From aa5840167780a315f8a050b77f41acb852465e2d Mon Sep 17 00:00:00 2001
From: lvxiafei <lvxiafei@sensetime.com>
Date: Thu, 22 May 2025 17:19:54 +0800
Subject: netfilter: conntrack: table full detailed log

Add the netns field in the "nf_conntrack: table full, dropping packet"
log to help locate the specific netns when the table is full.

Signed-off-by: lvxiafei <lvxiafei@sensetime.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 2a90945aef89..fbd901b3b7ce 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1673,7 +1673,11 @@ __nf_conntrack_alloc(struct net *net,
 			if (!conntrack_gc_work.early_drop)
 				conntrack_gc_work.early_drop = true;
 			atomic_dec(&cnet->count);
-			net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
+			if (net == &init_net)
+				net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
+			else
+				net_warn_ratelimited("nf_conntrack: table full in netns %u, dropping packet\n",
+						     net->ns.inum);
 			return ERR_PTR(-ENOMEM);
 		}
 	}
-- 
cgit v1.2.3


From e89a68046687fe9913ce3bfad82f7ccbb65687e0 Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Mon, 26 May 2025 16:59:02 +0800
Subject: netfilter: load nf_log_syslog on enabling nf_conntrack_log_invalid

When no logger is registered, nf_conntrack_log_invalid fails to log invalid
packets, leaving users unaware of actual invalid traffic. Improve this by
loading nf_log_syslog, similar to how 'iptables -I FORWARD 1 -m conntrack
--ctstate INVALID -j LOG' triggers it.

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Zi Li <zi.li@linux.dev>
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_log.h          |  3 +++
 net/netfilter/nf_conntrack_standalone.c | 26 +++++++++++++++++++++++++-
 net/netfilter/nf_log.c                  | 26 ++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 1 deletion(-)

(limited to 'net')

diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index e55eedc84ed7..00506792a06d 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -59,6 +59,9 @@ extern int sysctl_nf_log_all_netns;
 int nf_log_register(u_int8_t pf, struct nf_logger *logger);
 void nf_log_unregister(struct nf_logger *logger);
 
+/* Check if any logger is registered for a given protocol family. */
+bool nf_log_is_registered(u_int8_t pf);
+
 int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger);
 void nf_log_unset(struct net *net, const struct nf_logger *logger);
 
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 829f60496008..9b8b10a85233 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -14,6 +14,7 @@
 #include <linux/sysctl.h>
 #endif
 
+#include <net/netfilter/nf_log.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
@@ -555,6 +556,29 @@ nf_conntrack_hash_sysctl(const struct ctl_table *table, int write,
 	return ret;
 }
 
+static int
+nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret, i;
+
+	ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos);
+	if (ret < 0 || !write)
+		return ret;
+
+	if (*(u8 *)table->data == 0)
+		return ret;
+
+	/* Load nf_log_syslog only if no logger is currently registered */
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		if (nf_log_is_registered(i))
+			return ret;
+	}
+	request_module("%s", "nf_log_syslog");
+
+	return ret;
+}
+
 static struct ctl_table_header *nf_ct_netfilter_header;
 
 enum nf_ct_sysctl_index {
@@ -651,7 +675,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.data		= &init_net.ct.sysctl_log_invalid,
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
-		.proc_handler	= proc_dou8vec_minmax,
+		.proc_handler	= nf_conntrack_log_invalid_sysctl,
 	},
 	[NF_SYSCTL_CT_EXPECT_MAX] = {
 		.procname	= "nf_conntrack_expect_max",
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 6dd0de33eebd..74cef8bf554c 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -125,6 +125,32 @@ void nf_log_unregister(struct nf_logger *logger)
 }
 EXPORT_SYMBOL(nf_log_unregister);
 
+/**
+ * nf_log_is_registered - Check if any logger is registered for a given
+ * protocol family.
+ *
+ * @pf: Protocol family
+ *
+ * Returns: true if at least one logger is active for @pf, false otherwise.
+ */
+bool nf_log_is_registered(u_int8_t pf)
+{
+	int i;
+
+	if (pf >= NFPROTO_NUMPROTO) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
+
+	for (i = 0; i < NF_LOG_TYPE_MAX; i++) {
+		if (rcu_access_pointer(loggers[pf][i]))
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(nf_log_is_registered);
+
 int nf_log_bind_pf(struct net *net, u_int8_t pf,
 		   const struct nf_logger *logger)
 {
-- 
cgit v1.2.3


From 29f0f4cefc28611f260fe5c305fcfa0568655135 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 28 Jun 2025 18:32:40 +0800
Subject: netfilter: conntrack: Remove unused net in nf_conntrack_double_lock()

Since commit a3efd81205b1 ("netfilter: conntrack: move generation
seqcnt out of netns_ct") this param is unused.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index fbd901b3b7ce..344f88295976 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -136,8 +136,8 @@ static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
 }
 
 /* return true if we need to recompute hashes (in case hash table was resized) */
-static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
-				     unsigned int h2, unsigned int sequence)
+static bool nf_conntrack_double_lock(unsigned int h1, unsigned int h2,
+				     unsigned int sequence)
 {
 	h1 %= CONNTRACK_LOCKS;
 	h2 %= CONNTRACK_LOCKS;
@@ -613,7 +613,7 @@ static void __nf_ct_delete_from_lists(struct nf_conn *ct)
 		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 					   nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
-	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+	} while (nf_conntrack_double_lock(hash, reply_hash, sequence));
 
 	clean_from_lists(ct);
 	nf_conntrack_double_unlock(hash, reply_hash);
@@ -890,7 +890,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 					   nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
-	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+	} while (nf_conntrack_double_lock(hash, reply_hash, sequence));
 
 	max_chainlen = MIN_CHAINLEN + get_random_u32_below(MAX_CHAINLEN);
 
@@ -1234,7 +1234,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 					   nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
-	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+	} while (nf_conntrack_double_lock(hash, reply_hash, sequence));
 
 	/* We're not in hash table, and we refuse to set up related
 	 * connections for unconfirmed conns.  But packet copies and
-- 
cgit v1.2.3


From 9fce66583f06c212e95e4b76dd61d8432ffa56b6 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 30 Jun 2025 17:44:23 +0200
Subject: netfilter: Exclude LEGACY TABLES on PREEMPT_RT.

The seqcount xt_recseq is used to synchronize the replacement of
xt_table::private in xt_replace_table() against all readers such as
ipt_do_table()

To ensure that there is only one writer, the writing side disables
bottom halves. The sequence counter can be acquired recursively. Only the
first invocation modifies the sequence counter (signaling that a writer
is in progress) while the following (recursive) writer does not modify
the counter.
The lack of a proper locking mechanism for the sequence counter can lead
to live lock on PREEMPT_RT if the high prior reader preempts the
writer. Additionally if the per-CPU lock on PREEMPT_RT is removed from
local_bh_disable() then there is no synchronisation for the per-CPU
sequence counter.

The affected code is "just" the legacy netfilter code which is replaced
by "netfilter tables". That code can be disabled without sacrificing
functionality because everything is provided by the newer
implementation. This will only requires the usage of the "-nft" tools
instead of the "-legacy" ones.
The long term plan is to remove the legacy code so lets accelerate the
progress.

Relax dependencies on iptables legacy, replace select with depends on,
this should cause no harm to existing kernel configs and users can still
toggle IP{6}_NF_IPTABLES_LEGACY in any case.
Make EBTABLES_LEGACY, IPTABLES_LEGACY and ARPTABLES depend on
NETFILTER_XTABLES_LEGACY. Hide xt_recseq and its users,
xt_register_table() and xt_percpu_counter_alloc() behind
NETFILTER_XTABLES_LEGACY. Let NETFILTER_XTABLES_LEGACY depend on
!PREEMPT_RT.

This will break selftest expecing the legacy options enabled and will be
addressed in a following patch.

