[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <160200018165.719143.3249298786187115149.stgit@firesoul>
Date: Tue, 06 Oct 2020 18:03:01 +0200
From: Jesper Dangaard Brouer <brouer@...hat.com>
To: bpf@...r.kernel.org
Cc: Jesper Dangaard Brouer <brouer@...hat.com>, netdev@...r.kernel.org,
Daniel Borkmann <borkmann@...earbox.net>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
maze@...gle.com, lmb@...udflare.com, shaun@...era.io,
Lorenzo Bianconi <lorenzo@...nel.org>, marek@...udflare.com,
John Fastabend <john.fastabend@...il.com>,
Jakub Kicinski <kuba@...nel.org>
Subject: [PATCH bpf-next V1 3/6] bpf: add BPF-helper for reading MTU from
net_device via ifindex
FIXME: add description.
FIXME: IMHO we can create a better BPF-helper named bpf_mtu_check()
instead of bpf_mtu_lookup(), because a flag can be used for requesting
GRO segment size checking. The ret value of bpf_mtu_check() says
if MTU was violoated, but also return MTU via pointer arg to allow
BPF-progs to do own logic.
Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
include/uapi/linux/bpf.h | 13 +++++++++++
net/core/filter.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 69 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 50ce65e37b16..29b335cb96ef 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3718,6 +3718,18 @@ union bpf_attr {
* never return NULL.
* Return
* A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * int bpf_mtu_lookup(void *ctx, u32 ifindex, u64 flags)
+ * Description
+ * Lookup MTU of net device based on ifindex. The Linux kernel
+ * route table can configure MTUs on a more specific per route
+ * level, which is not provided by this helper. For route level
+ * MTU checks use the **bpf_fib_lookup**\ () helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ * Return
+ * On success, MTU size is returned. On error, a negative value.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3875,6 +3887,7 @@ union bpf_attr {
FN(redirect_neigh), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
+ FN(mtu_lookup), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index d84723f347c0..49ae3b80027b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5512,6 +5512,58 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
.arg4_type = ARG_ANYTHING,
};
+static int bpf_mtu_lookup(struct net *netns, u32 ifindex, u64 flags)
+{
+ struct net_device *dev;
+
+ // XXX: Do we even need flags?
+ // Flag idea: get ctx dev->mtu for XDP_TX or redir out-same-dev
+ if (flags)
+ return -EINVAL;
+
+ dev = dev_get_by_index_rcu(netns, ifindex);
+ if (!dev)
+ return -ENODEV;
+
+ return dev->mtu;
+}
+
+BPF_CALL_3(bpf_skb_mtu_lookup, struct sk_buff *, skb,
+ u32, ifindex, u64, flags)
+{
+ struct net *netns = dev_net(skb->dev);
+
+ return bpf_mtu_lookup(netns, ifindex, flags);
+}
+
+BPF_CALL_3(bpf_xdp_mtu_lookup, struct xdp_buff *, xdp,
+ u32, ifindex, u64, flags)
+{
+ struct net *netns = dev_net(xdp->rxq->dev);
+ // XXX: Handle if this runs in devmap prog (then is rxq invalid?)
+
+ return bpf_mtu_lookup(netns, ifindex, flags);
+}
+
+static const struct bpf_func_proto bpf_skb_mtu_lookup_proto = {
+ .func = bpf_skb_mtu_lookup,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto bpf_xdp_mtu_lookup_proto = {
+ .func = bpf_xdp_mtu_lookup,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
+
#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
{
@@ -7075,6 +7127,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_uid_proto;
case BPF_FUNC_fib_lookup:
return &bpf_skb_fib_lookup_proto;
+ case BPF_FUNC_mtu_lookup:
+ return &bpf_skb_mtu_lookup_proto;
case BPF_FUNC_sk_fullsock:
return &bpf_sk_fullsock_proto;
case BPF_FUNC_sk_storage_get:
@@ -7144,6 +7198,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_adjust_tail_proto;
case BPF_FUNC_fib_lookup:
return &bpf_xdp_fib_lookup_proto;
+ case BPF_FUNC_mtu_lookup:
+ return &bpf_xdp_mtu_lookup_proto;
#ifdef CONFIG_INET
case BPF_FUNC_sk_lookup_udp:
return &bpf_xdp_sk_lookup_udp_proto;
Powered by blists - more mailing lists