linux-kernel - [PATCH] netfilter: netns nf_conntrack: per-netns net.netfilter.nf_conntrack

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250407095052.49526-1-xiafei_xupt@163.com>
Date: Mon,  7 Apr 2025 17:50:51 +0800
From: lvxiafei <xiafei_xupt@....com>
To: "David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Simon Horman <horms@...nel.org>,
	Pablo Neira Ayuso <pablo@...filter.org>,
	Jozsef Kadlecsik <kadlec@...filter.org>
Cc: lvxiafei <lvxiafei@...setime.com>,
	netdev@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	netfilter-devel@...r.kernel.org,
	coreteam@...filter.org
Subject: [PATCH] netfilter: netns nf_conntrack: per-netns net.netfilter.nf_conntrack_max sysctl

From: lvxiafei <lvxiafei@...setime.com>

The modification of nf_conntrack_max in one netns
should not affect the value in another one.

Signed-off-by: lvxiafei <lvxiafei@...setime.com>
---
 include/net/netns/conntrack.h           |  1 +
 net/netfilter/nf_conntrack_core.c       | 12 +++++++-----
 net/netfilter/nf_conntrack_standalone.c |  6 ++++--
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index bae914815aa3..dd31ba205419 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -102,6 +102,7 @@ struct netns_ct {
 	u8			sysctl_acct;
 	u8			sysctl_tstamp;
 	u8			sysctl_checksum;
+	u8			sysctl_max;
 
 	struct ip_conntrack_stat __percpu *stat;
 	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7f8b245e287a..5f0dbd358d66 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1498,7 +1498,7 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
 
 static void gc_worker(struct work_struct *work)
 {
-	unsigned int i, hashsz, nf_conntrack_max95 = 0;
+	unsigned int i, hashsz;
 	u32 end_time, start_time = nfct_time_stamp;
 	struct conntrack_gc_work *gc_work;
 	unsigned int expired_count = 0;
@@ -1509,8 +1509,6 @@ static void gc_worker(struct work_struct *work)
 	gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
 
 	i = gc_work->next_bucket;
-	if (gc_work->early_drop)
-		nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
 
 	if (i == 0) {
 		gc_work->avg_timeout = GC_SCAN_INTERVAL_INIT;
@@ -1538,6 +1536,7 @@ static void gc_worker(struct work_struct *work)
 		}
 
 		hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
+			unsigned int nf_conntrack_max95 = 0;
 			struct nf_conntrack_net *cnet;
 			struct net *net;
 			long expires;
@@ -1567,11 +1566,14 @@ static void gc_worker(struct work_struct *work)
 			expires = clamp(nf_ct_expires(tmp), GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_CLAMP);
 			expires = (expires - (long)next_run) / ++count;
 			next_run += expires;
+			net = nf_ct_net(tmp);
+
+			if (gc_work->early_drop)
+				nf_conntrack_max95 = net->ct.sysctl_max / 100u * 95u;
 
 			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
 				continue;
 
-			net = nf_ct_net(tmp);
 			cnet = nf_ct_pernet(net);
 			if (atomic_read(&cnet->count) < nf_conntrack_max95)
 				continue;
@@ -1654,7 +1656,7 @@ __nf_conntrack_alloc(struct net *net,
 	/* We don't want any race condition at early drop stage */
 	ct_count = atomic_inc_return(&cnet->count);
 
-	if (nf_conntrack_max && unlikely(ct_count > nf_conntrack_max)) {
+	if (net->ct.sysctl_max && unlikely(ct_count > net->ct.sysctl_max)) {
 		if (!early_drop(net, hash)) {
 			if (!conntrack_gc_work.early_drop)
 				conntrack_gc_work.early_drop = true;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 2f666751c7e7..5ac1893e9045 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -615,7 +615,7 @@ enum nf_ct_sysctl_index {
 static struct ctl_table nf_ct_sysctl_table[] = {
 	[NF_SYSCTL_CT_MAX] = {
 		.procname	= "nf_conntrack_max",
-		.data		= &nf_conntrack_max,
+		.data		= &init_net.ct.sysctl_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -948,7 +948,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 static struct ctl_table nf_ct_netfilter_table[] = {
 	{
 		.procname	= "nf_conntrack_max",
-		.data		= &nf_conntrack_max,
+		.data		= &init_net.ct.sysctl_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -1063,6 +1063,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 
 	table[NF_SYSCTL_CT_COUNT].data = &cnet->count;
 	table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
+	table[NF_SYSCTL_CT_MAX].data = &net->ct.sysctl_max;
 	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
 	table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
@@ -1139,6 +1140,7 @@ static int nf_conntrack_pernet_init(struct net *net)
 	int ret;
 
 	net->ct.sysctl_checksum = 1;
+	net->ct.sysctl_max = nf_conntrack_max;
 
 	ret = nf_conntrack_standalone_init_sysctl(net);
 	if (ret < 0)
-- 
2.40.1