diff options
author | Florian Westphal <fw@strlen.de> | 2022-04-11 14:01:21 +0300 |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2022-05-13 19:52:16 +0300 |
commit | c56716c69ce1ac320432fb1ea5654196ba24d2f8 (patch) | |
tree | f73e61917bcaf98caf3b306a2d6a3270e7a20a96 /net/netfilter/nf_conntrack_core.c | |
parent | 17438b42ce14cb60ceda9ae62ad5dd022d55a216 (diff) | |
download | linux-c56716c69ce1ac320432fb1ea5654196ba24d2f8.tar.xz |
netfilter: extensions: introduce extension genid count
Multiple netfilter extensions store pointers to external data
in their extension area struct.
Examples:
1. Timeout policies
2. Connection tracking helpers.
No references are taken for these.
When a helper or timeout policy is removed, the conntrack table gets
traversed and affected extensions are cleared.
Conntrack entries not yet in the hashtable are referenced via a special
list, the unconfirmed list.
On removal of a policy or connection tracking helper, the unconfirmed
list gets traversed an all entries are marked as dying, this prevents
them from getting committed to the table at insertion time: core checks
for dying bit, if set, the conntrack entry gets destroyed at confirm
time.
The disadvantage is that each new conntrack has to be added to the percpu
unconfirmed list, and each insertion needs to remove it from this list.
The list is only ever needed when a policy or helper is removed -- a rare
occurrence.
Add a generation ID count: Instead of adding to the list and then
traversing that list on policy/helper removal, increment a counter
that is stored in the extension area.
For unconfirmed conntracks, the extension has the genid valid at ct
allocation time.
Removal of a helper/policy etc. increments the counter.
At confirmation time, validate that ext->genid == global_id.
If the stored number is not the same, do not allow the conntrack
insertion, just like as if a confirmed-list traversal would have flagged
the entry as dying.
After insertion, the genid is no longer relevant (conntrack entries
are now reachable via the conntrack table iterators and is set to 0.
This allows removal of the percpu unconfirmed list.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter/nf_conntrack_core.c')
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 55 |
1 files changed, 55 insertions, 0 deletions
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b3cc318ceb45..76310940cbd7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -876,6 +876,33 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, &nf_conntrack_hash[reply_hash]); } +static bool nf_ct_ext_valid_pre(const struct nf_ct_ext *ext) +{ + /* if ext->gen_id is not equal to nf_conntrack_ext_genid, some extensions + * may contain stale pointers to e.g. helper that has been removed. + * + * The helper can't clear this because the nf_conn object isn't in + * any hash and synchronize_rcu() isn't enough because associated skb + * might sit in a queue. + */ + return !ext || ext->gen_id == atomic_read(&nf_conntrack_ext_genid); +} + +static bool nf_ct_ext_valid_post(struct nf_ct_ext *ext) +{ + if (!ext) + return true; + + if (ext->gen_id != atomic_read(&nf_conntrack_ext_genid)) + return false; + + /* inserted into conntrack table, nf_ct_iterate_cleanup() + * will find it. Disable nf_ct_ext_find() id check. + */ + WRITE_ONCE(ext->gen_id, 0); + return true; +} + int nf_conntrack_hash_check_insert(struct nf_conn *ct) { @@ -891,6 +918,11 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) zone = nf_ct_zone(ct); + if (!nf_ct_ext_valid_pre(ct->ext)) { + NF_CT_STAT_INC(net, insert_failed); + return -ETIMEDOUT; + } + local_bh_disable(); do { sequence = read_seqcount_begin(&nf_conntrack_generation); @@ -931,6 +963,13 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); local_bh_enable(); + + if (!nf_ct_ext_valid_post(ct->ext)) { + nf_ct_kill(ct); + NF_CT_STAT_INC(net, drop); + return -ETIMEDOUT; + } + return 0; chaintoolong: NF_CT_STAT_INC(net, chaintoolong); @@ -1198,6 +1237,11 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_DROP; } + if (!nf_ct_ext_valid_pre(ct->ext)) { + NF_CT_STAT_INC(net, insert_failed); + goto dying; + } + pr_debug("Confirming conntrack %p\n", ct); /* We have to check the DYING flag after unlink to prevent * a race against nf_ct_get_next_corpse() possibly called from @@ -1254,6 +1298,16 @@ chaintoolong: nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); + /* ext area is still valid (rcu read lock is held, + * but will go out of scope soon, we need to remove + * this conntrack again. + */ + if (!nf_ct_ext_valid_post(ct->ext)) { + nf_ct_kill(ct); + NF_CT_STAT_INC(net, drop); + return NF_DROP; + } + help = nfct_help(ct); if (help && help->helper) nf_conntrack_event_cache(IPCT_HELPER, ct); @@ -2491,6 +2545,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) */ synchronize_net(); + nf_ct_ext_bump_genid(); nf_ct_iterate_cleanup(iter, data, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_iterate_destroy); |