[PATCH RFC bpf-next 1/4] bpf: Handle 8-byte values in DEVMAP and DEVMAP_HASH

[David Ahern <dsahern@kernel.org>]

Add support to DEVMAP and DEVMAP_HASH to support 8-byte values as a
<device index, program id> pair. To do this, a new struct is needed in
bpf_dtab_netdev to hold the values to return on lookup.

Signed-off-by: David Ahern <dsahern@kernel.org>
---
 kernel/bpf/devmap.c | 53 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a51d9fb7a359..2c01ce434306 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -60,12 +60,19 @@ struct xdp_dev_bulk_queue {
 	unsigned int count;
 };
 
+/* devmap value can be dev index or dev index + prog id */
+struct dev_map_ext_val {
+	u32 ifindex;	/* must be first for compat with 4-byte values */
+	u32 prog_id;
+};
+
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
 	struct rcu_head rcu;
 	unsigned int idx;
+	struct dev_map_ext_val val;
 };
 
 struct bpf_dtab {
@@ -108,9 +115,13 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 	u64 cost = 0;
 	int err;
 
-	/* check sanity of attributes */
+	/* check sanity of attributes. 2 value sizes supported:
+	 * 4 bytes: ifindex
+	 * 8 bytes: ifindex + prog id
+	 */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
+	    (attr->value_size != 4 && attr->value_size != 8) ||
+	    attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return -EINVAL;
 
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
@@ -472,18 +483,15 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
 
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
 								*(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
-
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void __dev_map_entry_free(struct rcu_head *rcu)
@@ -552,15 +560,18 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 		return ERR_PTR(-ENOMEM);
 
 	dev->dev = dev_get_by_index(net, ifindex);
-	if (!dev->dev) {
-		kfree(dev);
-		return ERR_PTR(-EINVAL);
-	}
+	if (!dev->dev)
+		goto err_out;
 
 	dev->idx = idx;
 	dev->dtab = dtab;
 
+	dev->val.ifindex = ifindex;
+
 	return dev;
+err_out:
+	kfree(dev);
+	return ERR_PTR(-EINVAL);
 }
 
 static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
@@ -568,8 +579,16 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
 	u32 i = *(u32 *)key;
+	u32 ifindex;
+
+	if (map->value_size == 4) {
+		ifindex = *(u32 *)value;
+	} else {
+		struct dev_map_ext_val *val = value;
+
+		ifindex = val->ifindex;
+	}
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -609,10 +628,18 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
 	u32 idx = *(u32 *)key;
 	unsigned long flags;
 	int err = -EEXIST;
+	u32 ifindex;
+
+	if (map->value_size == 4) {
+		ifindex = *(u32 *)value;
+	} else {
+		struct dev_map_ext_val *val = value;
+
+		ifindex = val->ifindex;
+	}
 
 	if (unlikely(map_flags > BPF_EXIST || !ifindex))
 		return -EINVAL;
-- 
2.21.1 (Apple Git-122.3)