xdp: add a new helper for dev map multicast support

.travis.yml

@@ -0,0 +1,32 @@
+sudo: required
+language: bash
+dist: bionic
+services:
+    - docker
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

include/linux/bpf.h

@@ -292,6 +292,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	ARG_CONST_MAP_PTR_OR_NULL,	/* const argument used as pointer to bpf_map or NULL */
 };
 
 /* type of values returned from helper functions */
@@ -1341,6 +1342,11 @@ 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);
@@ -1516,6 +1522,21 @@ 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

@@ -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;
 };
 

include/net/xdp.h

@@ -132,6 +132,7 @@ 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)

include/uapi/linux/bpf.h

@@ -3579,6 +3579,27 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 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*.
+ *
+ * 		The forwarding *map* could be either BPF_MAP_TYPE_DEVMAP or
+ * 		BPF_MAP_TYPE_DEVMAP_HASH. But the *ex_map* must be
+ * 		BPF_MAP_TYPE_DEVMAP_HASH to get better performance.
+ *
+ * 		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),			\
@@ -3730,6 +3751,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(redirect_map_multi),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -3901,6 +3923,11 @@ 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;			\

kernel/bpf/devmap.c

@@ -511,6 +511,138 @@ 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)
+{
+	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;
+	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)
 {

kernel/bpf/verifier.c

@@ -3966,9 +3966,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		expected_type = SCALAR_VALUE;
 		if (type != expected_type)
 			goto err_type;
-	} else if (arg_type == ARG_CONST_MAP_PTR) {
+	} else if (arg_type == ARG_CONST_MAP_PTR ||
+		   arg_type == ARG_CONST_MAP_PTR_OR_NULL) {
 		expected_type = CONST_PTR_TO_MAP;
-		if (type != expected_type)
+		if (register_is_null(reg) &&
+		    arg_type == ARG_CONST_MAP_PTR_OR_NULL)
+			/* fall through to next check */;
+		else if (type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_PTR_TO_CTX ||
 		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
@@ -4085,9 +4089,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		return -EFAULT;
 	}
 
-	if (arg_type == ARG_CONST_MAP_PTR) {
-		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
-		meta->map_ptr = reg->map_ptr;
+	if (arg_type == ARG_CONST_MAP_PTR ||
+	    arg_type == ARG_CONST_MAP_PTR_OR_NULL) {
+		meta->map_ptr = register_is_null(reg) ? NULL : reg->map_ptr;
 	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
 		/* bpf_map_xxx(..., map_ptr, ..., key) call:
 		 * check that [key, key + map->key_size) are within
@@ -4269,6 +4273,7 @@ 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;
@@ -4368,6 +4373,11 @@ 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: