Re: [PATCH bpf-next v3 3/3] xsk: build skb by page

This patch is used to construct skb based on page to save memory copy
overhead.

This function is implemented based on IFF_TX_SKB_NO_LINEAR. Only the
network card priv_flags supports IFF_TX_SKB_NO_LINEAR will use page to
directly construct skb. If this feature is not supported, it is still
necessary to copy data to construct skb.

---------------- Performance Testing ------------

The test environment is Aliyun ECS server.
Test cmd:

xdpsock -i eth0 -t  -S -s <msg size>

Test result data:

size    64      512     1024    1500
copy    1916747 1775988 1600203 1440054
page    1974058 1953655 1945463 1904478
percent 3.0%    10.0%   21.58%  32.3%

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
---
 net/xdp/xsk.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 86 insertions(+), 18 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4a83117..38af7f1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c

@@ -430,6 +430,87 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
+					      struct xdp_desc *desc)
+{
+	u32 len, offset, copy, copied;
+	struct sk_buff *skb;
+	struct page *page;
+	void *buffer;
+	int err, i;
+	u64 addr;
+
+	skb = sock_alloc_send_skb(&xs->sk, 0, 1, &err);
+	if (unlikely(!skb))
+		return ERR_PTR(err);
+
+	addr = desc->addr;
+	len = desc->len;
+
+	buffer = xsk_buff_raw_get_data(xs->pool, addr);
+	offset = offset_in_page(buffer);
+	addr = buffer - xs->pool->addrs;
+
+	for (copied = 0, i = 0; copied < len; i++) {
+		page = xs->pool->umem->pgs[addr >> PAGE_SHIFT];
+
+		get_page(page);
+
+		copy = min_t(u32, PAGE_SIZE - offset, len - copied);
+
+		skb_fill_page_desc(skb, i, page, offset, copy);
+
+		copied += copy;
+		addr += copy;
+		offset = 0;
+	}
+
+	skb->len += len;
+	skb->data_len += len;