Commit 90964016 authored by Pablo Neira Ayuso's avatar Pablo Neira Ayuso

netfilter: nf_conntrack: add IPS_OFFLOAD status bit

This new bit tells us that the conntrack entry is owned by the flow
table offload infrastructure.

 # cat /proc/net/nf_conntrack
 ipv4     2 tcp      6 src=10.141.10.2 dst=147.75.205.195 sport=36392 dport=443 src=147.75.205.195 dst=192.168.2.195 sport=443 dport=36392 [OFFLOAD] mark=0 zone=0 use=2

Note the [OFFLOAD] tag in the listing.

The timer of such conntrack entries look like stopped from userspace.
In practise, to make sure the conntrack entry does not go away, the
conntrack timer is periodically set to an arbitrary large value that
gets refreshed on every iteration from the garbage collector, so it
never expires- and they display no internal state in the case of TCP
flows. This allows us to save a bitcheck from the packet path via
nf_ct_is_expired().

Conntrack entries that have been offloaded to the flow table
infrastructure cannot be deleted/flushed via ctnetlink. The flow table
infrastructure is also responsible for releasing this conntrack entry.
Signed-off-by: default avatarPablo Neira Ayuso <pablo@netfilter.org>
parent 0befd061
...@@ -101,12 +101,16 @@ enum ip_conntrack_status { ...@@ -101,12 +101,16 @@ enum ip_conntrack_status {
IPS_HELPER_BIT = 13, IPS_HELPER_BIT = 13,
IPS_HELPER = (1 << IPS_HELPER_BIT), IPS_HELPER = (1 << IPS_HELPER_BIT),
/* Conntrack has been offloaded to flow table. */
IPS_OFFLOAD_BIT = 14,
IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT),
/* Be careful here, modifying these bits can make things messy, /* Be careful here, modifying these bits can make things messy,
* so don't let users modify them directly. * so don't let users modify them directly.
*/ */
IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
IPS_SEQ_ADJUST | IPS_TEMPLATE), IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
__IPS_MAX_BIT = 14, __IPS_MAX_BIT = 14,
}; };
......
...@@ -901,6 +901,9 @@ static unsigned int early_drop_list(struct net *net, ...@@ -901,6 +901,9 @@ static unsigned int early_drop_list(struct net *net,
hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) { hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h); tmp = nf_ct_tuplehash_to_ctrack(h);
if (test_bit(IPS_OFFLOAD_BIT, &tmp->status))
continue;
if (nf_ct_is_expired(tmp)) { if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp); nf_ct_gc_expired(tmp);
continue; continue;
...@@ -975,6 +978,18 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) ...@@ -975,6 +978,18 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
return false; return false;
} }
#define DAY (86400 * HZ)
/* Set an arbitrary timeout large enough not to ever expire, this save
* us a check for the IPS_OFFLOAD_BIT from the packet path via
* nf_ct_is_expired().
*/
static void nf_ct_offload_timeout(struct nf_conn *ct)
{
if (nf_ct_expires(ct) < DAY / 2)
ct->timeout = nfct_time_stamp + DAY;
}
static void gc_worker(struct work_struct *work) static void gc_worker(struct work_struct *work)
{ {
unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
...@@ -1011,6 +1026,11 @@ static void gc_worker(struct work_struct *work) ...@@ -1011,6 +1026,11 @@ static void gc_worker(struct work_struct *work)
tmp = nf_ct_tuplehash_to_ctrack(h); tmp = nf_ct_tuplehash_to_ctrack(h);
scanned++; scanned++;
if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
nf_ct_offload_timeout(tmp);
continue;
}
if (nf_ct_is_expired(tmp)) { if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp); nf_ct_gc_expired(tmp);
expired_count++; expired_count++;
......
...@@ -1110,6 +1110,14 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { ...@@ -1110,6 +1110,14 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
.len = NF_CT_LABELS_MAX_SIZE }, .len = NF_CT_LABELS_MAX_SIZE },
}; };
static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data)
{
if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
return 0;
return ctnetlink_filter_match(ct, data);
}
static int ctnetlink_flush_conntrack(struct net *net, static int ctnetlink_flush_conntrack(struct net *net,
const struct nlattr * const cda[], const struct nlattr * const cda[],
u32 portid, int report) u32 portid, int report)
...@@ -1122,7 +1130,7 @@ static int ctnetlink_flush_conntrack(struct net *net, ...@@ -1122,7 +1130,7 @@ static int ctnetlink_flush_conntrack(struct net *net,
return PTR_ERR(filter); return PTR_ERR(filter);
} }
nf_ct_iterate_cleanup_net(net, ctnetlink_filter_match, filter, nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter,
portid, report); portid, report);
kfree(filter); kfree(filter);
...@@ -1168,6 +1176,11 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, ...@@ -1168,6 +1176,11 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
ct = nf_ct_tuplehash_to_ctrack(h); ct = nf_ct_tuplehash_to_ctrack(h);
if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) {
nf_ct_put(ct);
return -EBUSY;
}
if (cda[CTA_ID]) { if (cda[CTA_ID]) {
u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID])); u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
if (id != (u32)(unsigned long)ct) { if (id != (u32)(unsigned long)ct) {
......
...@@ -305,6 +305,9 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple, ...@@ -305,6 +305,9 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
/* Print out the private part of the conntrack. */ /* Print out the private part of the conntrack. */
static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
{ {
if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
return;
seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]); seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]);
} }
#endif #endif
......
...@@ -309,10 +309,12 @@ static int ct_seq_show(struct seq_file *s, void *v) ...@@ -309,10 +309,12 @@ static int ct_seq_show(struct seq_file *s, void *v)
WARN_ON(!l4proto); WARN_ON(!l4proto);
ret = -ENOSPC; ret = -ENOSPC;
seq_printf(s, "%-8s %u %-8s %u %ld ", seq_printf(s, "%-8s %u %-8s %u ",
l3proto_name(l3proto->l3proto), nf_ct_l3num(ct), l3proto_name(l3proto->l3proto), nf_ct_l3num(ct),
l4proto_name(l4proto->l4proto), nf_ct_protonum(ct), l4proto_name(l4proto->l4proto), nf_ct_protonum(ct));
nf_ct_expires(ct) / HZ);
if (!test_bit(IPS_OFFLOAD_BIT, &ct->status))
seq_printf(s, "%ld ", nf_ct_expires(ct) / HZ);
if (l4proto->print_conntrack) if (l4proto->print_conntrack)
l4proto->print_conntrack(s, ct); l4proto->print_conntrack(s, ct);
...@@ -339,7 +341,9 @@ static int ct_seq_show(struct seq_file *s, void *v) ...@@ -339,7 +341,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
goto release; goto release;
if (test_bit(IPS_ASSURED_BIT, &ct->status)) if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
seq_puts(s, "[OFFLOAD] ");
else if (test_bit(IPS_ASSURED_BIT, &ct->status))
seq_puts(s, "[ASSURED] "); seq_puts(s, "[ASSURED] ");
if (seq_has_overflowed(s)) if (seq_has_overflowed(s))
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment