bpf, xdp: Restructure redirect actions

The XDP_REDIRECT implementations for maps and non-maps are fairly
similar, but obviously need to take different code paths depending on
if the target is using a map or not. Today, the redirect targets for
XDP either uses a map, or is based on ifindex.

Here, the map type and id are added to bpf_redirect_info, instead of
the actual map. Map type, map item/ifindex, and the map_id (if any) is
passed to xdp_do_redirect().

For ifindex-based redirect, used by the bpf_redirect() XDP BFP helper,
a special map type/id are used. Map type of UNSPEC together with map id
equal to INT_MAX has the special meaning of an ifindex based
redirect. Note that valid map ids are 1 inclusive, INT_MAX exclusive
([1,INT_MAX[).

In addition to making the code easier to follow, using explicit type
and id in bpf_redirect_info has a slight positive performance impact
by avoiding a pointer indirection for the map type lookup, and instead
use the cacheline for bpf_redirect_info.

Since the actual map is not passed via bpf_redirect_info anymore, the
map lookup is only done in the BPF helper. This means that the
bpf_clear_redirect_map() function can be removed. The actual map item
is RCU protected.

The bpf_redirect_info flags member is not used by XDP, and not
read/written any more. The map member is only written to when
required/used, and not unconditionally.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210308112907.559576-3-bjorn.topel@gmail.com

include/linux/filter.h

@@ -646,7 +646,8 @@ struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
-	struct bpf_map *map;
+	u32 map_id;
+	enum bpf_map_type map_type;
 	u32 kern_flags;
 	struct bpf_nh_params nh;
 };
@@ -1488,13 +1489,14 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
 		 * performs multiple lookups, the last one always takes
 		 * precedence.
 		 */
-		WRITE_ONCE(ri->map, NULL);
+		ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
+		ri->map_type = BPF_MAP_TYPE_UNSPEC;
 		return flags;
 	}
 
-	ri->flags = flags;
 	ri->tgt_index = ifindex;
-	WRITE_ONCE(ri->map, map);
+	ri->map_id = map->id;
+	ri->map_type = map->map_type;
 
 	return XDP_REDIRECT;
 }

include/trace/events/xdp.h

@@ -86,19 +86,15 @@ struct _bpf_dtab_netdev {
 };
 #endif /* __DEVMAP_OBJ_TYPE */
 
-#define devmap_ifindex(tgt, map)				\
-	(((map->map_type == BPF_MAP_TYPE_DEVMAP ||	\
-		  map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
-	  ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
-
 DECLARE_EVENT_CLASS(xdp_redirect_template,
 
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
 
-	TP_ARGS(dev, xdp, tgt, err, map, index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index),
 
 	TP_STRUCT__entry(
 		__field(int, prog_id)
@@ -111,14 +107,22 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 	),
 
 	TP_fast_assign(
+		u32 ifindex = 0, map_index = index;
+
+		if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+			ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+		} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
+			ifindex = index;
+			map_index = 0;
+		}
+
 		__entry->prog_id	= xdp->aux->id;
 		__entry->act		= XDP_REDIRECT;
 		__entry->ifindex	= dev->ifindex;
 		__entry->err		= err;
-		__entry->to_ifindex	= map ? devmap_ifindex(tgt, map) :
+		__entry->to_ifindex	= ifindex;
-						index;
+		__entry->map_id		= map_id;
-		__entry->map_id		= map ? map->id : 0;
+		__entry->map_index	= map_index;
-		__entry->map_index	= map ? index : 0;
 	),
 
 	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
@@ -133,45 +137,49 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
-#define _trace_xdp_redirect(dev, xdp, to)				\
+#define _trace_xdp_redirect(dev, xdp, to)						\
-	 trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to)
+	 trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
 
-#define _trace_xdp_redirect_err(dev, xdp, to, err)			\
+#define _trace_xdp_redirect_err(dev, xdp, to, err)					\
-	 trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to)
+	 trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
 
