1 files changed, 467 insertions, 168 deletions

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 5fdbc776a760..482d284a1553 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -48,6 +48,7 @@
 #include <net/xdp.h>
 #include <linux/filter.h>
 #include <trace/events/xdp.h>
+#include <linux/btf_ids.h>
 
 #define DEV_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -57,13 +58,13 @@ struct xdp_dev_bulk_queue {
 	struct list_head flush_node;
 	struct net_device *dev;
 	struct net_device *dev_rx;
+	struct bpf_prog *xdp_prog;
 	unsigned int count;
 };
 
 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 bpf_prog *xdp_prog;
 	struct rcu_head rcu;
 	unsigned int idx;
@@ -72,7 +73,7 @@ struct bpf_dtab_netdev {
 
 struct bpf_dtab {
 	struct bpf_map map;
-	struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */
+	struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */
 	struct list_head list;
 
 	/* these are only used for DEVMAP_HASH type maps */
@@ -82,7 +83,6 @@ struct bpf_dtab {
 	u32 n_buckets;
 };
 
-static DEFINE_PER_CPU(struct list_head, dev_flush_list);
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
@@ -92,7 +92,7 @@ static struct hlist_head *dev_map_create_hash(unsigned int entries,
 	int i;
 	struct hlist_head *hash;
 
-	hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node);
+	hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node);
 	if (hash != NULL)
 		for (i = 0; i < entries; i++)
 			INIT_HLIST_HEAD(&hash[i]);
@@ -106,11 +106,9 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
 	return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
 }
 
-static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
+static int dev_map_alloc_check(union bpf_attr *attr)
 {
 	u32 valsize = attr->value_size;
-	u64 cost = 0;
-	int err;
 
 	/* check sanity of attributes. 2 value sizes supported:
 	 * 4 bytes: ifindex
@@ -122,49 +120,43 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 	    attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return -EINVAL;
 
+	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		/* Hash table size must be power of 2; roundup_pow_of_two()
+		 * can overflow into UB on 32-bit arches
+		 */
+		if (attr->max_entries > 1UL << 31)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
+{
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
 	 * verifier prevents writes from the BPF side
 	 */
 	attr->map_flags |= BPF_F_RDONLY_PROG;
-
-
 	bpf_map_init_from_attr(&dtab->map, attr);
 
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		/* Hash table size must be power of 2 */
 		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
-
-		if (!dtab->n_buckets) /* Overflow check */
-			return -EINVAL;
-		cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets;
-	} else {
-		cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
-	}
-
-	/* if map size is larger than memlock limit, reject it */
-	err = bpf_map_charge_init(&dtab->map.memory, cost);
-	if (err)
-		return -EINVAL;
-
-	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
 		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
 							   dtab->map.numa_node);
 		if (!dtab->dev_index_head)
-			goto free_charge;
+			return -ENOMEM;
 
 		spin_lock_init(&dtab->index_lock);
 	} else {
-		dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
+		dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries *
 						      sizeof(struct bpf_dtab_netdev *),
 						      dtab->map.numa_node);
 		if (!dtab->netdev_map)
-			goto free_charge;
+			return -ENOMEM;
 	}
 
 	return 0;
-
-free_charge:
-	bpf_map_charge_finish(&dtab->map.memory);
-	return -ENOMEM;
 }
 
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
@@ -172,16 +164,13 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	struct bpf_dtab *dtab;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
-	dtab = kzalloc(sizeof(*dtab), GFP_USER);
+	dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE);
 	if (!dtab)
 		return ERR_PTR(-ENOMEM);
 
 	err = dev_map_init_map(dtab, attr);
 	if (err) {
-		kfree(dtab);
+		bpf_map_area_free(dtab);
 		return ERR_PTR(err);
 	}
 
@@ -195,7 +184,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 static void dev_map_free(struct bpf_map *map)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	int i;
+	u32 i;
 
 	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
 	 * so the programs (can be more than one that used this map) were
@@ -211,7 +200,14 @@ static void dev_map_free(struct bpf_map *map)
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
-	bpf_clear_redirect_map(map);
+	/* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map()
+	 * during NAPI callback and cleared after the XDP redirect. There is no
+	 * explicit RCU read section which protects bpf_redirect_info->map but
+	 * local_bh_disable() also marks the beginning an RCU section. This
+	 * makes the complete softirq callback RCU protected. Thus after
+	 * following synchronize_rcu() there no bpf_redirect_info->map == map
+	 * assignment.
+	 */
 	synchronize_rcu();
 
 	/* Make sure prior __dev_map_entry_free() have completed. */
@@ -239,7 +235,7 @@ static void dev_map_free(struct bpf_map *map)
 		for (i = 0; i < dtab->map.max_entries; i++) {
 			struct bpf_dtab_netdev *dev;
 
-			dev = dtab->netdev_map[i];
+			dev = rcu_dereference_raw(dtab->netdev_map[i]);
 			if (!dev)
 				continue;
 
@@ -252,7 +248,7 @@ static void dev_map_free(struct bpf_map *map)
 		bpf_map_area_free(dtab->netdev_map);
 	}
 
-	kfree(dtab);
+	bpf_map_area_free(dtab);
 }
 
 static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -272,7 +268,11 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
+static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct hlist_head *head = dev_map_index_hash(dtab, key);
@@ -331,82 +331,112 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 	return -ENOENT;
 }
 
-bool dev_map_can_have_prog(struct bpf_map *map)
+static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
+				struct xdp_frame **frames, int n,
+				struct net_device *tx_dev,
+				struct net_device *rx_dev)
 {
-	if ((map->map_type == BPF_MAP_TYPE_DEVMAP ||
-	     map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) &&
-	    map->value_size != offsetofend(struct bpf_devmap_val, ifindex))
-		return true;
-
-	return false;
+	struct xdp_txq_info txq = { .dev = tx_dev };
+	struct xdp_rxq_info rxq = { .dev = rx_dev };
+	struct xdp_buff xdp;
+	int i, nframes = 0;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		u32 act;
+		int err;
+
+		xdp_convert_frame_to_buff(xdpf, &xdp);
+		xdp.txq = &txq;
+		xdp.rxq = &rxq;
+
+		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		switch (act) {
+		case XDP_PASS:
+			err = xdp_update_frame_from_buff(&xdp, xdpf);
+			if (unlikely(err < 0))
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				frames[nframes++] = xdpf;
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(tx_dev, xdp_prog, act);
+			fallthrough;
+		case XDP_DROP:
+			xdp_return_frame_rx_napi(xdpf);
+			break;
+		}
+	}
+	return nframes; /* sent frames count */
 }
 
-static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
+static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 {
 	struct net_device *dev = bq->dev;
-	int sent = 0, drops = 0, err = 0;
+	unsigned int cnt = bq->count;
+	int sent = 0, err = 0;
+	int to_send = cnt;
 	int i;
 
-	if (unlikely(!bq->count))
-		return 0;
+	if (unlikely(!cnt))
+		return;
 
-	for (i = 0; i < bq->count; i++) {
+	for (i = 0; i < cnt; i++) {
 		struct xdp_frame *xdpf = bq->q[i];
 
 		prefetch(xdpf);
 	}
 
-	sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+	if (bq->xdp_prog) {
+		to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx);
+		if (!to_send)
+			goto out;
+	}
+
+	sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
 	if (sent < 0) {
+		/* If ndo_xdp_xmit fails with an errno, no frames have
+		 * been xmit'ed.
+		 */
 		err = sent;
 		sent = 0;
-		goto error;
 	}
-	drops = bq->count - sent;
-out:
-	bq->count = 0;
 
-	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
-	bq->dev_rx = NULL;
-	__list_del_clearprev(&bq->flush_node);
-	return 0;
-error:
-	/* If ndo_xdp_xmit fails with an errno, no frames have been
-	 * xmit'ed and it's our responsibility to them free all.
+	/* If not all frames have been transmitted, it is our
+	 * responsibility to free them
 	 */
-	for (i = 0; i < bq->count; i++) {
-		struct xdp_frame *xdpf = bq->q[i];
+	for (i = sent; unlikely(i < to_send); i++)
+		xdp_return_frame_rx_napi(bq->q[i]);
 
-		xdp_return_frame_rx_napi(xdpf);
-		drops++;
-	}
-	goto out;
-}
-
-/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
- * from the driver before returning from its napi->poll() routine. The poll()
- * routine is called either from busy_poll context or net_rx_action signaled
- * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
- * net device can be torn down. On devmap tear down we ensure the flush list
- * is empty before completing to ensure all flush operations have completed.
- * When drivers update the bpf program they may need to ensure any flush ops
- * are also complete. Using synchronize_rcu or call_rcu will suffice for this
- * because both wait for napi context to exit.
+out:
+	bq->count = 0;
+	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
+}
+
+/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the
+ * driver before returning from its napi->poll() routine. See the comment above
+ * xdp_do_flush() in filter.c.
  */
-void __dev_flush(void)
+void __dev_flush(struct list_head *flush_list)
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
 	struct xdp_dev_bulk_queue *bq, *tmp;
 
-	list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
 		bq_xmit_all(bq, XDP_XMIT_FLUSH);
+		bq->dev_rx = NULL;
+		bq->xdp_prog = NULL;
+		__list_del_clearprev(&bq->flush_node);
+	}
 }
 
-/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
- * update happens in parallel here a dev_put wont happen until after reading the
- * ifindex.
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
  */
-struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
+static void *__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 *obj;
@@ -414,17 +444,18 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	obj = READ_ONCE(dtab->netdev_map[key]);
+	obj = rcu_dereference_check(dtab->netdev_map[key],
+				    rcu_read_lock_bh_held());
 	return obj;
 }
 
-/* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
+ * variable access, and map elements stick around. See comment above
+ * xdp_do_flush() in filter.c.
  */
-static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
-		      struct net_device *dev_rx)
+static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
+		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
 	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
@@ -433,99 +464,334 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 	/* Ingress dev_rx will be the same for all xdp_frame's in
 	 * bulk_queue, because bq stored per-CPU and must be flushed
 	 * from net_device drivers NAPI func end.
+	 *
+	 * Do the same with xdp_prog and flush_list since these fields
+	 * are only ever modified together.
 	 */
-	if (!bq->dev_rx)
-		bq->dev_rx = dev_rx;
-
-	bq->q[bq->count++] = xdpf;
+	if (!bq->dev_rx) {
+		struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
 
-	if (!bq->flush_node.prev)
+		bq->dev_rx = dev_rx;
+		bq->xdp_prog = xdp_prog;
 		list_add(&bq->flush_node, flush_list);
+	}
 
-	return 0;
+	bq->q[bq->count++] = xdpf;
 }
 
-static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
-			       struct net_device *dev_rx)
+static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
+				struct net_device *dev_rx,
+				struct bpf_prog *xdp_prog)
 {
-	struct xdp_frame *xdpf;
 	int err;
 
-	if (!dev->netdev_ops->ndo_xdp_xmit)
+	if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+		return -EOPNOTSUPP;
+
+	if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+		     xdp_frame_has_frags(xdpf)))
 		return -EOPNOTSUPP;
 
-	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf));
 	if (unlikely(err))
 		return err;
 
-	xdpf = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
-	return bq_enqueue(dev, xdpf, dev_rx);
+	bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
+	return 0;
 }
 
-static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
-					 struct xdp_buff *xdp,
-					 struct bpf_prog *xdp_prog)
+static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst)
 {
-	struct xdp_txq_info txq = { .dev = dev };
+	struct xdp_txq_info txq = { .dev = dst->dev };
+	struct xdp_buff xdp;
 	u32 act;
 
-	xdp_set_data_meta_invalid(xdp);
-	xdp->txq = &txq;
+	if (!dst->xdp_prog)
+		return XDP_PASS;
+
+	__skb_pull(skb, skb->mac_len);
+	xdp.txq = &txq;
 
-	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog);
 	switch (act) {
 	case XDP_PASS:
-		return xdp;
-	case XDP_DROP:
+		__skb_push(skb, skb->mac_len);
 		break;
 	default:
-		bpf_warn_invalid_xdp_action(act);
+		bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(dev, xdp_prog, act);
+		trace_xdp_exception(dst->dev, dst->xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		kfree_skb(skb);
 		break;
 	}
 
-	xdp_return_buff(xdp);
-	return NULL;
+	return act;
 }
 
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
-	return __xdp_enqueue(dev, xdp, dev_rx);
+	return __xdp_enqueue(dev, xdpf, dev_rx, NULL);
 }
 
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
 	struct net_device *dev = dst->dev;
 
-	if (dst->xdp_prog) {
-		xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
-		if (!xdp)
-			return 0;
+	return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog);
+}
+
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf)
+{
+	if (!obj)
+		return false;
+
+	if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+		return false;
+
+	if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+		     xdp_frame_has_frags(xdpf)))
+		return false;
+
+	if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf)))
+		return false;
+
+	return true;
+}
+
+static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
+				 struct net_device *dev_rx,
+				 struct xdp_frame *xdpf)
+{
+	struct xdp_frame *nxdpf;
+
+	nxdpf = xdpf_clone(xdpf);
+	if (!nxdpf)
+		return -ENOMEM;
+
+	bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+	return 0;
+}
+
+static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex)
+{
+	while (num_excluded--) {
+		if (ifindex == excluded[num_excluded])
+			return true;
 	}
-	return __xdp_enqueue(dev, xdp, dev_rx);
+	return false;
+}
+
+/* Get ifindex of each upper device. 'indexes' must be able to hold at
+ * least MAX_NEST_DEV elements.
+ * Returns the number of ifindexes added.
+ */
+static int get_upper_ifindexes(struct net_device *dev, int *indexes)
+{
+	struct net_device *upper;
+	struct list_head *iter;
+	int n = 0;
+
+	netdev_for_each_upper_dev_rcu(dev, upper, iter) {
+		indexes[n++] = upper->ifindex;
+	}
+	return n;
+}
+
+int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
+			  struct bpf_map *map, bool exclude_ingress)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	int excluded_devices[1+MAX_NEST_DEV];
+	struct hlist_head *head;
+	int num_excluded = 0;
+	unsigned int i;
+	int err;
+
+	if (exclude_ingress) {
+		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
+		excluded_devices[num_excluded++] = dev_rx->ifindex;
+	}
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		for (i = 0; i < map->max_entries; i++) {
+			dst = rcu_dereference_check(dtab->netdev_map[i],
+						    rcu_read_lock_bh_held());
+			if (!is_valid_dst(dst, xdpf))
+				continue;
+
+			if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
+				continue;
+
+			/* we only need n-1 clones; last_dst enqueued below */
+			if (!last_dst) {
+				last_dst = dst;
+				continue;
+			}
+
+			err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+			if (err)
+				return err;
+
+			last_dst = dst;
+		}
+	} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+		for (i = 0; i < dtab->n_buckets; i++) {
+			head = dev_map_index_hash(dtab, i);
+			hlist_for_each_entry_rcu(dst, head, index_hlist,
+						 lockdep_is_held(&dtab->index_lock)) {
+				if (!is_valid_dst(dst, xdpf))
+					continue;
+
+				if (is_ifindex_excluded(excluded_devices, num_excluded,
+							dst->dev->ifindex))
+					continue;
+
+				/* we only need n-1 clones; last_dst enqueued below */
+				if (!last_dst) {
+					last_dst = dst;
+					continue;
+				}
+
+				err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+				if (err)
+					return err;
+
+				last_dst = dst;
+			}
+		}
+	}
+
+	/* consume the last copy of the frame */
+	if (last_dst)
+		bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
+	else
+		xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
+
+	return 0;
 }
 
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
-			     struct bpf_prog *xdp_prog)
+			     const struct bpf_prog *xdp_prog)
 {
 	int err;
 
 	err = xdp_ok_fwd_dev(dst->dev, skb->len);
 	if (unlikely(err))
 		return err;
+
+	/* Redirect has already succeeded semantically at this point, so we just
+	 * return 0 even if packet is dropped. Helper below takes care of
+	 * freeing skb.
+	 */
+	if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS)
+		return 0;
+
 	skb->dev = dst->dev;
 	generic_xdp_tx(skb, xdp_prog);
 
 	return 0;
 }
 
+static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
+				  struct sk_buff *skb,
+				  const struct bpf_prog *xdp_prog)
+{
+	struct sk_buff *nskb;
+	int err;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	err = dev_map_generic_redirect(dst, nskb, xdp_prog);
+	if (unlikely(err)) {
+		consume_skb(nskb);
+		return err;
+	}
+
+	return 0;
+}
+
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+			   const struct bpf_prog *xdp_prog,
+			   struct bpf_map *map, bool exclude_ingress)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	int excluded_devices[1+MAX_NEST_DEV];
+	struct hlist_head *head;
+	struct hlist_node *next;
+	int num_excluded = 0;
+	unsigned int i;
+	int err;
+
+	if (exclude_ingress) {
+		num_excluded = get_upper_ifindexes(dev, excluded_devices);
+		excluded_devices[num_excluded++] = dev->ifindex;
+	}
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		for (i = 0; i < map->max_entries; i++) {
+			dst = rcu_dereference_check(dtab->netdev_map[i],
+						    rcu_read_lock_bh_held());
+			if (!dst)
+				continue;
+
+			if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
+				continue;
+
+			/* we only need n-1 clones; last_dst enqueued below */
+			if (!last_dst) {
+				last_dst = dst;
+				continue;
+			}
+
+			err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+			if (err)
+				return err;
+
+			last_dst = dst;
+
+		}
+	} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+		for (i = 0; i < dtab->n_buckets; i++) {
+			head = dev_map_index_hash(dtab, i);
+			hlist_for_each_entry_safe(dst, next, head, index_hlist) {
+				if (is_ifindex_excluded(excluded_devices, num_excluded,
+							dst->dev->ifindex))
+					continue;
+
+				/* we only need n-1 clones; last_dst enqueued below */
+				if (!last_dst) {
+					last_dst = dst;
+					continue;
+				}
+
+				err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+				if (err)
+					return err;
+
+				last_dst = dst;
+			}
+		}
+	}
+
+	/* consume the first skb and return */
+	if (last_dst)
+		return dev_map_generic_redirect(last_dst, skb, xdp_prog);
+
+	/* dtab is empty */
+	consume_skb(skb);
+	return 0;
+}
+
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -551,33 +817,28 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
 	kfree(dev);
 }
 
-static int dev_map_delete_elem(struct bpf_map *map, void *key)
+static long dev_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *old_dev;
-	int k = *(u32 *)key;
+	u32 k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;
 
-	/* Use call_rcu() here to ensure any rcu critical sections have
-	 * completed as well as any flush operations because call_rcu
-	 * will wait for preempt-disable region to complete, NAPI in this
-	 * context.  And additionally, the driver tear down ensures all
-	 * soft irqs are complete before removing the net device in the
-	 * case of dev_put equals zero.
-	 */
-	old_dev = xchg(&dtab->netdev_map[k], NULL);
-	if (old_dev)
+	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
+	if (old_dev) {
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+		atomic_dec((atomic_t *)&dtab->items);
+	}
 	return 0;
 }
 
-static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
+static long dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *old_dev;
-	int k = *(u32 *)key;
+	u32 k = *(u32 *)key;
 	unsigned long flags;
 	int ret = -ENOENT;
 
@@ -603,8 +864,9 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	struct bpf_prog *prog = NULL;
 	struct bpf_dtab_netdev *dev;
 
-	dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
-			   dtab->map.numa_node);
+	dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
+				   GFP_NOWAIT | __GFP_NOWARN,
+				   dtab->map.numa_node);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -617,12 +879,12 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 					     BPF_PROG_TYPE_XDP, false);
 		if (IS_ERR(prog))
 			goto err_put_dev;
-		if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+		if (prog->expected_attach_type != BPF_XDP_DEVMAP ||
+		    !bpf_prog_map_compatible(&dtab->map, prog))
 			goto err_put_prog;
 	}
 
 	dev->idx = idx;
-	dev->dtab = dtab;
 	if (prog) {
 		dev->xdp_prog = prog;
 		dev->val.bpf_prog.id = prog->aux->id;
@@ -642,8 +904,8 @@ err_out:
 	return ERR_PTR(-EINVAL);
 }
 
