xsk: add support for AF_XDP multi-buffer on Rx path

Add multi-buffer support for AF_XDP by extending the XDP multi-buffer
support to be reflected in user-space when a packet is redirected to
an AF_XDP socket.

In the XDP implementation, the NIC driver builds the xdp_buff from the
first frag of the packet and adds any subsequent frags in the skb_shinfo
area of the xdp_buff. In AF_XDP core, XDP buffers are allocated from
xdp_sock's pool and data is copied from the driver's xdp_buff and frags.

Once an allocated XDP buffer is full and there is still data to be
copied, the 'XDP_PKT_CONTD' flag in'options' field of the corresponding
xdp ring descriptor is set and passed to the application. When application
sees the aforementioned flag set it knows there is pending data for this
packet that will be carried in the following descriptors. If there is no
more data to be copied, the flag in 'options' field is cleared for that
descriptor signalling EOP to the application.

If application reads a batch of descriptors using for example the libxdp
interfaces, it is not guaranteed that the batch will end with a full
packet. It might end in the middle of a packet and the rest of the frames
of that packet will arrive at the beginning of the next batch.

AF_XDP ensures that only a complete packet (along with all its frags) is
sent to application.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-6-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

net/core/filter.c

@@ -4345,13 +4345,8 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	enum bpf_map_type map_type = ri->map_type;
 
-	if (map_type == BPF_MAP_TYPE_XSKMAP) {
-		/* XDP_REDIRECT is not supported AF_XDP yet. */
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			return -EOPNOTSUPP;
-
+	if (map_type == BPF_MAP_TYPE_XSKMAP)
 		return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
-	}
 
 	return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
 				       xdp_prog);

net/xdp/xsk.c

@@ -159,43 +159,107 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	return __xsk_rcv_zc(xs, xskb, len, 0);
 }
 
-static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
+static void *xsk_copy_xdp_start(struct xdp_buff *from)
 {
-	void *from_buf, *to_buf;
-	u32 metalen;
+	if (unlikely(xdp_data_meta_unsupported(from)))
+		return from->data;
+	else
+		return from->data_meta;
+}
 
-	if (unlikely(xdp_data_meta_unsupported(from))) {
-		from_buf = from->data;
-		to_buf = to->data;
-		metalen = 0;
-	} else {
-		from_buf = from->data_meta;
-		metalen = from->data - from->data_meta;
-		to_buf = to->data - metalen;
+static u32 xsk_copy_xdp(void *to, void **from, u32 to_len,
+			u32 *from_len, skb_frag_t **frag, u32 rem)
+{
+	u32 copied = 0;
+
+	while (1) {
+		u32 copy_len = min_t(u32, *from_len, to_len);
+
+		memcpy(to, *from, copy_len);
+		copied += copy_len;
+		if (rem == copied)
+			return copied;
+
+		if (*from_len == copy_len) {
+			*from = skb_frag_address(*frag);
+			*from_len = skb_frag_size((*frag)++);
+		} else {
+			*from += copy_len;
+			*from_len -= copy_len;
+		}
+		if (to_len == copy_len)
+			return copied;
+
+		to_len -= copy_len;
+		to += copy_len;
 	}
-
-	memcpy(to_buf, from_buf, len + metalen);
 }
 
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
+	u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool);
+	void *copy_from = xsk_copy_xdp_start(xdp), *copy_to;
+	u32 from_len, meta_len, rem, num_desc;
 	struct xdp_buff_xsk *xskb;
 	struct xdp_buff *xsk_xdp;
-	int err;
+	skb_frag_t *frag;
 
-	xsk_xdp = xsk_buff_alloc(xs->pool);
-	if (!xsk_xdp) {
+	from_len = xdp->data_end - copy_from;
+	meta_len = xdp->data - copy_from;
+	rem = len + meta_len;
+
+	if (len <= frame_size && !xdp_buff_has_frags(xdp)) {
+		int err;
+
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		if (!xsk_xdp) {
+			xs->rx_dropped++;
+			return -ENOMEM;
+		}
+		memcpy(xsk_xdp->data - meta_len, copy_from, rem);
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		err = __xsk_rcv_zc(xs, xskb, len, 0);
+		if (err) {
+			xsk_buff_free(xsk_xdp);
+			return err;
+		}
+
+		return 0;
+	}
+
+	num_desc = (len - 1) / frame_size + 1;
+
+	if (!xsk_buff_can_alloc(xs->pool, num_desc)) {
 		xs->rx_dropped++;
 		return -ENOMEM;
 	}
-
-	xsk_copy_xdp(xsk_xdp, xdp, len);
-	xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
-	err = __xsk_rcv_zc(xs, xskb, len, 0);
-	if (err) {
-		xsk_buff_free(xsk_xdp);
-		return err;
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		return -ENOBUFS;
 	}
+
+	if (xdp_buff_has_frags(xdp)) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		frag =  &sinfo->frags[0];
+	}
+
+	do {
+		u32 to_len = frame_size + meta_len;
+		u32 copied;
+
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		copy_to = xsk_xdp->data - meta_len;
+
+		copied = xsk_copy_xdp(copy_to, &copy_from, to_len, &from_len, &frag, rem);
+		rem -= copied;
+
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		__xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0);
+		meta_len = 0;
+	} while (rem);
+
 	return 0;
 }
 
@@ -225,7 +289,7 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
-	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
+	if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}