xdp: add a new helper for dev map multicast support

This patch is for xdp multicast support, which has been discussed
before[0], The goal is to be able to implement an OVS-like data plane in
XDP, i.e., a software switch that can forward XDP frames to multiple ports.

To achieve this, an application needs to specify a group of interfaces
to forward a packet to. It is also common to want to exclude one or more
physical interfaces from the forwarding operation - e.g., to forward a
packet to all interfaces in the multicast group except the interface it
arrived on. While this could be done simply by adding more groups, this
quickly leads to a combinatorial explosion in the number of groups an
application has to maintain.

To avoid the combinatorial explosion, we propose to include the ability
to specify an "exclude group" as part of the forwarding operation. This
needs to be a group (instead of just a single port index), because a
physical interface can be part of a logical grouping, such as a bond
device.

Thus, the logical forwarding operation becomes a "set difference"
operation, i.e. "forward to all ports in group A that are not also in
group B". This series implements such an operation using device maps to
represent the groups. This means that the XDP program specifies two
device maps, one containing the list of netdevs to redirect to, and the
other containing the exclude list.

To achieve this, a new helper bpf_redirect_map_multi() is implemented
to accept two maps, the forwarding map and exclude map. The forwarding
map could be DEVMAP or DEVMAP_HASH, but the exclude map *must* be
DEVMAP_HASH to get better performace. If user don't want to use exclude
map and just want simply stop redirecting back to ingress device, they
can use flag BPF_F_EXCLUDE_INGRESS.

As both bpf_xdp_redirect_map() and this new helpers are using struct
bpf_redirect_info, a new field ex_map is added and tgt_value is set to NULL
in the new helper to make a difference with bpf_xdp_redirect_map().

At last, keep the general data path in net/core/filter.c, the native data
path in kernel/bpf/devmap.c so we can use direct calls to get better
performace.

[0] https://xdp-project.net/#Handling-multicast

Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>

v16-v18: no update

v15:
a) Update bpf_redirect_map_multi() helper description that ex_map must be
   keyed by ifindex.
b) remove variable last_one in dev_map_enqueue_multi() as it's pointless.
c) add a comment about why we don't use READ/WRITE_ONCE() for ex_map.

v14: no update, only rebase the code

v13:
pass xdp_prog through bq_enqueue

v12:
rebase the code based on Jespoer's devmap xdp_prog patch

v11:
Fix bpf_redirect_map_multi() helper description typo.
Add loop limit for devmap_get_next_obj() and dev_map_redirect_multi().

v10:
Update helper bpf_xdp_redirect_map_multi()
- No need to check map pointer as we will do the check in verifier.

v9:
Update helper bpf_xdp_redirect_map_multi()
- Use ARG_CONST_MAP_PTR_OR_NULL for helper arg2

v8:
Update function dev_in_exclude_map():
- remove duplicate ex_map map_type check in
- lookup the element in dev map by obj dev index directly instead
  of looping all the map

v7:
a) Fix helper flag check
b) Limit the *ex_map* to use DEVMAP_HASH only and update function
   dev_in_exclude_map() to get better performance.

v6: converted helper return types from int to long

v5:
a) Check devmap_get_next_key() return value.
b) Pass through flags to __bpf_tx_xdp_map() instead of bool value.
c) In function dev_map_enqueue_multi(), consume xdpf for the last
   obj instead of the first on.
d) Update helper description and code comments to explain that we
   use NULL target value to distinguish multicast and unicast
   forwarding.
e) Update memory model, memory id and frame_sz in xdpf_clone().

v4: Fix bpf_xdp_redirect_map_multi_proto arg2_type typo

v3: Based on Toke's suggestion, do the following update
a) Update bpf_redirect_map_multi() description in bpf.h.
b) Fix exclude_ifindex checking order in dev_in_exclude_map().
c) Fix one more xdpf clone in dev_map_enqueue_multi().
d) Go find next one in dev_map_enqueue_multi() if the interface is not
   able to forward instead of abort the whole loop.
e) Remove READ_ONCE/WRITE_ONCE for ex_map.

v2: Add new syscall bpf_xdp_redirect_map_multi() which could accept
include/exclude maps directly.

Author: liuhangbin

include/linux/bpf.h

@@ -1441,6 +1441,11 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+bool dev_in_exclude_map(struct bpf_dtab_netdev *obj, struct bpf_map *map,
+			int exclude_ifindex);
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, struct bpf_map *ex_map,
+			  u32 flags);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
 bool dev_map_can_have_prog(struct bpf_map *map);
@@ -1609,6 +1614,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return 0;
 }
 
+static inline
+bool dev_in_exclude_map(struct bpf_dtab_netdev *obj, struct bpf_map *map,
+			int exclude_ifindex)
+{
+	return false;
+}
+
+static inline
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, struct bpf_map *ex_map,
+			  u32 flags)
+{
+	return 0;
+}
+
 struct sk_buff;
 
 static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,

include/linux/filter.h

@@ -637,6 +637,7 @@ struct bpf_redirect_info {
 	u32 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
+	struct bpf_map *ex_map;
 	u32 kern_flags;
 	struct bpf_nh_params nh;
 };

include/net/xdp.h

@@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					 struct net_device *dev);
 int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
 