-static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
-				 void *key, void *value, u64 map_flags)
+static long __dev_map_update_elem(struct net *net, struct bpf_map *map,
+				  void *key, void *value, u64 map_flags)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
@@ -675,22 +937,24 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	 * Remembering the driver side flush operation will happen before the
 	 * net device is removed.
 	 */
-	old_dev = xchg(&dtab->netdev_map[i], dev);
+	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
 	if (old_dev)
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+	else
+		atomic_inc((atomic_t *)&dtab->items);
 
 	return 0;
 }
 
-static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
-			       u64 map_flags)
+static long dev_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
 {
 	return __dev_map_update_elem(current->nsproxy->net_ns,
 				     map, key, value, map_flags);
 }
 
-static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
-				     void *key, void *value, u64 map_flags)
+static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
+				       void *key, void *value, u64 map_flags)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
@@ -742,14 +1006,45 @@ out_err:
 	return err;
 }
 
-static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
-				   u64 map_flags)
+static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
+				     u64 map_flags)
 {
 	return __dev_map_hash_update_elem(current->nsproxy->net_ns,
 					 map, key, value, map_flags);
 }
 
+static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags,
+				      BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+				      __dev_map_lookup_elem);
+}
+
+static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags,
+				      BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+				      __dev_map_hash_lookup_elem);
+}
+
+static u64 dev_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	u64 usage = sizeof(struct bpf_dtab);
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)
+		usage += (u64)dtab->n_buckets * sizeof(struct hlist_head);
+	else
+		usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *);
+	usage += atomic_read((atomic_t *)&dtab->items) *
+			 (u64)sizeof(struct bpf_dtab_netdev);
+	return usage;
+}
+
+BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab)
 const struct bpf_map_ops dev_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = dev_map_alloc_check,
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
 	.map_get_next_key = dev_map_get_next_key,
@@ -757,9 +1052,14 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_update_elem = dev_map_update_elem,
 	.map_delete_elem = dev_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = dev_map_mem_usage,
+	.map_btf_id = &dev_map_btf_ids[0],
+	.map_redirect = dev_map_redirect,
 };
 
 const struct bpf_map_ops dev_map_hash_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = dev_map_alloc_check,
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
 	.map_get_next_key = dev_map_hash_get_next_key,
@@ -767,6 +1067,9 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_update_elem = dev_map_hash_update_elem,
 	.map_delete_elem = dev_map_hash_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = dev_map_mem_usage,
+	.map_btf_id = &dev_map_btf_ids[0],
+	.map_redirect = dev_hash_map_redirect,
 };
 
 static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
@@ -808,9 +1111,7 @@ static int dev_map_notification(struct notifier_block *notifier,
 			break;
 
 		/* will be freed in free_netdev() */
-		netdev->xdp_bulkq =
-			__alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
-					   sizeof(void *), GFP_ATOMIC);
+		netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue);
 		if (!netdev->xdp_bulkq)
 			return NOTIFY_BAD;
 
@@ -833,13 +1134,15 @@ static int dev_map_notification(struct notifier_block *notifier,
 			for (i = 0; i < dtab->map.max_entries; i++) {
 				struct bpf_dtab_netdev *dev, *odev;
 
-				dev = READ_ONCE(dtab->netdev_map[i]);
+				dev = rcu_dereference(dtab->netdev_map[i]);
 				if (!dev || netdev != dev->dev)
 					continue;
-				odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
-				if (dev == odev)
+				odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL));
+				if (dev == odev) {
 					call_rcu(&dev->rcu,
 						 __dev_map_entry_free);
+					atomic_dec((atomic_t *)&dtab->items);
+				}
 			}
 		}
 		rcu_read_unlock();
@@ -856,15 +1159,11 @@ static struct notifier_block dev_map_notifier = {
 
 static int __init dev_map_init(void)
 {
-	int cpu;
-
 	/* 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);
 
-	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
 	return 0;
 }