diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b75207a2484cc1..4b68e975e990cc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1427,6 +1427,11 @@ 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);
@@ -1595,6 +1600,21 @@ 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,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7fdce5407214bb..dc9d79651c244f 100644
--- a/include/linux/filter.h
+++ b/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;
 };
diff --git a/include/net/xdp.h b/include/net/xdp.h
index c4bfdc9a8b79ff..fcc0f6f8bd910f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -169,6 +169,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct net_device *dev);
 struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					 struct net_device *dev);
+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)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c001766adcbc50..ef943c02432273 100644
--- a/include/uapi/linux/bpf.h
+++ b/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;			\
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 13ed68c24aad6d..6c9bc3c359e060 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -523,6 +523,134 @@ 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)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 89c60494dd6986..d645ec1f6d8892 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4461,6 +4461,7 @@ 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;
@@ -4565,6 +4566,11 @@ 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:
diff --git a/net/core/filter.c b/net/core/filter.c
index 9ab94e90d66059..03b3088ce8dbfb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3924,12 +3924,19 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 };
 
 static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
-			    struct bpf_map *map, struct xdp_buff *xdp)
+			    struct bpf_map *map, struct xdp_buff *xdp,
+			    struct bpf_map *ex_map, u32 flags)
 {
 	switch (map->map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		return dev_map_enqueue(fwd, xdp, dev_rx);
+		/* We use a NULL fwd value to distinguish multicast
+		 * and unicast forwarding
+		 */
+		if (fwd)
+			return dev_map_enqueue(fwd, xdp, dev_rx);
+		else
+			return dev_map_enqueue_multi(xdp, dev_rx, map, ex_map, flags);
 	case BPF_MAP_TYPE_CPUMAP:
 		return cpu_map_enqueue(fwd, xdp, dev_rx);
 	case BPF_MAP_TYPE_XSKMAP:
@@ -3986,12 +3993,19 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct bpf_map *map = READ_ONCE(ri->map);
+	struct bpf_map *ex_map = ri->ex_map;
 	u32 index = ri->tgt_index;
 	void *fwd = ri->tgt_value;
 	int err;
 
+	/* The READ/WRITE_ONCE() is not needed for ex_map because the field
+	 * is only read from or written to by the CPU owning the per-cpu
+	 * pointer. Whereas the 'map' field is manipulated by remote CPUs
+	 * in bpf_clear_redirect_map().
+	 */
 	ri->tgt_index = 0;
 	ri->tgt_value = NULL;
+	ri->ex_map = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
 	if (unlikely(!map)) {
@@ -4003,7 +4017,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 
 		err = dev_xdp_enqueue(fwd, xdp, dev);
 	} else {
-		err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+		err = __bpf_tx_xdp_map(dev, fwd, map, xdp, ex_map, ri->flags);
 	}
 
 	if (unlikely(err))
@@ -4017,6 +4031,63 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
+static int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+				  struct bpf_prog *xdp_prog,
+				  struct bpf_map *map, struct bpf_map *ex_map,
+				  u32 flags)
+
+{
+	struct bpf_dtab_netdev *dst;
+	struct sk_buff *nskb;
+	bool exclude_ingress;
+	u32 key, next_key, index;
+	void *fwd;
+	int err;
+
+	/* Get first key from forward map */
+	err = map->ops->map_get_next_key(map, NULL, &key);
+	if (err)
+		return err;
+
+	exclude_ingress = !!(flags & BPF_F_EXCLUDE_INGRESS);
+
+	/* 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++) {
+		fwd = __xdp_map_lookup_elem(map, key);
+		if (fwd) {
+			dst = (struct bpf_dtab_netdev *)fwd;
+			if (dev_in_exclude_map(dst, ex_map,
+					       exclude_ingress ? dev->ifindex : 0))
+				goto find_next;
+
+			nskb = skb_clone(skb, GFP_ATOMIC);
+			if (!nskb)
+				return -ENOMEM;
+
+			/* Try forword next one no mater the current forward
+			 * succeed or not.
+			 */
+			dev_map_generic_redirect(dst, nskb, xdp_prog);
+		}
+
+find_next:
+		err = map->ops->map_get_next_key(map, &key, &next_key);
+		if (err)
+			break;
+
+		key = next_key;
+	}
+
+	consume_skb(skb);
+	return 0;
+}
+
 static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
@@ -4024,19 +4095,30 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct bpf_map *map)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *ex_map = ri->ex_map;
 	u32 index = ri->tgt_index;
 	void *fwd = ri->tgt_value;
 	int err = 0;
 
 	ri->tgt_index = 0;
 	ri->tgt_value = NULL;
+	ri->ex_map = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
 	    map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		struct bpf_dtab_netdev *dst = fwd;
+		/* We use a NULL fwd value to distinguish multicast
+		 * and unicast forwarding
+		 */
+		if (fwd) {
+			struct bpf_dtab_netdev *dst = fwd;
+
+			err = dev_map_generic_redirect(dst, skb, xdp_prog);
+		} else {
+			err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+						     ex_map, ri->flags);
+		}
 
-		err = dev_map_generic_redirect(dst, skb, xdp_prog);
 		if (unlikely(err))
 			goto err;
 	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
@@ -4150,6 +4232,36 @@ static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_xdp_redirect_map_multi, struct bpf_map *, map,
+	   struct bpf_map *, ex_map, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	/* Limit ex_map type to DEVMAP_HASH to get better performance */
+	if (unlikely((ex_map && ex_map->map_type != BPF_MAP_TYPE_DEVMAP_HASH) ||
+		     flags & ~BPF_F_EXCLUDE_INGRESS))
+		return XDP_ABORTED;
+
+	ri->tgt_index = 0;
+	/* Set the tgt_value to NULL to distinguish with bpf_xdp_redirect_map */
+	ri->tgt_value = NULL;
+	ri->flags = flags;
+	ri->ex_map = ex_map;
+
+	WRITE_ONCE(ri->map, map);
+
+	return XDP_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_xdp_redirect_map_multi_proto = {
+	.func           = bpf_xdp_redirect_map_multi,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_CONST_MAP_PTR,
+	.arg2_type      = ARG_CONST_MAP_PTR_OR_NULL,
+	.arg3_type      = ARG_ANYTHING,
+};
+
 static unsigned long bpf_skb_copy(void *dst_buff, const void *skb,
 				  unsigned long off, unsigned long len)
 {
@@ -7248,6 +7360,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_proto;
 	case BPF_FUNC_redirect_map:
 		return &bpf_xdp_redirect_map_proto;
+	case BPF_FUNC_redirect_map_multi:
+		return &bpf_xdp_redirect_map_multi_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
 	case BPF_FUNC_fib_lookup:
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 0d2630a35c3e32..b44d05d24a2762 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -572,3 +572,32 @@ 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;
+}
+EXPORT_SYMBOL_GPL(xdpf_clone);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c001766adcbc50..ef943c02432273 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/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;			\