1 files changed, 109 insertions, 66 deletions

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 5c05c9b990fb..f250b5399344 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set,
 		      set->klen);
 }
 
+static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe)
+{
+	return nft_set_elem_expired(&rbe->ext) ||
+	       nft_set_elem_is_dead(&rbe->ext);
+}
+
 static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 				const u32 *key, const struct nft_set_ext **ext,
 				unsigned int seq)
@@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				continue;
 			}
 
-			if (nft_set_elem_expired(&rbe->ext))
+			if (nft_rbtree_elem_expired(rbe))
 				return false;
 
 			if (nft_rbtree_interval_end(rbe)) {
@@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_set_elem_expired(&interval->ext) &&
+	    !nft_rbtree_elem_expired(interval) &&
 	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
@@ -215,38 +221,70 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,
 	return rbe;
 }
 
+static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set,
+				 struct nft_rbtree *priv,
+				 struct nft_rbtree_elem *rbe)
+{
+	struct nft_set_elem elem = {
+		.priv	= rbe,
+	};
+
+	nft_setelem_data_deactivate(net, set, &elem);
+	rb_erase(&rbe->node, &priv->root);
+}
+
 static int nft_rbtree_gc_elem(const struct nft_set *__set,
 			      struct nft_rbtree *priv,
-			      struct nft_rbtree_elem *rbe)
+			      struct nft_rbtree_elem *rbe,
+			      u8 genmask)
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
-	struct nft_rbtree_elem *rbe_prev = NULL;
-	struct nft_set_gc_batch *gcb;
+	struct net *net = read_pnet(&set->net);
+	struct nft_rbtree_elem *rbe_prev;
+	struct nft_trans_gc *gc;
 
-	gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC);
-	if (!gcb)
+	gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC);
+	if (!gc)
 		return -ENOMEM;
 
-	/* search for expired end interval coming before this element. */
+	/* search for end interval coming before this element.
+	 * end intervals don't carry a timeout extension, they
+	 * are coupled with the interval start element.
+	 */
 	while (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
-		if (nft_rbtree_interval_end(rbe_prev))
+		if (nft_rbtree_interval_end(rbe_prev) &&
+		    nft_set_elem_active(&rbe_prev->ext, genmask))
 			break;
 
 		prev = rb_prev(prev);
 	}
 
-	if (rbe_prev) {
-		rb_erase(&rbe_prev->node, &priv->root);
-		atomic_dec(&set->nelems);
+	if (prev) {
+		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
+		nft_rbtree_gc_remove(net, set, priv, rbe_prev);
+
+		/* There is always room in this trans gc for this element,
+		 * memory allocation never actually happens, hence, the warning
+		 * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT,
+		 * this is synchronous gc which never fails.
+		 */
+		gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+		if (WARN_ON_ONCE(!gc))
+			return -ENOMEM;
+
+		nft_trans_gc_elem_add(gc, rbe_prev);
 	}
 
-	rb_erase(&rbe->node, &priv->root);
-	atomic_dec(&set->nelems);
+	nft_rbtree_gc_remove(net, set, priv, rbe);
+	gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+	if (WARN_ON_ONCE(!gc))
+		return -ENOMEM;
 
-	nft_set_gc_batch_add(gcb, rbe);
-	nft_set_gc_batch_complete(gcb);
+	nft_trans_gc_elem_add(gc, rbe);
+
+	nft_trans_gc_queue_sync_done(gc);
 
 	return 0;
 }
@@ -274,6 +312,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
 	struct rb_node *node, *next, *parent, **p, *first = NULL;
 	struct nft_rbtree *priv = nft_set_priv(set);
+	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
 	int d, err;
 
@@ -319,9 +358,12 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		if (!nft_set_elem_active(&rbe->ext, genmask))
 			continue;
 
-		/* perform garbage collection to avoid bogus overlap reports. */
-		if (nft_set_elem_expired(&rbe->ext)) {
-			err = nft_rbtree_gc_elem(set, priv, rbe);
+		/* perform garbage collection to avoid bogus overlap reports
+		 * but skip new elements in this transaction.
+		 */
+		if (nft_set_elem_expired(&rbe->ext) &&
+		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
+			err = nft_rbtree_gc_elem(set, priv, rbe, genmask);
 			if (err < 0)
 				return err;
 
