xsk: wire up XDP_SKB side of AF_XDP

This commit wires up the xskmap to XDP_SKB layer.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/filter.h

@@ -760,7 +760,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
  * This does not appear to be a real limitation for existing software.
  */
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
-			    struct bpf_prog *prog);
+			    struct xdp_buff *xdp, struct bpf_prog *prog);
 int xdp_do_redirect(struct net_device *dev,
 		    struct xdp_buff *xdp,
 		    struct bpf_prog *prog);

net/core/dev.c

@@ -3994,12 +3994,12 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
 }
 
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct xdp_buff *xdp,
 				     struct bpf_prog *xdp_prog)
 {
 	struct netdev_rx_queue *rxqueue;
 	void *orig_data, *orig_data_end;
 	u32 metalen, act = XDP_DROP;
-	struct xdp_buff xdp;
 	int hlen, off;
 	u32 mac_len;
 
@@ -4034,19 +4034,19 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	 */
 	mac_len = skb->data - skb_mac_header(skb);
 	hlen = skb_headlen(skb) + mac_len;
-	xdp.data = skb->data - mac_len;
-	xdp.data_meta = xdp.data;
-	xdp.data_end = xdp.data + hlen;
-	xdp.data_hard_start = skb->data - skb_headroom(skb);
-	orig_data_end = xdp.data_end;
-	orig_data = xdp.data;
+	xdp->data = skb->data - mac_len;
+	xdp->data_meta = xdp->data;
+	xdp->data_end = xdp->data + hlen;
+	xdp->data_hard_start = skb->data - skb_headroom(skb);
+	orig_data_end = xdp->data_end;
+	orig_data = xdp->data;
 
 	rxqueue = netif_get_rxqueue(skb);
-	xdp.rxq = &rxqueue->xdp_rxq;
+	xdp->rxq = &rxqueue->xdp_rxq;
 
-	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
-	off = xdp.data - orig_data;
+	off = xdp->data - orig_data;
 	if (off > 0)
 		__skb_pull(skb, off);
 	else if (off < 0)
@@ -4056,10 +4056,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
 	 * pckt.
 	 */
-	off = orig_data_end - xdp.data_end;
+	off = orig_data_end - xdp->data_end;
 	if (off != 0) {
-		skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
+		skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
 		skb->len -= off;
+
 	}
 
 	switch (act) {
@@ -4068,7 +4069,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		__skb_push(skb, mac_len);
 		break;
 	case XDP_PASS:
-		metalen = xdp.data - xdp.data_meta;
+		metalen = xdp->data - xdp->data_meta;
 		if (metalen)
 			skb_metadata_set(skb, metalen);
 		break;
@@ -4118,17 +4119,19 @@ static struct static_key generic_xdp_needed __read_mostly;
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
 {
 	if (xdp_prog) {
-		u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+		struct xdp_buff xdp;
+		u32 act;
 		int err;
 
+		act = netif_receive_generic_xdp(skb, &xdp, xdp_prog);
 		if (act != XDP_PASS) {
 			switch (act) {
 			case XDP_REDIRECT:
 				err = xdp_do_generic_redirect(skb->dev, skb,
-							      xdp_prog);
+							      &xdp, xdp_prog);
 				if (err)
 					goto out_redir;
-			/* fallthru to submit skb */
+				break;
 			case XDP_TX:
 				generic_xdp_tx(skb, xdp_prog);
 				break;

net/core/filter.c

@@ -59,6 +59,7 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -2973,13 +2974,14 @@ static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
 
 static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
+				       struct xdp_buff *xdp,
 				       struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
-	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
+	void *fwd = NULL;
 	int err = 0;
 
 	ri->ifindex = 0;
@@ -3001,6 +3003,14 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 		if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
 			goto err;
 		skb->dev = fwd;
+		generic_xdp_tx(skb, xdp_prog);
+	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+		struct xdp_sock *xs = fwd;
+
+		err = xsk_generic_rcv(xs, xdp);
+		if (err)
+			goto err;
+		consume_skb(skb);
 	} else {
 		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
 		err = -EBADRQC;
@@ -3015,7 +3025,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 }
 
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
-			    struct bpf_prog *xdp_prog)
+			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 	u32 index = ri->ifindex;
@@ -3023,7 +3033,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 	int err = 0;
 
 	if (ri->map)
-		return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+		return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog);
 
 	ri->ifindex = 0;
 	fwd = dev_get_by_index_rcu(dev_net(dev), index);
@@ -3037,6 +3047,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 
 	skb->dev = fwd;
 	_trace_xdp_redirect(dev, xdp_prog, index);
+	generic_xdp_tx(skb, xdp_prog);
 	return 0;
 err:
 	_trace_xdp_redirect_err(dev, xdp_prog, index, err);