Co-developed-by: Florian Westphal <fw@strlen.de>
Co-developed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/netfilter/Kconfig | 10 +++++-----
 net/ipv4/netfilter/Kconfig   | 24 ++++++++++++------------
 net/ipv6/netfilter/Kconfig   | 19 +++++++++----------
 net/netfilter/Kconfig        | 10 ++++++++++
 net/netfilter/x_tables.c     | 16 +++++++++++-----
 5 files changed, 47 insertions(+), 32 deletions(-)

(limited to 'net')

diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index f16bbbbb9481..60f28e4fb5c0 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -42,8 +42,8 @@ config NF_CONNTRACK_BRIDGE
 # old sockopt interface and eval loop
 config BRIDGE_NF_EBTABLES_LEGACY
 	tristate "Legacy EBTABLES support"
-	depends on BRIDGE && NETFILTER_XTABLES
-	default n
+	depends on BRIDGE && NETFILTER_XTABLES_LEGACY
+	default	n
 	help
 	 Legacy ebtables packet/frame classifier.
 	 This is not needed if you are using ebtables over nftables
@@ -65,7 +65,7 @@ if BRIDGE_NF_EBTABLES
 #
 config BRIDGE_EBT_BROUTE
 	tristate "ebt: broute table support"
-	select BRIDGE_NF_EBTABLES_LEGACY
+	depends on BRIDGE_NF_EBTABLES_LEGACY
 	help
 	  The ebtables broute table is used to define rules that decide between
 	  bridging and routing frames, giving Linux the functionality of a
@@ -76,7 +76,7 @@ config BRIDGE_EBT_BROUTE
 
 config BRIDGE_EBT_T_FILTER
 	tristate "ebt: filter table support"
-	select BRIDGE_NF_EBTABLES_LEGACY
+	depends on BRIDGE_NF_EBTABLES_LEGACY
 	help
 	  The ebtables filter table is used to define frame filtering rules at
 	  local input, forwarding and local output. See the man page for
@@ -86,7 +86,7 @@ config BRIDGE_EBT_T_FILTER
 
 config BRIDGE_EBT_T_NAT
 	tristate "ebt: nat table support"
-	select BRIDGE_NF_EBTABLES_LEGACY
+	depends on BRIDGE_NF_EBTABLES_LEGACY
 	help
 	  The ebtables nat table is used to define rules that alter the MAC
 	  source address (MAC SNAT) or the MAC destination address (MAC DNAT).
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index ef8009281da5..2c438b140e88 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -13,8 +13,8 @@ config NF_DEFRAG_IPV4
 # old sockopt interface and eval loop
 config IP_NF_IPTABLES_LEGACY
 	tristate "Legacy IP tables support"
-	default	n
-	select NETFILTER_XTABLES
+	depends on NETFILTER_XTABLES_LEGACY
+	default	m if NETFILTER_XTABLES_LEGACY
 	help
 	  iptables is a legacy packet classifier.
 	  This is not needed if you are using iptables over nftables
@@ -182,8 +182,8 @@ config IP_NF_MATCH_TTL
 # `filter', generic and specific targets
 config IP_NF_FILTER
 	tristate "Packet filtering"
-	default m if NETFILTER_ADVANCED=n
-	select IP_NF_IPTABLES_LEGACY
+	default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY
+	depends on IP_NF_IPTABLES_LEGACY
 	help
 	  Packet filtering defines a table `filter', which has a series of
 	  rules for simple packet filtering at local input, forwarding and
@@ -220,10 +220,10 @@ config IP_NF_TARGET_SYNPROXY
 config IP_NF_NAT
 	tristate "iptables NAT support"
 	depends on NF_CONNTRACK
+	depends on IP_NF_IPTABLES_LEGACY
 	default m if NETFILTER_ADVANCED=n
 	select NF_NAT
 	select NETFILTER_XT_NAT
-	select IP_NF_IPTABLES_LEGACY
 	help
 	  This enables the `nat' table in iptables. This allows masquerading,
 	  port forwarding and other forms of full Network Address Port
@@ -263,8 +263,8 @@ endif # IP_NF_NAT
 # mangle + specific targets
 config IP_NF_MANGLE
 	tristate "Packet mangling"
-	default m if NETFILTER_ADVANCED=n
-	select IP_NF_IPTABLES_LEGACY
+	default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY
+	depends on IP_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `mangle' table to iptables: see the man page for
 	  iptables(8).  This table is used for various packet alterations
@@ -299,7 +299,7 @@ config IP_NF_TARGET_TTL
 # raw + specific targets
 config IP_NF_RAW
 	tristate  'raw table support (required for NOTRACK/TRACE)'
-	select IP_NF_IPTABLES_LEGACY
+	depends on IP_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `raw' table to iptables. This table is the very
 	  first in the netfilter framework and hooks in at the PREROUTING
@@ -313,7 +313,7 @@ config IP_NF_SECURITY
 	tristate "Security table"
 	depends on SECURITY
 	depends on NETFILTER_ADVANCED
-	select IP_NF_IPTABLES_LEGACY
+	depends on IP_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `security' table to iptables, for use
 	  with Mandatory Access Control (MAC) policy.
@@ -325,8 +325,8 @@ endif # IP_NF_IPTABLES
 # ARP tables
 config IP_NF_ARPTABLES
 	tristate "Legacy ARPTABLES support"
-	depends on NETFILTER_XTABLES
-	default n
+	depends on NETFILTER_XTABLES_LEGACY
+	default	n
 	help
 	  arptables is a legacy packet classifier.
 	  This is not needed if you are using arptables over nftables
@@ -342,7 +342,7 @@ config IP_NF_ARPFILTER
 	tristate "arptables-legacy packet filtering support"
 	select IP_NF_ARPTABLES
 	select NETFILTER_FAMILY_ARP
-	depends on NETFILTER_XTABLES
+	depends on NETFILTER_XTABLES_LEGACY
 	help
 	  ARP packet filtering defines a table `filter', which has a series of
 	  rules for simple ARP packet filtering at local input and
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index e087a8e97ba7..276860f65baa 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -9,9 +9,8 @@ menu "IPv6: Netfilter Configuration"
 # old sockopt interface and eval loop
 config IP6_NF_IPTABLES_LEGACY
 	tristate "Legacy IP6 tables support"
-	depends on INET && IPV6
-	select NETFILTER_XTABLES
-	default n
+	depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY
+	default	m if NETFILTER_XTABLES_LEGACY
 	help
 	  ip6tables is a legacy packet classifier.
 	  This is not needed if you are using iptables over nftables
@@ -196,8 +195,8 @@ config IP6_NF_TARGET_HL
 
 config IP6_NF_FILTER
 	tristate "Packet filtering"
-	default m if NETFILTER_ADVANCED=n
-	select IP6_NF_IPTABLES_LEGACY
+	default m if NETFILTER_ADVANCED=n || IP6_NF_IPTABLES_LEGACY
+	depends on IP6_NF_IPTABLES_LEGACY
 	tristate
 	help
 	  Packet filtering defines a table `filter', which has a series of
@@ -233,8 +232,8 @@ config IP6_NF_TARGET_SYNPROXY
 
 config IP6_NF_MANGLE
 	tristate "Packet mangling"
-	default m if NETFILTER_ADVANCED=n
-	select IP6_NF_IPTABLES_LEGACY
+	default m if NETFILTER_ADVANCED=n || IP6_NF_IPTABLES_LEGACY
+	depends on IP6_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `mangle' table to iptables: see the man page for
 	  iptables(8).  This table is used for various packet alterations
@@ -244,7 +243,7 @@ config IP6_NF_MANGLE
 
 config IP6_NF_RAW
 	tristate  'raw table support (required for TRACE)'
-	select IP6_NF_IPTABLES_LEGACY
+	depends on IP6_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `raw' table to ip6tables. This table is the very
 	  first in the netfilter framework and hooks in at the PREROUTING
@@ -258,7 +257,7 @@ config IP6_NF_SECURITY
 	tristate "Security table"
 	depends on SECURITY
 	depends on NETFILTER_ADVANCED
-	select IP6_NF_IPTABLES_LEGACY
+	depends on IP6_NF_IPTABLES_LEGACY
 	help
 	  This option adds a `security' table to iptables, for use
 	  with Mandatory Access Control (MAC) policy.
@@ -269,8 +268,8 @@ config IP6_NF_NAT
 	tristate "ip6tables NAT support"
 	depends on NF_CONNTRACK
 	depends on NETFILTER_ADVANCED
+	depends on IP6_NF_IPTABLES_LEGACY
 	select NF_NAT
-	select IP6_NF_IPTABLES_LEGACY
 	select NETFILTER_XT_NAT
 	help
 	  This enables the `nat' table in ip6tables. This allows masquerading,
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ba60b48d7567..6cdc994fdc8a 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -758,6 +758,16 @@ config NETFILTER_XTABLES_COMPAT
 
 	   If unsure, say N.
 
+config NETFILTER_XTABLES_LEGACY
+	bool "Netfilter legacy tables support"
+	depends on !PREEMPT_RT
+	help
+	  Say Y here if you still require support for legacy tables. This is
+	  required by the legacy tools (iptables-legacy) and is not needed if
+	  you use iptables over nftables (iptables-nft).
+	  Legacy support is not limited to IP, it also includes EBTABLES and
+	  ARPTABLES.
+
 comment "Xtables combined modules"
 
 config NETFILTER_XT_MARK
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 709840612f0d..90b7630421c4 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1317,12 +1317,13 @@ void xt_compat_unlock(u_int8_t af)
 EXPORT_SYMBOL_GPL(xt_compat_unlock);
 #endif
 
-DEFINE_PER_CPU(seqcount_t, xt_recseq);
-EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq);
-
 struct static_key xt_tee_enabled __read_mostly;
 EXPORT_SYMBOL_GPL(xt_tee_enabled);
 
+#ifdef CONFIG_NETFILTER_XTABLES_LEGACY
+DEFINE_PER_CPU(seqcount_t, xt_recseq);
+EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq);
+
 static int xt_jumpstack_alloc(struct xt_table_info *i)
 {
 	unsigned int size;
@@ -1514,6 +1515,7 @@ void *xt_unregister_table(struct xt_table *table)
 	return private;
 }
 EXPORT_SYMBOL_GPL(xt_unregister_table);
+#endif
 
 #ifdef CONFIG_PROC_FS
 static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
@@ -1897,6 +1899,7 @@ void xt_proto_fini(struct net *net, u_int8_t af)
 }
 EXPORT_SYMBOL_GPL(xt_proto_fini);
 
+#ifdef CONFIG_NETFILTER_XTABLES_LEGACY
 /**
  * xt_percpu_counter_alloc - allocate x_tables rule counter
  *
@@ -1951,6 +1954,7 @@ void xt_percpu_counter_free(struct xt_counters *counters)
 		free_percpu((void __percpu *)pcnt);
 }
 EXPORT_SYMBOL_GPL(xt_percpu_counter_free);
+#endif
 
 static int __net_init xt_net_init(struct net *net)
 {
@@ -1983,8 +1987,10 @@ static int __init xt_init(void)
 	unsigned int i;
 	int rv;
 
-	for_each_possible_cpu(i) {
-		seqcount_init(&per_cpu(xt_recseq, i));
+	if (IS_ENABLED(CONFIG_NETFILTER_XTABLES_LEGACY)) {
+		for_each_possible_cpu(i) {
+			seqcount_init(&per_cpu(xt_recseq, i));
+		}
 	}
 
 	xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL);
-- 
cgit v1.2.3


From bfabc4f70ee72809f1de662e971ac55648981a31 Mon Sep 17 00:00:00 2001
From: WangYuli <wangyuli@uniontech.com>
Date: Fri, 4 Jul 2025 16:35:53 +0800
Subject: ipvs: Rename del_timer in comment in ip_vs_conn_expire_now()

Commit 8fa7292fee5c ("treewide: Switch/rename to timer_delete[_sync]()")
switched del_timer to timer_delete, but did not modify the comment for
ip_vs_conn_expire_now(). Now fix it.

Signed-off-by: WangYuli <wangyuli@uniontech.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_conn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 44b2ad695c15..965f3c8e5089 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -926,7 +926,7 @@ static void ip_vs_conn_expire(struct timer_list *t)
 void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 {
 	/* Using mod_timer_pending will ensure the timer is not
-	 * modified after the final del_timer in ip_vs_conn_expire.
+	 * modified after the final timer_delete in ip_vs_conn_expire.
 	 */
 	if (timer_pending(&cp->timer) &&
 	    time_after(cp->timer.expires, jiffies))
-- 
cgit v1.2.3


From b65504e7cf0a99eb75bbed0d1ef22950c080d84a Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 8 Jul 2025 15:04:01 +0200
Subject: netfilter: nfnetlink: New NFNLA_HOOK_INFO_DESC helper

Introduce a helper routine adding the nested attribute for use by a
second caller later.

Note how this introduces cancelling of 'nest2' for categorical reasons.
Since always followed by cancelling of the outer 'nest', it is
technically not needed.

Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_hook.c | 47 ++++++++++++++++++++++--------------------
 1 file changed, 25 insertions(+), 22 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index ade8ee1988b1..cd4056527ede 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -109,13 +109,30 @@ cancel_nest:
 	return -EMSGSIZE;
 }
 
+static int nfnl_hook_put_nft_info_desc(struct sk_buff *nlskb, const char *tname,
+				       const char *name, u8 family)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC);
+	if (!nest ||
+	    nla_put_string(nlskb, NFNLA_CHAIN_TABLE, tname) ||
+	    nla_put_string(nlskb, NFNLA_CHAIN_NAME, name) ||
+	    nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, family)) {
+		nla_nest_cancel(nlskb, nest);
+		return -EMSGSIZE;
+	}
+	nla_nest_end(nlskb, nest);
+	return 0;
+}
+
 static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
 					const struct nfnl_dump_hook_data *ctx,
 					unsigned int seq,
 					struct nft_chain *chain)
 {
 	struct net *net = sock_net(nlskb->sk);
-	struct nlattr *nest, *nest2;
+	struct nlattr *nest;
 	int ret = 0;
 
 	if (WARN_ON_ONCE(!chain))
@@ -128,29 +145,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
 	if (!nest)
 		return -EMSGSIZE;
 
-	nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC);
-	if (!nest2)
-		goto cancel_nest;
-
-	ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name);
-	if (ret)
-		goto cancel_nest;
-
-	ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name);
-	if (ret)
-		goto cancel_nest;
-
-	ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family);
-	if (ret)
-		goto cancel_nest;
+	ret = nfnl_hook_put_nft_info_desc(nlskb, chain->table->name,
+					  chain->name, chain->table->family);
+	if (ret) {
+		nla_nest_cancel(nlskb, nest);
+		return ret;
+	}
 
-	nla_nest_end(nlskb, nest2);
 	nla_nest_end(nlskb, nest);
-	return ret;
-
-cancel_nest:
-	nla_nest_cancel(nlskb, nest);
-	return -EMSGSIZE;
+	return 0;
 }
 
 static int nfnl_hook_dump_one(struct sk_buff *nlskb,
-- 
cgit v1.2.3


From bc8c43adfdc57c8253884fc1853cb6679cd5953d Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 8 Jul 2025 15:04:02 +0200
Subject: netfilter: nfnetlink_hook: Dump flowtable info

Introduce NFNL_HOOK_TYPE_NFT_FLOWTABLE to distinguish flowtable hooks
from base chain ones. Nested attributes are shared with the old NFTABLES
hook info type since they fit apart from their misleading name.