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)

include/uapi/linux/bpf.h

@@ -3836,6 +3836,28 @@ union bpf_attr {
  *	Return
  *		A pointer to a struct socket on success or NULL if the file is
  *		not a socket.
+ *
+ * long bpf_redirect_map_multi(struct bpf_map *map, struct bpf_map *ex_map, u64 flags)
+ * 	Description
+ * 		This is a multicast implementation for XDP redirect. It will
+ * 		redirect the packet to ALL the interfaces in *map*, but
+ * 		exclude the interfaces in *ex_map*.
+ *
+ * 		The forwarding *map* could be either BPF_MAP_TYPE_DEVMAP or
+ * 		BPF_MAP_TYPE_DEVMAP_HASH. To get better performance, the
+ * 		*ex_map* is limited to BPF_MAP_TYPE_DEVMAP_HASH and must be
+ * 		keyed by ifindex for the helper to work.
+ *
+ * 		Currently the *flags* only supports *BPF_F_EXCLUDE_INGRESS*,
+ * 		which additionally excludes the current ingress device.
+ *
+ * 		See also bpf_redirect_map() as a unicast implementation,
+ * 		which supports redirecting packet to a specific ifindex
+ * 		in the map. As both helpers use struct bpf_redirect_info
+ * 		to store the redirect info, we will use a a NULL tgt_value
+ * 		to distinguish multicast and unicast redirecting.
+ * 	Return
+ * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4001,6 +4023,7 @@ union bpf_attr {
 	FN(ktime_get_coarse_ns),	\
 	FN(ima_inode_hash),		\
 	FN(sock_from_file),		\
+	FN(redirect_map_multi),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4177,6 +4200,11 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
+/* BPF_FUNC_redirect_map_multi flags. */
+enum {
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 0),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\

kernel/bpf/devmap.c

@@ -519,6 +519,134 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
 }
 
+/* Use direct call in fast path instead of map->ops->map_get_next_key() */
+static int devmap_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_DEVMAP:
+		return dev_map_get_next_key(map, key, next_key);
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+		return dev_map_hash_get_next_key(map, key, next_key);
+	default:
+		break;
+	}
+
+	return -ENOENT;
+}
+
+bool dev_in_exclude_map(struct bpf_dtab_netdev *obj, struct bpf_map *map,
+			int exclude_ifindex)
+{
+	if (obj->dev->ifindex == exclude_ifindex)
+		return true;
+
+	if (!map)
+		return false;
+
+	return __dev_map_hash_lookup_elem(map, obj->dev->ifindex) != NULL;
+}
+
+static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp, struct bpf_map *map,
+						   struct bpf_map *ex_map, u32 *key,
+						   u32 *next_key, int ex_ifindex)
+{
+	struct bpf_dtab_netdev *obj;
+	struct net_device *dev;
+	u32 *tmp_key = key;
+	u32 index;
+	int err;
+
+	err = devmap_get_next_key(map, tmp_key, next_key);
+	if (err)
+		return NULL;
+
+	/* When using dev map hash, we could restart the hashtab traversal
+	 * in case the key has been updated/removed in the mean time.
+	 * So we may end up potentially looping due to traversal restarts
+	 * from first elem.
+	 *
+	 * Let's use map's max_entries to limit the loop number.
+	 */
+	for (index = 0; index < map->max_entries; index++) {
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_DEVMAP:
+			obj = __dev_map_lookup_elem(map, *next_key);
+			break;
+		case BPF_MAP_TYPE_DEVMAP_HASH:
+			obj = __dev_map_hash_lookup_elem(map, *next_key);
+			break;
+		default:
+			break;
+		}
+
+		if (!obj || dev_in_exclude_map(obj, ex_map, ex_ifindex))
+			goto find_next;
+
+		dev = obj->dev;
+
+		if (!dev->netdev_ops->ndo_xdp_xmit)
+			goto find_next;
+
+		err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+		if (unlikely(err))
+			goto find_next;
+
+		return obj;
+
+find_next:
+		tmp_key = next_key;
+		err = devmap_get_next_key(map, tmp_key, next_key);
+		if (err)
+			break;
+	}
+
+	return NULL;
+}
+
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, struct bpf_map *ex_map,
+			  u32 flags)
+{
+	struct bpf_dtab_netdev *obj = NULL, *next_obj = NULL;
+	struct xdp_frame *xdpf, *nxdpf;
+	int ex_ifindex;
+	u32 key, next_key;
+
+	ex_ifindex = flags & BPF_F_EXCLUDE_INGRESS ? dev_rx->ifindex : 0;
+
+	/* Find first available obj */
+	obj = devmap_get_next_obj(xdp, map, ex_map, NULL, &key, ex_ifindex);
+	if (!obj)
+		return 0;
+
+	xdpf = xdp_convert_buff_to_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	for (;;) {
+		/* Check if we still have one more available obj */
+		next_obj = devmap_get_next_obj(xdp, map, ex_map, &key,
+					       &next_key, ex_ifindex);
+		if (!next_obj) {
+			bq_enqueue(obj->dev, xdpf, dev_rx, obj->xdp_prog);
+			return 0;
+		}
+
+		nxdpf = xdpf_clone(xdpf);
+		if (unlikely(!nxdpf)) {
+			xdp_return_frame_rx_napi(xdpf);
+			return -ENOMEM;
+		}
+
+		bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+		/* Deal with next obj */
+		obj = next_obj;
+		key = next_key;
+	}
+}
+
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog)
 {

kernel/bpf/verifier.c

@@ -4469,6 +4469,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
 		if (func_id != BPF_FUNC_redirect_map &&
+		    func_id != BPF_FUNC_redirect_map_multi &&
 		    func_id != BPF_FUNC_map_lookup_elem)
 			goto error;
 		break;
@@ -4573,6 +4574,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_XSKMAP)
 			goto error;
 		break;
+	case BPF_FUNC_redirect_map_multi:
+		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+		    map->map_type != BPF_MAP_TYPE_DEVMAP_HASH)
+			goto error;
+		break;
 	case BPF_FUNC_sk_redirect_map:
 	case BPF_FUNC_msg_redirect_map:
 	case BPF_FUNC_sock_map_update: