Netdev List
 help / color / mirror / Atom feed
From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org,
	pabeni@redhat.com, edumazet@google.com, fw@strlen.de,
	horms@kernel.org
Subject: [PATCH net 04/10] netfilter: ipset: switch ext_size to atomic64_t
Date: Fri, 31 Jul 2026 17:18:00 +0200	[thread overview]
Message-ID: <20260731151806.849724-5-pablo@netfilter.org> (raw)
In-Reply-To: <20260731151806.849724-1-pablo@netfilter.org>

From: Jozsef Kadlecsik <kadlec@netfilter.org>

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 <kadlec@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h  | 2 +-
 net/netfilter/ipset/ip_set_bitmap_gen.h | 4 ++--
 net/netfilter/ipset/ip_set_core.c       | 6 +++---
 net/netfilter/ipset/ip_set_hash_gen.h   | 2 +-
 net/netfilter/ipset/ip_set_list_set.c   | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

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 */
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index bb9b5bed10e1..226fdf17b683 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set)
 		mtype_ext_cleanup(set);
 	bitmap_zero(map->members, map->elements);
 	set->elements = 0;
-	set->ext_size = 0;
+	atomic64_set(&set->ext_size, 0);
 }
 
 /* Calculate the actual memory size of the set data */
@@ -93,7 +93,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 {
 	const struct mtype *map = set->data;
 	struct nlattr *nested;
-	size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size;
+	size_t memsize = mtype_memsize(map, set->dsize) + atomic64_read(&set->ext_size);
 
 	nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 6cfad152d7d1..822a53a7f502 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -350,7 +350,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
 	size_t len = ext->comment ? strlen(ext->comment) : 0;
 
 	if (unlikely(c)) {
-		set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+		atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
 		rcu_assign_pointer(comment->c, NULL);
 		kfree_rcu(c, rcu);
 	}
@@ -362,7 +362,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
 	if (unlikely(!c))
 		return;
 	strscpy(c->str, ext->comment, len + 1);
-	set->ext_size += sizeof(*c) + strlen(c->str) + 1;
+	atomic64_add(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
 	rcu_assign_pointer(comment->c, c);
 }
 EXPORT_SYMBOL_GPL(ip_set_init_comment);
@@ -392,7 +392,7 @@ ip_set_comment_free(struct ip_set *set, void *ptr)
 	c = rcu_dereference_protected(comment->c, 1);
 	if (unlikely(!c))
 		return;
-	set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+	atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
 	rcu_assign_pointer(comment->c, NULL);
 	kfree_rcu(c, rcu);
 }
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index dd31992c915c..8841daf28f01 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1373,7 +1373,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	rcu_read_lock_bh();
 	t = rcu_dereference_bh(h->table);
 	mtype_ext_size(set, &elements, &ext_size);
-	memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size;
+	memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size);
 	htable_bits = t->htable_bits;
 	rcu_read_unlock_bh();
 
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 1cef84f15e8c..ca3ef9479e83 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -421,7 +421,7 @@ list_set_flush(struct ip_set *set)
 	list_for_each_entry_safe(e, n, &map->members, list)
 		list_set_del(set, e);
 	set->elements = 0;
-	set->ext_size = 0;
+	atomic64_set(&set->ext_size, 0);
 }
 
 static void
@@ -455,7 +455,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
 {
 	const struct list_set *map = set->data;
 	struct nlattr *nested;
-	size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size;
+	size_t memsize = list_set_memsize(map, set->dsize) + atomic64_read(&set->ext_size);
 
 	nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
-- 
2.47.3


  parent reply	other threads:[~2026-07-31 15:18 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-31 15:17 [PATCH net 00/10] Netfilter/IPVS fixes for net Pablo Neira Ayuso
2026-07-31 15:17 ` [PATCH net 01/10] ipvs: stop estimator after disabled calc phase Pablo Neira Ayuso
2026-07-31 15:17 ` [PATCH net 02/10] netfilter: ebt_nflog: pin the NFLOG backend Pablo Neira Ayuso
2026-07-31 15:17 ` [PATCH net 03/10] netfilter: ipset: rework cidr bookkeeping Pablo Neira Ayuso
2026-07-31 15:18 ` Pablo Neira Ayuso [this message]
2026-07-31 15:18 ` [PATCH net 05/10] netfilter: ipset: add small wrappers for hash and bucket sizes Pablo Neira Ayuso
2026-07-31 15:18 ` [PATCH net 06/10] netfilter: ipset: add and use mtype_del_cidr_all helper Pablo Neira Ayuso
2026-07-31 15:18 ` [PATCH net 07/10] netfilter: ipset: switch to rcu work Pablo Neira Ayuso
2026-07-31 15:18 ` [PATCH net 08/10] ipvs: avoid out-of-bounds write in ip_vs_nat_icmp Pablo Neira Ayuso
2026-07-31 15:18 ` [PATCH net 09/10] ipvs: return the csum validation for forward hook Pablo Neira Ayuso
2026-07-31 15:18 ` [PATCH net 10/10] netfilter: nft_ct: move custom expectation support to helper Pablo Neira Ayuso

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260731151806.849724-5-pablo@netfilter.org \
    --to=pablo@netfilter.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=fw@strlen.de \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=netfilter-devel@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox