Merge git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for net-next, misc
updates and fallout fixes from recent Florian's code rewritting (from
last pull request):
1) Use new flowi4_l3mdev field in ip_route_me_harder(), from Martin Willi.
2) Avoid unnecessary GC with a timestamp in conncount, from William Tu
and Yifeng Sun.
3) Remove TCP conntrack debugging, from Florian Westphal.
4) Fix compilation warning in ctnetlink, from Florian.
* git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: ctnetlink: fix up for "netfilter: conntrack: remove unconfirmed list"
netfilter: conntrack: remove pr_debug callsites from tcp tracker
netfilter: nf_conncount: reduce unnecessary GC
netfilter: Use l3mdev flow key when re-routing mangled packets
====================
Link: https://lore.kernel.org/r/20220519220206.722153-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 9645b47..e227d99 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -10,6 +10,7 @@
struct nf_conncount_list {
spinlock_t list_lock;
+ u32 last_gc; /* jiffies at most recent gc */
struct list_head head; /* connections with the same filtering key */
unsigned int count; /* length of list */
};
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index aff7079..bd13516 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -45,8 +45,7 @@
fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
- if (!fl4.flowi4_oif)
- fl4.flowi4_oif = l3mdev_master_ifindex(dev);
+ fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev);
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = flags;
fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 8ce60ab..857713d 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -31,6 +31,7 @@
int strict = (ipv6_addr_type(&iph->daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct flowi6 fl6 = {
+ .flowi6_l3mdev = l3mdev_master_ifindex(dev),
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
@@ -42,8 +43,6 @@
fl6.flowi6_oif = sk->sk_bound_dev_if;
else if (strict)
fl6.flowi6_oif = dev->ifindex;
- else
- fl6.flowi6_oif = l3mdev_master_ifindex(dev);
fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys);
dst = ip6_route_output(net, sk, &fl6);
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 82f36be..5d8ed6c 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -132,6 +132,9 @@
struct nf_conn *found_ct;
unsigned int collect = 0;
+ if (time_is_after_eq_jiffies((unsigned long)list->last_gc))
+ goto add_new_node;
+
/* check the saved connections */
list_for_each_entry_safe(conn, conn_n, &list->head, node) {
if (collect > CONNCOUNT_GC_MAX_NODES)
@@ -177,6 +180,7 @@
nf_ct_put(found_ct);
}
+add_new_node:
if (WARN_ON_ONCE(list->count > INT_MAX))
return -EOVERFLOW;
@@ -190,6 +194,7 @@
conn->jiffies32 = (u32)jiffies;
list_add_tail(&conn->node, &list->head);
list->count++;
+ list->last_gc = (u32)jiffies;
return 0;
}
@@ -214,6 +219,7 @@
spin_lock_init(&list->list_lock);
INIT_LIST_HEAD(&list->head);
list->count = 0;
+ list->last_gc = (u32)jiffies;
}
EXPORT_SYMBOL_GPL(nf_conncount_list_init);
@@ -227,6 +233,10 @@
unsigned int collected = 0;
bool ret = false;
+ /* don't bother if we just did GC */
+ if (time_is_after_eq_jiffies((unsigned long)READ_ONCE(list->last_gc)))
+ return false;
+
/* don't bother if other cpu is already doing GC */
if (!spin_trylock(&list->list_lock))
return false;
@@ -258,6 +268,7 @@
if (!list->count)
ret = true;
+ list->last_gc = (u32)jiffies;
spin_unlock(&list->list_lock);
return ret;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index e768f59..722af5e 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1714,6 +1714,7 @@
return 0;
}
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
static int ctnetlink_dump_one_entry(struct sk_buff *skb,
struct netlink_callback *cb,
struct nf_conn *ct,
@@ -1754,6 +1755,7 @@
return res;
}
+#endif
static int
ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 204a5cd..a63b51d 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -485,7 +485,6 @@
struct nf_tcp_net *tn = nf_tcp_pernet(net);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
- const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
u16 win_raw;
s32 receiver_offset;
@@ -508,18 +507,6 @@
ack -= receiver_offset;
sack -= receiver_offset;
- pr_debug("tcp_in_window: START\n");
- pr_debug("tcp_in_window: ");
- nf_ct_dump_tuple(tuple);
- pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
- seq, ack, receiver_offset, sack, receiver_offset, win, end);
- pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
- "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
- sender->td_end, sender->td_maxend, sender->td_maxwin,
- sender->td_scale,
- receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
- receiver->td_scale);
-
if (sender->td_maxwin == 0) {
/*
* Initialize sender data.
@@ -597,27 +584,10 @@
*/
seq = end = sender->td_end;
- pr_debug("tcp_in_window: ");
- nf_ct_dump_tuple(tuple);
- pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
- seq, ack, receiver_offset, sack, receiver_offset, win, end);
- pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
- "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
- sender->td_end, sender->td_maxend, sender->td_maxwin,
- sender->td_scale,
- receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
- receiver->td_scale);
-
/* Is the ending sequence in the receive window (if available)? */
in_recv_win = !receiver->td_maxwin ||
after(end, sender->td_end - receiver->td_maxwin - 1);
- pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
- before(seq, sender->td_maxend + 1),
- (in_recv_win ? 1 : 0),
- before(sack, receiver->td_end + 1),
- after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1));
-
if (before(seq, sender->td_maxend + 1) &&
in_recv_win &&
before(sack, receiver->td_end + 1) &&
@@ -698,11 +668,6 @@
}
}
- pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u "
- "receiver end=%u maxend=%u maxwin=%u\n",
- res, sender->td_end, sender->td_maxend, sender->td_maxwin,
- receiver->td_end, receiver->td_maxend, receiver->td_maxwin);
-
return res;
}
@@ -772,8 +737,6 @@
enum tcp_conntrack new_state;
struct net *net = nf_ct_net(ct);
const struct nf_tcp_net *tn = nf_tcp_pernet(net);
- const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0];
- const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1];
/* Don't need lock here: this conntrack not in circulation yet */
new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE];
@@ -826,14 +789,6 @@
/* tcp_packet will set them */
ct->proto.tcp.last_index = TCP_NONE_SET;
-
- pr_debug("%s: sender end=%u maxend=%u maxwin=%u scale=%i "
- "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
- __func__,
- sender->td_end, sender->td_maxend, sender->td_maxwin,
- sender->td_scale,
- receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
- receiver->td_scale);
return true;
}
@@ -1032,10 +987,11 @@
}
/* Invalid packet */
- pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
- dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
- nf_ct_l4proto_log_invalid(skb, ct, state, "invalid state");
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "packet (index %d) in dir %d invalid, state %s",
+ index, dir,
+ tcp_conntrack_names[old_state]);
return -NF_ACCEPT;
case TCP_CONNTRACK_TIME_WAIT:
/* RFC5961 compliance cause stack to send "challenge-ACK"
