bpf_xdp_redirect_map: Perform map lookup in eBPF helper

The bpf_redirect_map() helper used by XDP programs doesn't return any
indication of whether it can successfully redirect to the map index it was
given. Instead, BPF programs have to track this themselves, leading to
programs using duplicate maps to track which entries are populated in the
devmap.

This patch fixes this by moving the map lookup into the bpf_redirect_map()
helper, which makes it possible to return failure to the eBPF program. The
lower bits of the flags argument is used as the return code, which means
that existing users who pass a '0' flag argument will get XDP_ABORTED.

With this, a BPF program can check the return code from the helper call and
react by, for instance, substituting a different redirect. This works for
any type of map used for redirect.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 18 insertions, 14 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index b4a062379bb9..4836264f82ee 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3605,17 +3605,13 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 			       struct bpf_redirect_info *ri)
 {
 	u32 index = ri->tgt_index;
-	void *fwd = NULL;
+	void *fwd = ri->tgt_value;
 	int err;
 
 	ri->tgt_index = 0;
+	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
-	fwd = __xdp_map_lookup_elem(map, index);
-	if (unlikely(!fwd)) {
-		err = -EINVAL;
-		goto err;
-	}
 	if (ri->map_to_flush && unlikely(ri->map_to_flush != map))
 		xdp_do_flush_map();
 
@@ -3652,18 +3648,13 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	u32 index = ri->tgt_index;
-	void *fwd = NULL;
+	void *fwd = ri->tgt_value;
 	int err = 0;
 
 	ri->tgt_index = 0;
+	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
-	fwd = __xdp_map_lookup_elem(map, index);
-	if (unlikely(!fwd)) {
-		err = -EINVAL;
-		goto err;
-	}
-
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		struct bpf_dtab_netdev *dst = fwd;
 
@@ -3732,6 +3723,7 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 
 	ri->flags = flags;
 	ri->tgt_index = ifindex;
+	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
 	return XDP_REDIRECT;
@@ -3750,9 +3742,21 @@ BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
-	if (unlikely(flags))
+	/* Lower bits of the flags are used as return code on lookup failure */
+	if (unlikely(flags > XDP_TX))
 		return XDP_ABORTED;
 
+	ri->tgt_value = __xdp_map_lookup_elem(map, ifindex);
+	if (unlikely(!ri->tgt_value)) {
+		/* If the lookup fails we want to clear out the state in the
+		 * redirect_info struct completely, so that if an eBPF program
+		 * performs multiple lookups, the last one always takes
+		 * precedence.
+		 */
+		WRITE_ONCE(ri->map, NULL);
+		return flags;
+	}
+
 	ri->flags = flags;
 	ri->tgt_index = ifindex;
 	WRITE_ONCE(ri->map, map);