Old nftables in user space will ignore this new hook type and thus
continue to print flowtable hooks just like before, e.g.:

| family netdev {
| 	hook ingress device test0 {
| 		 0000000000 nf_flow_offload_ip_hook [nf_flow_table]
| 	}
| }

With this patch in place and support for the new hook info type, output
becomes more useful:

| family netdev {
| 	hook ingress device test0 {
| 		 0000000000 flowtable ip mytable myft [nf_flow_table]
| 	}
| }

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                     |  1 +
 include/uapi/linux/netfilter/nfnetlink_hook.h |  2 ++
 net/netfilter/nf_tables_api.c                 | 24 +++++++++---------
 net/netfilter/nfnetlink_hook.c                | 35 +++++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 11 deletions(-)

(limited to 'net')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 5f896fcc074d..efbbfa770d66 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -92,6 +92,7 @@ enum nf_hook_ops_type {
 	NF_HOOK_OP_UNDEFINED,
 	NF_HOOK_OP_NF_TABLES,
 	NF_HOOK_OP_BPF,
+	NF_HOOK_OP_NFT_FT,
 };
 
 struct nf_hook_ops {
diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h
index 84a561a74b98..1a2c4d6424b5 100644
--- a/include/uapi/linux/netfilter/nfnetlink_hook.h
+++ b/include/uapi/linux/netfilter/nfnetlink_hook.h
@@ -61,10 +61,12 @@ enum nfnl_hook_chain_desc_attributes {
  *
  * @NFNL_HOOK_TYPE_NFTABLES: nf_tables base chain
  * @NFNL_HOOK_TYPE_BPF: bpf program
+ * @NFNL_HOOK_TYPE_NFT_FLOWTABLE: nf_tables flowtable
  */
 enum nfnl_hook_chaintype {
 	NFNL_HOOK_TYPE_NFTABLES = 0x1,
 	NFNL_HOOK_TYPE_BPF,
+	NFNL_HOOK_TYPE_NFT_FLOWTABLE,
 };
 
 /**
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 04795af6e586..13d0ed9d1895 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8895,11 +8895,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx,
 
 	list_for_each_entry(hook, &flowtable_hook->list, list) {
 		list_for_each_entry(ops, &hook->ops_list, list) {
-			ops->pf		= NFPROTO_NETDEV;
-			ops->hooknum	= flowtable_hook->num;
-			ops->priority	= flowtable_hook->priority;
-			ops->priv	= &flowtable->data;
-			ops->hook	= flowtable->data.type->hook;
+			ops->pf			= NFPROTO_NETDEV;
+			ops->hooknum		= flowtable_hook->num;
+			ops->priority		= flowtable_hook->priority;
+			ops->priv		= &flowtable->data;
+			ops->hook		= flowtable->data.type->hook;
+			ops->hook_ops_type	= NF_HOOK_OP_NFT_FT;
 		}
 	}
 
@@ -9727,12 +9728,13 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev,
 			if (!ops)
 				return 1;
 
-			ops->pf		= NFPROTO_NETDEV;
-			ops->hooknum	= flowtable->hooknum;
-			ops->priority	= flowtable->data.priority;
-			ops->priv	= &flowtable->data;
-			ops->hook	= flowtable->data.type->hook;
-			ops->dev	= dev;
+			ops->pf			= NFPROTO_NETDEV;
+			ops->hooknum		= flowtable->hooknum;
+			ops->priority		= flowtable->data.priority;
+			ops->priv		= &flowtable->data;
+			ops->hook		= flowtable->data.type->hook;
+			ops->hook_ops_type	= NF_HOOK_OP_NFT_FT;
+			ops->dev		= dev;
 			if (nft_register_flowtable_ops(dev_net(dev),
 						       flowtable, ops)) {
 				kfree(ops);
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index cd4056527ede..92d869317cba 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -156,6 +156,38 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
 	return 0;
 }
 
+static int nfnl_hook_put_nft_ft_info(struct sk_buff *nlskb,
+				     const struct nfnl_dump_hook_data *ctx,
+				     unsigned int seq,
+				     struct nf_flowtable *nf_ft)
+{
+	struct nft_flowtable *ft =
+		container_of(nf_ft, struct nft_flowtable, data);
+	struct net *net = sock_net(nlskb->sk);
+	struct nlattr *nest;
+	int ret = 0;
+
+	if (WARN_ON_ONCE(!nf_ft))
+		return 0;
+
+	if (!nft_is_active(net, ft))
+		return 0;
+
+	nest = nfnl_start_info_type(nlskb, NFNL_HOOK_TYPE_NFT_FLOWTABLE);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = nfnl_hook_put_nft_info_desc(nlskb, ft->table->name,
+					  ft->name, ft->table->family);
+	if (ret) {
+		nla_nest_cancel(nlskb, nest);
+		return ret;
+	}
+
+	nla_nest_end(nlskb, nest);
+	return 0;
+}
+
 static int nfnl_hook_dump_one(struct sk_buff *nlskb,
 			      const struct nfnl_dump_hook_data *ctx,
 			      const struct nf_hook_ops *ops,
@@ -223,6 +255,9 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb,
 	case NF_HOOK_OP_BPF:
 		ret = nfnl_hook_put_bpf_prog_info(nlskb, ctx, seq, ops->priv);
 		break;
+	case NF_HOOK_OP_NFT_FT:
+		ret = nfnl_hook_put_nft_ft_info(nlskb, ctx, seq, ops->priv);
+		break;
 	case NF_HOOK_OP_UNDEFINED:
 		break;
 	default:
-- 
cgit v1.2.3


From 7792c1e03054440c60d4bce0c06a31c134601997 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 9 Jul 2025 19:05:12 +0200
Subject: netfilter: nft_set_pipapo: remove unused arguments

They are not used anymore, so remove them.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index c5855069bdab..08fb6720673f 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -502,8 +502,6 @@ out:
 
 /**
  * pipapo_get() - Get matching element reference given key data
- * @net:	Network namespace
- * @set:	nftables API set representation
  * @m:		storage containing active/existing elements
  * @data:	Key data to be matched against existing elements
  * @genmask:	If set, check that element is active in given genmask
@@ -516,9 +514,7 @@ out:
  *
  * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise.
  */
-static struct nft_pipapo_elem *pipapo_get(const struct net *net,
-					  const struct nft_set *set,
-					  const struct nft_pipapo_match *m,
+static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
 					  const u8 *data, u8 genmask,
 					  u64 tstamp, gfp_t gfp)
 {
@@ -615,7 +611,7 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_match *m = rcu_dereference(priv->match);
 	struct nft_pipapo_elem *e;
 
-	e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data,
+	e = pipapo_get(m, (const u8 *)elem->key.val.data,
 		       nft_genmask_cur(net), get_jiffies_64(),
 		       GFP_ATOMIC);
 	if (IS_ERR(e))
@@ -1345,7 +1341,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(net, set, m, start, genmask, tstamp, GFP_KERNEL);
+	dup = pipapo_get(m, start, genmask, tstamp, GFP_KERNEL);
 	if (!IS_ERR(dup)) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
@@ -1367,7 +1363,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	if (PTR_ERR(dup) == -ENOENT) {
 		/* Look for partially overlapping entries */
-		dup = pipapo_get(net, set, m, end, nft_genmask_next(net), tstamp,
+		dup = pipapo_get(m, end, nft_genmask_next(net), tstamp,
 				 GFP_KERNEL);
 	}
 
@@ -1914,7 +1910,7 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set,
 	if (!m)
 		return NULL;
 
-	e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data,
+	e = pipapo_get(m, (const u8 *)elem->key.val.data,
 		       nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL);
 	if (IS_ERR(e))
 		return NULL;
-- 
cgit v1.2.3


From 17a20e09f086f2c574ac87f3cf6e14c4377f65f6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 9 Jul 2025 19:05:13 +0200
Subject: netfilter: nft_set: remove one argument from lookup and update
 functions

Return the extension pointer instead of passing it as a function
argument to be filled in by the callee.

As-is, whenever false is returned, the extension pointer is not used.

For all set types, when true is returned, the extension pointer was set
to the matching element.

Only exception: nft_set_bitmap doesn't support extensions.
Return a pointer to a static const empty element extension container.

return false -> return NULL
return true -> return the elements' extension pointer.

