From 712a6f545c359b427daa9a5a782e30d2f8331e25 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 30 Jul 2026 20:38:50 +0200 Subject: netfilter: ipset: switch ext_size to atomic64_t The hash types do not acquire set->lock, they use 'region locking' where only part of the hash table is locked. Parallel inserts and deletes are possible and CPUs can race on ->ext_size update. Switch to atomic64_t. This leaves another bug unresolved: there still can be a race on comment extension re-init. This will be handled in a later commit when converting to rhashtable backend. Fixes: f66ee0410b1c ("netfilter: ipset: Fix "INFO: rcu detected stall in hash_xxx" reports") Signed-off-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index b98331572ad2..cadae9b2578f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -273,7 +273,7 @@ struct ip_set { /* Number of elements (vs timeout) */ u32 elements; /* Size of the dynamic extensions (vs timeout) */ - size_t ext_size; + atomic64_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ -- cgit v1.2.3 From 7defddefa95b3699b05b23bf3ceea94d872509bb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2026 20:38:53 +0200 Subject: netfilter: ipset: switch to rcu work In the initial ipset rhashtable conversion RFC series syzbot reported following splat: BUG: sleeping function [..] at kernel/irq_work.c:289 in_atomic(): 1, [..] irq_work_sync.. kernel/irq_work.c:289 rhashtable_free_and_destroy.. lib/rhashtable.c:1295 hash_netport4_destroy.. net/netfilter/ipset/ip_set_hash_gen.h:420 ip_set_destroy_set_rcu.. net/netfilter/ipset/ip_set_core.c:1169 rcu_core.. kernel/rcu/tree.c:2897 This is because post-rhashtable-conversion hash implementation needs to schedule in the destroy callback. At this time this isn't allowed. Replace existing call_rcu() based destruction with rcu_work api. Also allows to undo split of set destruction and gc work cancelling in a future patch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index cadae9b2578f..c46864cc6623 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -244,8 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { - /* For call_cru in destroy */ - struct rcu_head rcu; + /* for set destruction */ + struct rcu_work rwork; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ -- cgit v1.2.3 From 646922a0379496154e8c8faca4f8e2fd9100cacc Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 30 Jul 2026 21:35:05 +0300 Subject: ipvs: avoid out-of-bounds write in ip_vs_nat_icmp Sashiko warns that local attacker can modify the packet while it is processed by IPVS. Some places read the IP ihl field multiple times which can cause out-of-bounds access. One such place is ip_vs_nat_icmp where we can write after the validated area. Fix it by providing ciph argument just like it is done for IPv6 and use ciph->len as offset to the embedded transport header. Modify some IPv4 header checks by reading the ihl field only once. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260722101517.36313-1-ja%40ssi.bg Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e6ca930a3507..1235f1934e94 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -2062,7 +2062,7 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp) void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, - bool has_ports); + bool has_ports, struct ip_vs_iphdr *ciph); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, -- cgit v1.2.3 From 99609cb0aa789c8d071050ce8579989551882cc6 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 30 Jul 2026 21:35:06 +0300 Subject: ipvs: return the csum validation for forward hook Sashiko notes that playing games with the skb dst and rt flags instead of providing hooknum is not a good idea when validating the checksums. Also, skipping checksum validation for FORWARD packets risk silent data corruption, even if the only user is the FTP-CMD packets coming from the real server. Sashiko also noticed that by using common checksum helper in the previous commit we actually fixed old bug where the TCP/UDP checksum for IPv6 on CHECKSUM_COMPLETE was not validated correctly. Fixes: e876b75b9020 ("ipvs: fix the checksum validations") Link: https://sashiko.dev/#/patchset/20260722211420.153933-1-pablo%40netfilter.org Link: https://sashiko.dev/#/patchset/20260727185024.67534-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260728202520.59179-1-ja%40ssi.bg Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1235f1934e94..d2813eb795be 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,7 @@ #include /* for union nf_inet_addr */ #include #include /* for struct ipv6hdr */ -#include #include -#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -2095,30 +2093,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } -static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +static inline bool ip_vs_checksum_needed(struct sk_buff *skb) { /* Checksum unnecessary or already validated? */ if (skb_csum_unnecessary(skb)) return false; - /* LOCAL_OUT ? */ - if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + /* Locally generated ? */ + if (!skb->dev) return false; - /* !LOCAL_IN (FORWARD) ? */ - if (af == AF_INET6) { - if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) - return false; - } else { - if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) - return false; - } return true; } static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, int offset, int proto, int af) { - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return true; + /* Validate csum even for FORWARD */ return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); } -- cgit v1.2.3