bpf: devmap introduce dev_map_enqueue

Functionality is the same, but the ndo_xdp_xmit call is now
simply invoked from inside the devmap.c code.

V2: Fix compile issue reported by kbuild test robot <lkp@intel.com>

V5: Cleanups requested by Daniel
 - Newlines before func definition
 - Use BUILD_BUG_ON checks
 - Remove unnecessary use return value store in dev_map_enqueue

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -487,14 +487,16 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
 /* Map specifics */
-struct net_device  *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
+struct xdp_buff;
+
+struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp);
 
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
 void __cpu_map_flush(struct bpf_map *map);
-struct xdp_buff;
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 
@@ -573,6 +575,15 @@ static inline void __dev_map_flush(struct bpf_map *map)
 {
 }
 
+struct xdp_buff;
+struct bpf_dtab_netdev;
+
+static inline
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp)
+{
+	return 0;
+}
+
 static inline
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -587,7 +598,6 @@ static inline void __cpu_map_flush(struct bpf_map *map)
 {
 }
 
-struct xdp_buff;
 static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 				  struct xdp_buff *xdp,
 				  struct net_device *dev_rx)

include/trace/events/xdp.h

@@ -138,11 +138,18 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
 		  __entry->map_id, __entry->map_index)
 );
 
+#ifndef __DEVMAP_OBJ_TYPE
+#define __DEVMAP_OBJ_TYPE
+struct _bpf_dtab_netdev {
+	struct net_device *dev;
+};
+#endif /* __DEVMAP_OBJ_TYPE */
+
 #define devmap_ifindex(fwd, map)				\
 	(!fwd ? 0 :						\
 	 (!map ? 0 :						\
 	  ((map->map_type == BPF_MAP_TYPE_DEVMAP) ?		\
-	   ((struct net_device *)fwd)->ifindex : 0)))
+	   ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)))
 
 #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\
 	 trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map),	\

kernel/bpf/devmap.c

@@ -48,13 +48,15 @@
  * calls will fail at this point.
  */
 #include <linux/bpf.h>
+#include <net/xdp.h>
 #include <linux/filter.h>
+#include <trace/events/xdp.h>
 
 #define DEV_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
 struct bpf_dtab_netdev {
-	struct net_device *dev;
+	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct bpf_dtab *dtab;
 	unsigned int bit;
 	struct rcu_head rcu;
@@ -240,21 +242,38 @@ void __dev_map_flush(struct bpf_map *map)
  * update happens in parallel here a dev_put wont happen until after reading the
  * ifindex.
  */
-struct net_device  *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
+struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	struct bpf_dtab_netdev *dev;
+	struct bpf_dtab_netdev *obj;
 
 	if (key >= map->max_entries)
 		return NULL;
 
-	dev = READ_ONCE(dtab->netdev_map[key]);
-	return dev ? dev->dev : NULL;
+	obj = READ_ONCE(dtab->netdev_map[key]);
+	return obj;
+}
+
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp)
+{
+	struct net_device *dev = dst->dev;
+	struct xdp_frame *xdpf;
+
+	if (!dev->netdev_ops->ndo_xdp_xmit)
+		return -EOPNOTSUPP;
+
+	xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	/* TODO: implement a bulking/enqueue step later */
+	return dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
 }
 
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
-	struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key);
+	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
+	struct net_device *dev = dev = obj ? obj->dev : NULL;
 
 	return dev ? &dev->ifindex : NULL;
 }
@@ -405,6 +424,9 @@ static struct notifier_block dev_map_notifier = {
 
 static int __init dev_map_init(void)
 {
+	/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
+	BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
+		     offsetof(struct _bpf_dtab_netdev, dev));
 	register_netdevice_notifier(&dev_map_notifier);
 	return 0;
 }

net/core/filter.c

@@ -3065,20 +3065,9 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 
 	switch (map->map_type) {
 	case BPF_MAP_TYPE_DEVMAP: {
-		struct net_device *dev = fwd;
-		struct xdp_frame *xdpf;
+		struct bpf_dtab_netdev *dst = fwd;
 
-		if (!dev->netdev_ops->ndo_xdp_xmit)
-			return -EOPNOTSUPP;
-
-		xdpf = convert_to_xdp_frame(xdp);
-		if (unlikely(!xdpf))
-			return -EOVERFLOW;
-
-		/* TODO: move to inside map code instead, for bulk support
-		 * err = dev_map_enqueue(dev, xdp);
-		 */
-		err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
+		err = dev_map_enqueue(dst, xdp);
 		if (err)
 			return err;
 		__dev_map_insert_ctx(map, index);