* [PATCH net-next 01/15] ipvs: add conn_max sysctl to limit connections
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 02/15] netfilter: nfnetlink_osf: fix mss parsing on big-endian architectures Pablo Neira Ayuso
` (13 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Julian Anastasov <ja@ssi.bg>
Currently, we are using atomic_t to track the number of
connections. On 64-bit setups with large memory there is
a risk this counter to overflow. Also, setups with many
containers may need to tune the limit for connections.
Add sysctl control to limit the number of connections to
1,073,741,824 (64-bit) and 16,777,216 (32-bit).
Depending on the admin's privilege, the value is
used to change a soft or hard limit allowing
unprivileged admins to change the soft limit in
range determined by privileged admins.
Link: https://sashiko.dev/#/patchset/20260523172715.94795-1-ja%40ssi.bg
Link: https://sashiko.dev/#/patchset/20260430074420.26697-7-ja%40ssi.bg
Link: https://sashiko.dev/#/patchset/20260522105546.13732-1-ja%40ssi.bg
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
Documentation/networking/ipvs-sysctl.rst | 35 ++++++++++++++++
include/net/ip_vs.h | 22 ++++++++++
net/netfilter/ipvs/ip_vs_conn.c | 10 ++++-
net/netfilter/ipvs/ip_vs_ctl.c | 53 ++++++++++++++++++++++++
4 files changed, 119 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
index a556439f8be7..b6bac2612420 100644
--- a/Documentation/networking/ipvs-sysctl.rst
+++ b/Documentation/networking/ipvs-sysctl.rst
@@ -56,6 +56,41 @@ conn_lfactor - INTEGER
-4: grow if load goes above 6% (buckets = nodes * 16)
2: grow if load goes above 400% (buckets = nodes / 4)
+conn_max - INTEGER
+ Limit for number of connections, per netns.
+
+ Controls the soft and hard limit for number of connections.
+ Initially, the platform specific limit is assigned for init_net.
+ The value can be changed and later the soft limit propagated
+ to other networking namespaces.
+
+ Privileged admin can change both limits up to the value of the
+ platform limit while the unprivileged admin can change only the
+ soft limit up to the value of the hard limit.
+
+ For setups using conntrack=1 (CONFIG_IP_VS_NFCT for
+ Netfilter connection tracking) the connections can be
+ limited also by nf_conntrack_max.
+
+ soft limit hard limit
+ =====================================================
+ init_net:
+ create netns platform platform
+ priv admin 0 .. platform 0 .. platform
+ =====================================================
+ new netns:
+ create netns init_net:soft init_net:soft
+ priv admin 0 .. platform 0 .. platform
+ unpriv admin 0 .. hard N/A
+
+ Limits per platform:
+ 1,073,741,824 (2^30 for 64-bit)
+ 16,777,216 (2^24 for 32-bit)
+
+ Possible values: 0 .. platform limit
+
+ Default: platform limit
+
conn_reuse_mode - INTEGER
1 - default
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e517eaaa177b..49297fec448a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -44,6 +44,14 @@
#define IP_VS_CONN_TAB_MAX_BITS 20
#endif
+/* conn_max limits */
+#if BITS_PER_LONG > 32
+/* Limit of atomic_t but restricted by roundup_pow_of_two() in ip_vs_core.c */
+#define IP_VS_CONN_MAX (1 << 30)
+#else
+#define IP_VS_CONN_MAX (1 << 24)
+#endif
+
/* svc_table limits */
#define IP_VS_SVC_TAB_MIN_BITS 4
#define IP_VS_SVC_TAB_MAX_BITS 20
@@ -1220,6 +1228,10 @@ struct netns_ipvs {
/* sysctl variables */
int sysctl_amemthresh;
int sysctl_am_droprate;
+#ifdef CONFIG_SYSCTL
+ int sysctl_conn_max;/* soft limit for conns */
+ int conn_max_limit; /* hard limit for conn_max */
+#endif
int sysctl_drop_entry;
int sysctl_drop_packet;
int sysctl_secure_tcp;
@@ -1317,6 +1329,11 @@ struct netns_ipvs {
#ifdef CONFIG_SYSCTL
+static inline int sysctl_conn_max(struct netns_ipvs *ipvs)
+{
+ return READ_ONCE(ipvs->sysctl_conn_max);
+}
+
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
{
return ipvs->sysctl_sync_threshold[0];
@@ -1436,6 +1453,11 @@ static inline int sysctl_est_nice(struct netns_ipvs *ipvs)
#else
+static inline int sysctl_conn_max(struct netns_ipvs *ipvs)
+{
+ return IP_VS_CONN_MAX;
+}
+
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
{
return DEFAULT_SYNC_THRESHOLD;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9ea6b4fa78bf..e76a73d183d5 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1358,9 +1358,18 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
struct netns_ipvs *ipvs = p->ipvs;
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs,
p->protocol);
+ /* Increment conn_count up to conn_max */
+ int count = atomic_read(&ipvs->conn_count);
+ int max = sysctl_conn_max(ipvs);
+
+ do {
+ if (count >= max)
+ return NULL;
+ } while (!atomic_try_cmpxchg(&ipvs->conn_count, &count, count + 1));
cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC);
if (cp == NULL) {
+ atomic_dec(&ipvs->conn_count);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NULL;
}
@@ -1414,7 +1423,6 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
cp->in_seq.delta = 0;
cp->out_seq.delta = 0;
- atomic_inc(&ipvs->conn_count);
if (unlikely(flags & IP_VS_CONN_F_NO_CPORT)) {
int af_id = ip_vs_af_index(cp->af);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 16daba8cac83..f765d1506839 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2322,6 +2322,45 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs)
#ifdef CONFIG_SYSCTL
+static int
+proc_do_conn_max(const struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int *valp = table->data;
+ /* We can not use *valp to check if new value is provided, use INT_MIN
+ * for this because different admins change different limits.
+ */
+ int unset = INT_MIN;
+ int val = write ? unset : READ_ONCE(*valp);
+ int rc;
+
+ const struct ctl_table tmp = {
+ .data = &val,
+ .maxlen = sizeof(int),
+ };
+
+ rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+ if (write && !rc && val != unset) {
+ struct netns_ipvs *ipvs = table->extra2;
+ bool priv = capable(CAP_NET_ADMIN);
+ int max;
+
+ mutex_lock(&ipvs->service_mutex);
+ /* Unprivileged admins can not go above the hard limit */
+ max = priv ? IP_VS_CONN_MAX : ipvs->conn_max_limit;
+ if (val < 0 || val > max) {
+ rc = -EINVAL;
+ } else {
+ /* Privileged admin changes both limits */
+ if (priv)
+ ipvs->conn_max_limit = val;
+ WRITE_ONCE(*valp, val);
+ }
+ mutex_unlock(&ipvs->service_mutex);
+ }
+ return rc;
+}
+
static int
proc_do_defense_mode(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
@@ -2626,6 +2665,12 @@ static struct ctl_table vs_vars[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "conn_max",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_do_conn_max,
+ },
{
.procname = "drop_entry",
.maxlen = sizeof(int),
@@ -4980,6 +5025,14 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
tbl[idx++].data = &ipvs->sysctl_amemthresh;
ipvs->sysctl_am_droprate = 10;
tbl[idx++].data = &ipvs->sysctl_am_droprate;
+
+ /* Inherit both limits from init_net:conn_max */
+ ipvs->conn_max_limit = net_eq(net, &init_net) ? IP_VS_CONN_MAX :
+ READ_ONCE(*(int *)vs_vars[idx].data);
+ ipvs->sysctl_conn_max = ipvs->conn_max_limit;
+ tbl[idx].extra2 = ipvs;
+ tbl[idx++].data = &ipvs->sysctl_conn_max;
+
tbl[idx++].data = &ipvs->sysctl_drop_entry;
tbl[idx++].data = &ipvs->sysctl_drop_packet;
#ifdef CONFIG_IP_VS_NFCT
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 02/15] netfilter: nfnetlink_osf: fix mss parsing on big-endian architectures
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 01/15] ipvs: add conn_max sysctl to limit connections Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 03/15] netfilter: nfnetlink_cthelper: use {READ,WRITE}_ONCE for accessing helper flags Pablo Neira Ayuso
` (12 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Fernando Fernandez Mancera <fmancera@suse.de>
The MSS calculation in nf_osf_match_one() manually shifts bytes to
construct a 16-bit value before passing it to ntohs().
This works on little-endian hosts but it does not work on big-endian as
the bytes are being always shifted and set in the same way for all
architectures.
Use get_unaligned_be16() to fix this on big-endian systems. It also
simplifies the code.
Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nfnetlink_osf.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index acb753ec5697..92002079f8ea 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -95,11 +95,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
switch (*optp) {
case OSFOPT_MSS:
- mss = optp[3];
- mss <<= 8;
- mss |= optp[2];
-
- mss = ntohs((__force __be16)mss);
+ mss = get_unaligned_be16(&optp[2]);
break;
case OSFOPT_TS:
break;
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 03/15] netfilter: nfnetlink_cthelper: use {READ,WRITE}_ONCE for accessing helper flags
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 01/15] ipvs: add conn_max sysctl to limit connections Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 02/15] netfilter: nfnetlink_osf: fix mss parsing on big-endian architectures Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 04/15] netfilter: synproxy: drop packets if timestamp adjustment fails Pablo Neira Ayuso
` (11 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
Conntrack helper flags are accessed from packet and netlink dump path.
Concurrent update of userspace helper flags is not possible, because the
nfnl_mutex in held on updates. These flags are only used by userspace
helpers. Use {READ,WRITE}_ONCE() to access this flags from lockless
paths.
Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 4 +++-
net/netfilter/nfnetlink_cthelper.c | 20 +++++++++++++-------
2 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b521b5ebd664..c072a14a306a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2213,6 +2213,7 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
{
const struct nf_conntrack_helper *helper;
const struct nf_conn_help *help;
+ unsigned int helper_flags;
int protoff;
help = nfct_help(ct);
@@ -2223,7 +2224,8 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
if (!helper)
return NF_ACCEPT;
- if (!(helper->flags & NF_CT_HELPER_F_USERSPACE))
+ helper_flags = READ_ONCE(helper->flags);
+ if (!(helper_flags & NF_CT_HELPER_F_USERSPACE))
return NF_ACCEPT;
switch (nf_ct_l3num(ct)) {
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 34af6840803e..267eac1167f3 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -41,8 +41,9 @@ static int
nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
- const struct nf_conn_help *help;
struct nf_conntrack_helper *helper;
+ const struct nf_conn_help *help;
+ unsigned int helper_flags;
help = nfct_help(ct);
if (help == NULL)
@@ -53,8 +54,10 @@ nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
if (helper == NULL)
return NF_DROP;
+ helper_flags = READ_ONCE(helper->flags);
+
/* This is a user-space helper not yet configured, skip. */
- if ((helper->flags &
+ if ((helper_flags &
(NF_CT_HELPER_F_USERSPACE | NF_CT_HELPER_F_CONFIGURED)) ==
NF_CT_HELPER_F_USERSPACE)
return NF_ACCEPT;
@@ -404,10 +407,10 @@ nfnl_cthelper_update(const struct nlattr * const tb[],
switch(status) {
case NFCT_HELPER_STATUS_ENABLED:
- helper->flags |= NF_CT_HELPER_F_CONFIGURED;
+ WRITE_ONCE(helper->flags, helper->flags | NF_CT_HELPER_F_CONFIGURED);
break;
case NFCT_HELPER_STATUS_DISABLED:
- helper->flags &= ~NF_CT_HELPER_F_CONFIGURED;
+ WRITE_ONCE(helper->flags, helper->flags & ~NF_CT_HELPER_F_CONFIGURED);
break;
}
}
@@ -529,8 +532,8 @@ static int
nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
int event, struct nf_conntrack_helper *helper)
{
- struct nlmsghdr *nlh;
unsigned int flags = portid ? NLM_F_MULTI : 0;
+ struct nlmsghdr *nlh;
int status;
event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event);
@@ -554,7 +557,7 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
if (nla_put_be32(skb, NFCTH_PRIV_DATA_LEN, htonl(helper->data_len)))
goto nla_put_failure;
- if (helper->flags & NF_CT_HELPER_F_CONFIGURED)
+ if (READ_ONCE(helper->flags) & NF_CT_HELPER_F_CONFIGURED)
status = NFCT_HELPER_STATUS_ENABLED;
else
status = NFCT_HELPER_STATUS_DISABLED;
@@ -575,6 +578,7 @@ static int
nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
struct nf_conntrack_helper *cur, *last;
+ unsigned int helper_flags;
rcu_read_lock();
last = (struct nf_conntrack_helper *)cb->args[1];
@@ -583,8 +587,10 @@ nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
hlist_for_each_entry_rcu(cur,
&nf_ct_helper_hash[cb->args[0]], hnode) {
+ helper_flags = READ_ONCE(cur->flags);
+
/* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ if (!(helper_flags & NF_CT_HELPER_F_USERSPACE))
continue;
if (cb->args[1]) {
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 04/15] netfilter: synproxy: drop packets if timestamp adjustment fails
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (2 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 03/15] netfilter: nfnetlink_cthelper: use {READ,WRITE}_ONCE for accessing helper flags Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 05/15] netfilter: synproxy: adjust duplicate timestamp options Pablo Neira Ayuso
` (10 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Fernando Fernandez Mancera <fmancera@suse.de>
If a packet was malformed or if skb_ensure_writable() failed, the
synproxy_tstamp_adjust() function returned 0 indicating an error but it
was ignored on the callers.