-#define _trace_xdp_redirect_map(dev, xdp, to, map, index)		\
+#define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \
-	 trace_xdp_redirect(dev, xdp, to, 0, map, index)
+	 trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index)
 
-#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err)	\
+#define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \
-	 trace_xdp_redirect_err(dev, xdp, to, err, map, index)
+	 trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index)
 
 /* not used anymore, but kept around so as not to break old programs */
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 TRACE_EVENT(xdp_cpumap_kthread,

kernel/bpf/cpumap.c

@@ -543,7 +543,6 @@ static void cpu_map_free(struct bpf_map *map)
 	 * complete.
 	 */
 
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* For cpu_map the remote CPUs can still be using the entries

kernel/bpf/devmap.c

@@ -197,7 +197,6 @@ static void dev_map_free(struct bpf_map *map)
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* Make sure prior __dev_map_entry_free() have completed. */

net/core/filter.c

@@ -3918,23 +3918,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
-			    struct bpf_map *map, struct xdp_buff *xdp)
-{
-	switch (map->map_type) {
-	case BPF_MAP_TYPE_DEVMAP:
-	case BPF_MAP_TYPE_DEVMAP_HASH:
-		return dev_map_enqueue(fwd, xdp, dev_rx);
-	case BPF_MAP_TYPE_CPUMAP:
-		return cpu_map_enqueue(fwd, xdp, dev_rx);
-	case BPF_MAP_TYPE_XSKMAP:
-		return __xsk_map_redirect(fwd, xdp);
-	default:
-		return -EBADRQC;
-	}
-	return 0;
-}
-
 void xdp_do_flush(void)
 {
 	__dev_flush();
@@ -3943,55 +3926,52 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
-void bpf_clear_redirect_map(struct bpf_map *map)
-{
-	struct bpf_redirect_info *ri;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
-		/* Avoid polluting remote cacheline due to writes if
-		 * not needed. Once we pass this test, we need the
-		 * cmpxchg() to make sure it hasn't been changed in
-		 * the meantime by remote CPU.
-		 */
-		if (unlikely(READ_ONCE(ri->map) == map))
-			cmpxchg(&ri->map, map, NULL);
-	}
-}
-
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct bpf_map *map = READ_ONCE(ri->map);
+	enum bpf_map_type map_type = ri->map_type;
-	u32 index = ri->tgt_index;
 	void *fwd = ri->tgt_value;
+	u32 map_id = ri->map_id;
 	int err;
 
-	ri->tgt_index = 0;
+	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
-	ri->tgt_value = NULL;
+	ri->map_type = BPF_MAP_TYPE_UNSPEC;
-	WRITE_ONCE(ri->map, NULL);
 
-	if (unlikely(!map)) {
+	switch (map_type) {
-		fwd = dev_get_by_index_rcu(dev_net(dev), index);
+	case BPF_MAP_TYPE_DEVMAP:
-		if (unlikely(!fwd)) {
+		fallthrough;
-			err = -EINVAL;
+	case BPF_MAP_TYPE_DEVMAP_HASH:
-			goto err;
+		err = dev_map_enqueue(fwd, xdp, dev);
+		break;
+	case BPF_MAP_TYPE_CPUMAP:
+		err = cpu_map_enqueue(fwd, xdp, dev);
+		break;
+	case BPF_MAP_TYPE_XSKMAP:
+		err = __xsk_map_redirect(fwd, xdp);
+		break;
+	case BPF_MAP_TYPE_UNSPEC:
+		if (map_id == INT_MAX) {
+			fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
+			if (unlikely(!fwd)) {
+				err = -EINVAL;
+				break;
+			}
+			err = dev_xdp_enqueue(fwd, xdp, dev);
+			break;
 		}
-
+		fallthrough;
-		err = dev_xdp_enqueue(fwd, xdp, dev);
+	default:
-	} else {
+		err = -EBADRQC;
-		err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
 	}
 
 	if (unlikely(err))
 		goto err;
 
