Merge branch 'xdp-grow-tail'

Jesper Dangaard Brouer says:

====================
V4:
- Fixup checkpatch.pl issues
- Collected more ACKs

V3:
- Fix issue on virtio_net patch spotted by Jason Wang
- Adjust name for variable in mlx5 patch
- Collected more ACKs

V2:
- Fix bug in mlx5 for XDP_PASS case
- Collected nitpicks and ACKs from mailing list

V1:
- Fix bug in dpaa2

XDP have evolved to support several frame sizes, but xdp_buff was not
updated with this information. This have caused the side-effect that
XDP frame data hard end is unknown. This have limited the BPF-helper
bpf_xdp_adjust_tail to only shrink the packet. This patchset address
this and add packet tail extend/grow.

The purpose of the patchset is ALSO to reserve a memory area that can be
used for storing extra information, specifically for extending XDP with
multi-buffer support. One proposal is to use same layout as
skb_shared_info, which is why this area is currently 320 bytes.

When converting xdp_frame to SKB (veth and cpumap), the full tailroom
area can now be used and SKB truesize is now correct. For most
drivers this result in a much larger tailroom in SKB "head" data
area. The network stack can now take advantage of this when doing SKB
coalescing. Thus, a good driver test is to use xdp_redirect_cpu from
samples/bpf/ and do some TCP stream testing.

Use-cases for tail grow/extend:
(1) IPsec / XFRM needs a tail extend[1][2].
(2) DNS-cache responses in XDP.
(3) HAProxy ALOHA would need it to convert to XDP.
(4) Add tail info e.g. timestamp and collect via tcpdump

[1] http://vger.kernel.org/netconf2019_files/xfrm_xdp.pdf
[2] http://vger.kernel.org/netconf2019.html

Examples on howto access the tail area of an XDP packet is shown in the
XDP-tutorial example[3].

[3] https://github.com/xdp-project/xdp-tutorial/blob/master/experiment01-tailgrow/
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 16 insertions, 12 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index aece0e5eec8c..b586d2fa5551 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -405,10 +405,6 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 {
 	struct sk_buff *skb;
 
-	if (!buflen) {
-		buflen = SKB_DATA_ALIGN(headroom + len) +
-			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	}
 	skb = build_skb(head, buflen);
 	if (!skb)
 		return NULL;
@@ -564,13 +560,15 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 					struct veth_stats *stats)
 {
 	void *hard_start = frame->data - frame->headroom;
-	void *head = hard_start - sizeof(struct xdp_frame);
 	int len = frame->len, delta = 0;
 	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
 	unsigned int headroom;
 	struct sk_buff *skb;
 
+	/* bpf_xdp_adjust_head() assures BPF cannot access xdp_frame area */
+	hard_start -= sizeof(struct xdp_frame);
+
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (likely(xdp_prog)) {
@@ -581,6 +579,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 		xdp.data = frame->data;
 		xdp.data_end = frame->data + frame->len;
 		xdp.data_meta = frame->data - frame->metasize;
+		xdp.frame_sz = frame->frame_sz;
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -592,7 +591,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 			break;
 		case XDP_TX:
 			orig_frame = *frame;
-			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
 			if (unlikely(veth_xdp_tx(rq, &xdp, bq) < 0)) {
 				trace_xdp_exception(rq->dev, xdp_prog, act);
@@ -605,7 +603,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			orig_frame = *frame;
-			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
 			if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
 				frame = &orig_frame;
@@ -629,7 +626,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 	rcu_read_unlock();
 
 	headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
-	skb = veth_build_skb(head, headroom, len, 0);
+	skb = veth_build_skb(hard_start, headroom, len, frame->frame_sz);
 	if (!skb) {
 		xdp_return_frame(frame);
 		stats->rx_drops++;
@@ -695,9 +692,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 			goto drop;
 		}
 
-		nskb = veth_build_skb(head,
-				      VETH_XDP_HEADROOM + mac_len, skb->len,
-				      PAGE_SIZE);
+		nskb = veth_build_skb(head, VETH_XDP_HEADROOM + mac_len,
+				      skb->len, PAGE_SIZE);
 		if (!nskb) {
 			page_frag_free(head);
 			goto drop;
@@ -715,6 +711,11 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 	xdp.data_end = xdp.data + pktlen;
 	xdp.data_meta = xdp.data;
 	xdp.rxq = &rq->xdp_rxq;
+
+	/* SKB "head" area always have tailroom for skb_shared_info */
+	xdp.frame_sz = (void *)skb_end_pointer(skb) - xdp.data_hard_start;
+	xdp.frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
 	orig_data = xdp.data;
 	orig_data_end = xdp.data_end;
 
@@ -758,6 +759,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 	}
 	rcu_read_unlock();
 
+	/* check if bpf_xdp_adjust_head was used */
 	delta = orig_data - xdp.data;
 	off = mac_len + delta;
 	if (off > 0)
@@ -765,9 +767,11 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 	else if (off < 0)
 		__skb_pull(skb, -off);
 	skb->mac_header -= delta;
+
+	/* check if bpf_xdp_adjust_tail was used */
 	off = xdp.data_end - orig_data_end;
 	if (off != 0)
-		__skb_put(skb, off);
+		__skb_put(skb, off); /* positive on grow, negative on shrink */
 	skb->protocol = eth_type_trans(skb, rq->dev);
 
 	metalen = xdp.data - xdp.data_meta;