diff mbox series

[PATCHv6,bpf-next,1/3] xdp: add a new helper for dev map multicast support

Message ID 20200709013008.3900892-2-liuhangbin@gmail.com
State Changes Requested
Delegated to: BPF Maintainers
Headers show
Series xdp: add a new helper for dev map multicast support | expand

Commit Message

Hangbin Liu July 9, 2020, 1:30 a.m. UTC 
This patch is for xdp multicast support. In this implementation we
add a new helper to accept two maps: forward map and exclude map.
We will redirect the packet to all the interfaces in *forward map*, but
exclude the interfaces that in *exclude map*.

To achive this I add a new ex_map for struct bpf_redirect_info.
in the helper I set tgt_value to NULL to make a difference with
bpf_xdp_redirect_map()

We also add a flag *BPF_F_EXCLUDE_INGRESS* incase you don't want to
create a exclude map for each interface and just want to exclude the
ingress interface.

The general data path is kept in net/core/filter.c. The native data
path is in kernel/bpf/devmap.c so we can use direct calls to
get better performace.

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.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
 include/linux/bpf.h            |  20 +++++
 include/linux/filter.h         |   1 +
 include/net/xdp.h              |   1 +
 include/uapi/linux/bpf.h       |  22 +++++
 kernel/bpf/devmap.c            | 154 +++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          |   6 ++
 net/core/filter.c              | 109 +++++++++++++++++++++--
 net/core/xdp.c                 |  29 +++++++
 tools/include/uapi/linux/bpf.h |  22 +++++
 9 files changed, 359 insertions(+), 5 deletions(-)

Comments

David Ahern July 9, 2020, 4:33 p.m. UTC | #1 
On 7/8/20 7:30 PM, Hangbin Liu wrote:
> This patch is for xdp multicast support. In this implementation we
> add a new helper to accept two maps: forward map and exclude map.
> We will redirect the packet to all the interfaces in *forward map*, but
> exclude the interfaces that in *exclude map*.
> 

good feature. I bet we could use this to create a simpler xdp dumper -
redirect to an xdpmon device which converts to an skb and passes to any
attached sockets.


> diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> index 10abb06065bb..617a51391971 100644
> --- a/kernel/bpf/devmap.c
> +++ b/kernel/bpf/devmap.c
> @@ -512,6 +512,160 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
>  	return __xdp_enqueue(dev, xdp, dev_rx);
>  }
>  
> +/* 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)
> +{
> +	struct bpf_dtab_netdev *ex_obj = NULL;
> +	u32 key, next_key;
> +	int err;
> +
> +	if (obj->dev->ifindex == exclude_ifindex)
> +		return true;
> +
> +	if (!map)
> +		return false;
> +
> +	err = devmap_get_next_key(map, NULL, &key);
> +	if (err)
> +		return false;
> +
> +	for (;;) {
> +		switch (map->map_type) {
> +		case BPF_MAP_TYPE_DEVMAP:
> +			ex_obj = __dev_map_lookup_elem(map, key);
> +			break;
> +		case BPF_MAP_TYPE_DEVMAP_HASH:
> +			ex_obj = __dev_map_hash_lookup_elem(map, key);
> +			break;
> +		default:
> +			break;
> +		}
> +
> +		if (ex_obj && ex_obj->dev->ifindex == obj->dev->ifindex)

I'm probably missing something fundamental, but why do you need to walk
the keys? Why not just do a lookup on the device index?

> +			return true;
> +
> +		err = devmap_get_next_key(map, &key, &next_key);
> +		if (err)
> +			break;
> +
> +		key = next_key;
> +	}
> +
> +	return false;
> +}
> +




> @@ -3741,6 +3810,34 @@ 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);
> +
> +	if (unlikely(!map || flags > BPF_F_EXCLUDE_INGRESS))

If flags is a bitfield, the check should be:
    flags & ~BPF_F_EXCLUDE_INGRESS
Hangbin Liu July 10, 2020, 6:55 a.m. UTC | #2 
Hi David,
On Thu, Jul 09, 2020 at 10:33:38AM -0600, David Ahern wrote:
> > +bool dev_in_exclude_map(struct bpf_dtab_netdev *obj, struct bpf_map *map,
> > +			int exclude_ifindex)
> > +{
> > +	struct bpf_dtab_netdev *ex_obj = NULL;
> > +	u32 key, next_key;
> > +	int err;
> > +
> > +	if (obj->dev->ifindex == exclude_ifindex)
> > +		return true;
> > +
> > +	if (!map)
> > +		return false;
> > +
> > +	err = devmap_get_next_key(map, NULL, &key);
> > +	if (err)
> > +		return false;
> > +
> > +	for (;;) {
> > +		switch (map->map_type) {
> > +		case BPF_MAP_TYPE_DEVMAP:
> > +			ex_obj = __dev_map_lookup_elem(map, key);
> > +			break;
> > +		case BPF_MAP_TYPE_DEVMAP_HASH:
> > +			ex_obj = __dev_map_hash_lookup_elem(map, key);
> > +			break;
> > +		default:
> > +			break;
> > +		}
> > +
> > +		if (ex_obj && ex_obj->dev->ifindex == obj->dev->ifindex)
> 
> I'm probably missing something fundamental, but why do you need to walk
> the keys? Why not just do a lookup on the device index?

