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, 18 insertions, 12 deletions

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index a5a0fb60193a..e1f4be4b3d69 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -884,23 +884,28 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 			  struct xdp_buff *xdp)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	unsigned int len = xdp->data_end - xdp->data;
+	unsigned int sync, len = xdp->data_end - xdp->data;
 	u32 ret = NETSEC_XDP_PASS;
+	struct page *page;
 	int err;
 	u32 act;
 
 	act = bpf_prog_run_xdp(prog, xdp);
 
+	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+	sync = xdp->data_end - xdp->data_hard_start - NETSEC_RXBUF_HEADROOM;
+	sync = max(sync, len);
+
 	switch (act) {
 	case XDP_PASS:
 		ret = NETSEC_XDP_PASS;
 		break;
 	case XDP_TX:
 		ret = netsec_xdp_xmit_back(priv, xdp);
-		if (ret != NETSEC_XDP_TX)
-			page_pool_put_page(dring->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+		if (ret != NETSEC_XDP_TX) {
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(dring->page_pool, page, sync, true);
+		}
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(priv->ndev, xdp, prog);
@@ -908,9 +913,8 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 			ret = NETSEC_XDP_REDIR;
 		} else {
 			ret = NETSEC_XDP_CONSUMED;
-			page_pool_put_page(dring->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(dring->page_pool, page, sync, true);
 		}
 		break;
 	default:
@@ -921,8 +925,8 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 		/* fall through -- handle aborts by dropping packet */
 	case XDP_DROP:
 		ret = NETSEC_XDP_CONSUMED;
-		page_pool_put_page(dring->page_pool,
-				   virt_to_head_page(xdp->data), len, true);
+		page = virt_to_head_page(xdp->data);
+		page_pool_put_page(dring->page_pool, page, sync, true);
 		break;
 	}
 
@@ -936,10 +940,14 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_rx_pkt_info rx_info;
 	enum dma_data_direction dma_dir;
 	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
 	u16 xdp_xmit = 0;
 	u32 xdp_act = 0;
 	int done = 0;
 
+	xdp.rxq = &dring->xdp_rxq;
+	xdp.frame_sz = PAGE_SIZE;
+
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(priv->xdp_prog);
 	dma_dir = page_pool_get_dma_dir(dring->page_pool);
@@ -953,7 +961,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct sk_buff *skb = NULL;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
-		struct xdp_buff xdp;
 		void *buf_addr;
 
 		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
@@ -1002,7 +1009,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		xdp.data = desc->addr + NETSEC_RXBUF_HEADROOM;
 		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + pkt_len;
-		xdp.rxq = &dring->xdp_rxq;
 
 		if (xdp_prog) {
 			xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);