From: Pablo Neira Ayuso Date: Mon, 3 Feb 2014 19:01:53 +0000 (+0100) Subject: netfilter: nf_conntrack: don't release a conntrack with non-zero refcnt X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=e53376bef2cd97d3e3f61fdc677fb8da7d03d0da;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git netfilter: nf_conntrack: don't release a conntrack with non-zero refcnt With this patch, the conntrack refcount is initially set to zero and it is bumped once it is added to any of the list, so we fulfill Eric's golden rule which is that all released objects always have a refcount that equals zero. Andrey Vagin reports that nf_conntrack_free can't be called for a conntrack with non-zero ref-counter, because it can race with nf_conntrack_find_get(). A conntrack slab is created with SLAB_DESTROY_BY_RCU. Non-zero ref-counter says that this conntrack is used. So when we release a conntrack with non-zero counter, we break this assumption. CPU1 CPU2 ____nf_conntrack_find() nf_ct_put() destroy_conntrack() ... init_conntrack __nf_conntrack_alloc (set use = 1) atomic_inc_not_zero(&ct->use) (use = 2) if (!l4proto->new(ct, skb, dataoff, timeouts)) nf_conntrack_free(ct); (use = 2 !!!) ... __nf_conntrack_alloc (set use = 1) if (!nf_ct_key_equal(h, tuple, zone)) nf_ct_put(ct); (use = 0) destroy_conntrack() /* continue to work with CT */ After applying the path "[PATCH] netfilter: nf_conntrack: fix RCU race in nf_conntrack_find_get" another bug was triggered in destroy_conntrack(): <4>[67096.759334] ------------[ cut here ]------------ <2>[67096.759353] kernel BUG at net/netfilter/nf_conntrack_core.c:211! ... <4>[67096.759837] Pid: 498649, comm: atdd veid: 666 Tainted: G C --------------- 2.6.32-042stab084.18 #1 042stab084_18 /DQ45CB <4>[67096.759932] RIP: 0010:[] [] destroy_conntrack+0x15c/0x190 [nf_conntrack] <4>[67096.760255] Call Trace: <4>[67096.760255] [] nf_conntrack_destroy+0x17/0x30 <4>[67096.760255] [] nf_conntrack_find_get+0x85/0x130 [nf_conntrack] <4>[67096.760255] [] nf_conntrack_in+0x352/0xb60 [nf_conntrack] <4>[67096.760255] [] ipv4_conntrack_local+0x51/0x60 [nf_conntrack_ipv4] <4>[67096.760255] [] nf_iterate+0x69/0xb0 <4>[67096.760255] [] ? dst_output+0x0/0x20 <4>[67096.760255] [] nf_hook_slow+0x74/0x110 <4>[67096.760255] [] ? dst_output+0x0/0x20 <4>[67096.760255] [] raw_sendmsg+0x775/0x910 <4>[67096.760255] [] ? flush_tlb_others_ipi+0x128/0x130 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] inet_sendmsg+0x4a/0xb0 <4>[67096.760255] [] ? sock_sendmsg+0x13/0x140 <4>[67096.760255] [] sock_sendmsg+0x117/0x140 <4>[67096.760255] [] ? native_smp_send_reschedule+0x49/0x60 <4>[67096.760255] [] ? _spin_unlock_bh+0x1b/0x20 <4>[67096.760255] [] ? autoremove_wake_function+0x0/0x40 <4>[67096.760255] [] ? do_ip_setsockopt+0x90/0xd80 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] sys_sendto+0x139/0x190 <4>[67096.760255] [] ? audit_syscall_entry+0x1d7/0x200 <4>[67096.760255] [] ? __audit_syscall_exit+0x265/0x290 <4>[67096.760255] [] compat_sys_socketcall+0x13f/0x210 <4>[67096.760255] [] ia32_sysret+0x0/0x5 I have reused the original title for the RFC patch that Andrey posted and most of the original patch description. Cc: Eric Dumazet Cc: Andrew Vagin Cc: Florian Westphal Reported-by: Andrew Vagin Signed-off-by: Pablo Neira Ayuso Reviewed-by: Eric Dumazet Acked-by: Andrew Vagin --- diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 01ea6eed1bb1..b2ac6246b7e0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -284,6 +284,8 @@ extern unsigned int nf_conntrack_max; extern unsigned int nf_conntrack_hash_rnd; void init_nf_conntrack_hash_rnd(void); +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl); + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 4d1fb5d094c3..356bef519fe5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -448,7 +448,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) goto out; add_timer(&ct->timeout); - nf_conntrack_get(&ct->ct_general); + smp_wmb(); + /* The caller holds a reference to this object */ + atomic_set(&ct->ct_general.use, 2); __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); @@ -462,6 +464,21 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); +/* deletion from this larval template list happens via nf_ct_put() */ +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) +{ + __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); + nf_conntrack_get(&tmpl->ct_general); + + spin_lock_bh(&nf_conntrack_lock); + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &net->ct.tmpl); + spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); + /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -733,11 +750,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone, nf_ct_zone->id = zone; } #endif - /* - * changes to lookup keys must be done before setting refcnt to 1 + /* Because we use RCU lookups, we set ct_general.use to zero before + * this is inserted in any list. */ - smp_wmb(); - atomic_set(&ct->ct_general.use, 1); + atomic_set(&ct->ct_general.use, 0); return ct; #ifdef CONFIG_NF_CONNTRACK_ZONES @@ -761,6 +777,11 @@ void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + /* A freed object has refcnt == 0, that's + * the golden rule for SLAB_DESTROY_BY_RCU + */ + NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0); + nf_ct_ext_destroy(ct); nf_ct_ext_free(ct); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); @@ -856,6 +877,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, NF_CT_STAT_INC(net, new); } + /* Now it is inserted into the unconfirmed list, bump refcount */ + nf_conntrack_get(&ct->ct_general); + /* Overload tuple linked list to put us in unconfirmed list. */ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.unconfirmed); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9858e3e51a3a..52e20c9a46a5 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -363,9 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_tmpl_insert(net, ct); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); @@ -390,7 +389,7 @@ static void __net_exit synproxy_net_exit(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - nf_conntrack_free(snet->tmpl); + nf_ct_put(snet->tmpl); synproxy_proc_exit(net); free_percpu(snet->stats); } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 5929be622c5c..75747aecdebe 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -228,12 +228,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err3; } - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); - - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &par->net->ct.tmpl); + nf_conntrack_tmpl_insert(par->net, ct); out: info->ct = ct; return 0;