This saves one function argument.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h      | 10 +++----
 include/net/netfilter/nf_tables_core.h | 47 ++++++++++++++++-------------
 net/netfilter/nft_dynset.c             |  5 ++--
 net/netfilter/nft_lookup.c             | 27 +++++++++--------
 net/netfilter/nft_objref.c             |  5 ++--
 net/netfilter/nft_set_bitmap.c         | 11 +++++--
 net/netfilter/nft_set_hash.c           | 54 +++++++++++++++-------------------
 net/netfilter/nft_set_pipapo.c         | 19 +++++++-----
 net/netfilter/nft_set_pipapo_avx2.c    | 25 +++++++++-------
 net/netfilter/nft_set_rbtree.c         | 40 ++++++++++++-------------
 10 files changed, 126 insertions(+), 117 deletions(-)

(limited to 'net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index b092e57d3c75..5b6725475906 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -459,19 +459,17 @@ struct nft_set_ext;
  *	control plane functions.
  */
 struct nft_set_ops {
-	bool				(*lookup)(const struct net *net,
+	const struct nft_set_ext *	(*lookup)(const struct net *net,
 						  const struct nft_set *set,
-						  const u32 *key,
-						  const struct nft_set_ext **ext);
-	bool				(*update)(struct nft_set *set,
+						  const u32 *key);
+	const struct nft_set_ext *	(*update)(struct nft_set *set,
 						  const u32 *key,
 						  struct nft_elem_priv *
 							(*new)(struct nft_set *,
 							       const struct nft_expr *,
 							       struct nft_regs *),
 						  const struct nft_expr *expr,
-						  struct nft_regs *regs,
-						  const struct nft_set_ext **ext);
+						  struct nft_regs *regs);
 	bool				(*delete)(const struct nft_set *set,
 						  const u32 *key);
 
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 03b6165756fc..6a52fb97b844 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -94,34 +94,41 @@ extern const struct nft_set_type nft_set_pipapo_type;
 extern const struct nft_set_type nft_set_pipapo_avx2_type;
 
 #ifdef CONFIG_MITIGATION_RETPOLINE
-bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
-		      const u32 *key, const struct nft_set_ext **ext);
-bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext);
-bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext);
-bool nft_hash_lookup_fast(const struct net *net,
-			  const struct nft_set *set,
-			  const u32 *key, const struct nft_set_ext **ext);
-bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
-		     const u32 *key, const struct nft_set_ext **ext);
-bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext);
+const struct nft_set_ext *
+nft_rhash_lookup(const struct net *net, const struct nft_set *set,
+		 const u32 *key);
+const struct nft_set_ext *
+nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key);
+const struct nft_set_ext *
+nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key);
+const struct nft_set_ext *
+nft_hash_lookup_fast(const struct net *net, const struct nft_set *set,
+		     const u32 *key);
+const struct nft_set_ext *
+nft_hash_lookup(const struct net *net, const struct nft_set *set,
+		const u32 *key);
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key);
 #else
-static inline bool
+static inline const struct nft_set_ext *
 nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key, const struct nft_set_ext **ext)
+		  const u32 *key)
 {
-	return set->ops->lookup(net, set, key, ext);
+	return set->ops->lookup(net, set, key);
 }
 #endif
 
 /* called from nft_pipapo_avx2.c */
-bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext);
+const struct nft_set_ext *
+nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key);
 /* called from nft_set_pipapo.c */
-bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
-			    const u32 *key, const struct nft_set_ext **ext);
+const struct nft_set_ext *
+nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+			const u32 *key);
 
 void nft_counter_init_seqcount(void);
 
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 88922e0e8e83..e24493d9e776 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -91,8 +91,9 @@ void nft_dynset_eval(const struct nft_expr *expr,
 		return;
 	}
 
-	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
-			     expr, regs, &ext)) {
+	ext = set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
+			     expr, regs);
+	if (ext) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
 		    READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) {
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 63ef832b8aa7..40c602ffbcba 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -25,32 +25,33 @@ struct nft_lookup {
 };
 
 #ifdef CONFIG_MITIGATION_RETPOLINE
-bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	if (set->ops == &nft_set_hash_fast_type.ops)
-		return nft_hash_lookup_fast(net, set, key, ext);
+		return nft_hash_lookup_fast(net, set, key);
 	if (set->ops == &nft_set_hash_type.ops)
-		return nft_hash_lookup(net, set, key, ext);
+		return nft_hash_lookup(net, set, key);
 
 	if (set->ops == &nft_set_rhash_type.ops)
-		return nft_rhash_lookup(net, set, key, ext);
+		return nft_rhash_lookup(net, set, key);
 
 	if (set->ops == &nft_set_bitmap_type.ops)
-		return nft_bitmap_lookup(net, set, key, ext);
+		return nft_bitmap_lookup(net, set, key);
 
 	if (set->ops == &nft_set_pipapo_type.ops)
-		return nft_pipapo_lookup(net, set, key, ext);
+		return nft_pipapo_lookup(net, set, key);
 #if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
 	if (set->ops == &nft_set_pipapo_avx2_type.ops)
-		return nft_pipapo_avx2_lookup(net, set, key, ext);
+		return nft_pipapo_avx2_lookup(net, set, key);
 #endif
 
 	if (set->ops == &nft_set_rbtree_type.ops)
-		return nft_rbtree_lookup(net, set, key, ext);
+		return nft_rbtree_lookup(net, set, key);
 
 	WARN_ON_ONCE(1);
-	return set->ops->lookup(net, set, key, ext);
+	return set->ops->lookup(net, set, key);
 }
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
 #endif
@@ -61,12 +62,12 @@ void nft_lookup_eval(const struct nft_expr *expr,
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
-	const struct nft_set_ext *ext = NULL;
 	const struct net *net = nft_net(pkt);
+	const struct nft_set_ext *ext;
 	bool found;
 
-	found =	nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext) ^
-				  priv->invert;
+	ext = nft_set_do_lookup(net, set, &regs->data[priv->sreg]);
+	found = !!ext ^ priv->invert;
 	if (!found) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 09da7a3f9f96..8ee66a86c3bc 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -111,10 +111,9 @@ void nft_objref_map_eval(const struct nft_expr *expr,
 	struct net *net = nft_net(pkt);
 	const struct nft_set_ext *ext;
 	struct nft_object *obj;
-	bool found;
 
-	found = nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext);
-	if (!found) {
+	ext = nft_set_do_lookup(net, set, &regs->data[priv->sreg]);
+	if (!ext) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {
 			regs->verdict.code = NFT_BREAK;
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 12390d2e994f..c24c922f895d 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -75,16 +75,21 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask)
 }
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	const struct nft_bitmap *priv = nft_set_priv(set);
+	static const struct nft_set_ext found;
 	u8 genmask = nft_genmask_cur(net);
 	u32 idx, off;
 
 	nft_bitmap_location(set, key, &idx, &off);
 
-	return nft_bitmap_active(priv->bitmap, idx, off, genmask);
+	if (nft_bitmap_active(priv->bitmap, idx, off, genmask))
+		return &found;
+
+	return NULL;
 }
 
 static struct nft_bitmap_elem *
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index abb0c8ec6371..9903c737c9f0 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -81,8 +81,9 @@ static const struct rhashtable_params nft_rhash_params = {
 };
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
-		      const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_rhash_lookup(const struct net *net, const struct nft_set *set,
+		 const u32 *key)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
 	const struct nft_rhash_elem *he;
@@ -95,9 +96,9 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
 	if (he != NULL)
-		*ext = &he->ext;
+		return &he->ext;
 
-	return !!he;
+	return NULL;
 }
 
 static struct nft_elem_priv *
@@ -120,14 +121,11 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
 	return ERR_PTR(-ENOENT);
 }
 
