[PATCH v3 bpf-next 1/5] bpf: add bpf helper bpf_skb_ecn_set_ce

[PATCH v3 bpf-next 1/5] bpf: add bpf helper bpf_skb_ecn_set_ce

[brakmo]

This patch adds a new bpf helper BPF_FUNC_skb_ecn_set_ce
"int bpf_skb_ecn_set_ce(struct sk_buff *skb)". It is added to
BPF_PROG_TYPE_CGROUP_SKB typed bpf_prog which currently can
be attached to the ingress and egress path. The helper is needed
because his type of bpf_prog cannot modify the skb directly.

This helper is used to set the ECN field of ECN capable IP packets to ce
(congestion encountered) in the IPv6 or IPv4 header of the skb. It can be
used by a bpf_prog to manage egress or ingress network bandwdith limit
per cgroupv2 by inducing an ECN response in the TCP sender.
This works best when using DCTCP.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/uapi/linux/bpf.h | 10 +++++++++-
 net/core/filter.c        | 28 ++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2e308e90ffea..3c38ac9a92a7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2359,6 +2359,13 @@ union bpf_attr {
  *	Return
  *		A **struct bpf_tcp_sock** pointer on success, or NULL in
  *		case of failure.
+ *
+ * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ *     Description
+ *             Sets ECN of IP header to ce (congestion encountered) if
+ *             current value is ect (ECN capable). Works with IPv6 and IPv4.
+ *     Return
+ *             1 if set, 0 if not set.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2457,7 +2464,8 @@ union bpf_attr {
 	FN(spin_lock),			\
 	FN(spin_unlock),		\
 	FN(sk_fullsock),		\
-	FN(tcp_sock),
+	FN(tcp_sock),			\
+	FN(skb_ecn_set_ce),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index 85749f6ec789..558ca72f2254 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5426,6 +5426,32 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
 	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
 };
 
+BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
+{
+	unsigned int iphdr_len;
+
+	if (skb->protocol == cpu_to_be16(ETH_P_IP))
+		iphdr_len = sizeof(struct iphdr);
+	else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+		iphdr_len = sizeof(struct ipv6hdr);
+	else
+		return 0;
+
+	if (skb_headlen(skb) < iphdr_len)
+		return 0;
+
+	if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len))
+		return 0;
+
+	return INET_ECN_set_ce(skb);
+}
+
+static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
+	.func           = bpf_skb_ecn_set_ce,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5585,6 +5611,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
+	case BPF_FUNC_skb_ecn_set_ce:
+		return &bpf_skb_ecn_set_ce_proto;
 #endif
 	default:
 		return sk_filter_func_proto(func_id, prog);
-- 
2.17.1

Re: [PATCH v3 bpf-next 1/5] bpf: add bpf helper bpf_skb_ecn_set_ce

[Song Liu]

On Fri, Mar 1, 2019 at 12:39 PM brakmo <brakmo@fb.com> wrote:
>
> This patch adds a new bpf helper BPF_FUNC_skb_ecn_set_ce
> "int bpf_skb_ecn_set_ce(struct sk_buff *skb)". It is added to
> BPF_PROG_TYPE_CGROUP_SKB typed bpf_prog which currently can
> be attached to the ingress and egress path. The helper is needed
> because his type of bpf_prog cannot modify the skb directly.
>
> This helper is used to set the ECN field of ECN capable IP packets to ce
> (congestion encountered) in the IPv6 or IPv4 header of the skb. It can be
> used by a bpf_prog to manage egress or ingress network bandwdith limit
> per cgroupv2 by inducing an ECN response in the TCP sender.
> This works best when using DCTCP.
>
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> Signed-off-by: Martin KaFai Lau <kafai@fb.com>

Acked-by: Song Liu <songliubraving@fb.com>

> ---
>  include/uapi/linux/bpf.h | 10 +++++++++-
>  net/core/filter.c        | 28 ++++++++++++++++++++++++++++
>  2 files changed, 37 insertions(+), 1 deletion(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 2e308e90ffea..3c38ac9a92a7 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2359,6 +2359,13 @@ union bpf_attr {
>   *     Return
>   *             A **struct bpf_tcp_sock** pointer on success, or NULL in
>   *             case of failure.
> + *
> + * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
> + *     Description
> + *             Sets ECN of IP header to ce (congestion encountered) if
> + *             current value is ect (ECN capable). Works with IPv6 and IPv4.
> + *     Return
> + *             1 if set, 0 if not set.
>   */
>  #define __BPF_FUNC_MAPPER(FN)          \
>         FN(unspec),                     \
> @@ -2457,7 +2464,8 @@ union bpf_attr {
>         FN(spin_lock),                  \
>         FN(spin_unlock),                \
>         FN(sk_fullsock),                \
> -       FN(tcp_sock),
> +       FN(tcp_sock),                   \
> +       FN(skb_ecn_set_ce),
>
>  /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>   * function eBPF program intends to call
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 85749f6ec789..558ca72f2254 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5426,6 +5426,32 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
>         .arg1_type      = ARG_PTR_TO_SOCK_COMMON,
>  };
>
> +BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
> +{
> +       unsigned int iphdr_len;
> +
> +       if (skb->protocol == cpu_to_be16(ETH_P_IP))
> +               iphdr_len = sizeof(struct iphdr);
> +       else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
> +               iphdr_len = sizeof(struct ipv6hdr);
> +       else
> +               return 0;
> +
> +       if (skb_headlen(skb) < iphdr_len)
> +               return 0;
> +
> +       if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len))
> +               return 0;
> +
> +       return INET_ECN_set_ce(skb);
> +}
> +
> +static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
> +       .func           = bpf_skb_ecn_set_ce,
> +       .gpl_only       = false,
> +       .ret_type       = RET_INTEGER,
> +       .arg1_type      = ARG_PTR_TO_CTX,
> +};
>  #endif /* CONFIG_INET */
>
>  bool bpf_helper_changes_pkt_data(void *func)
> @@ -5585,6 +5611,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>  #ifdef CONFIG_INET
>         case BPF_FUNC_tcp_sock:
>                 return &bpf_tcp_sock_proto;
> +       case BPF_FUNC_skb_ecn_set_ce:
> +               return &bpf_skb_ecn_set_ce_proto;
>  #endif
>         default:
>                 return sk_filter_func_proto(func_id, prog);
> --
> 2.17.1
>