Make the function return a boolean instead to clarify the result and
drop the packet if synproxy_tstamp_adjust() failed due to ENOMEM from
skb_ensure_writable(). In addition, if there are malformed options, skip
the tstamp update but do not drop the packet as that should be done by
the policy directly.
Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_synproxy_core.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index ed00114f65f3..f99c22f57b7e 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -184,7 +184,7 @@ synproxy_check_timestamp_cookie(struct synproxy_options *opts)
opts->options |= opts->tsecr & (1 << 5) ? NF_SYNPROXY_OPT_ECN : 0;
}
-static unsigned int
+static bool
synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
struct tcphdr *th, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -194,13 +194,13 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
__be32 *ptr, old;
if (synproxy->tsoff == 0)
- return 1;
+ return true;
optoff = protoff + sizeof(struct tcphdr);
optend = protoff + th->doff * 4;
if (skb_ensure_writable(skb, optend))
- return 0;
+ return false;
th = (struct tcphdr *)(skb->data + protoff);
@@ -209,7 +209,7 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
switch (op[0]) {
case TCPOPT_EOL:
- return 1;
+ return true;
case TCPOPT_NOP:
optoff++;
continue;
@@ -217,7 +217,7 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
if (optoff + 1 == optend ||
optoff + op[1] > optend ||
op[1] < 2)
- return 0;
+ return true;
if (op[0] == TCPOPT_TIMESTAMP &&
op[1] == TCPOLEN_TIMESTAMP) {
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
@@ -233,12 +233,12 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
}
inet_proto_csum_replace4(&th->check, skb,
old, *ptr, false);
- return 1;
+ return true;
}
optoff += op[1];
}
}
- return 1;
+ return true;
}
#ifdef CONFIG_PROC_FS
@@ -749,7 +749,9 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb,
break;
}
- synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
+ if (!synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy))
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NETFILTER_DROP, ENOMEM);
+
return NF_ACCEPT;
}
EXPORT_SYMBOL_GPL(ipv4_synproxy_hook);
@@ -1177,7 +1179,9 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb,
break;
}
- synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
+ if (!synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy))
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NETFILTER_DROP, ENOMEM);
+
return NF_ACCEPT;
}
EXPORT_SYMBOL_GPL(ipv6_synproxy_hook);
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 05/15] netfilter: synproxy: adjust duplicate timestamp options
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (3 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 04/15] netfilter: synproxy: drop packets if timestamp adjustment fails Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 06/15] netfilter: synproxy: fix unaligned memory access in timestamp adjustment Pablo Neira Ayuso
` (9 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Fernando Fernandez Mancera <fmancera@suse.de>
RFC 9293 does not mention anything about duplicated options and each
networking stack handles it in their own way. Currently, Linux kernel is
processing options sequentially and in case of duplicated timestamp
options, the value from the latest one overrides the others.
As SYNPROXY is modifying only the first timestamp option found, a packet
can reach the backend server and it might parse the wrong timestamp
value. Let's just continue parsing the following options and in case a
duplicated timestamp is found, adjust it too.
Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_synproxy_core.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index f99c22f57b7e..a0bcf188810d 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -233,7 +233,6 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
}
inet_proto_csum_replace4(&th->check, skb,
old, *ptr, false);
- return true;
}
optoff += op[1];
}
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 06/15] netfilter: synproxy: fix unaligned memory access in timestamp adjustment
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (4 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 05/15] netfilter: synproxy: adjust duplicate timestamp options Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 07/15] netfilter: synproxy: protect nf_ct_seqadj_init() with conntrack lock Pablo Neira Ayuso
` (8 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Fernando Fernandez Mancera <fmancera@suse.de>
Use get_unaligned_be32() and put_unaligned_be32() to safely read and
write the timestamp fields. This prevents performance degradation due to
unaligned memory access or even a crash on strict alignment
architectures.
This follows the implementation of timestamp parsing in the networking
stack at tcp_parse_options() and synproxy_parse_options().
Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_synproxy_core.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index a0bcf188810d..acd360515972 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -191,7 +191,7 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
const struct nf_conn_synproxy *synproxy)
{
unsigned int optoff, optend;
- __be32 *ptr, old;
+ u32 new, old;
if (synproxy->tsoff == 0)
return true;
@@ -221,18 +221,17 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
if (op[0] == TCPOPT_TIMESTAMP &&
op[1] == TCPOLEN_TIMESTAMP) {
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
- ptr = (__be32 *)&op[2];
- old = *ptr;
- *ptr = htonl(ntohl(*ptr) -
- synproxy->tsoff);
+ old = get_unaligned_be32(&op[2]);
+ new = old - synproxy->tsoff;
+ put_unaligned_be32(new, &op[2]);
} else {
- ptr = (__be32 *)&op[6];
- old = *ptr;
- *ptr = htonl(ntohl(*ptr) +
- synproxy->tsoff);
+ old = get_unaligned_be32(&op[6]);
+ new = old + synproxy->tsoff;
+ put_unaligned_be32(new, &op[6]);
}
inet_proto_csum_replace4(&th->check, skb,
- old, *ptr, false);
+ cpu_to_be32(old),
+ cpu_to_be32(new), false);
}
optoff += op[1];
}
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 07/15] netfilter: synproxy: protect nf_ct_seqadj_init() with conntrack lock
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (5 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 06/15] netfilter: synproxy: fix unaligned memory access in timestamp adjustment Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 08/15] netfilter: cttimeout: detach dataplane timeout policy and repurpose refcount Pablo Neira Ayuso
` (7 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Fernando Fernandez Mancera <fmancera@suse.de>
nf_ct_seqadj_init() is called without holding the ct lock. This can race
with nf_ct_seq_adjust() when a connection is in CLOSE state due to an
RST or connection reopening. In addition for SYN_RECV state, concurrent
processing of packets can trigger nf_ct_seq_adjust() too. These
situations create a read/write data race.
As synproxy is the only user of nf_ct_seqadj_init() at the moment, fix
this by holding ct->lock inside nf_ct_seqadj_init() until all is done.
Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_seqadj.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index 7ab2b25b57bc..b7e99f34dfce 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -17,12 +17,14 @@ int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
if (off == 0)
return 0;
+ spin_lock_bh(&ct->lock);
set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
seqadj = nfct_seqadj(ct);
this_way = &seqadj->seq[dir];
this_way->offset_before = off;
this_way->offset_after = off;
+ spin_unlock_bh(&ct->lock);
return 0;
}
EXPORT_SYMBOL_GPL(nf_ct_seqadj_init);
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 08/15] netfilter: cttimeout: detach dataplane timeout policy and repurpose refcount
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (6 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 07/15] netfilter: synproxy: protect nf_ct_seqadj_init() with conntrack lock Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 09/15] netfilter: nf_conntrack_helper: dynamically allocate struct nf_conntrack_helper Pablo Neira Ayuso
` (6 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
Add a refcount for struct nf_ct_timeout which is used by ct extension to
set the custom ct timeout policy, this tells us that the ct timeout is
being used by a conntrack entry. When the last conntrack entry drops the
refcount on the ct timeout, the ct timeout is released.
Remove the refcount for control plane which controls if the ruleset
refers to the timeout policy. After this update, it is possible to
remove the ct timeout policy from nfnetlink_cttimeout immediately.
This is for simplicity not to handle two refcounts on a single object.
Remove nf_queue_nf_hook_drop(): a packet sitting in nfqueue will just
hold a reference to the nf_ct_timeout object until packet is reinjected,
since this is part of the ct extension, this will be released by the
time the conntrack is freed.
nf_ct_untimeout() is still called to clean up in a best effort basis:
the ct timeout on existing entries gets removed when the ct timeout goes
away, but as long as the iptables ruleset still refers to the ct timeout
through a template, new conntracks may keep attaching it and extend its
lifetime until the rule is removed.
nf_ct_untimeout() is not called anymore from module removal path, this
is unlikely to find timeouts give module refcount is bumped, and the new
refcount already tracks the ct timeout policy use so it is released when
unused.
Fixes: 50978462300f ("netfilter: add cttimeout infrastructure for fine timeout tuning")
Fixes: 7e0b2b57f01d ("netfilter: nft_ct: add ct timeout support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_timeout.h | 27 ++++-
net/netfilter/nf_conntrack_core.c | 6 +-
net/netfilter/nf_conntrack_timeout.c | 27 ++++-
net/netfilter/nfnetlink_cttimeout.c | 112 +++++++++----------
net/netfilter/nft_ct.c | 7 +-
net/netfilter/xt_CT.c | 2 +-
6 files changed, 107 insertions(+), 74 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 3a66d4abb6d6..d60aa86be019 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -12,6 +12,7 @@
#define CTNL_TIMEOUT_NAME_MAX 32
struct nf_ct_timeout {
+ refcount_t refcnt;
__u16 l3num;
const struct nf_conntrack_l4proto *l4proto;
struct rcu_head rcu;
@@ -22,6 +23,22 @@ struct nf_conn_timeout {
struct nf_ct_timeout __rcu *timeout;
};
+static inline void nf_ct_timeout_put(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+ struct nf_conn_timeout *timeout_ext;
+ struct nf_ct_timeout *timeout;
+
+ timeout_ext = nf_ct_ext_find(ct, NF_CT_EXT_TIMEOUT);
+ if (!timeout_ext)
+ return;
+
+ timeout = rcu_dereference(timeout_ext->timeout);
+ if (timeout && refcount_dec_and_test(&timeout->refcnt))
+ kfree_rcu(timeout, rcu);
+#endif
+}
+
static inline unsigned int *
nf_ct_timeout_data(const struct nf_conn_timeout *t)
{
@@ -56,8 +73,14 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct,
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
struct nf_conn_timeout *timeout_ext;
+ if (!timeout)
+ return NULL;
+
timeout_ext = nf_ct_ext_add(ct, NF_CT_EXT_TIMEOUT, gfp);
- if (timeout_ext == NULL)
+ if (!timeout_ext || timeout_ext->timeout)
+ return NULL;
+
+ if (!refcount_inc_not_zero(&timeout->refcnt))
return NULL;
rcu_assign_pointer(timeout_ext->timeout, timeout);
@@ -75,7 +98,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
struct nf_conn_timeout *timeout_ext;
timeout_ext = nf_ct_timeout_find(ct);
- if (timeout_ext)
+ if (timeout_ext && rcu_access_pointer(timeout_ext->timeout))
timeouts = nf_ct_timeout_data(timeout_ext);
#endif
return timeouts;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index c072a14a306a..a45b73239369 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1737,16 +1737,18 @@ void nf_conntrack_free(struct nf_conn *ct)
*/
WARN_ON(refcount_read(&ct->ct_general.use) != 0);
+ rcu_read_lock();
if (ct->status & IPS_SRC_NAT_DONE) {
const struct nf_nat_hook *nat_hook;
- rcu_read_lock();
nat_hook = rcu_dereference(nf_nat_hook);
if (nat_hook)
nat_hook->remove_nat_bysrc(ct);
- rcu_read_unlock();
}
+ nf_ct_timeout_put(ct);
+ rcu_read_unlock();
+
kfree(ct->ext);
kmem_cache_free(nf_conntrack_cachep, ct);
cnet = nf_ct_pernet(net);
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 0cc584d3dbb1..c81becde2afa 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -25,17 +25,32 @@
const struct nf_ct_timeout_hooks __rcu *nf_ct_timeout_hook __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_timeout_hook);
+/* nf_ct_iterate_cleanup() holds the conntrack lock. */
static int untimeout(struct nf_conn *ct, void *timeout)
{
struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
if (timeout_ext) {
- const struct nf_ct_timeout *t;
+ struct nf_ct_timeout *t;
- t = rcu_access_pointer(timeout_ext->timeout);
+ rcu_read_lock();
+ t = rcu_dereference(timeout_ext->timeout);
+ if (!t) {
+ rcu_read_unlock();
+ return 0;
+ }
- if (!timeout || t == timeout)
+ if (!timeout || t == timeout) {
RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+
+ /* No race with nf_conntrack_free() which is called
+ * only after the conntrack has been removed from
+ * the hashes.