-static bool nft_rhash_update(struct nft_set *set, const u32 *key,
-			     struct nft_elem_priv *
-				   (*new)(struct nft_set *,
-					  const struct nft_expr *,
-					  struct nft_regs *regs),
-			     const struct nft_expr *expr,
-			     struct nft_regs *regs,
-			     const struct nft_set_ext **ext)
+static const struct nft_set_ext *
+nft_rhash_update(struct nft_set *set, const u32 *key,
+		 struct nft_elem_priv *(*new)(struct nft_set *, const struct nft_expr *,
+		 struct nft_regs *regs),
+		 const struct nft_expr *expr, struct nft_regs *regs)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
 	struct nft_rhash_elem *he, *prev;
@@ -161,14 +159,13 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 	}
 
 out:
-	*ext = &he->ext;
-	return true;
+	return &he->ext;
 
 err2:
 	nft_set_elem_destroy(set, &he->priv, true);
 	atomic_dec(&set->nelems);
 err1:
-	return false;
+	return NULL;
 }
 
 static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
@@ -507,8 +504,9 @@ struct nft_hash_elem {
 };
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
-		     const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_hash_lookup(const struct net *net, const struct nft_set *set,
+		const u32 *key)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_cur(net);
@@ -519,12 +517,10 @@ bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
 	hash = reciprocal_scale(hash, priv->buckets);
 	hlist_for_each_entry_rcu(he, &priv->table[hash], node) {
 		if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) &&
-		    nft_set_elem_active(&he->ext, genmask)) {
-			*ext = &he->ext;
-			return true;
-		}
+		    nft_set_elem_active(&he->ext, genmask))
+			return &he->ext;
 	}
-	return false;
+	return NULL;
 }
 
 static struct nft_elem_priv *
@@ -547,9 +543,9 @@ nft_hash_get(const struct net *net, const struct nft_set *set,
 }
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_hash_lookup_fast(const struct net *net,
-			  const struct nft_set *set,
-			  const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_hash_lookup_fast(const struct net *net, const struct nft_set *set,
+		     const u32 *key)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_cur(net);
@@ -562,12 +558,10 @@ bool nft_hash_lookup_fast(const struct net *net,
 	hlist_for_each_entry_rcu(he, &priv->table[hash], node) {
 		k2 = *(u32 *)nft_set_ext_key(&he->ext)->data;
 		if (k1 == k2 &&
-		    nft_set_elem_active(&he->ext, genmask)) {
-			*ext = &he->ext;
-			return true;
-		}
+		    nft_set_elem_active(&he->ext, genmask))
+			return &he->ext;
 	}
-	return false;
+	return NULL;
 }
 
 static u32 nft_jhash(const struct nft_set *set, const struct nft_hash *priv,
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 08fb6720673f..36a4de11995b 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -407,8 +407,9 @@ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules,
  *
  * Return: true on match, false otherwise.
  */
-bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;
@@ -465,13 +466,15 @@ next_match:
 			scratch->map_index = map_index;
 			local_bh_enable();
 
-			return false;
+			return NULL;
 		}
 
 		if (last) {
-			*ext = &f->mt[b].e->ext;
-			if (unlikely(nft_set_elem_expired(*ext) ||
-				     !nft_set_elem_active(*ext, genmask)))
+			const struct nft_set_ext *ext;
+
+			ext = &f->mt[b].e->ext;
+			if (unlikely(nft_set_elem_expired(ext) ||
+				     !nft_set_elem_active(ext, genmask)))
 				goto next_match;
 
 			/* Last field: we're just returning the key without
@@ -482,7 +485,7 @@ next_match:
 			scratch->map_index = map_index;
 			local_bh_enable();
 
-			return true;
+			return ext;
 		}
 
 		/* Swap bitmap indices: res_map is the initial bitmap for the
@@ -497,7 +500,7 @@ next_match:
 
 out:
 	local_bh_enable();
-	return false;
+	return NULL;
 }
 
 /**
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index be7c16c79f71..6c441e2dc8af 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1146,8 +1146,9 @@ static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, uns
  *
  * Return: true on match, false otherwise.
  */
-bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
-			    const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;
@@ -1155,17 +1156,18 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
 	const u8 *rp = (const u8 *)key;
+	const struct nft_set_ext *ext;
 	unsigned long *res, *fill;
 	bool map_index;
-	int i, ret = 0;
+	int i;
 
 	local_bh_disable();
 
 	if (unlikely(!irq_fpu_usable())) {
-		bool fallback_res = nft_pipapo_lookup(net, set, key, ext);
+		ext = nft_pipapo_lookup(net, set, key);
 
 		local_bh_enable();
-		return fallback_res;
+		return ext;
 	}
 
 	m = rcu_dereference(priv->match);
@@ -1182,7 +1184,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
 		local_bh_enable();
-		return false;
+		return NULL;
 	}
 
 	map_index = scratch->map_index;
@@ -1197,6 +1199,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 next_match:
 	nft_pipapo_for_each_field(f, i, m) {
 		bool last = i == m->field_count - 1, first = !i;
+		int ret = 0;
 
 #define NFT_SET_PIPAPO_AVX2_LOOKUP(b, n)				\
 		(ret = nft_pipapo_avx2_lookup_##b##b_##n(res, fill, f,	\
@@ -1244,10 +1247,10 @@ next_match:
 			goto out;
 
 		if (last) {
-			*ext = &f->mt[ret].e->ext;
-			if (unlikely(nft_set_elem_expired(*ext) ||
-				     !nft_set_elem_active(*ext, genmask))) {
-				ret = 0;
+			ext = &f->mt[ret].e->ext;
+			if (unlikely(nft_set_elem_expired(ext) ||
+				     !nft_set_elem_active(ext, genmask))) {
+				ext = NULL;
 				goto next_match;
 			}
 
@@ -1264,5 +1267,5 @@ out:
 	kernel_fpu_end();
 	local_bh_enable();
 
-	return ret >= 0;
+	return ext;
 }
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2e8ef16ff191..938a257c069e 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -52,9 +52,9 @@ static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe)
 	return nft_set_elem_expired(&rbe->ext);
 }
 
-static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-				const u32 *key, const struct nft_set_ext **ext,
-				unsigned int seq)
+static const struct nft_set_ext *
+__nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		    const u32 *key, unsigned int seq)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
@@ -65,7 +65,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 	parent = rcu_dereference_raw(priv->root.rb_node);
 	while (parent != NULL) {
 		if (read_seqcount_retry(&priv->count, seq))
-			return false;
+			return NULL;
 
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -87,50 +87,48 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 			}
 
 			if (nft_rbtree_elem_expired(rbe))
-				return false;
+				return NULL;
 
 			if (nft_rbtree_interval_end(rbe)) {
 				if (nft_set_is_anonymous(set))
-					return false;
+					return NULL;
 				parent = rcu_dereference_raw(parent->rb_left);
 				interval = NULL;
 				continue;
 			}
 
-			*ext = &rbe->ext;
-			return true;
+			return &rbe->ext;
 		}
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
 	    !nft_rbtree_elem_expired(interval) &&
-	    nft_rbtree_interval_start(interval)) {
-		*ext = &interval->ext;
-		return true;
-	}
+	    nft_rbtree_interval_start(interval))
+		return &interval->ext;
 
-	return false;
+	return NULL;
 }
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	unsigned int seq = read_seqcount_begin(&priv->count);
-	bool ret;
+	const struct nft_set_ext *ext;
 
-	ret = __nft_rbtree_lookup(net, set, key, ext, seq);
-	if (ret || !read_seqcount_retry(&priv->count, seq))
-		return ret;
+	ext = __nft_rbtree_lookup(net, set, key, seq);
+	if (ext || !read_seqcount_retry(&priv->count, seq))
+		return ext;
 
 	read_lock_bh(&priv->lock);
 	seq = read_seqcount_begin(&priv->count);
-	ret = __nft_rbtree_lookup(net, set, key, ext, seq);
+	ext = __nft_rbtree_lookup(net, set, key, seq);
 	read_unlock_bh(&priv->lock);
 
-	return ret;
+	return ext;
 }
 
 static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
-- 
cgit v1.2.3


From 531e61312104d991459af73c838396db26aa3550 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 9 Jul 2025 19:05:14 +0200
Subject: netfilter: nft_set: remove indirection from update API call

This stems from a time when sets and nft_dynset resided in different kernel
modules.  We can replace this with a direct call.

