bpf: add meta pointer for direct access

This work enables generic transfer of metadata from XDP into skb. The
basic idea is that we can make use of the fact that the resulting skb
must be linear and already comes with a larger headroom for supporting
bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work
on a similar principle and introduce a small helper bpf_xdp_adjust_meta()
for adjusting a new pointer called xdp->data_meta. Thus, the packet has
a flexible and programmable room for meta data, followed by the actual
packet data. struct xdp_buff is therefore laid out that we first point
to data_hard_start, then data_meta directly prepended to data followed
by data_end marking the end of packet. bpf_xdp_adjust_head() takes into
account whether we have meta data already prepended and if so, memmove()s
this along with the given offset provided there's enough room.

xdp->data_meta is optional and programs are not required to use it. The
rationale is that when we process the packet in XDP (e.g. as DoS filter),
we can push further meta data along with it for the XDP_PASS case, and
give the guarantee that a clsact ingress BPF program on the same device
can pick this up for further post-processing. Since we work with skb
there, we can also set skb->mark, skb->priority or other skb meta data
out of BPF, thus having this scratch space generic and programmable
allows for more flexibility than defining a direct 1:1 transfer of
potentially new XDP members into skb (it's also more efficient as we
don't need to initialize/handle each of such new members). The facility
also works together with GRO aggregation. The scratch space at the head
of the packet can be multiple of 4 byte up to 32 byte large. Drivers not
yet supporting xdp->data_meta can simply be set up with xdp->data_meta
as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out,
such that the subsequent match against xdp->data for later access is
guaranteed to fail.

The verifier treats xdp->data_meta/xdp->data the same way as we treat
xdp->data/xdp->data_end pointer comparisons. The requirement for doing
the compare against xdp->data is that it hasn't been modified from it's
original address we got from ctx access. It may have a range marking
already from prior successful xdp->data/xdp->data_end pointer comparisons
though.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 101 insertions, 9 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 97abddd9039a..e350c768d4b5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3864,8 +3864,8 @@ drop:
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 				     struct bpf_prog *xdp_prog)
 {
+	u32 metalen, act = XDP_DROP;
 	struct xdp_buff xdp;
-	u32 act = XDP_DROP;
 	void *orig_data;
 	int hlen, off;
 	u32 mac_len;
@@ -3876,8 +3876,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	if (skb_cloned(skb))
 		return XDP_PASS;
 
-	if (skb_linearize(skb))
-		goto do_drop;
+	/* XDP packets must be linear and must have sufficient headroom
+	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+	 * native XDP provides, thus we need to do it here as well.
+	 */
+	if (skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+		int troom = skb->tail + skb->data_len - skb->end;
+
+		/* In case we have to go down the path and also linearize,
+		 * then lets do the pskb_expand_head() work just once here.
+		 */
+		if (pskb_expand_head(skb,
+				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+			goto do_drop;
+		if (troom > 0 && __skb_linearize(skb))
+			goto do_drop;
+	}
 
 	/* The XDP program wants to see the packet starting at the MAC
 	 * header.
@@ -3885,6 +3902,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	mac_len = skb->data - skb_mac_header(skb);
 	hlen = skb_headlen(skb) + mac_len;
 	xdp.data = skb->data - mac_len;
+	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + hlen;
 	xdp.data_hard_start = skb->data - skb_headroom(skb);
 	orig_data = xdp.data;
@@ -3902,10 +3920,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	case XDP_REDIRECT:
 	case XDP_TX:
 		__skb_push(skb, mac_len);
-		/* fall through */
+		break;
 	case XDP_PASS:
+		metalen = xdp.data - xdp.data_meta;
+		if (metalen)
+			skb_metadata_set(skb, metalen);
 		break;
-
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		/* fall through */
@@ -4695,6 +4715,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		diffs |= skb_metadata_dst_cmp(p, skb);
+		diffs |= skb_metadata_differs(p, skb);
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
 						      skb_mac_header(skb));
diff --git a/net/core/filter.c b/net/core/filter.c
index c468e7cfad19..9b6e7e84aafd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2447,14 +2447,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
+{
+	return xdp_data_meta_unsupported(xdp) ? 0 :
+	       xdp->data - xdp->data_meta;
+}
+
 BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
 {
+	unsigned long metalen = xdp_get_metalen(xdp);
+	void *data_start = xdp->data_hard_start + metalen;
 	void *data = xdp->data + offset;
 
-	if (unlikely(data < xdp->data_hard_start ||
+	if (unlikely(data < data_start ||
 		     data > xdp->data_end - ETH_HLEN))
 		return -EINVAL;
 
+	if (metalen)
+		memmove(xdp->data_meta + offset,
+			xdp->data_meta, metalen);
+	xdp->data_meta += offset;
 	xdp->data = data;
 
 	return 0;
@@ -2468,6 +2480,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
+{
+	void *meta = xdp->data_meta + offset;
+	unsigned long metalen = xdp->data - meta;
+
+	if (xdp_data_meta_unsupported(xdp))
+		return -ENOTSUPP;
+	if (unlikely(meta < xdp->data_hard_start ||
+		     meta > xdp->data))
+		return -EINVAL;
+	if (unlikely((metalen & (sizeof(__u32) - 1)) ||
+		     (metalen > 32)))
+		return -EACCES;
+
+	xdp->data_meta = meta;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
+	.func		= bpf_xdp_adjust_meta,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static int __bpf_tx_xdp(struct net_device *dev,
 			struct bpf_map *map,
 			struct xdp_buff *xdp,
@@ -2692,7 +2731,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
-	    func == bpf_xdp_adjust_head)
+	    func == bpf_xdp_adjust_head ||
+	    func == bpf_xdp_adjust_meta)
 		return true;
 
 	return false;
@@ -3288,6 +3328,8 @@ xdp_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_xdp_adjust_head:
 		return &bpf_xdp_adjust_head_proto;
+	case BPF_FUNC_xdp_adjust_meta:
+		return &bpf_xdp_adjust_meta_proto;
 	case BPF_FUNC_redirect:
 		return &bpf_xdp_redirect_proto;
 	case BPF_FUNC_redirect_map:
@@ -3418,6 +3460,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 	case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
 	case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
 	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		if (size != size_default)
 			return false;
@@ -3444,6 +3487,7 @@ static bool sk_filter_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
@@ -3468,6 +3512,7 @@ static bool lwt_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 		return false;
 	}
 
@@ -3586,6 +3631,9 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data):
 		info->reg_type = PTR_TO_PACKET;
 		break;
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+		info->reg_type = PTR_TO_PACKET_META;
+		break;
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
@@ -3619,6 +3667,9 @@ static bool xdp_is_valid_access(int off, int size,
 	case offsetof(struct xdp_md, data):
 		info->reg_type = PTR_TO_PACKET;
 		break;
+	case offsetof(struct xdp_md, data_meta):
+		info->reg_type = PTR_TO_PACKET_META;
+		break;
 	case offsetof(struct xdp_md, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
@@ -3677,6 +3728,12 @@ static bool sk_skb_is_valid_access(int off, int size,
 				   enum bpf_access_type type,
 				   struct bpf_insn_access_aux *info)
 {
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, tc_classid):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+		return false;
+	}
+
 	if (type == BPF_WRITE) {
 		switch (off) {
 		case bpf_ctx_range(struct __sk_buff, mark):
@@ -3689,8 +3746,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 	}
 
 	switch (off) {
-	case bpf_ctx_range(struct __sk_buff, tc_classid):
-		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 		info->reg_type = PTR_TO_PACKET;
 		break;
@@ -3847,6 +3902,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct sk_buff, data));
 		break;
 
+	case offsetof(struct __sk_buff, data_meta):
+		off  = si->off;
+		off -= offsetof(struct __sk_buff, data_meta);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct bpf_skb_data_end, data_meta);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+				      si->src_reg, off);
+		break;
+
 	case offsetof(struct __sk_buff, data_end):
 		off  = si->off;
 		off -= offsetof(struct __sk_buff, data_end);
@@ -4095,6 +4159,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      si->dst_reg, si->src_reg,
 				      offsetof(struct xdp_buff, data));
 		break;
+	case offsetof(struct xdp_md, data_meta):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, data_meta));
+		break;
 	case offsetof(struct xdp_md, data_end):
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end),
 				      si->dst_reg, si->src_reg,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 000ce735fa8d..d98c2e3ce2bf 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	skb->nohdr    = 0;
 	atomic_set(&skb_shinfo(skb)->dataref, 1);
 
+	skb_metadata_clear(skb);
+
 	/* It is not generally safe to change skb->truesize.
 	 * For the moment, we really care of rx path, or
 	 * when skb is orphaned (not attached to a socket).