+ */
+ if (refcount_dec_and_test(&t->refcnt))
+ kfree_rcu(t, rcu);
+ }
+ rcu_read_unlock();
}
/* We are not intended to delete this conntrack. */
@@ -70,6 +85,8 @@ int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
const char *errmsg = NULL;
int ret = 0;
+ WARN_ON_ONCE(!nf_ct_is_template(ct));
+
rcu_read_lock();
h = rcu_dereference(nf_ct_timeout_hook);
if (!h) {
@@ -127,6 +144,8 @@ void nf_ct_destroy_timeout(struct nf_conn *ct)
struct nf_conn_timeout *timeout_ext;
const struct nf_ct_timeout_hooks *h;
+ WARN_ON_ONCE(!nf_ct_is_template(ct));
+
rcu_read_lock();
h = rcu_dereference(nf_ct_timeout_hook);
@@ -139,6 +158,8 @@ void nf_ct_destroy_timeout(struct nf_conn *ct)
if (t)
h->timeout_put(t);
RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+ if (t && refcount_dec_and_test(&t->refcnt))
+ kfree_rcu(t, rcu);
}
}
rcu_read_unlock();
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index dca6826af7de..170d3db860c5 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -37,11 +37,8 @@ struct ctnl_timeout {
struct list_head head;
struct list_head free_head;
struct rcu_head rcu_head;
- refcount_t refcnt;
char name[CTNL_TIMEOUT_NAME_MAX];
-
- /* must be at the end */
- struct nf_ct_timeout timeout;
+ struct nf_ct_timeout *timeout;
};
struct nfct_timeout_pernet {
@@ -132,12 +129,12 @@ static int cttimeout_new_timeout(struct sk_buff *skb,
/* You cannot replace one timeout policy by another of
* different kind, sorry.
*/
- if (matching->timeout.l3num != l3num ||
- matching->timeout.l4proto->l4proto != l4num)
+ if (matching->timeout->l3num != l3num ||
+ matching->timeout->l4proto->l4proto != l4num)
return -EINVAL;
- return ctnl_timeout_parse_policy(&matching->timeout.data,
- matching->timeout.l4proto,
+ return ctnl_timeout_parse_policy(&matching->timeout->data,
+ matching->timeout->l4proto,
info->net,
cda[CTA_TIMEOUT_DATA]);
}
@@ -153,26 +150,35 @@ static int cttimeout_new_timeout(struct sk_buff *skb,
goto err_proto_put;
}
- timeout = kzalloc(sizeof(struct ctnl_timeout) +
- l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
+ timeout = kzalloc(sizeof(*timeout), GFP_KERNEL);
if (timeout == NULL) {
ret = -ENOMEM;
goto err_proto_put;
}
- ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto,
+ timeout->timeout = kzalloc(sizeof(*timeout->timeout) +
+ l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
+ if (!timeout->timeout) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ ret = ctnl_timeout_parse_policy(&timeout->timeout->data, l4proto,
info->net, cda[CTA_TIMEOUT_DATA]);
if (ret < 0)
- goto err;
+ goto err_free_timeout_policy;
strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
- timeout->timeout.l3num = l3num;
- timeout->timeout.l4proto = l4proto;
- refcount_set(&timeout->refcnt, 1);
+ timeout->timeout->l3num = l3num;
+ timeout->timeout->l4proto = l4proto;
+ refcount_set(&timeout->timeout->refcnt, 1);
__module_get(THIS_MODULE);
list_add_tail_rcu(&timeout->head, &pernet->nfct_timeout_list);
return 0;
+
+err_free_timeout_policy:
+ kfree(timeout->timeout);
err:
kfree(timeout);
err_proto_put:
@@ -185,7 +191,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
{
struct nlmsghdr *nlh;
unsigned int flags = portid ? NLM_F_MULTI : 0;
- const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto;
+ const struct nf_conntrack_l4proto *l4proto = timeout->timeout->l4proto;
struct nlattr *nest_parms;
int ret;
@@ -197,17 +203,17 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) ||
nla_put_be16(skb, CTA_TIMEOUT_L3PROTO,
- htons(timeout->timeout.l3num)) ||
+ htons(timeout->timeout->l3num)) ||
nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto) ||
nla_put_be32(skb, CTA_TIMEOUT_USE,
- htonl(refcount_read(&timeout->refcnt))))
+ htonl(refcount_read(&timeout->timeout->refcnt))))
goto nla_put_failure;
nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA);
if (!nest_parms)
goto nla_put_failure;
- ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->timeout.data);
+ ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->timeout->data);
if (ret < 0)
goto nla_put_failure;
@@ -307,23 +313,17 @@ static int cttimeout_get_timeout(struct sk_buff *skb,
return ret;
}
-/* try to delete object, fail if it is still in use. */
-static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
+static void ctnl_timeout_del(struct net *net, struct ctnl_timeout *timeout)
{
- int ret = 0;
+ /* We are protected by nfnl mutex. */
+ list_del_rcu(&timeout->head);
+ nf_ct_untimeout(net, timeout->timeout);
- /* We want to avoid races with ctnl_timeout_put. So only when the
- * current refcnt is 1, we decrease it to 0.
- */
- if (refcount_dec_if_one(&timeout->refcnt)) {
- /* We are protected by nfnl mutex. */
- list_del_rcu(&timeout->head);
- nf_ct_untimeout(net, &timeout->timeout);
- kfree_rcu(timeout, rcu_head);
- } else {
- ret = -EBUSY;
- }
- return ret;
+ if (refcount_dec_and_test(&timeout->timeout->refcnt))
+ kfree_rcu(timeout->timeout, rcu);
+
+ kfree_rcu(timeout, rcu_head);
+ module_put(THIS_MODULE);
}
static int cttimeout_del_timeout(struct sk_buff *skb,
@@ -338,7 +338,7 @@ static int cttimeout_del_timeout(struct sk_buff *skb,
if (!cda[CTA_TIMEOUT_NAME]) {
list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list,
head)
- ctnl_timeout_try_del(info->net, cur);
+ ctnl_timeout_del(info->net, cur);
return 0;
}
@@ -348,10 +348,8 @@ static int cttimeout_del_timeout(struct sk_buff *skb,
if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0)
continue;
- ret = ctnl_timeout_try_del(info->net, cur);
- if (ret < 0)
- return ret;
-
+ ctnl_timeout_del(info->net, cur);
+ ret = 0;
break;
}
return ret;
@@ -511,24 +509,22 @@ static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net,
if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0)
continue;
- if (!refcount_inc_not_zero(&timeout->refcnt))
+ if (!refcount_inc_not_zero(&timeout->timeout->refcnt))
goto err;
matching = timeout;
+ __module_get(THIS_MODULE);
break;
}
err:
- return matching ? &matching->timeout : NULL;
+ return matching ? matching->timeout : NULL;
}
-static void ctnl_timeout_put(struct nf_ct_timeout *t)
+static void ctnl_timeout_put(struct nf_ct_timeout *timeout)
{
- struct ctnl_timeout *timeout =
- container_of(t, struct ctnl_timeout, timeout);
+ if (refcount_dec_and_test(&timeout->refcnt))
+ kfree_rcu(timeout, rcu);
- if (refcount_dec_and_test(&timeout->refcnt)) {
- kfree_rcu(timeout, rcu_head);
- module_put(THIS_MODULE);
- }
+ module_put(THIS_MODULE);
}
static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = {
@@ -609,8 +605,11 @@ static void __net_exit cttimeout_net_exit(struct net *net)
list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) {
list_del(&cur->free_head);
- if (refcount_dec_and_test(&cur->refcnt))
- kfree_rcu(cur, rcu_head);
+ if (refcount_dec_and_test(&cur->timeout->refcnt))
+ kfree_rcu(cur->timeout, rcu);
+
+ kfree_rcu(cur, rcu_head);
+ module_put(THIS_MODULE);
}
}
@@ -649,24 +648,13 @@ static int __init cttimeout_init(void)
return ret;
}
-static int untimeout(struct nf_conn *ct, void *timeout)
-{
- struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
-
- if (timeout_ext)
- RCU_INIT_POINTER(timeout_ext->timeout, NULL);
-
- return 0;
-}
-
static void __exit cttimeout_exit(void)
{
nfnetlink_subsys_unregister(&cttimeout_subsys);
unregister_pernet_subsys(&cttimeout_ops);
RCU_INIT_POINTER(nf_ct_timeout_hook, NULL);
-
- nf_ct_iterate_destroy(untimeout, NULL);
+ synchronize_net();
}
module_init(cttimeout_init);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 357513c6dcea..801c01c6af95 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -897,8 +897,6 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj,
}
}
- rcu_assign_pointer(timeout->timeout, priv->timeout);
-
/* adjust the timeout as per 'new' state. ct is unconfirmed,
* so the current timestamp must not be added.
*/
@@ -949,6 +947,7 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx,
timeout->l3num = l3num;
timeout->l4proto = l4proto;
+ refcount_set(&timeout->refcnt, 1);
ret = nf_ct_netns_get(ctx->net, ctx->family);
if (ret < 0)
@@ -969,10 +968,10 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx,
struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
struct nf_ct_timeout *timeout = priv->timeout;
- nf_queue_nf_hook_drop(ctx->net);
nf_ct_untimeout(ctx->net, timeout);
nf_ct_netns_put(ctx->net, ctx->family);
- kfree_rcu(priv->timeout, rcu);
+ if (refcount_dec_and_test(&timeout->refcnt))
+ kfree_rcu(priv->timeout, rcu);
}
static int nft_ct_timeout_obj_dump(struct sk_buff *skb,
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index d2aeacf94230..b94f004d5f5c 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -284,7 +284,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
struct nf_conn_help *help;
if (ct) {
- if (info->helper[0] || info->timeout[0])
+ if (info->helper[0])
nf_queue_nf_hook_drop(par->net);
help = nfct_help(ct);
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 09/15] netfilter: nf_conntrack_helper: dynamically allocate struct nf_conntrack_helper
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (7 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 08/15] netfilter: cttimeout: detach dataplane timeout policy and repurpose refcount Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 10/15] netfilter: nf_conntrack_pptp: move GRE specific cleanup to GRE tracker Pablo Neira Ayuso
` (5 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
Adapt all existing helpers to use a modified version of
nf_ct_helper_init(), to dynamically allocate struct nf_conntrack_helper.
Allocate expect_policy[] built-in into the helper to ensure this area is
reachable after helper removal since a follow up patch adds refcount to
track use of the nf_conntrack_helper structure from packet path so it
remains around until last reference from ct helper extension is dropped.
Export __nf_conntrack_helper_register() which allows to register
nfnetlink_cthelper dynamically allocated helper. Adapt nfnetlink_cthelper
to use the built-in expect_policy[].
This is a preparation patch to add packet path refcounting to helpers.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_helper.h | 16 +--
net/ipv4/netfilter/nf_nat_snmp_basic_main.c | 27 +++--
net/netfilter/nf_conntrack_amanda.c | 39 +++----
net/netfilter/nf_conntrack_ftp.c | 5 +-
net/netfilter/nf_conntrack_h323_main.c | 107 ++++++++------------
net/netfilter/nf_conntrack_helper.c | 75 +++++++++++---
net/netfilter/nf_conntrack_irc.c | 5 +-
net/netfilter/nf_conntrack_netbios_ns.c | 20 ++--
net/netfilter/nf_conntrack_pptp.c | 22 ++--
net/netfilter/nf_conntrack_sane.c | 5 +-
net/netfilter/nf_conntrack_sip.c | 5 +-
net/netfilter/nf_conntrack_snmp.c | 21 ++--
net/netfilter/nf_conntrack_tftp.c | 5 +-
net/netfilter/nfnetlink_cthelper.c | 47 ++++-----
14 files changed, 210 insertions(+), 189 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index de2f956abf34..1956bc12bf56 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -29,13 +29,16 @@ enum nf_ct_helper_flags {
#define NF_CT_HELPER_NAME_LEN 16
+/* Must be kept in sync with the classes defined by helpers */
+#define NF_CT_MAX_EXPECT_CLASSES 4
+
struct nf_conntrack_helper {
struct hlist_node hnode; /* Internal use. */
char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */
refcount_t refcnt;
struct module *me; /* pointer to self */
- const struct nf_conntrack_expect_policy *expect_policy;
+ struct nf_conntrack_expect_policy expect_policy[NF_CT_MAX_EXPECT_CLASSES];
/* Tuple of things we will help (compared against server response) */
struct nf_conntrack_tuple tuple;
@@ -63,9 +66,6 @@ struct nf_conntrack_helper {
char nat_mod_name[NF_CT_HELPER_NAME_LEN];
};
-/* Must be kept in sync with the classes defined by helpers */
-#define NF_CT_MAX_EXPECT_CLASSES 4
-
/* nf_conn feature for connections that have a helper */
struct nf_conn_help {
/* Helper. if any */
@@ -103,11 +103,13 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
struct nf_conn *ct),
struct module *module);
-int nf_conntrack_helper_register(struct nf_conntrack_helper *);
+int nf_conntrack_helper_register(struct nf_conntrack_helper *, struct nf_conntrack_helper **);
+int __nf_conntrack_helper_register(struct nf_conntrack_helper *);
void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
-int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int);
-void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *,
+int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int,
+ struct nf_conntrack_helper **);
+void nf_conntrack_helpers_unregister(struct nf_conntrack_helper **,
unsigned int);
struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp);
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
index 717b726504fe..0ede138dfd29 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
@@ -202,29 +202,34 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
.timeout = 180,
};
-static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
- .me = THIS_MODULE,
- .help = help,
- .expect_policy = &snmp_exp_policy,
- .name = "snmp_trap",
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_TRAP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
-};
+static struct nf_conntrack_helper snmp_trap_helper __read_mostly;
+static struct nf_conntrack_helper *snmp_trap_helper_ptr __read_mostly;
static int __init nf_nat_snmp_basic_init(void)
{
+ int err;
+
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
- return nf_conntrack_helper_register(&snmp_trap_helper);
+ nf_ct_helper_init(&snmp_trap_helper, AF_INET, IPPROTO_UDP,
+ "snmp_trap", SNMP_TRAP_PORT, SNMP_TRAP_PORT, SNMP_TRAP_PORT,
+ &snmp_exp_policy, 0, help, NULL, THIS_MODULE);
+
+ err = nf_conntrack_helper_register(&snmp_trap_helper, &snmp_trap_helper_ptr);
+ if (err < 0) {
+ RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+ return err;
+ }
+
+ return 0;
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
synchronize_rcu();
- nf_conntrack_helper_unregister(&snmp_trap_helper);
+ nf_conntrack_helper_unregister(snmp_trap_helper_ptr);
}
module_init(nf_nat_snmp_basic_init);
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index d2c09e8dd872..ddafbdfc96dc 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -169,35 +169,15 @@ static const struct nf_conntrack_expect_policy amanda_exp_policy = {
.timeout = 180,
};
-static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
- {
- .name = HELPER_NAME,
- .me = THIS_MODULE,
- .help = amanda_help,
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(10080),
- .tuple.dst.protonum = IPPROTO_UDP,
- .expect_policy = &amanda_exp_policy,
- .nat_mod_name = NF_NAT_HELPER_NAME(HELPER_NAME),
- },
- {
- .name = "amanda",
- .me = THIS_MODULE,
- .help = amanda_help,
- .tuple.src.l3num = AF_INET6,
- .tuple.src.u.udp.port = cpu_to_be16(10080),
- .tuple.dst.protonum = IPPROTO_UDP,
- .expect_policy = &amanda_exp_policy,
- .nat_mod_name = NF_NAT_HELPER_NAME(HELPER_NAME),
- },
-};
+static struct nf_conntrack_helper amanda_helper[2] __read_mostly;
+static struct nf_conntrack_helper *amanda_helper_ptr[2] __read_mostly;
static void __exit nf_conntrack_amanda_fini(void)
{
int i;
- nf_conntrack_helpers_unregister(amanda_helper,
- ARRAY_SIZE(amanda_helper));
+ nf_conntrack_helpers_unregister(amanda_helper_ptr,
+ ARRAY_SIZE(amanda_helper_ptr));
for (i = 0; i < ARRAY_SIZE(search); i++)
textsearch_destroy(search[i].ts);
}
@@ -217,8 +197,17 @@ static int __init nf_conntrack_amanda_init(void)
goto err1;
}
}
+
+ nf_ct_helper_init(&amanda_helper[0], AF_INET, IPPROTO_UDP,
+ HELPER_NAME, 10080, 10080, 10080,
+ &amanda_exp_policy, 0, amanda_help, NULL, THIS_MODULE);
+ nf_ct_helper_init(&amanda_helper[1], AF_INET6, IPPROTO_UDP,
+ HELPER_NAME, 10080, 10080, 10080,
+ &amanda_exp_policy, 0, amanda_help, NULL, THIS_MODULE);
+
ret = nf_conntrack_helpers_register(amanda_helper,
- ARRAY_SIZE(amanda_helper));
+ ARRAY_SIZE(amanda_helper),
+ amanda_helper_ptr);
if (ret < 0)
goto err1;
return 0;
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index dc6f0017ca6b..c7777f37371a 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -555,6 +555,7 @@ static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
}
static struct nf_conntrack_helper ftp[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *ftp_ptr[MAX_PORTS * 2] __read_mostly;
static const struct nf_conntrack_expect_policy ftp_exp_policy = {
.max_expected = 1,
@@ -563,7 +564,7 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = {
static void __exit nf_conntrack_ftp_fini(void)
{
- nf_conntrack_helpers_unregister(ftp, ports_c * 2);
+ nf_conntrack_helpers_unregister(ftp_ptr, ports_c * 2);
}
static int __init nf_conntrack_ftp_init(void)
@@ -588,7 +589,7 @@ static int __init nf_conntrack_ftp_init(void)
nf_ct_ftp_from_nlattr, THIS_MODULE);
}
- ret = nf_conntrack_helpers_register(ftp, ports_c * 2);
+ ret = nf_conntrack_helpers_register(ftp, ports_c * 2, ftp_ptr);
if (ret < 0) {
pr_err("failed to register helpers\n");
return ret;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index b2fe6554b9cf..ebae9fdab897 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -577,14 +577,8 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = {
.timeout = 240,
};
-static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
- .name = "H.245",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_UNSPEC,
- .tuple.dst.protonum = IPPROTO_UDP,
- .help = h245_help,
- .expect_policy = &h245_exp_policy,
-};
+static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_h245_ptr __read_mostly;
int get_h225_addr(struct nf_conn *ct, unsigned char *data,
TransportAddress *taddr,
@@ -643,7 +637,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_h245_ptr);
nathook = rcu_dereference(nfct_h323_nat_hook);
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -732,6 +726,9 @@ static int callforward_do_filter(struct net *net,
}
+static struct nf_conntrack_helper nf_conntrack_helper_q931[2] __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_q931_ptr[2] __read_mostly;
+
static int expect_callforwarding(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -767,7 +764,7 @@ static int expect_callforwarding(struct sk_buff *skb,
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
nathook = rcu_dereference(nfct_h323_nat_hook);
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -1140,27 +1137,6 @@ static const struct nf_conntrack_expect_policy q931_exp_policy = {
.timeout = 240,
};
-static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
- {
- .name = "Q.931",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT),
- .tuple.dst.protonum = IPPROTO_TCP,
- .help = q931_help,
- .expect_policy = &q931_exp_policy,
- },
- {
- .name = "Q.931",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_INET6,
- .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT),
- .tuple.dst.protonum = IPPROTO_TCP,
- .help = q931_help,
- .expect_policy = &q931_exp_policy,
- },
-};
-
static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff,
int *datalen)
{
@@ -1234,7 +1210,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3 : NULL,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */
nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1275,6 +1251,9 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
+static struct nf_conntrack_helper nf_conntrack_helper_ras[2] __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_ras_ptr[2] __read_mostly;
+
static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1306,7 +1285,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_UDP, NULL, &port);
- rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras_ptr[0]);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect RAS ");
@@ -1523,7 +1502,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
- rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1577,7 +1556,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
- rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1711,59 +1690,57 @@ static const struct nf_conntrack_expect_policy ras_exp_policy = {
.timeout = 240,
};
-static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
- {
- .name = "RAS",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
- .help = ras_help,
- .expect_policy = &ras_exp_policy,
- },
- {
- .name = "RAS",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_INET6,
- .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
- .help = ras_help,
- .expect_policy = &ras_exp_policy,
- },
-};
-
static int __init h323_helper_init(void)
{
int ret;
- ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245);
+ nf_ct_helper_init(&nf_conntrack_helper_ras[0], AF_INET, IPPROTO_UDP,
+ "RAS", RAS_PORT, RAS_PORT, RAS_PORT,
+ &ras_exp_policy, 0, ras_help, NULL, THIS_MODULE);
+ nf_ct_helper_init(&nf_conntrack_helper_ras[1], AF_INET6, IPPROTO_UDP,
+ "RAS", RAS_PORT, RAS_PORT, RAS_PORT,
+ &ras_exp_policy, 0, ras_help, NULL, THIS_MODULE);
+ nf_ct_helper_init(&nf_conntrack_helper_h245, AF_UNSPEC, IPPROTO_UDP,
+ "H.245", 0, 0, 0,
+ &h245_exp_policy, 0, h245_help, NULL, THIS_MODULE);
+ nf_ct_helper_init(&nf_conntrack_helper_q931[0], AF_INET, IPPROTO_TCP,
+ "Q.931", Q931_PORT, Q931_PORT, Q931_PORT,
+ &q931_exp_policy, 0, q931_help, NULL, THIS_MODULE);
+ nf_ct_helper_init(&nf_conntrack_helper_q931[1], AF_INET6, IPPROTO_TCP,
+ "Q.931", Q931_PORT, Q931_PORT, Q931_PORT,
+ &q931_exp_policy, 0, q931_help, NULL, THIS_MODULE);
+
+ ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245,
+ &nf_conntrack_helper_h245_ptr);
if (ret < 0)
return ret;
ret = nf_conntrack_helpers_register(nf_conntrack_helper_q931,
- ARRAY_SIZE(nf_conntrack_helper_q931));
+ ARRAY_SIZE(nf_conntrack_helper_q931),
+ nf_conntrack_helper_q931_ptr);
if (ret < 0)
goto err1;
ret = nf_conntrack_helpers_register(nf_conntrack_helper_ras,
- ARRAY_SIZE(nf_conntrack_helper_ras));
+ ARRAY_SIZE(nf_conntrack_helper_ras),
+ nf_conntrack_helper_ras_ptr);
if (ret < 0)
goto err2;
return 0;
err2:
- nf_conntrack_helpers_unregister(nf_conntrack_helper_q931,
- ARRAY_SIZE(nf_conntrack_helper_q931));
+ nf_conntrack_helpers_unregister(nf_conntrack_helper_q931_ptr,
+ ARRAY_SIZE(nf_conntrack_helper_q931_ptr));
err1:
- nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
+ nf_conntrack_helper_unregister(nf_conntrack_helper_h245_ptr);
return ret;
}
static void __exit h323_helper_exit(void)
{
- nf_conntrack_helpers_unregister(nf_conntrack_helper_ras,
+ nf_conntrack_helpers_unregister(nf_conntrack_helper_ras_ptr,
ARRAY_SIZE(nf_conntrack_helper_ras));
- nf_conntrack_helpers_unregister(nf_conntrack_helper_q931,
+ nf_conntrack_helpers_unregister(nf_conntrack_helper_q931_ptr,
ARRAY_SIZE(nf_conntrack_helper_q931));
- nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
+ nf_conntrack_helper_unregister(nf_conntrack_helper_h245_ptr);
}
static void __exit nf_conntrack_h323_fini(void)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 17e971bd4c74..ce2d59331dfb 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -347,14 +347,13 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct,
}
EXPORT_SYMBOL_GPL(nf_ct_helper_log);
-int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
+int __nf_conntrack_helper_register(struct nf_conntrack_helper *me)
{
struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
unsigned int h = helper_hash(&me->tuple);
struct nf_conntrack_helper *cur;
int ret = 0, i;
- BUG_ON(me->expect_policy == NULL);
BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
@@ -394,6 +393,33 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
mutex_unlock(&nf_ct_helper_mutex);
return ret;
}
+EXPORT_SYMBOL_GPL(__nf_conntrack_helper_register);
+
+int nf_conntrack_helper_register(struct nf_conntrack_helper *me,
+ struct nf_conntrack_helper **helper_ptr)
+{
+ struct nf_conntrack_helper *new_helper;
+ int err;
+
+ new_helper = kzalloc_obj(*new_helper, GFP_KERNEL_ACCOUNT);
+ if (!new_helper)
+ return -ENOMEM;
+
+ memcpy(new_helper, me, sizeof(*new_helper));
+ *helper_ptr = new_helper;
+
+ err = __nf_conntrack_helper_register(new_helper);
+ if (err < 0)
+ goto err_helper;
+
+ return 0;
+
+err_helper:
+ *helper_ptr = NULL;
+ kfree(new_helper);
+
+ return err;
+}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_register);
static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
@@ -430,6 +456,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
* last step, this ensures rcu readers of exp->helper are done.