-	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
 	return 0;
 err:
-	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
@@ -4000,41 +3980,36 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
 				       struct bpf_prog *xdp_prog,
-				       struct bpf_map *map)
+				       void *fwd,
+				       enum bpf_map_type map_type, u32 map_id)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	u32 index = ri->tgt_index;
+	int err;
-	void *fwd = ri->tgt_value;
-	int err = 0;
 
-	ri->tgt_index = 0;
+	switch (map_type) {
-	ri->tgt_value = NULL;
+	case BPF_MAP_TYPE_DEVMAP:
-	WRITE_ONCE(ri->map, NULL);
+		fallthrough;
-
+	case BPF_MAP_TYPE_DEVMAP_HASH:
-	if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
+		err = dev_map_generic_redirect(fwd, skb, xdp_prog);
-	    map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		struct bpf_dtab_netdev *dst = fwd;
-
-		err = dev_map_generic_redirect(dst, skb, xdp_prog);
 		if (unlikely(err))
 			goto err;
-	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+		break;
-		struct xdp_sock *xs = fwd;
+	case BPF_MAP_TYPE_XSKMAP:
-
+		err = xsk_generic_rcv(fwd, xdp);
-		err = xsk_generic_rcv(xs, xdp);
 		if (err)
 			goto err;
 		consume_skb(skb);
-	} else {
+		break;
+	default:
 		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
 		err = -EBADRQC;
 		goto err;
 	}
 
-	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
 	return 0;
 err:
-	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
 	return err;
 }
 
@@ -4042,31 +4017,34 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct bpf_map *map = READ_ONCE(ri->map);
+	enum bpf_map_type map_type = ri->map_type;
-	u32 index = ri->tgt_index;
+	void *fwd = ri->tgt_value;
-	struct net_device *fwd;
+	u32 map_id = ri->map_id;
-	int err = 0;
+	int err;
 
-	if (map)
+	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
-		return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog,
+	ri->map_type = BPF_MAP_TYPE_UNSPEC;
-						   map);
+
-	ri->tgt_index = 0;
+	if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
-	fwd = dev_get_by_index_rcu(dev_net(dev), index);
+		fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
-	if (unlikely(!fwd)) {
+		if (unlikely(!fwd)) {
-		err = -EINVAL;
+			err = -EINVAL;
-		goto err;
+			goto err;
+		}
+
+		err = xdp_ok_fwd_dev(fwd, skb->len);
+		if (unlikely(err))
+			goto err;
+
+		skb->dev = fwd;
+		_trace_xdp_redirect(dev, xdp_prog, ri->tgt_index);
+		generic_xdp_tx(skb, xdp_prog);
+		return 0;
 	}
 
-	err = xdp_ok_fwd_dev(fwd, skb->len);
+	return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id);
-	if (unlikely(err))
-		goto err;
-
-	skb->dev = fwd;
-	_trace_xdp_redirect(dev, xdp_prog, index);
-	generic_xdp_tx(skb, xdp_prog);
-	return 0;
 err:
-	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
+	_trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err);
 	return err;
 }
 
@@ -4077,10 +4055,12 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 	if (unlikely(flags))
 		return XDP_ABORTED;
 
-	ri->flags = flags;
+	/* NB! Map type UNSPEC and map_id == INT_MAX (never generated
+	 * by map_idr) is used for ifindex based XDP redirect.
+	 */
 	ri->tgt_index = ifindex;
-	ri->tgt_value = NULL;
+	ri->map_id = INT_MAX;
-	WRITE_ONCE(ri->map, NULL);
+	ri->map_type = BPF_MAP_TYPE_UNSPEC;
 
 	return XDP_REDIRECT;
 }

net/xdp/xskmap.c

@@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
 
-	bpf_clear_redirect_map(map);
 	synchronize_net();
 	bpf_map_area_free(m);
 }