [<ffffffff815fea16>] netlink_sendmsg+0x2c6/0x320 > [<ffffffff815b2a87>] sock_sendmsg+0x117/0x130 > [<ffffffff81125093>] ? might_fault+0x53/0xb0 > [<ffffffff811250dc>] ? might_fault+0x9c/0xb0 > [<ffffffff81125093>] ? might_fault+0x53/0xb0 > [<ffffffff815b5991>] ? move_addr_to_kernel+0x71/0x80 > [<ffffffff815b644e>] sys_sendto+0xfe/0x130 > [<ffffffff815b5c94>] ? sys_bind+0xb4/0xd0 > [<ffffffff817a8a0e>] ? retint_swapgs+0xe/0x13 > [<ffffffff817afcd2>] system_call_fastpath+0x16/0x1b > > > Reported-by: Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx> Tested-by: Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx> > Signed-off-by: Eric Dumazet <eric.dumazet@xxxxxxxxx> > --- > net/netfilter/nf_conntrack_netlink.c | 31 ++++++++++++++----------- > 1 file changed, 18 insertions(+), 13 deletions(-) > > diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c > index e07dc3a..14840d9 100644 > --- a/net/netfilter/nf_conntrack_netlink.c > +++ b/net/netfilter/nf_conntrack_netlink.c > @@ -110,15 +110,15 @@ ctnetlink_dump_tuples(struct sk_buff *skb, > struct nf_conntrack_l3proto *l3proto; > struct nf_conntrack_l4proto *l4proto; > > + rcu_read_lock(); > l3proto = __nf_ct_l3proto_find(tuple->src.l3num); > ret = ctnetlink_dump_tuples_ip(skb, tuple, l3proto); > > - if (unlikely(ret < 0)) > - return ret; > - > - l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); > - ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); > - > + if (ret >= 0) { > + l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); > + ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); > + } > + rcu_read_unlock(); > return ret; > } > > @@ -703,6 +703,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) > struct hlist_nulls_node *n; > struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); > u_int8_t l3proto = nfmsg->nfgen_family; > + int res; > > spin_lock_bh(&nf_conntrack_lock); > last = (struct nf_conn *)cb->args[1]; > @@ -723,11 +724,14 @@ restart: > continue; > cb->args[1] = 0; > } > - if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, > + rcu_read_lock(); > + res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, > cb->nlh->nlmsg_seq, > NFNL_MSG_TYPE( > cb->nlh->nlmsg_type), > - ct) < 0) { > + ct); > + rcu_read_unlock(); > + if (res < 0) { > nf_conntrack_get(&ct->ct_general); > cb->args[1] = (unsigned long)ct; > goto out; > @@ -1626,17 +1630,18 @@ ctnetlink_exp_dump_mask(struct sk_buff *skb, > if (!nest_parms) > goto nla_put_failure; > > + rcu_read_lock(); > l3proto = __nf_ct_l3proto_find(tuple->src.l3num); > ret = ctnetlink_dump_tuples_ip(skb, &m, l3proto); > + if (ret >= 0) { > + l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); > + ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); > + } > + rcu_read_unlock(); > > if (unlikely(ret < 0)) > goto nla_put_failure; > > - l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); > - ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); > - if (unlikely(ret < 0)) > - goto nla_put_failure; > - > nla_nest_end(skb, nest_parms); > > return 0; > > > -- Thank's Eric It works I cant get the fault any more. Tested-by: Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx> -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html