bpf: Add BPF-helper for MTU checking

This BPF-helper bpf_check_mtu() works for both XDP and TC-BPF programs.

The SKB object is complex and the skb->len value (accessible from
BPF-prog) also include the length of any extra GRO/GSO segments, but
without taking into account that these GRO/GSO segments get added
transport (L4) and network (L3) headers before being transmitted. Thus,
this BPF-helper is created such that the BPF-programmer don't need to
handle these details in the BPF-prog.

The API is designed to help the BPF-programmer, that want to do packet
context size changes, which involves other helpers. These other helpers
usually does a delta size adjustment. This helper also support a delta
size (len_diff), which allow BPF-programmer to reuse arguments needed by
these other helpers, and perform the MTU check prior to doing any actual
size adjustment of the packet context.

It is on purpose, that we allow the len adjustment to become a negative
result, that will pass the MTU check. This might seem weird, but it's not
this helpers responsibility to "catch" wrong len_diff adjustments. Other
helpers will take care of these checks, if BPF-programmer chooses to do
actual size adjustment.

V14:
 - Improve man-page desc of len_diff.

V13:
 - Enforce flag BPF_MTU_CHK_SEGS cannot use len_diff.

V12:
 - Simplify segment check that calls skb_gso_validate_network_len.
 - Helpers should return long

V9:
- Use dev->hard_header_len (instead of ETH_HLEN)
- Annotate with unlikely req from Daniel
- Fix logic error using skb_gso_validate_network_len from Daniel

V6:
- Took John's advice and dropped BPF_MTU_CHK_RELAX
- Returned MTU is kept at L3-level (like fib_lookup)

V4: Lot of changes
 - ifindex 0 now use current netdev for MTU lookup
 - rename helper from bpf_mtu_check to bpf_check_mtu
 - fix bug for GSO pkt length (as skb->len is total len)
 - remove __bpf_len_adj_positive, simply allow negative len adj

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287790461.790810.3429728639563297353.stgit@firesoul

1 files changed, 114 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index e7a9b1667dd6..439f43f00483 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5637,6 +5637,116 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static struct net_device *__dev_via_ifindex(struct net_device *dev_curr,
+					    u32 ifindex)
+{
+	struct net *netns = dev_net(dev_curr);
+
+	/* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */
+	if (ifindex == 0)
+		return dev_curr;
+
+	return dev_get_by_index_rcu(netns, ifindex);
+}
+
+BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
+	   u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+	int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+	struct net_device *dev = skb->dev;
+	int skb_len, dev_len;
+	int mtu;
+
+	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
+		return -EINVAL;
+
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+		return -EINVAL;
+
+	dev = __dev_via_ifindex(dev, ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	mtu = READ_ONCE(dev->mtu);
+
+	dev_len = mtu + dev->hard_header_len;
+	skb_len = skb->len + len_diff; /* minus result pass check */
+	if (skb_len <= dev_len) {
+		ret = BPF_MTU_CHK_RET_SUCCESS;
+		goto out;
+	}
+	/* At this point, skb->len exceed MTU, but as it include length of all
+	 * segments, it can still be below MTU.  The SKB can possibly get
+	 * re-segmented in transmit path (see validate_xmit_skb).  Thus, user
+	 * must choose if segs are to be MTU checked.
+	 */
+	if (skb_is_gso(skb)) {
+		ret = BPF_MTU_CHK_RET_SUCCESS;
+
+		if (flags & BPF_MTU_CHK_SEGS &&
+		    !skb_gso_validate_network_len(skb, mtu))
+			ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
+	}
+out:
+	/* BPF verifier guarantees valid pointer */
+	*mtu_len = mtu;
+
+	return ret;
+}
+
+BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
+	   u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+	struct net_device *dev = xdp->rxq->dev;
+	int xdp_len = xdp->data_end - xdp->data;
+	int ret = BPF_MTU_CHK_RET_SUCCESS;
+	int mtu, dev_len;
+
+	/* XDP variant doesn't support multi-buffer segment check (yet) */
+	if (unlikely(flags))
+		return -EINVAL;
+
+	dev = __dev_via_ifindex(dev, ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	mtu = READ_ONCE(dev->mtu);
+
+	/* Add L2-header as dev MTU is L3 size */
+	dev_len = mtu + dev->hard_header_len;
+
+	xdp_len += len_diff; /* minus result pass check */
+	if (xdp_len > dev_len)
+		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+
+	/* BPF verifier guarantees valid pointer */
+	*mtu_len = mtu;
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
+	.func		= bpf_skb_check_mtu,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_PTR_TO_INT,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
+	.func		= bpf_xdp_check_mtu,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_PTR_TO_INT,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_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)
 {
@@ -7222,6 +7332,8 @@ 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_check_mtu:
+		return &bpf_skb_check_mtu_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
 	case BPF_FUNC_sk_storage_get:
@@ -7291,6 +7403,8 @@ 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_check_mtu:
+		return &bpf_xdp_check_mtu_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_udp:
 		return &bpf_xdp_sk_lookup_udp_proto;