@@ -474,7 +516,6 @@ static void nft_rbtree_activate(const struct net *net,
 	struct nft_rbtree_elem *rbe = elem->priv;
 
 	nft_set_elem_change_active(net, set, &rbe->ext);
-	nft_set_elem_clear_busy(&rbe->ext);
 }
 
 static bool nft_rbtree_flush(const struct net *net,
@@ -482,12 +523,9 @@ static bool nft_rbtree_flush(const struct net *net,
 {
 	struct nft_rbtree_elem *rbe = priv;
 
-	if (!nft_set_elem_mark_busy(&rbe->ext) ||
-	    !nft_is_active(net, &rbe->ext)) {
-		nft_set_elem_change_active(net, set, &rbe->ext);
-		return true;
-	}
-	return false;
+	nft_set_elem_change_active(net, set, &rbe->ext);
+
+	return true;
 }
 
 static void *nft_rbtree_deactivate(const struct net *net,
@@ -544,8 +582,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (nft_set_elem_expired(&rbe->ext))
-			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;
 
@@ -564,26 +600,43 @@ cont:
 
 static void nft_rbtree_gc(struct work_struct *work)
 {
-	struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL;
-	struct nft_set_gc_batch *gcb = NULL;
+	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct nftables_pernet *nft_net;
 	struct nft_rbtree *priv;
+	struct nft_trans_gc *gc;
 	struct rb_node *node;
 	struct nft_set *set;
+	unsigned int gc_seq;
 	struct net *net;
-	u8 genmask;
 
 	priv = container_of(work, struct nft_rbtree, gc_work.work);
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	genmask = nft_genmask_cur(net);
+	nft_net = nft_pernet(net);
+	gc_seq  = READ_ONCE(nft_net->gc_seq);
+
+	if (nft_set_gc_is_pending(set))
+		goto done;
+
+	gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL);
+	if (!gc)
+		goto done;
 
 	write_lock_bh(&priv->lock);
 	write_seqcount_begin(&priv->count);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
+
+		/* Ruleset has been updated, try later. */
+		if (READ_ONCE(nft_net->gc_seq) != gc_seq) {
+			nft_trans_gc_destroy(gc);
+			gc = NULL;
+			goto try_later;
+		}
+
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 
-		if (!nft_set_elem_active(&rbe->ext, genmask))
-			continue;
+		if (nft_set_elem_is_dead(&rbe->ext))
+			goto dead_elem;
 
 		/* elements are reversed in the rbtree for historical reasons,
 		 * from highest to lowest value, that is why end element is
@@ -596,46 +649,36 @@ static void nft_rbtree_gc(struct work_struct *work)
 		if (!nft_set_elem_expired(&rbe->ext))
 			continue;
 
-		if (nft_set_elem_mark_busy(&rbe->ext)) {
-			rbe_end = NULL;
+		nft_set_elem_dead(&rbe->ext);
+
+		if (!rbe_end)
 			continue;
-		}
 
-		if (rbe_prev) {
-			rb_erase(&rbe_prev->node, &priv->root);
-			rbe_prev = NULL;
-		}
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (!gcb)
-			break;
+		nft_set_elem_dead(&rbe_end->ext);
 
-		atomic_dec(&set->nelems);
-		nft_set_gc_batch_add(gcb, rbe);
-		rbe_prev = rbe;
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			goto try_later;
 
-		if (rbe_end) {
-			atomic_dec(&set->nelems);
-			nft_set_gc_batch_add(gcb, rbe_end);
-			rb_erase(&rbe_end->node, &priv->root);
-			rbe_end = NULL;
-		}
-		node = rb_next(node);
-		if (!node)
-			break;
+		nft_trans_gc_elem_add(gc, rbe_end);
+		rbe_end = NULL;
+dead_elem:
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			goto try_later;
+
+		nft_trans_gc_elem_add(gc, rbe);
 	}
-	if (rbe_prev)
-		rb_erase(&rbe_prev->node, &priv->root);
+
+	gc = nft_trans_gc_catchall(gc, gc_seq);
+
+try_later:
 	write_seqcount_end(&priv->count);
 	write_unlock_bh(&priv->lock);
 
-	rbe = nft_set_catchall_gc(set);
-	if (rbe) {
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (gcb)
-			nft_set_gc_batch_add(gcb, rbe);
-	}
-	nft_set_gc_batch_complete(gcb);
-
+	if (gc)
+		nft_trans_gc_queue_async_done(gc);
+done:
 	queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
 			   nft_set_gc_interval(set));
 }