This functions is to check if the device index is in exclude map.

The device indexes are stored as values in the map. The user could store
the values by any key number. There is no way to lookup the device index
directly unless loop the map and check each values we stored.

Is there a map feature which could get an exact value directly?

> > +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);
> > +
> > +	if (unlikely(!map || flags > BPF_F_EXCLUDE_INGRESS))
> 
> If flags is a bitfield, the check should be:
>     flags & ~BPF_F_EXCLUDE_INGRESS

Thanks for the tips, I will fix it.

Cheers
Hangbin
David Ahern July 10, 2020, 1:46 p.m. UTC | #3 
On 7/10/20 12:55 AM, Hangbin Liu wrote:
> Hi David,
> On Thu, Jul 09, 2020 at 10:33:38AM -0600, David Ahern wrote:
>>> +bool dev_in_exclude_map(struct bpf_dtab_netdev *obj, struct bpf_map *map,
>>> +			int exclude_ifindex)
>>> +{
>>> +	struct bpf_dtab_netdev *ex_obj = NULL;
>>> +	u32 key, next_key;
>>> +	int err;
>>> +
>>> +	if (obj->dev->ifindex == exclude_ifindex)
>>> +		return true;
>>> +
>>> +	if (!map)
>>> +		return false;
>>> +
>>> +	err = devmap_get_next_key(map, NULL, &key);
>>> +	if (err)
>>> +		return false;
>>> +
>>> +	for (;;) {
>>> +		switch (map->map_type) {
>>> +		case BPF_MAP_TYPE_DEVMAP:
>>> +			ex_obj = __dev_map_lookup_elem(map, key);
>>> +			break;
>>> +		case BPF_MAP_TYPE_DEVMAP_HASH:
>>> +			ex_obj = __dev_map_hash_lookup_elem(map, key);
>>> +			break;
>>> +		default:
>>> +			break;
>>> +		}
>>> +
>>> +		if (ex_obj && ex_obj->dev->ifindex == obj->dev->ifindex)
>>
>> I'm probably missing something fundamental, but why do you need to walk
>> the keys? Why not just do a lookup on the device index?
> 
> This functions is to check if the device index is in exclude map.
> 
> The device indexes are stored as values in the map. The user could store
> the values by any key number. There is no way to lookup the device index
> directly unless loop the map and check each values we stored.

Right.

The point of DEVMAP_HASH is to allow map management where key == device
index (vs DEVMAP which for any non-trivial use case is going to require
key != device index). You could require the exclude map to be
DEVMAP_HASH and the key to be the index allowing you to do a direct
lookup. Having to roam the entire map looking for a match does not scale
and is going to have poor performance with increasing number of entries.
XDP is targeted at performance with expert level of control, so
constraints like this have to be part of the deal.
Hangbin Liu July 11, 2020, 12:26 a.m. UTC | #4 
On Fri, Jul 10, 2020 at 07:46:18AM -0600, David Ahern wrote:
> >>
> >> I'm probably missing something fundamental, but why do you need to walk
> >> the keys? Why not just do a lookup on the device index?
> > 
> > This functions is to check if the device index is in exclude map.
> > 
> > The device indexes are stored as values in the map. The user could store
> > the values by any key number. There is no way to lookup the device index
> > directly unless loop the map and check each values we stored.
> 
> Right.
> 
> The point of DEVMAP_HASH is to allow map management where key == device
> index (vs DEVMAP which for any non-trivial use case is going to require
> key != device index). You could require the exclude map to be
> DEVMAP_HASH and the key to be the index allowing you to do a direct
> lookup. Having to roam the entire map looking for a match does not scale
> and is going to have poor performance with increasing number of entries.
> XDP is targeted at performance with expert level of control, so
> constraints like this have to be part of the deal.

Yes, if we have this constraints the performance should have some improvement.

Do you think we should do it right now or in later performance update patch.

Thanks
Hangbin
David Ahern July 11, 2020, 4:09 p.m. UTC | #5 
On 7/10/20 6:26 PM, Hangbin Liu wrote:
>>
>> The point of DEVMAP_HASH is to allow map management where key == device
>> index (vs DEVMAP which for any non-trivial use case is going to require
>> key != device index). You could require the exclude map to be
>> DEVMAP_HASH and the key to be the index allowing you to do a direct
>> lookup. Having to roam the entire map looking for a match does not scale
>> and is going to have poor performance with increasing number of entries.
>> XDP is targeted at performance with expert level of control, so
>> constraints like this have to be part of the deal.
> 
> Yes, if we have this constraints the performance should have some improvement.
> 
> Do you think we should do it right now or in later performance update patch.
> 

