xdp: Extend xdp_redirect_map with broadcast support

This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
extend xdp_redirect_map for broadcast support.

With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces
in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be
excluded when do broadcasting.

When getting the devices in dev hash map via dev_map_hash_get_next_key(),
there is a possibility that we fall back to the first key when a device
was removed. This will duplicate packets on some interfaces. So just walk
the whole buckets to avoid this issue. For dev array map, we also walk the
whole map to find valid interfaces.

Function bpf_clear_redirect_map() was removed in
commit ee75aef23afe ("bpf, xdp: Restructure redirect actions").
Add it back as we need to use ri->map again.

With test topology:
  +-------------------+             +-------------------+
  | Host A (i40e 10G) |  ---------- | eno1(i40e 10G)    |
  +-------------------+             |                   |
                                    |   Host B          |
  +-------------------+             |                   |
  | Host C (i40e 10G) |  ---------- | eno2(i40e 10G)    |
  +-------------------+             |                   |
                                    |          +------+ |
                                    | veth0 -- | Peer | |
                                    | veth1 -- |      | |
                                    | veth2 -- |  NS  | |
                                    |          +------+ |
                                    +-------------------+

On Host A:
 # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64

On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory):
Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing.
All the veth peers in the NS have a XDP_DROP program loaded. The
forward_map max_entries in xdp_redirect_map_multi is modify to 4.

Testing the performance impact on the regular xdp_redirect path with and
without patch (to check impact of additional check for broadcast mode):

5.12 rc4         | redirect_map        i40e->i40e      |    2.0M |  9.7M
5.12 rc4         | redirect_map        i40e->veth      |    1.7M | 11.8M
5.12 rc4 + patch | redirect_map        i40e->i40e      |    2.0M |  9.6M
5.12 rc4 + patch | redirect_map        i40e->veth      |    1.7M | 11.7M

Testing the performance when cloning packets with the redirect_map_multi
test, using a redirect map size of 4, filled with 1-3 devices:

5.12 rc4 + patch | redirect_map multi  i40e->veth (x1) |    1.7M | 11.4M
5.12 rc4 + patch | redirect_map multi  i40e->veth (x2) |    1.1M |  4.3M
5.12 rc4 + patch | redirect_map multi  i40e->veth (x3) |    0.8M |  2.6M

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com

2 files changed, 63 insertions, 2 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 582ac196fd94..caa88955562e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3930,6 +3930,23 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
+void bpf_clear_redirect_map(struct bpf_map *map)
+{
+	struct bpf_redirect_info *ri;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
+		/* Avoid polluting remote cacheline due to writes if
+		 * not needed. Once we pass this test, we need the
+		 * cmpxchg() to make sure it hasn't been changed in
+		 * the meantime by remote CPU.
+		 */
+		if (unlikely(READ_ONCE(ri->map) == map))
+			cmpxchg(&ri->map, map, NULL);
+	}
+}
+
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
@@ -3937,6 +3954,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	enum bpf_map_type map_type = ri->map_type;
 	void *fwd = ri->tgt_value;
 	u32 map_id = ri->map_id;
+	struct bpf_map *map;
 	int err;
 
 	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
@@ -3946,7 +3964,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_enqueue(fwd, xdp, dev);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_enqueue_multi(xdp, dev, map,
+						    ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_enqueue(fwd, xdp, dev);
+		}
 		break;
 	case BPF_MAP_TYPE_CPUMAP:
 		err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3988,13 +4013,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       enum bpf_map_type map_type, u32 map_id)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map;
 	int err;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+						     ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		}
 		if (unlikely(err))
 			goto err;
 		break;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 858276e72c68..725d20f1b100 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -584,3 +584,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	return __xdp_build_skb_from_frame(xdpf, skb, dev);
 }
 EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+	unsigned int headroom, totalsize;
+	struct xdp_frame *nxdpf;
+	struct page *page;
+	void *addr;
+
+	headroom = xdpf->headroom + sizeof(*xdpf);
+	totalsize = headroom + xdpf->len;
+
+	if (unlikely(totalsize > PAGE_SIZE))
+		return NULL;
+	page = dev_alloc_page();
+	if (!page)
+		return NULL;
+	addr = page_to_virt(page);
+
+	memcpy(addr, xdpf, totalsize);
+
+	nxdpf = addr;
+	nxdpf->data = addr + headroom;
+	nxdpf->frame_sz = PAGE_SIZE;
+	nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+	nxdpf->mem.id = 0;
+
+	return nxdpf;
+}