We could even remove both ->update and ->delete, given its only
supported by rhashtable, but on the off-chance we'll see runtime
add/delete for other types or a new set type keep that as-is for now.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h      | 4 ----
 include/net/netfilter/nf_tables_core.h | 3 +++
 net/netfilter/nft_dynset.c             | 9 ++++-----
 net/netfilter/nft_set_hash.c           | 4 +---
 net/netfilter/nft_set_pipapo_avx2.c    | 1 -
 5 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 5b6725475906..891e43a01bdc 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -464,10 +464,6 @@ struct nft_set_ops {
 						  const u32 *key);
 	const struct nft_set_ext *	(*update)(struct nft_set *set,
 						  const u32 *key,
-						  struct nft_elem_priv *
-							(*new)(struct nft_set *,
-							       const struct nft_expr *,
-							       struct nft_regs *),
 						  const struct nft_expr *expr,
 						  struct nft_regs *regs);
 	bool				(*delete)(const struct nft_set *set,
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 6a52fb97b844..6c2f483d9828 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -188,4 +188,7 @@ void nft_objref_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		     const struct nft_pktinfo *pkt);
 void nft_objref_map_eval(const struct nft_expr *expr, struct nft_regs *regs,
 			 const struct nft_pktinfo *pkt);
+struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
+				     const struct nft_expr *expr,
+				     struct nft_regs *regs);
 #endif /* _NET_NF_TABLES_CORE_H */
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index e24493d9e776..7807d8129664 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -44,9 +44,9 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv,
 	return 0;
 }
 
-static struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
-					    const struct nft_expr *expr,
-					    struct nft_regs *regs)
+struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
+				     const struct nft_expr *expr,
+				     struct nft_regs *regs)
 {
 	const struct nft_dynset *priv = nft_expr_priv(expr);
 	struct nft_set_ext *ext;
@@ -91,8 +91,7 @@ void nft_dynset_eval(const struct nft_expr *expr,
 		return;
 	}
 
-	ext = set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
-			     expr, regs);
+	ext = set->ops->update(set, &regs->data[priv->sreg_key], expr, regs);
 	if (ext) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 9903c737c9f0..266d0c637225 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -123,8 +123,6 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
 
 static const struct nft_set_ext *
 nft_rhash_update(struct nft_set *set, const u32 *key,
-		 struct nft_elem_priv *(*new)(struct nft_set *, const struct nft_expr *,
-		 struct nft_regs *regs),
 		 const struct nft_expr *expr, struct nft_regs *regs)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
@@ -141,7 +139,7 @@ nft_rhash_update(struct nft_set *set, const u32 *key,
 	if (he != NULL)
 		goto out;
 
-	elem_priv = new(set, expr, regs);
+	elem_priv = nft_dynset_new(set, expr, regs);
 	if (!elem_priv)
 		goto err1;
 
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 6c441e2dc8af..db5d367e43c4 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1137,7 +1137,6 @@ static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, uns
  * @net:	Network namespace
  * @set:	nftables API set representation
  * @key:	nftables API element representation containing key data
- * @ext:	nftables API extension pointer, filled with matching reference
  *
  * For more details, see DOC: Theory of Operation in nft_set_pipapo.c.
  *
-- 
cgit v1.2.3


From d8d871a35ca9ee4881d34995444ed1cb826d01db Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 9 Jul 2025 19:05:15 +0200
Subject: netfilter: nft_set_pipapo: merge pipapo_get/lookup

The matching algorithm has implemented thrice:
1. data path lookup, generic version
2. data path lookup, avx2 version
3. control plane lookup

Merge 1 and 3 by refactoring pipapo_get as a common helper, then make
nft_pipapo_lookup and nft_pipapo_get both call the common helper.

Aside from the code savings this has the benefit that we no longer allocate
temporary scratch maps for each control plane get and insertion operation.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c | 188 +++++++++++++----------------------------
 1 file changed, 58 insertions(+), 130 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 36a4de11995b..28e67c4d7132 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -397,35 +397,36 @@ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules,
 }
 
 /**
- * nft_pipapo_lookup() - Lookup function
- * @net:	Network namespace
- * @set:	nftables API set representation
- * @key:	nftables API element representation containing key data
- * @ext:	nftables API extension pointer, filled with matching reference
+ * pipapo_get() - Get matching element reference given key data
+ * @m:		storage containing the set elements
+ * @data:	Key data to be matched against existing elements
+ * @genmask:	If set, check that element is active in given genmask
+ * @tstamp:	timestamp to check for expired elements
  *
  * For more details, see DOC: Theory of Operation.
  *
- * Return: true on match, false otherwise.
+ * This is the main lookup function.  It matches key data against either
+ * the working match set or the uncommitted copy, depending on what the
+ * caller passed to us.
+ * nft_pipapo_get (lookup from userspace/control plane) and nft_pipapo_lookup
+ * (datapath lookup) pass the active copy.
+ * The insertion path will pass the uncommitted working copy.
+ *
+ * Return: pointer to &struct nft_pipapo_elem on match, NULL otherwise.
  */
-const struct nft_set_ext *
-nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
+static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
+					  const u8 *data, u8 genmask,
+					  u64 tstamp)
 {
-	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;
 	unsigned long *res_map, *fill_map;
-	u8 genmask = nft_genmask_cur(net);
-	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
-	const u8 *rp = (const u8 *)key;
 	bool map_index;
 	int i;
 
 	local_bh_disable();
 
-	m = rcu_dereference(priv->match);
-
-	if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
+	if (unlikely(!raw_cpu_ptr(m->scratch)))
 		goto out;
 
 	scratch = *raw_cpu_ptr(m->scratch);
@@ -445,12 +446,12 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		 * packet bytes value, then AND bucket value
 		 */
 		if (likely(f->bb == 8))
-			pipapo_and_field_buckets_8bit(f, res_map, rp);
+			pipapo_and_field_buckets_8bit(f, res_map, data);
 		else
-			pipapo_and_field_buckets_4bit(f, res_map, rp);
+			pipapo_and_field_buckets_4bit(f, res_map, data);
 		NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4;
 
-		rp += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
+		data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
 
 		/* Now populate the bitmap for the next field, unless this is
 		 * the last field, in which case return the matched 'ext'
@@ -470,11 +471,11 @@ next_match:
 		}
 
 		if (last) {
-			const struct nft_set_ext *ext;
+			struct nft_pipapo_elem *e;
 
-			ext = &f->mt[b].e->ext;
-			if (unlikely(nft_set_elem_expired(ext) ||
-				     !nft_set_elem_active(ext, genmask)))
+			e = f->mt[b].e;
+			if (unlikely(__nft_set_elem_expired(&e->ext, tstamp) ||
+				     !nft_set_elem_active(&e->ext, genmask)))
 				goto next_match;
 
 			/* Last field: we're just returning the key without
@@ -484,8 +485,7 @@ next_match:
 			 */
 			scratch->map_index = map_index;
 			local_bh_enable();
-
-			return ext;
+			return e;
 		}
 
 		/* Swap bitmap indices: res_map is the initial bitmap for the
@@ -495,7 +495,7 @@ next_match:
 		map_index = !map_index;
 		swap(res_map, fill_map);
 
