Received-SPF: pass (google.com: domain of linux-kernel+bounces-12979-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: "D. Wythe" <alibuda@linux.alibaba.com>
To: pablo@netfilter.org,
	kadlec@netfilter.org,
	fw@strlen.de
Cc: bpf@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	netdev@vger.kernel.org,
	coreteam@netfilter.org,
	netfilter-devel@vger.kernel.org,
	davem@davemloft.net,
	edumazet@google.com,
	kuba@kernel.org,
	pabeni@redhat.com,
	ast@kernel.org
Subject: [RFC nf-next v4 1/2] netfilter: bpf: support prog update
Date: Fri, 29 Dec 2023 15:54:08 +0800
Message-Id: <1703836449-88705-2-git-send-email-alibuda@linux.alibaba.com>
In-Reply-To: <1703836449-88705-1-git-send-email-alibuda@linux.alibaba.com>
References: <1703836449-88705-1-git-send-email-alibuda@linux.alibaba.com>
Precedence: bulk

From: "D. Wythe" <alibuda@linux.alibaba.com>

To support the prog update, we need to ensure that the prog seen
within the hook is always valid. Considering that hooks are always
protected by rcu_read_lock(), which provide us the ability to
access the prog under rcu.

Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
 net/netfilter/nf_bpf_link.c | 50 ++++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index e502ec0..7c32ccb 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -8,26 +8,26 @@
 #include <net/netfilter/nf_bpf_link.h>
 #include <uapi/linux/netfilter_ipv4.h>
 
-static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb,
-				    const struct nf_hook_state *s)
-{
-	const struct bpf_prog *prog = bpf_prog;
-	struct bpf_nf_ctx ctx = {
-		.state = s,
-		.skb = skb,
-	};
-
-	return bpf_prog_run(prog, &ctx);
-}
-
 struct bpf_nf_link {
 	struct bpf_link link;
 	struct nf_hook_ops hook_ops;
 	struct net *net;
 	u32 dead;
 	const struct nf_defrag_hook *defrag_hook;
+	struct rcu_head head;
 };
 
+static unsigned int nf_hook_run_bpf(void *bpf_link, struct sk_buff *skb,
+				    const struct nf_hook_state *s)
+{
+	const struct bpf_nf_link *nf_link = bpf_link;
+	struct bpf_nf_ctx ctx = {
+		.state = s,
+		.skb = skb,
+	};
+	return bpf_prog_run(rcu_dereference_raw(nf_link->link.prog), &ctx);
+}
+
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 static const struct nf_defrag_hook *
 get_proto_defrag_hook(struct bpf_nf_link *link,
@@ -126,8 +126,7 @@ static void bpf_nf_link_release(struct bpf_link *link)
 static void bpf_nf_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
-
-	kfree(nf_link);
+	kfree_rcu(nf_link, head);
 }
 
 static int bpf_nf_link_detach(struct bpf_link *link)
@@ -162,7 +161,22 @@ static int bpf_nf_link_fill_link_info(const struct bpf_link *link,
 static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 			      struct bpf_prog *old_prog)
 {
-	return -EOPNOTSUPP;
+	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
+	int err = 0;
+
+	if (nf_link->dead)
+		return -EPERM;
+
+	if (old_prog) {
+		/* target old_prog mismatch */
+		if (!cmpxchg(&link->prog, old_prog, new_prog))
+			return -EPERM;
+	} else {
+		old_prog = xchg(&link->prog, new_prog);
+	}
+
+	bpf_prog_put(old_prog);
+	return err;
 }
 
 static const struct bpf_link_ops bpf_nf_link_lops = {
@@ -226,7 +240,11 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 
 	link->hook_ops.hook = nf_hook_run_bpf;
 	link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF;
-	link->hook_ops.priv = prog;
+
+	/* bpf_nf_link_release & bpf_nf_link_dealloc() can ensures that link remains
+	 * valid at all times within nf_hook_run_bpf().
+	 */
+	link->hook_ops.priv = link;
 
 	link->hook_ops.pf = attr->link_create.netfilter.pf;
 	link->hook_ops.priority = attr->link_create.netfilter.priority;
-- 
1.8.3.1