* No need for another synchronize_rcu() here.
*/
+ kfree(me);
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
@@ -445,11 +472,12 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
struct nf_conn *ct),
struct module *module)
{
+ memset(helper, 0, sizeof(*helper));
+
helper->tuple.src.l3num = l3num;
helper->tuple.dst.protonum = protonum;
helper->tuple.src.u.all = htons(spec_port);
- helper->expect_policy = exp_pol;
- helper->expect_class_max = expect_class_max;
+
helper->help = help;
helper->from_nlattr = from_nlattr;
helper->me = module;
@@ -460,34 +488,57 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
snprintf(helper->name, sizeof(helper->name), "%s", name);
else
snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id);
+
+ if (WARN_ON_ONCE(expect_class_max >= NF_CT_MAX_EXPECT_CLASSES))
+ return;
+
+ memcpy(helper->expect_policy, exp_pol,
+ (expect_class_max + 1) * sizeof(*exp_pol));
+ helper->expect_class_max = expect_class_max;
}
EXPORT_SYMBOL_GPL(nf_ct_helper_init);
int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper,
- unsigned int n)
+ unsigned int n, struct nf_conntrack_helper **helper_ptr)
{
+ struct nf_conntrack_helper *new_helper;
unsigned int i;
int err = 0;
for (i = 0; i < n; i++) {
- err = nf_conntrack_helper_register(&helper[i]);
- if (err < 0)
+ new_helper = kzalloc_obj(*new_helper, GFP_KERNEL_ACCOUNT);
+ if (!new_helper) {
+ err = -ENOMEM;
goto err;
+ }
+
+ memcpy(new_helper, &helper[i], sizeof(*new_helper));
+ helper_ptr[i] = new_helper;
+
+ err = __nf_conntrack_helper_register(new_helper);
+ if (err < 0) {
+ helper_ptr[i] = NULL;
+ goto err_helper;
+ }
}
return err;
+err_helper:
+ kfree(new_helper);
err:
if (i > 0)
- nf_conntrack_helpers_unregister(helper, i);
+ nf_conntrack_helpers_unregister(helper_ptr, i);
return err;
}
EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register);
-void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper,
- unsigned int n)
+void nf_conntrack_helpers_unregister(struct nf_conntrack_helper **helper,
+ unsigned int n)
{
- while (n-- > 0)
- nf_conntrack_helper_unregister(&helper[n]);
+ while (n-- > 0) {
+ nf_conntrack_helper_unregister(helper[n]);
+ helper[n] = NULL;
+ }
}
EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister);
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 4d539657d4cb..0c117b8492e9 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -255,6 +255,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
}
static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly;
+static struct nf_conntrack_helper *irc_ptr[MAX_PORTS] __read_mostly;
static struct nf_conntrack_expect_policy irc_exp_policy;
static int __init nf_conntrack_irc_init(void)
@@ -289,7 +290,7 @@ static int __init nf_conntrack_irc_init(void)
0, help, NULL, THIS_MODULE);
}
- ret = nf_conntrack_helpers_register(&irc[0], ports_c);
+ ret = nf_conntrack_helpers_register(&irc[0], ports_c, irc_ptr);
if (ret) {
pr_err("failed to register helpers\n");
kfree(irc_buffer);
@@ -301,7 +302,7 @@ static int __init nf_conntrack_irc_init(void)
static void __exit nf_conntrack_irc_fini(void)
{
- nf_conntrack_helpers_unregister(irc, ports_c);
+ nf_conntrack_helpers_unregister(irc_ptr, ports_c);
kfree(irc_buffer);
}
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 55415f011943..89d1cf7d6512 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -44,27 +44,25 @@ static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
return nf_conntrack_broadcast_help(skb, ct, ctinfo, timeout);
}
-static struct nf_conntrack_helper helper __read_mostly = {
- .name = HELPER_NAME,
- .tuple.src.l3num = NFPROTO_IPV4,
- .tuple.src.u.udp.port = cpu_to_be16(NMBD_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
- .me = THIS_MODULE,
- .help = netbios_ns_help,
- .expect_policy = &exp_policy,
-};
+static struct nf_conntrack_helper helper __read_mostly;
+static struct nf_conntrack_helper *helper_ptr __read_mostly;
static int __init nf_conntrack_netbios_ns_init(void)
{
NF_CT_HELPER_BUILD_BUG_ON(0);
exp_policy.timeout = timeout;
- return nf_conntrack_helper_register(&helper);
+
+ nf_ct_helper_init(&helper, AF_INET, IPPROTO_UDP, HELPER_NAME,
+ NMBD_PORT, NMBD_PORT, NMBD_PORT,
+ &exp_policy, 0, netbios_ns_help, NULL, THIS_MODULE);
+
+ return nf_conntrack_helper_register(&helper, &helper_ptr);
}
static void __exit nf_conntrack_netbios_ns_fini(void)
{
- nf_conntrack_helper_unregister(&helper);
+ nf_conntrack_helper_unregister(helper_ptr);
}
module_init(nf_conntrack_netbios_ns_init);
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index dc23e4181618..edc85a3eef1e 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -582,27 +582,25 @@ static const struct nf_conntrack_expect_policy pptp_exp_policy = {
};
/* control protocol helper */
-static struct nf_conntrack_helper pptp __read_mostly = {
- .name = "pptp",
- .me = THIS_MODULE,
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.tcp.port = cpu_to_be16(PPTP_CONTROL_PORT),
- .tuple.dst.protonum = IPPROTO_TCP,
- .help = conntrack_pptp_help,
- .destroy = pptp_destroy_siblings,
- .expect_policy = &pptp_exp_policy,
-};
+static struct nf_conntrack_helper pptp __read_mostly;
+static struct nf_conntrack_helper *pptp_ptr __read_mostly;
static int __init nf_conntrack_pptp_init(void)
{
NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_pptp_master));
- return nf_conntrack_helper_register(&pptp);
+ nf_ct_helper_init(&pptp, AF_INET, IPPROTO_TCP,
+ "pptp", PPTP_CONTROL_PORT, PPTP_CONTROL_PORT, PPTP_CONTROL_PORT,
+ &pptp_exp_policy, 0, conntrack_pptp_help, NULL, THIS_MODULE);
+
+ pptp.destroy = pptp_destroy_siblings;
+
+ return nf_conntrack_helper_register(&pptp, &pptp_ptr);
}
static void __exit nf_conntrack_pptp_fini(void)
{
- nf_conntrack_helper_unregister(&pptp);
+ nf_conntrack_helper_unregister(pptp_ptr);
}
module_init(nf_conntrack_pptp_init);
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 13dc421fc4f5..a7f7b07ba0c2 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -167,6 +167,7 @@ static int help(struct sk_buff *skb,
}
static struct nf_conntrack_helper sane[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *sane_ptr[MAX_PORTS * 2] __read_mostly;
static const struct nf_conntrack_expect_policy sane_exp_policy = {
.max_expected = 1,
@@ -175,7 +176,7 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = {
static void __exit nf_conntrack_sane_fini(void)
{
- nf_conntrack_helpers_unregister(sane, ports_c * 2);
+ nf_conntrack_helpers_unregister(sane_ptr, ports_c * 2);
}
static int __init nf_conntrack_sane_init(void)
@@ -200,7 +201,7 @@ static int __init nf_conntrack_sane_init(void)
THIS_MODULE);
}
- ret = nf_conntrack_helpers_register(sane, ports_c * 2);
+ ret = nf_conntrack_helpers_register(sane, ports_c * 2, sane_ptr);
if (ret < 0) {
pr_err("failed to register helpers\n");
return ret;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index e69941f1a101..2c78a3e1dab5 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1731,6 +1731,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff,
}
static struct nf_conntrack_helper sip[MAX_PORTS * 4] __read_mostly;
+static struct nf_conntrack_helper *sip_ptr[MAX_PORTS * 4] __read_mostly;
static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = {
[SIP_EXPECT_SIGNALLING] = {
@@ -1757,7 +1758,7 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1
static void __exit nf_conntrack_sip_fini(void)
{
- nf_conntrack_helpers_unregister(sip, ports_c * 4);
+ nf_conntrack_helpers_unregister(sip_ptr, ports_c * 4);
}
static int __init nf_conntrack_sip_init(void)
@@ -1788,7 +1789,7 @@ static int __init nf_conntrack_sip_init(void)
NULL, THIS_MODULE);
}
- ret = nf_conntrack_helpers_register(sip, ports_c * 4);
+ ret = nf_conntrack_helpers_register(sip, ports_c * 4, sip_ptr);
if (ret < 0) {
pr_err("failed to register helpers\n");
return ret;
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
index 7b7eed43c54f..b6fce5703fce 100644
--- a/net/netfilter/nf_conntrack_snmp.c
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -47,25 +47,24 @@ static struct nf_conntrack_expect_policy exp_policy = {
.max_expected = 1,
};
-static struct nf_conntrack_helper helper __read_mostly = {
- .name = "snmp",
- .tuple.src.l3num = NFPROTO_IPV4,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
- .me = THIS_MODULE,
- .help = snmp_conntrack_help,
- .expect_policy = &exp_policy,
-};
+static struct nf_conntrack_helper helper __read_mostly;
+static struct nf_conntrack_helper *helper_ptr __read_mostly;
static int __init nf_conntrack_snmp_init(void)
{
exp_policy.timeout = timeout;
- return nf_conntrack_helper_register(&helper);
+
+ nf_ct_helper_init(&helper, AF_INET, IPPROTO_UDP,
+ "snmp", SNMP_PORT, SNMP_PORT, SNMP_PORT,
+ &exp_policy, 0, snmp_conntrack_help, NULL,
+ THIS_MODULE);
+
+ return nf_conntrack_helper_register(&helper, &helper_ptr);
}
static void __exit nf_conntrack_snmp_fini(void)
{
- nf_conntrack_helper_unregister(&helper);
+ nf_conntrack_helper_unregister(helper_ptr);
}
module_init(nf_conntrack_snmp_init);
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index a2e6833a0bf7..4393c435aa35 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -96,6 +96,7 @@ static int tftp_help(struct sk_buff *skb,
}
static struct nf_conntrack_helper tftp[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *tftp_ptr[MAX_PORTS * 2] __read_mostly;
static const struct nf_conntrack_expect_policy tftp_exp_policy = {
.max_expected = 1,
@@ -104,7 +105,7 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = {
static void __exit nf_conntrack_tftp_fini(void)
{
- nf_conntrack_helpers_unregister(tftp, ports_c * 2);
+ nf_conntrack_helpers_unregister(tftp_ptr, ports_c * 2);
}
static int __init nf_conntrack_tftp_init(void)
@@ -127,7 +128,7 @@ static int __init nf_conntrack_tftp_init(void)
THIS_MODULE);
}
- ret = nf_conntrack_helpers_register(tftp, ports_c * 2);
+ ret = nf_conntrack_helpers_register(tftp, ports_c * 2, tftp_ptr);
if (ret < 0) {
pr_err("failed to register helpers\n");
return ret;
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 267eac1167f3..338515697c91 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -32,7 +32,7 @@ MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
struct nfnl_cthelper {
struct list_head list;
- struct nf_conntrack_helper helper;
+ struct nf_conntrack_helper *helper;
};
static LIST_HEAD(nfnl_cthelper_list);
@@ -176,7 +176,6 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
const struct nlattr *attr)