-		rp += NFT_PIPAPO_GROUPS_PADDING(f);
+		data += NFT_PIPAPO_GROUPS_PADDING(f);
 	}
 
 out:
@@ -504,99 +504,29 @@ out:
 }
 
 /**
- * pipapo_get() - Get matching element reference given key data
- * @m:		storage containing active/existing elements
- * @data:	Key data to be matched against existing elements
- * @genmask:	If set, check that element is active in given genmask
- * @tstamp:	timestamp to check for expired elements
- * @gfp:	the type of memory to allocate (see kmalloc).
+ * nft_pipapo_lookup() - Dataplane fronted for main lookup function
+ * @net:	Network namespace
+ * @set:	nftables API set representation
+ * @key:	pointer to nft registers containing key data
  *
- * This is essentially the same as the lookup function, except that it matches
- * key data against the uncommitted copy and doesn't use preallocated maps for
- * bitmap results.
+ * This function is called from the data path.  It will search for
+ * an element matching the given key in the current active copy.
  *
- * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise.
+ * Return: ntables API extension pointer or NULL if no match.
  */
-static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
-					  const u8 *data, u8 genmask,
-					  u64 tstamp, gfp_t gfp)
+const struct nft_set_ext *
+nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
-	struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
-	unsigned long *res_map, *fill_map = NULL;
-	const struct nft_pipapo_field *f;
-	int i;
-
-	if (m->bsize_max == 0)
-		return ret;
-
-	res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), gfp);
-	if (!res_map) {
-		ret = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	fill_map = kcalloc(m->bsize_max, sizeof(*res_map), gfp);
-	if (!fill_map) {
-		ret = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	pipapo_resmap_init(m, res_map);
-
-	nft_pipapo_for_each_field(f, i, m) {
-		bool last = i == m->field_count - 1;
-		int b;
-
-		/* For each bit group: select lookup table bucket depending on
-		 * packet bytes value, then AND bucket value
-		 */
-		if (f->bb == 8)
-			pipapo_and_field_buckets_8bit(f, res_map, data);
-		else if (f->bb == 4)
-			pipapo_and_field_buckets_4bit(f, res_map, data);
-		else
-			BUG();
-
-		data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
-
-		/* Now populate the bitmap for the next field, unless this is
-		 * the last field, in which case return the matched 'ext'
-		 * pointer if any.
-		 *
-		 * Now res_map contains the matching bitmap, and fill_map is the
-		 * bitmap for the next field.
-		 */
-next_match:
-		b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
-				  last);
-		if (b < 0)
-			goto out;
-
-		if (last) {
-			if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
-				goto next_match;
-			if ((genmask &&
-			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
-				goto next_match;
-
-			ret = f->mt[b].e;
-			goto out;
-		}
-
-		data += NFT_PIPAPO_GROUPS_PADDING(f);
+	struct nft_pipapo *priv = nft_set_priv(set);
+	u8 genmask = nft_genmask_cur(net);
+	const struct nft_pipapo_match *m;
+	const struct nft_pipapo_elem *e;
 
-		/* Swap bitmap indices: fill_map will be the initial bitmap for
-		 * the next field (i.e. the new res_map), and res_map is
-		 * guaranteed to be all-zeroes at this point, ready to be filled
-		 * according to the next mapping table.
-		 */
-		swap(res_map, fill_map);
-	}
+	m = rcu_dereference(priv->match);
+	e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64());
 
-out:
-	kfree(fill_map);
-	kfree(res_map);
-	return ret;
+	return e ? &e->ext : NULL;
 }
 
 /**
@@ -605,6 +535,11 @@ out:
  * @set:	nftables API set representation
  * @elem:	nftables API element representation containing key data
  * @flags:	Unused
+ *
+ * This function is called from the control plane path under
+ * RCU read lock.
+ *
+ * Return: set element private pointer or ERR_PTR(-ENOENT).
  */
 static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,
@@ -615,10 +550,9 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(m, (const u8 *)elem->key.val.data,
-		       nft_genmask_cur(net), get_jiffies_64(),
-		       GFP_ATOMIC);
-	if (IS_ERR(e))
-		return ERR_CAST(e);
+		       nft_genmask_cur(net), get_jiffies_64());
+	if (!e)
+		return ERR_PTR(-ENOENT);
 
 	return &e->priv;
 }
@@ -1344,8 +1278,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(m, start, genmask, tstamp, GFP_KERNEL);
-	if (!IS_ERR(dup)) {
+	dup = pipapo_get(m, start, genmask, tstamp);
+	if (dup) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
 
@@ -1364,15 +1298,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 		return -ENOTEMPTY;
 	}
 
-	if (PTR_ERR(dup) == -ENOENT) {
-		/* Look for partially overlapping entries */
-		dup = pipapo_get(m, end, nft_genmask_next(net), tstamp,
-				 GFP_KERNEL);
-	}
-
-	if (PTR_ERR(dup) != -ENOENT) {
-		if (IS_ERR(dup))
-			return PTR_ERR(dup);
+	/* Look for partially overlapping entries */
+	dup = pipapo_get(m, end, nft_genmask_next(net), tstamp);
+	if (dup) {
 		*elem_priv = &dup->priv;
 		return -ENOTEMPTY;
 	}
@@ -1914,8 +1842,8 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set,
 		return NULL;
 
 	e = pipapo_get(m, (const u8 *)elem->key.val.data,
-		       nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL);
-	if (IS_ERR(e))
+		       nft_genmask_next(net), nft_net_tstamp(net));
+	if (!e)
 		return NULL;
 
 	nft_set_elem_change_active(net, set, &e->ext);
-- 
cgit v1.2.3


From 897eefee2eb73ec6c119a0ca357d7b4a3e92c5ef Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 9 Jul 2025 19:05:16 +0200
Subject: netfilter: nft_set_pipapo: prefer kvmalloc for scratch maps

The scratchmap size depends on the number of elements in the set.
For huge sets, each scratch map can easily require very large
allocations, e.g. for 100k entries each scratch map will require
close to 64kbyte of memory.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 28e67c4d7132..1a19649c2851 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1152,7 +1152,7 @@ static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int c
 
 	mem = s;
 	mem -= s->align_off;
-	kfree(mem);
+	kvfree(mem);
 }
 
 /**
@@ -1173,10 +1173,9 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 		void *scratch_aligned;
 		u32 align_off;
 #endif
-		scratch = kzalloc_node(struct_size(scratch, map,
-						   bsize_max * 2) +
-				       NFT_PIPAPO_ALIGN_HEADROOM,
-				       GFP_KERNEL_ACCOUNT, cpu_to_node(i));
+		scratch = kvzalloc_node(struct_size(scratch, map, bsize_max * 2) +
+					NFT_PIPAPO_ALIGN_HEADROOM,
+					GFP_KERNEL_ACCOUNT, cpu_to_node(i));
 		if (!scratch) {
 			/* On failure, there's no need to undo previous
 			 * allocations: this means that some scratch maps have
-- 
cgit v1.2.3


From bf58e667af7d96c8eb9411f926a0a0955f41ce21 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 18 Jul 2025 13:27:13 +0200
Subject: netfilter: xt_nfacct: don't assume acct name is null-terminated

BUG: KASAN: slab-out-of-bounds in .. lib/vsprintf.c:721
Read of size 1 at addr ffff88801eac95c8 by task syz-executor183/5851
[..]
 string+0x231/0x2b0 lib/vsprintf.c:721
 vsnprintf+0x739/0xf00 lib/vsprintf.c:2874
 [..]
 nfacct_mt_checkentry+0xd2/0xe0 net/netfilter/xt_nfacct.c:41
 xt_check_match+0x3d1/0xab0 net/netfilter/x_tables.c:523

nfnl_acct_find_get() handles non-null input, but the error
printk relied on its presence.

Reported-by: syzbot+4ff165b9251e4d295690@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=4ff165b9251e4d295690
Tested-by: syzbot+4ff165b9251e4d295690@syzkaller.appspotmail.com
Fixes: ceb98d03eac5 ("netfilter: xtables: add nfacct match to support extended accounting")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_nfacct.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index 7c6bf1c16813..0ca1cdfc4095 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -38,8 +38,8 @@ nfacct_mt_checkentry(const struct xt_mtchk_param *par)
 
 	nfacct = nfnl_acct_find_get(par->net, info->name);
 	if (nfacct == NULL) {
-		pr_info_ratelimited("accounting object `%s' does not exists\n",
-				    info->name);
+		pr_info_ratelimited("accounting object `%.*s' does not exist\n",
+				    NFACCT_NAME_MAX, info->name);
 		return -ENOENT;
 	}
 	info->nfacct = nfacct;
-- 
cgit v1.2.3