[RFC,nf-next,v4,1/2] netfilter: bpf: support prog update

Commit Message

D. Wythe Dec. 29, 2023, 7:54 a.m. UTC

From: "D. Wythe" <[e-mail]>

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 <[e-mail]>
---
 net/netfilter/nf_bpf_link.c | 50 ++++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 16 deletions(-)

Comments

D. Wythe Dec. 29, 2023, 8:03 a.m. UTC | #1

On 12/29/23 3:54 PM, D. Wythe wrote:
> From: "D. Wythe" <[e-mail]>
>
> 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 <[e-mail]>
> ---
>   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;
>   }

I made a mistake here, and I will fix it in the next version.
Sorry for that.

D. Wythe

>   
>   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;

Patch

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;