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>

4 files changed, 41 insertions, 12 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 29dbdd4c29f6..30ba7d38941d 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -470,25 +470,34 @@ out:
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
+	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	u32 headroom = XDP_PACKET_HEADROOM;
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
 	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
+	u32 max_data_sz;
 	void *data;
 	int ret;
 
 	if (kattr->test.ctx_in || kattr->test.ctx_out)
 		return -EINVAL;
 
-	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
+	/* XDP have extra tailroom as (most) drivers use full page */
+	max_data_sz = 4096 - headroom - tailroom;
+	if (size > max_data_sz)
+		return -EINVAL;
+
+	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
 	xdp.data_hard_start = data;
-	xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
+	xdp.data = data + headroom;
 	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + size;
+	xdp.frame_sz = headroom + max_data_sz + tailroom;
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp.rxq = &rxqueue->xdp_rxq;
@@ -496,8 +505,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
 	if (ret)
 		goto out;
-	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN ||
-	    xdp.data_end != xdp.data + size)
+	if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
 		size = xdp.data_end - xdp.data;
 	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
 out:
diff --git a/net/core/dev.c b/net/core/dev.c
index 4c91de39890a..f937a3ff668d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4617,6 +4617,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp->data_meta = xdp->data;
 	xdp->data_end = xdp->data + hlen;
 	xdp->data_hard_start = skb->data - skb_headroom(skb);
+
+	/* 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_end = xdp->data_end;
 	orig_data = xdp->data;
 	eth = (struct ethhdr *)xdp->data;
@@ -4640,14 +4645,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		skb_reset_network_header(skb);
 	}
 
-	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
-	 * pckt.
-	 */
-	off = orig_data_end - xdp->data_end;
+	/* check if bpf_xdp_adjust_tail was used */
+	off = xdp->data_end - orig_data_end;
 	if (off != 0) {
 		skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
-		skb->len -= off;
-
+		skb->len += off; /* positive on grow, negative on shrink */
 	}
 
 	/* check if XDP changed eth hdr such SKB needs update */
diff --git a/net/core/filter.c b/net/core/filter.c
index 5815902bb617..a85eb538d4d6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3411,15 +3411,26 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 
 BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 {
+	void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
 	void *data_end = xdp->data_end + offset;
 
-	/* only shrinking is allowed for now. */
-	if (unlikely(offset >= 0))
+	/* Notice that xdp_data_hard_end have reserved some tailroom */
+	if (unlikely(data_end > data_hard_end))
 		return -EINVAL;
 
+	/* ALL drivers MUST init xdp->frame_sz, chicken check below */
+	if (unlikely(xdp->frame_sz > PAGE_SIZE)) {
+		WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz);
+		return -EINVAL;
+	}
+
 	if (unlikely(data_end < xdp->data + ETH_HLEN))
 		return -EINVAL;
 
+	/* Clear memory area on grow, can contain uninit kernel memory */
+	if (offset > 0)
+		memset(xdp->data_end, 0, offset);
+
 	xdp->data_end = data_end;
 
 	return 0;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 4c7ea85486af..490b8f5fa8ee 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
+#include <linux/bug.h>
 #include <net/page_pool.h>
 
 #include <net/xdp.h>
@@ -496,3 +497,10 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
 	return xdpf;
 }
 EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame);
+
+/* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */
+void xdp_warn(const char *msg, const char *func, const int line)
+{
+	WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg);
+};
+EXPORT_SYMBOL_GPL(xdp_warn);