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-next 05/11] netfilter: nf_conncount: split count_tree_node rbtree walk into helper
Date: Sun, 14 Jun 2026 13:45:59 +0200	[thread overview]
Message-ID: <20260614114605.474783-6-pablo@netfilter.org> (raw)
In-Reply-To: <20260614114605.474783-1-pablo@netfilter.org>

From: Florian Westphal <fw@strlen.de>

Add find_tree_node() helper that fetches a matching rbtree node.

This is used by followup patch to optionally search the tree again while
preventing concurrent updates via tree lock.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 102 +++++++++++++++++++++--------------
 1 file changed, 62 insertions(+), 40 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index faecc05d34d4..56ac64ecfb75 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -488,6 +488,34 @@ insert_tree(struct net *net,
 	return count;
 }
 
+static struct nf_conncount_rb *
+find_tree_node(struct nf_conncount_root *root, struct nf_conncount_data *data,
+	       const u32 *key)
+{
+	struct rb_node *parent;
+
+	parent = rcu_dereference_check(root->root.rb_node,
+				       lockdep_is_held(&root->lock));
+	while (parent) {
+		struct nf_conncount_rb *rbconn;
+		int diff;
+
+		rbconn = rb_entry(parent, struct nf_conncount_rb, node);
+
+		diff = key_diff(key, rbconn->key, data->keylen);
+		if (diff < 0)
+			parent = rcu_dereference_check(parent->rb_left,
+						       lockdep_is_held(&root->lock));
+		else if (diff > 0)
+			parent = rcu_dereference_check(parent->rb_right,
+						       lockdep_is_held(&root->lock));
+		else
+			return rbconn;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
 static unsigned int
 count_tree(struct net *net,
 	   const struct sk_buff *skb,
@@ -496,59 +524,53 @@ count_tree(struct net *net,
 	   const u32 *key)
 {
 	struct nf_conncount_root *root;
-	struct rb_node *parent;
 	struct nf_conncount_rb *rbconn;
 	unsigned int hash;
+	int ret;
 
 	hash = jhash2(key, data->keylen, data->initval) % CONNCOUNT_SLOTS;
 	root = &data->root[hash];
 
-	parent = rcu_dereference(root->root.rb_node);
-	while (parent) {
-		int diff;
-
-		rbconn = rb_entry(parent, struct nf_conncount_rb, node);
+	rbconn = find_tree_node(root, data, key);
+	if (IS_ERR(rbconn)) {
+		if (PTR_ERR(rbconn) == -ENOENT) {
+			if (!skb)
+				return 0;
 
-		diff = key_diff(key, rbconn->key, data->keylen);
-		if (diff < 0) {
-			parent = rcu_dereference(parent->rb_left);
-		} else if (diff > 0) {
-			parent = rcu_dereference(parent->rb_right);
-		} else {
-			int ret;
+			return insert_tree(net, skb, l3num, data, hash, key);
+		}
+		DEBUG_NET_WARN_ON_ONCE(IS_ERR(rbconn));
+	}
 
-			if (!skb) {
-				nf_conncount_gc_list(net, &rbconn->list);
-				return rbconn->list.count;
-			}
+	DEBUG_NET_WARN_ON_ONCE(IS_ERR_OR_NULL(rbconn));
+	if (IS_ERR_OR_NULL(rbconn))
+		return 0;
 
-			spin_lock_bh(&rbconn->list.list_lock);
-			/* Node might be about to be free'd.
-			 * We need to defer to insert_tree() in this case.
-			 */
-			if (rbconn->list.count == 0) {
-				spin_unlock_bh(&rbconn->list.list_lock);
-				break;
-			}
+	if (!skb) {
+		nf_conncount_gc_list(net, &rbconn->list);
+		return rbconn->list.count;
+	}
 
-			/* same source network -> be counted! */
-			ret = __nf_conncount_add(net, skb, l3num, &rbconn->list);
-			spin_unlock_bh(&rbconn->list.list_lock);
-			if (ret && ret != -EEXIST) {
-				return 0; /* hotdrop */
-			} else {
-				/* -EEXIST means add was skipped, update the list */
-				if (ret == -EEXIST)
-					nf_conncount_gc_list(net, &rbconn->list);
-				return rbconn->list.count;
-			}
-		}
+	spin_lock_bh(&rbconn->list.list_lock);
+	/* Node might be about to be free'd.
+	 * We need to defer to insert_tree() in this case.
+	 */
+	if (rbconn->list.count == 0) {
+		spin_unlock_bh(&rbconn->list.list_lock);
+		return insert_tree(net, skb, l3num, data, hash, key);
 	}
 
-	if (!skb)
-		return 0;
+	/* same source network -> be counted! */
+	ret = __nf_conncount_add(net, skb, l3num, &rbconn->list);
+	spin_unlock_bh(&rbconn->list.list_lock);
+
+	if (ret && ret != -EEXIST)
+		return 0; /* hotdrop */
+	/* -EEXIST means add was skipped, update the list */
+	if (ret == -EEXIST)
+		nf_conncount_gc_list(net, &rbconn->list);
 
-	return insert_tree(net, skb, l3num, data, hash, key);
+	return rbconn->list.count;
 }
 
 static void tree_gc_worker(struct work_struct *work)
-- 
2.47.3


  parent reply	other threads:[~2026-06-14 11:46 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-14 11:45 [PATCH net-next 00/11] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
2026-06-14 11:45 ` [PATCH net-next 01/11] ipvs: Replace use of system_unbound_wq with system_dfl_long_wq Pablo Neira Ayuso
2026-06-14 11:45 ` [PATCH net-next 02/11] netfilter: nf_tables: use DEBUG_NET_WARN_ON_ONCE in packet and control paths Pablo Neira Ayuso
2026-06-14 11:45 ` [PATCH net-next 03/11] netfilter: nf_conncount: callers must hold rcu read lock Pablo Neira Ayuso
2026-06-14 11:45 ` [PATCH net-next 04/11] netfilter: nf_conncount: use per nf_conncount_data spinlocks Pablo Neira Ayuso
2026-06-14 11:45 ` Pablo Neira Ayuso [this message]
2026-06-14 11:46 ` [PATCH net-next 06/11] netfilter: nf_conncount: add sequence counter to detect tree modifications Pablo Neira Ayuso
2026-06-14 11:46 ` [PATCH net-next 07/11] netfilter: nf_conncount: gc and rcu fixes Pablo Neira Ayuso
2026-06-14 11:46 ` [PATCH net-next 08/11] netfilter: conntrack: check NULL when retrieving ct extension Pablo Neira Ayuso
2026-06-14 11:46 ` [PATCH net-next 09/11] netfilter: flowtable: bail out if forward path cannot be discovered Pablo Neira Ayuso
2026-06-14 11:46 ` [PATCH net-next 10/11] ipvs: fix doc syntax for conn_max sysctl Pablo Neira Ayuso
2026-06-14 11:46 ` [PATCH net-next 11/11] netfilter: nf_dup_netdev: add nf_dev_xmit_recursion*() helpers and use them 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=20260614114605.474783-6-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