It needs to be in the same release as the initial patches. Easiest to
include with the initial set, but a followup is fine if it happens
before this dev cycle is over.
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0cd7f6884c5c..b48d587b8b3b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1264,6 +1264,11 @@  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);
@@ -1406,6 +1411,21 @@  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 259377723603..cf5b5b1d9ae5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -612,6 +612,7 @@  struct bpf_redirect_info {
 	u32 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
+	struct bpf_map *ex_map;
 	u32 kern_flags;
 };
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 609f819ed08b..deb6c104e698 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -110,6 +110,7 @@  void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
 
 struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
+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 548a749aebb3..a14e41309e73 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3319,6 +3319,22 @@  union bpf_attr {
  *		A non-negative value equal to or less than *size* on success,
  *		or a negative error in case of failure.
  *
+ * 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*.
+ *
+ * 		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),			\
@@ -3463,6 +3479,7 @@  union bpf_attr {
 	FN(skc_to_tcp_request_sock),	\
 	FN(skc_to_udp6_sock),		\
 	FN(get_task_stack),		\
+	FN(redirect_map_multi),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -3624,6 +3641,11 @@  enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_IP,
 };
 
+/* 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 10abb06065bb..617a51391971 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -512,6 +512,160 @@  int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return __xdp_enqueue(dev, xdp, dev_rx);
 }
 
+/* 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)
+{
+	struct bpf_dtab_netdev *ex_obj = NULL;
+	u32 key, next_key;
+	int err;
+
+	if (obj->dev->ifindex == exclude_ifindex)
+		return true;
+
+	if (!map)
+		return false;
+
+	err = devmap_get_next_key(map, NULL, &key);
+	if (err)
+		return false;
+
+	for (;;) {
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_DEVMAP:
+			ex_obj = __dev_map_lookup_elem(map, key);
+			break;
+		case BPF_MAP_TYPE_DEVMAP_HASH:
+			ex_obj = __dev_map_hash_lookup_elem(map, key);
+			break;
+		default:
+			break;
+		}
+
+		if (ex_obj && ex_obj->dev->ifindex == obj->dev->ifindex)
+			return true;
+
+		err = devmap_get_next_key(map, &key, &next_key);
+		if (err)
+			break;
+
+		key = next_key;
+	}
+
+	return false;
+}
+
+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;
+	int err;
+
+	err = devmap_get_next_key(map, tmp_key, next_key);
+	if (err)
+		return NULL;
+
+	for (;;) {
+		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;
+	bool last_one = false;
+	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)
+			last_one = true;
+
+		if (last_one) {
+			bq_enqueue(obj->dev, xdpf, dev_rx);
+			return 0;
+		}
+
+		nxdpf = xdpf_clone(xdpf);
+		if (unlikely(!nxdpf)) {
+			xdp_return_frame_rx_napi(xdpf);
+			return -ENOMEM;
+		}
+
+		bq_enqueue(obj->dev, nxdpf, dev_rx);
+
+		/* 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 b608185e1ffd..ceaf28ec111a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4110,6 +4110,7 @@  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;
@@ -4202,6 +4203,11 @@  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 ddcc0d6209e1..673d12a051ef 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3515,12 +3515,19 @@  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:
@@ -3577,12 +3584,14 @@  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;
 
 	ri->tgt_index = 0;
 	ri->tgt_value = NULL;
+	ri->ex_map = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
 	if (unlikely(!map)) {
@@ -3594,7 +3603,7 @@  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))
@@ -3608,6 +3617,55 @@  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;
+	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);
+
+	for (;;) {
+		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,
@@ -3615,19 +3673,30 @@  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) {
@@ -3741,6 +3810,34 @@  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);
+
+	if (unlikely(!map || 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,
+	.arg3_type      = ARG_ANYTHING,
+};
+
 static unsigned long bpf_skb_copy(void *dst_buff, const void *skb,
 				  unsigned long off, unsigned long len)
 {
@@ -6464,6 +6561,8 @@  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 3c45f99e26d5..9b43d0a208a7 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -476,3 +476,32 @@  void xdp_warn(const char *msg, const char *func, const int line)
 	WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg);
 };
 EXPORT_SYMBOL_GPL(xdp_warn);
+
+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 548a749aebb3..a14e41309e73 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3319,6 +3319,22 @@  union bpf_attr {
  *		A non-negative value equal to or less than *size* on success,
  *		or a negative error in case of failure.
  *
+ * 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*.
+ *
+ * 		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),			\
@@ -3463,6 +3479,7 @@  union bpf_attr {
 	FN(skc_to_tcp_request_sock),	\
 	FN(skc_to_udp6_sock),		\
 	FN(get_task_stack),		\
+	FN(redirect_map_multi),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -3624,6 +3641,11 @@  enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_IP,
 };
 
+/* BPF_FUNC_redirect_map_multi flags. */
+enum {
+	BPF_F_EXCLUDE_INGRESS		= (1ULL << 0),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\