{
int i, ret;
- struct nf_conntrack_expect_policy *expect_policy;
struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
unsigned int class_max;
@@ -195,26 +194,19 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
if (class_max > NF_CT_MAX_EXPECT_CLASSES)
return -EOVERFLOW;
- expect_policy = kzalloc_objs(struct nf_conntrack_expect_policy,
- class_max);
- if (expect_policy == NULL)
- return -ENOMEM;
-
for (i = 0; i < class_max; i++) {
if (!tb[NFCTH_POLICY_SET+i])
goto err;
- ret = nfnl_cthelper_expect_policy(&expect_policy[i],
+ ret = nfnl_cthelper_expect_policy(&helper->expect_policy[i],
tb[NFCTH_POLICY_SET+i]);
if (ret < 0)
goto err;
}
helper->expect_class_max = class_max - 1;
- helper->expect_policy = expect_policy;
return 0;
err:
- kfree(expect_policy);
return -EINVAL;
}
@@ -230,21 +222,28 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
return -EINVAL;
- nfcth = kzalloc_obj(*nfcth);
+ nfcth = kzalloc_obj(*nfcth, GFP_KERNEL_ACCOUNT);
if (nfcth == NULL)
return -ENOMEM;
- helper = &nfcth->helper;
+
+ helper = kzalloc_obj(*helper, GFP_KERNEL_ACCOUNT);
+ if (!helper) {
+ ret = -ENOMEM;
+ goto err_cth;
+ }
+
+ nfcth->helper = helper;
ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
- goto err1;
+ goto err_helper;
nla_strscpy(helper->name,
tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
if (size > sizeof_field(struct nf_conn_help, data)) {
ret = -ENOMEM;
- goto err2;
+ goto err_helper;
}
helper->data_len = size;
@@ -273,15 +272,15 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
}
}
- ret = nf_conntrack_helper_register(helper);
+ ret = __nf_conntrack_helper_register(helper);
if (ret < 0)
- goto err2;
+ goto err_helper;
list_add_tail(&nfcth->list, &nfnl_cthelper_list);
return 0;
-err2:
- kfree(helper->expect_policy);
-err1:
+err_helper:
+ kfree(helper);
+err_cth:
kfree(nfcth);
return ret;
}
@@ -439,7 +438,7 @@ static int nfnl_cthelper_new(struct sk_buff *skb, const struct nfnl_info *info,
return ret;
list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
- cur = &nlcth->helper;
+ cur = nlcth->helper;
if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
continue;
@@ -650,7 +649,7 @@ static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info,
}
list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
- cur = &nlcth->helper;
+ cur = nlcth->helper;
if (helper_name &&
strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
continue;
@@ -708,7 +707,7 @@ static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info,
ret = -ENOENT;
list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
- cur = &nlcth->helper;
+ cur = nlcth->helper;
j++;
if (helper_name &&
@@ -723,7 +722,6 @@ static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info,
if (refcount_dec_if_one(&cur->refcnt)) {
found = true;
nf_conntrack_helper_unregister(cur);
- kfree(cur->expect_policy);
list_del(&nlcth->list);
kfree(nlcth);
@@ -796,10 +794,9 @@ static void __exit nfnl_cthelper_exit(void)
nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
- cur = &nlcth->helper;
+ cur = nlcth->helper;
nf_conntrack_helper_unregister(cur);
- kfree(cur->expect_policy);
kfree(nlcth);
}
}
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 10/15] netfilter: nf_conntrack_pptp: move GRE specific cleanup to GRE tracker
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (8 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 09/15] netfilter: nf_conntrack_helper: dynamically allocate struct nf_conntrack_helper Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 11/15] netfilter: nf_conntrack_helper: add refcounting from datapath Pablo Neira Ayuso
` (4 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
Move the GRE specific cleanup to nf_conntrack_proto_gre.c to ensure that
the .destroy callback for the pptp helper is still reachable by existing
conntrack entries while pptp module is being removed.
This is a preparation patch, no functional changes are intended.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../net/netfilter/ipv4/nf_conntrack_ipv4.h | 4 ++
net/netfilter/nf_conntrack_pptp.c | 63 +------------------
net/netfilter/nf_conntrack_proto_gre.c | 61 ++++++++++++++++++
3 files changed, 67 insertions(+), 61 deletions(-)
diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index b39417ad955e..0b07d5e69c15 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -20,4 +20,8 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp;
extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre;
#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_PPTP)
+void gre_pptp_destroy_siblings(struct nf_conn *ct);
+#endif
+
#endif /*_NF_CONNTRACK_IPV4_H*/
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index edc85a3eef1e..ed567a1cf7fd 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -124,65 +124,6 @@ static void pptp_expectfn(struct nf_conn *ct,
}
}
-static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
- const struct nf_conntrack_tuple *t)
-{
- const struct nf_conntrack_tuple_hash *h;
- const struct nf_conntrack_zone *zone;
- struct nf_conntrack_expect *exp;
- struct nf_conn *sibling;
-
- pr_debug("trying to timeout ct or exp for tuple ");
- nf_ct_dump_tuple(t);
-
- zone = nf_ct_zone(ct);
- h = nf_conntrack_find_get(net, zone, t);
- if (h) {
- sibling = nf_ct_tuplehash_to_ctrack(h);
- pr_debug("setting timeout of conntrack %p to 0\n", sibling);
- sibling->proto.gre.timeout = 0;
- sibling->proto.gre.stream_timeout = 0;
- nf_ct_kill(sibling);
- nf_ct_put(sibling);
- return 1;
- } else {
- exp = nf_ct_expect_find_get(net, zone, t);
- if (exp) {
- pr_debug("unexpect_related of expect %p\n", exp);
- nf_ct_unexpect_related(exp);
- nf_ct_expect_put(exp);
- return 1;
- }
- }
- return 0;
-}
-
-/* timeout GRE data connections */
-static void pptp_destroy_siblings(struct nf_conn *ct)
-{
- struct net *net = nf_ct_net(ct);
- const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
- struct nf_conntrack_tuple t;
-
- nf_ct_gre_keymap_destroy(ct);
-
- /* try original (pns->pac) tuple */
- memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t));
- t.dst.protonum = IPPROTO_GRE;
- t.src.u.gre.key = ct_pptp_info->pns_call_id;
- t.dst.u.gre.key = ct_pptp_info->pac_call_id;
- if (!destroy_sibling_or_exp(net, ct, &t))
- pr_debug("failed to timeout original pns->pac ct/exp\n");
-
- /* try reply (pac->pns) tuple */
- memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t));
- t.dst.protonum = IPPROTO_GRE;
- t.src.u.gre.key = ct_pptp_info->pac_call_id;
- t.dst.u.gre.key = ct_pptp_info->pns_call_id;
- if (!destroy_sibling_or_exp(net, ct, &t))
- pr_debug("failed to timeout reply pac->pns ct/exp\n");
-}
-
/* expect GRE connections (PNS->PAC and PAC->PNS direction) */
static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
{
@@ -343,7 +284,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
info->cstate = PPTP_CALL_NONE;
/* untrack this call id, unexpect GRE packets */
- pptp_destroy_siblings(ct);
+ gre_pptp_destroy_siblings(ct);
break;
case PPTP_WAN_ERROR_NOTIFY:
@@ -593,7 +534,7 @@ static int __init nf_conntrack_pptp_init(void)
"pptp", PPTP_CONTROL_PORT, PPTP_CONTROL_PORT, PPTP_CONTROL_PORT,
&pptp_exp_policy, 0, conntrack_pptp_help, NULL, THIS_MODULE);
- pptp.destroy = pptp_destroy_siblings;
+ pptp.destroy = gre_pptp_destroy_siblings;
return nf_conntrack_helper_register(&pptp, &pptp_ptr);
}
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 35e22082d65a..473658259f1a 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -349,6 +349,67 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = {
};
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_PPTP)
+static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
+ const struct nf_conntrack_tuple *t)
+{
+ const struct nf_conntrack_tuple_hash *h;
+ const struct nf_conntrack_zone *zone;
+ struct nf_conntrack_expect *exp;
+ struct nf_conn *sibling;
+
+ pr_debug("trying to timeout ct or exp for tuple ");
+ nf_ct_dump_tuple(t);
+
+ zone = nf_ct_zone(ct);
+ h = nf_conntrack_find_get(net, zone, t);
+ if (h) {
+ sibling = nf_ct_tuplehash_to_ctrack(h);
+ pr_debug("setting timeout of conntrack %p to 0\n", sibling);
+ sibling->proto.gre.timeout = 0;
+ sibling->proto.gre.stream_timeout = 0;
+ nf_ct_kill(sibling);
+ nf_ct_put(sibling);
+ return 1;
+ } else {
+ exp = nf_ct_expect_find_get(net, zone, t);
+ if (exp) {
+ pr_debug("unexpect_related of expect %p\n", exp);
+ nf_ct_unexpect_related(exp);
+ nf_ct_expect_put(exp);
+ return 1;
+ }
+ }
+ return 0;
+}
+
+void gre_pptp_destroy_siblings(struct nf_conn *ct)
+{
+ struct net *net = nf_ct_net(ct);
+ const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
+ struct nf_conntrack_tuple t;
+
+ nf_ct_gre_keymap_destroy(ct);
+
+ /* try original (pns->pac) tuple */
+ memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t));
+ t.dst.protonum = IPPROTO_GRE;
+ t.src.u.gre.key = ct_pptp_info->pns_call_id;
+ t.dst.u.gre.key = ct_pptp_info->pac_call_id;
+ if (!destroy_sibling_or_exp(net, ct, &t))
+ pr_debug("failed to timeout original pns->pac ct/exp\n");
+
+ /* try reply (pac->pns) tuple */
+ memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t));
+ t.dst.protonum = IPPROTO_GRE;
+ t.src.u.gre.key = ct_pptp_info->pac_call_id;
+ t.dst.u.gre.key = ct_pptp_info->pns_call_id;
+ if (!destroy_sibling_or_exp(net, ct, &t))
+ pr_debug("failed to timeout reply pac->pns ct/exp\n");
+}
+EXPORT_SYMBOL_GPL(gre_pptp_destroy_siblings);
+#endif
+
void nf_conntrack_gre_init_net(struct net *net)
{
struct nf_gre_net *net_gre = gre_pernet(net);
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 11/15] netfilter: nf_conntrack_helper: add refcounting from datapath
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (9 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 10/15] netfilter: nf_conntrack_pptp: move GRE specific cleanup to GRE tracker Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 12/15] netfilter: conntrack: revert ct extension genid infrastructure Pablo Neira Ayuso
` (3 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
This patch adds a new ->ct_refcnt field to struct nf_conntrack_helper
which is bumped when the helper is used by the ct helper extension. Drop
this reference count when the conntrack entry is released. This is a
packet path refcount which ensures that struct nf_conntrack_helper
remains in place for tricky scenarios where a packet sits in nfqueue, or
elsewhere, with a conntrack that refers to this helper.
For simplicity, this leaves a single refcount for helper objects in
place, remove the existing refcount for control plane that ensures that
the helper does not go away if it is used by ruleset.
On helper removal, the help callback is set to NULL to disable it from
packet path and, after rcu grace period, existing expectations are
removed. Update ctnetlink to disable access to .to_nlattr and
.from_nlattr if the helper is going away.
Remove nf_queue_nf_hook_drop() since it has proven not to be effective
because packets with unconfirmed conntracks which are still flying to
sit in nfqueue.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_helper.h | 26 +++++++++--
net/netfilter/nf_conntrack_core.c | 3 +-
net/netfilter/nf_conntrack_helper.c | 52 ++++++++++-----------
net/netfilter/nf_conntrack_netlink.c | 28 +++++++----
net/netfilter/nf_conntrack_ovs.c | 9 +++-
net/netfilter/nf_conntrack_proto.c | 15 ++++--
net/netfilter/nfnetlink_cthelper.c | 14 ++----
net/netfilter/nft_ct.c | 3 +-
net/netfilter/xt_CT.c | 3 --
9 files changed, 89 insertions(+), 64 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 1956bc12bf56..ed93a5a1adc8 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -35,20 +35,22 @@ enum nf_ct_helper_flags {
struct nf_conntrack_helper {
struct hlist_node hnode; /* Internal use. */
+ struct rcu_head rcu;
+
char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */
- refcount_t refcnt;
struct module *me; /* pointer to self */
struct nf_conntrack_expect_policy expect_policy[NF_CT_MAX_EXPECT_CLASSES];
+ refcount_t ct_refcnt;
+
/* Tuple of things we will help (compared against server response) */
struct nf_conntrack_tuple tuple;
/* Function to call when data passes; return verdict, or -1 to
invalidate. */
- int (*help)(struct sk_buff *skb,
- unsigned int protoff,
- struct nf_conn *ct,
- enum ip_conntrack_info conntrackinfo);
+ int __rcu (*help)(struct sk_buff *skb, unsigned int protoff,
+ struct nf_conn *ct,
+ enum ip_conntrack_info conntrackinfo);
void (*destroy)(struct nf_conn *ct);
@@ -138,6 +140,20 @@ static inline void *nfct_help_data(const struct nf_conn *ct)
return (void *)help->data;
}
+static inline void nf_ct_help_put(const struct nf_conn *ct)
+{
+ struct nf_conntrack_helper *helper;
+ struct nf_conn_help *help;
+
+ help = nfct_help(ct);
+ if (!help)
+ return;
+
+ helper = rcu_dereference(help->helper);
+ if (helper && refcount_dec_and_test(&helper->ct_refcnt))
+ kfree_rcu(helper, rcu);
+}
+
int nf_conntrack_helper_init(void);
void nf_conntrack_helper_fini(void);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index a45b73239369..7c135fe3dd03 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1746,6 +1746,7 @@ void nf_conntrack_free(struct nf_conn *ct)
nat_hook->remove_nat_bysrc(ct);
}
+ nf_ct_help_put(ct);
nf_ct_timeout_put(ct);
rcu_read_unlock();
@@ -1829,7 +1830,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
assign_helper = rcu_dereference(exp->assign_helper);
if (assign_helper) {
help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
- if (help)
+ if (help && refcount_inc_not_zero(&assign_helper->ct_refcnt))
rcu_assign_pointer(help->helper, assign_helper);
}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index ce2d59331dfb..83dfdb06bfdd 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -92,7 +92,7 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum)
#endif
if (h != NULL && !try_module_get(h->me))
h = NULL;
- if (h != NULL && !refcount_inc_not_zero(&h->refcnt)) {
+ if (h != NULL && !refcount_inc_not_zero(&h->ct_refcnt)) {
module_put(h->me);
h = NULL;
}
@@ -105,8 +105,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
void nf_conntrack_helper_put(struct nf_conntrack_helper *helper)
{
- refcount_dec(&helper->refcnt);
module_put(helper->me);
+ if (refcount_dec_and_test(&helper->ct_refcnt))
+ kfree_rcu(helper, rcu);
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_put);
@@ -210,8 +211,13 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
help = nfct_help(ct);
if (helper == NULL) {
- if (help)
+ if (help) {
+ struct nf_conntrack_helper *tmp = rcu_dereference(help->helper);
+
RCU_INIT_POINTER(help->helper, NULL);
+ if (tmp && refcount_dec_and_test(&tmp->ct_refcnt))
+ kfree_rcu(tmp, rcu);
+ }
return 0;
}
@@ -225,32 +231,23 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
*/
struct nf_conntrack_helper *tmp = rcu_dereference(help->helper);
- if (tmp && tmp->help != helper->help) {
- RCU_INIT_POINTER(help->helper, NULL);
+ if (tmp) {
+ if (tmp->help != helper->help) {
+ RCU_INIT_POINTER(help->helper, NULL);
+ if (refcount_dec_and_test(&tmp->ct_refcnt))
+ kfree_rcu(tmp, rcu);
+ }
return 0;
}
}
- rcu_assign_pointer(help->helper, helper);
+ if (refcount_inc_not_zero(&helper->ct_refcnt))
+ rcu_assign_pointer(help->helper, helper);
return 0;
}
EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper);
-/* appropriate ct lock protecting must be taken by caller */
-static int unhelp(struct nf_conn *ct, void *me)
-{
- struct nf_conn_help *help = nfct_help(ct);
-
- if (help && rcu_dereference_raw(help->helper) == me) {
- nf_conntrack_event(IPCT_HELPER, ct);
- RCU_INIT_POINTER(help->helper, NULL);
- }
-
- /* We are not intended to delete this conntrack. */
- return 0;
-}
-
void nf_ct_helper_destroy(struct nf_conn *ct)
{
struct nf_conn_help *help = nfct_help(ct);
@@ -386,7 +383,7 @@ int __nf_conntrack_helper_register(struct nf_conntrack_helper *me)
}
}
}
- refcount_set(&me->refcnt, 1);
+ refcount_set(&me->ct_refcnt, 1);
hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
nf_ct_helper_count++;
out:
@@ -444,19 +441,18 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
nf_ct_helper_count--;
mutex_unlock(&nf_ct_helper_mutex);
+ /* This helper is going away, disable it. */
+ rcu_assign_pointer(me->help, NULL);
+
/* Make sure every nothing is still using the helper unless its a
* connection in the hash.
*/
synchronize_rcu();
nf_ct_expect_iterate_destroy(expect_iter_me, me);
- nf_ct_iterate_destroy(unhelp, me);
- /* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as
- * last step, this ensures rcu readers of exp->helper are done.
- * No need for another synchronize_rcu() here.
- */
- kfree(me);
+ if (refcount_dec_and_test(&me->ct_refcnt))
+ kfree_rcu(me, rcu);
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
@@ -478,7 +474,7 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
helper->tuple.dst.protonum = protonum;
helper->tuple.src.u.all = htons(spec_port);
- helper->help = help;
+ rcu_assign_pointer(helper->help, help);
helper->from_nlattr = from_nlattr;
helper->me = module;
snprintf(helper->nat_mod_name, sizeof(helper->nat_mod_name),
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d429f9c9546c..b429e648f06c 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -240,7 +240,8 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb,
if (nla_put_string(skb, CTA_HELP_NAME, helper->name))
goto nla_put_failure;
- if (helper->to_nlattr)
+ if (rcu_access_pointer(helper->help) &&
+ helper->to_nlattr)
helper->to_nlattr(skb, ct);
nla_nest_end(skb, nest_helper);
@@ -1935,6 +1936,7 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
if (err < 0)
return err;
+ rcu_read_lock();
/* don't change helper of sibling connections */
if (ct->master) {
/* If we try to change the helper to the same thing twice,
@@ -1943,27 +1945,27 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
*/
err = -EBUSY;
if (help) {
- rcu_read_lock();
helper = rcu_dereference(help->helper);
if (helper && !strcmp(helper->name, helpname))
err = 0;
- rcu_read_unlock();
}
-
+ rcu_read_unlock();
return err;
}
- if (!strcmp(helpname, "")) {
- if (help && help->helper) {
+ if (!strcmp(helpname, "") && help) {
+ helper = rcu_dereference(help->helper);
+ if (helper) {
/* we had a helper before ... */
nf_ct_remove_expectations(ct);
RCU_INIT_POINTER(help->helper, NULL);
+ if (refcount_dec_and_test(&helper->ct_refcnt))
+ kfree_rcu(helper, rcu);
}
-
+ rcu_read_unlock();
return 0;
}
- rcu_read_lock();
helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
nf_ct_protonum(ct));
if (helper == NULL) {
@@ -1974,7 +1976,8 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
if (help) {
if (rcu_access_pointer(help->helper) == helper) {
/* update private helper data if allowed. */
- if (helper->from_nlattr)
+ if (rcu_access_pointer(helper->help) &&
+ helper->from_nlattr)
helper->from_nlattr(helpinfo, ct);
err = 0;
} else
@@ -2289,11 +2292,16 @@ ctnetlink_create_conntrack(struct net *net,
goto err2;
}
/* set private helper data if allowed. */
- if (helper->from_nlattr)
+ if (rcu_access_pointer(helper->help) &&
+ helper->from_nlattr)
helper->from_nlattr(helpinfo, ct);
/* disable helper auto-assignment for this entry */
ct->status |= IPS_HELPER;
+ if (!refcount_inc_not_zero(&helper->ct_refcnt)) {
+ err = -ENOENT;
+ goto err2;
+ }
RCU_INIT_POINTER(help->helper, helper);
}
}
diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c
index a6988eeb1579..49d1511e9921 100644
--- a/net/netfilter/nf_conntrack_ovs.c
+++ b/net/netfilter/nf_conntrack_ovs.c
@@ -12,6 +12,9 @@
int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo, u16 proto)
{
+ int (*helper_cb)(struct sk_buff *skb, unsigned int protoff,
+ struct nf_conn *ct,
+ enum ip_conntrack_info conntrackinfo);
const struct nf_conntrack_helper *helper;
const struct nf_conn_help *help;
unsigned int protoff;
@@ -60,7 +63,11 @@ int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct,
if (helper->tuple.dst.protonum != proto)
return NF_ACCEPT;
- err = helper->help(skb, protoff, ct, ctinfo);
+ helper_cb = rcu_dereference(helper->help);
+ if (!helper_cb)
+ return NF_ACCEPT;
+
+ err = helper_cb(skb, protoff, ct, ctinfo);
if (err != NF_ACCEPT)
return err;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 50ddd3d613e1..ad96896516b6 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -129,6 +129,9 @@ unsigned int nf_confirm(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
+ int (*helper_cb)(struct sk_buff *skb, unsigned int protoff,
+ struct nf_conn *ct,
+ enum ip_conntrack_info conntrackinfo);
const struct nf_conn_help *help;
enum ip_conntrack_info ctinfo;
unsigned int protoff;
@@ -175,11 +178,13 @@ unsigned int nf_confirm(void *priv,
/* rcu_read_lock()ed by nf_hook */
helper = rcu_dereference(help->helper);
if (helper) {
- ret = helper->help(skb,
- protoff,
- ct, ctinfo);
- if (ret != NF_ACCEPT)
- return ret;
+ helper_cb = rcu_dereference(helper->help);
+ if (helper_cb) {
+ ret = helper_cb(skb, protoff,
+ ct, ctinfo);
+ if (ret != NF_ACCEPT)
+ return ret;
+ }
}
}
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 338515697c91..033ea90c4401 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -719,15 +719,11 @@ static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info,
tuple.dst.protonum != cur->tuple.dst.protonum))
continue;
- if (refcount_dec_if_one(&cur->refcnt)) {
- found = true;
- nf_conntrack_helper_unregister(cur);
-
- list_del(&nlcth->list);
- kfree(nlcth);
- } else {
- ret = -EBUSY;
- }
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+
+ list_del(&nlcth->list);
+ kfree(nlcth);
}
/* Make sure we return success if we flush and there is no helpers */
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 801c01c6af95..9fe179d688da 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1101,7 +1101,6 @@ static void nft_ct_helper_obj_destroy(const struct nft_ctx *ctx,
{
struct nft_ct_helper_obj *priv = nft_obj_data(obj);
- nf_queue_nf_hook_drop(ctx->net);
if (priv->helper4)
nf_conntrack_helper_put(priv->helper4);
if (priv->helper6)
@@ -1144,7 +1143,7 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj,
return;
help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
- if (help) {
+ if (help && refcount_inc_not_zero(&to_assign->ct_refcnt)) {
rcu_assign_pointer(help->helper, to_assign);
set_bit(IPS_HELPER_BIT, &ct->status);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index b94f004d5f5c..e78660dfdf4b 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -284,9 +284,6 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
struct nf_conn_help *help;
if (ct) {
- if (info->helper[0])
- nf_queue_nf_hook_drop(par->net);
-
help = nfct_help(ct);
xt_ct_put_helper(help);
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 12/15] netfilter: conntrack: revert ct extension genid infrastructure
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (10 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 11/15] netfilter: nf_conntrack_helper: add refcounting from datapath Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 13/15] netfilter: conntrack: call nf_ct_gre_keymap_destroy() if master helper is pptp Pablo Neira Ayuso
` (2 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
This infrastructure is not used anymore after moving ct timeout and
helper to use datapath refcount to track object use.
Revert commit c56716c69ce1 ("netfilter: extensions: introduce extension
genid count") this patch disables all ct extensions (leading to NULL)
for unconfirmed conntracks, when this is only targeted at ct helper and
ct timeout. There is also codebase that dereferences the ct extension
without checking for NULL which could lead to crash.
Fixes: c56716c69ce1 ("netfilter: extensions: introduce extension genid count")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_extend.h | 12 ----
net/netfilter/nf_conntrack_core.c | 61 +--------------------
net/netfilter/nf_conntrack_extend.c | 32 +----------
3 files changed, 2 insertions(+), 103 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 0b247248b032..fd5c4dbf72ca 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -38,7 +38,6 @@ enum nf_ct_ext_id {
struct nf_ct_ext {
u8 offset[NF_CT_EXT_NUM];
u8 len;
- unsigned int gen_id;
char data[] __aligned(8);
};
@@ -52,8 +51,6 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
return (ct->ext && __nf_ct_ext_exist(ct->ext, id));
}
-void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id);
-
static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id)
{
struct nf_ct_ext *ext = ct->ext;
@@ -61,19 +58,10 @@ static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id)
if (!ext || !__nf_ct_ext_exist(ext, id))
return NULL;
- if (unlikely(ext->gen_id))
- return __nf_ct_ext_find(ext, id);
-
return (void *)ct->ext + ct->ext->offset[id];
}
/* Add this type, returns pointer to data or NULL. */
void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
-/* ext genid. if ext->id != ext_genid, extensions cannot be used
- * anymore unless conntrack has CONFIRMED bit set.
- */
-extern atomic_t nf_conntrack_ext_genid;
-void nf_ct_ext_bump_genid(void);
-
#endif /* _NF_CONNTRACK_EXTEND_H */
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7c135fe3dd03..91255fd3b35d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -840,33 +840,6 @@ 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)
{
@@ -882,9 +855,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
zone = nf_ct_zone(ct);
- if (!nf_ct_ext_valid_pre(ct->ext))
- return -EAGAIN;
-
local_bh_disable();
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
@@ -918,18 +888,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
goto chaintoolong;
}
- /* If genid has changed, we can't insert anymore because ct
- * extensions could have stale pointers and nf_ct_iterate_destroy
- * might have completed its table scan already.
- *
- * Increment of the ext genid right after this check is fine:
- * nf_ct_iterate_destroy blocks until locks are released.
- */
- if (!nf_ct_ext_valid_post(ct->ext)) {
- err = -EAGAIN;
- goto out;
- }
-
smp_wmb();
/* The caller holds a reference to this object */
refcount_set(&ct->ct_general.use, 2);
@@ -1257,11 +1215,6 @@ __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;
- }
-
/* We have to check the DYING flag after unlink to prevent
* a race against nf_ct_get_next_corpse() possibly called from
* user context, else we insert an already 'dead' hash, blocking
@@ -1324,16 +1277,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
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_ATOMIC(net, drop);
- return NF_DROP;
- }
-
help = nfct_help(ct);
if (help && help->helper)
nf_conntrack_event_cache(IPCT_HELPER, ct);
@@ -2441,13 +2384,11 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
*/
synchronize_net();
- nf_ct_ext_bump_genid();
iter_data.data = data;
nf_ct_iterate_cleanup(iter, &iter_data);
/* Another cpu might be in a rcu read section with
- * rcu protected pointer cleared in iter callback
- * or hidden via nf_ct_ext_bump_genid() above.
+ * rcu protected pointer cleared in iter callback.
*
* Wait until those are done.
*/
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index dd62cc12e775..0da105e1ded9 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -27,8 +27,6 @@
#define NF_CT_EXT_PREALLOC 128u /* conntrack events are on by default */
-atomic_t nf_conntrack_ext_genid __read_mostly = ATOMIC_INIT(1);
-
static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = {
[NF_CT_EXT_HELPER] = sizeof(struct nf_conn_help),
#if IS_ENABLED(CONFIG_NF_NAT)
@@ -118,10 +116,8 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
if (!new)
return NULL;
- if (!ct->ext) {
+ if (!ct->ext)
memset(new->offset, 0, sizeof(new->offset));
- new->gen_id = atomic_read(&nf_conntrack_ext_genid);
- }
new->offset[id] = newoff;
new->len = newlen;
@@ -131,29 +127,3 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
return (void *)new + newoff;
}
EXPORT_SYMBOL(nf_ct_ext_add);
-
-/* Use nf_ct_ext_find wrapper. This is only useful for unconfirmed entries. */
-void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id)
-{
- unsigned int gen_id = atomic_read(&nf_conntrack_ext_genid);
- unsigned int this_id = READ_ONCE(ext->gen_id);
-
- if (!__nf_ct_ext_exist(ext, id))
- return NULL;
-
- if (this_id == 0 || ext->gen_id == gen_id)
- return (void *)ext + ext->offset[id];
-
- return NULL;
-}
-EXPORT_SYMBOL(__nf_ct_ext_find);
-
-void nf_ct_ext_bump_genid(void)
-{
- unsigned int value = atomic_inc_return(&nf_conntrack_ext_genid);
-
- if (value == UINT_MAX)
- atomic_set(&nf_conntrack_ext_genid, 1);
-
- msleep(HZ);
-}
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 13/15] netfilter: conntrack: call nf_ct_gre_keymap_destroy() if master helper is pptp
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (11 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 12/15] netfilter: conntrack: revert ct extension genid infrastructure Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 14/15] netfilter: flowtable: avoid num_encaps underflow on bridge VLAN untag Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 15/15] netfilter: nf_conntrack: use get_unaligned_be32() in tcp_sack() Pablo Neira Ayuso
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
For GRE flows, validate that the ct master helper (if any) is pptp
before calling nf_ct_gre_keymap_destroy(), so the helper data area
can be accessed safely. Note that only the pptp helper provides a
.destroy callback.
Fixes: e56894356f60 ("netfilter: conntrack: remove l4proto destroy hook")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 91255fd3b35d..4fb3a2d18631 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -562,9 +562,23 @@ static void destroy_gre_conntrack(struct nf_conn *ct)
{
#ifdef CONFIG_NF_CT_PROTO_GRE
struct nf_conn *master = ct->master;
+ struct nf_conn_help *help;
+
+ if (!master)
+ return;
+
+ help = nfct_help(master);
+ if (help) {
+ struct nf_conntrack_helper *helper;
- if (master)
- nf_ct_gre_keymap_destroy(master);
+ rcu_read_lock();
+ helper = rcu_dereference(help->helper);
+ /* Only pptp helper has a destroy callback. */
+ if (helper && helper->destroy)
+ nf_ct_gre_keymap_destroy(master);
+
+ rcu_read_unlock();
+ }
#endif
}
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 14/15] netfilter: flowtable: avoid num_encaps underflow on bridge VLAN untag
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (12 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 13/15] netfilter: conntrack: call nf_ct_gre_keymap_destroy() if master helper is pptp Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
2026-06-07 9:49 ` [PATCH net-next 15/15] netfilter: nf_conntrack: use get_unaligned_be32() in tcp_sack() Pablo Neira Ayuso
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: David Carlier <devnexen@gmail.com>
The DEV_PATH_BR_VLAN_UNTAG case post-decrements info->num_encaps
inside WARN_ON_ONCE(). num_encaps is u8, so if it's already 0 the
decrement still happens and wraps it to 255. The break only leaves
the inner switch -- a later path entry can set info->indev back to
a real device, and we end up returning with num_encaps == 255.
nft_dev_forward_path() then walks info.encap[] (size 2) up to
num_encaps, which means an OOB stack read and a bogus count copied
into the route descriptor.
Should only happen on a malformed bridge path stack, hence the WARN,
but worth handling sanely. Move the decrement out of the WARN.
[ While at this, remove the WARN_ON_ONCE since this can only happen
with a buggy bridge path stack --pablo ].
Fixes: e990cef6516d ("netfilter: flowtable: add bridge vlan filtering support")
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_path.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c
index 9e88ea6a2eef..a3e6b82f2f8e 100644
--- a/net/netfilter/nf_flow_table_path.c
+++ b/net/netfilter/nf_flow_table_path.c
@@ -163,10 +163,11 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
info->num_encaps++;
break;
case DEV_PATH_BR_VLAN_UNTAG:
- if (WARN_ON_ONCE(info->num_encaps-- == 0)) {
+ if (info->num_encaps == 0) {
info->indev = NULL;
break;
}
+ info->num_encaps--;
break;
case DEV_PATH_BR_VLAN_KEEP:
break;
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH net-next 15/15] netfilter: nf_conntrack: use get_unaligned_be32() in tcp_sack()
2026-06-07 9:49 [PATCH net-next 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
` (13 preceding siblings ...)
2026-06-07 9:49 ` [PATCH net-next 14/15] netfilter: flowtable: avoid num_encaps underflow on bridge VLAN untag Pablo Neira Ayuso
@ 2026-06-07 9:49 ` Pablo Neira Ayuso
14 siblings, 0 replies; 16+ messages in thread
From: Pablo Neira Ayuso @ 2026-06-07 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev, kuba, pabeni, edumazet, fw, horms
From: Rosen Penev <rosenp@gmail.com>
The timestamp-only fast path dereferences the option stream as
*(__be32 *)ptr, which assumes 4-byte alignment that the TCP option
stream does not guarantee. Use get_unaligned_be32() instead, which
reads the value safely and already returns host byte order, so the
htonl() on the comparison constant can be dropped.
This matches the existing get_unaligned_be32() use later in the same
function.
Assisted-by: Claude:Opus-4.7
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_proto_tcp.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 027d69edba44..ceeed3d7fe52 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -405,11 +405,11 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
return;
/* Fast path for timestamp-only option */
- if (length == TCPOLEN_TSTAMP_ALIGNED
- && *(__be32 *)ptr == htonl((TCPOPT_NOP << 24)
- | (TCPOPT_NOP << 16)
- | (TCPOPT_TIMESTAMP << 8)
- | TCPOLEN_TIMESTAMP))
+ if (length == TCPOLEN_TSTAMP_ALIGNED &&
+ get_unaligned_be32(ptr) == ((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP))
return;
while (length > 0) {
--
2.47.3
^ permalink raw reply related [flat|nested] 16+ messages in thread