1 files changed, 52 insertions, 75 deletions

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1458b3eae8ad..a0b47f2b896e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -477,6 +477,7 @@ struct nft_set_elem_expr {
  *
  *	@list: table set list node
  *	@bindings: list of set bindings
+ *	@refs: internal refcounting for async set destruction
  *	@table: table this set belongs to
  *	@net: netnamespace this set belongs to
  * 	@name: name of the set
@@ -498,6 +499,7 @@ struct nft_set_elem_expr {
  *	@expr: stateful expression
  * 	@ops: set ops
  * 	@flags: set flags
+ *	@dead: set will be freed, never cleared
  *	@genmask: generation mask
  * 	@klen: key length
  * 	@dlen: data length
@@ -506,6 +508,7 @@ struct nft_set_elem_expr {
 struct nft_set {
 	struct list_head		list;
 	struct list_head		bindings;
+	refcount_t			refs;
 	struct nft_table		*table;
 	possible_net_t			net;
 	char				*name;
@@ -527,7 +530,8 @@ struct nft_set {
 	struct list_head		pending_update;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
-	u16				flags:14,
+	u16				flags:13,
+					dead:1,
 					genmask:2;
 	u8				klen;
 	u8				dlen;
@@ -548,6 +552,11 @@ static inline void *nft_set_priv(const struct nft_set *set)
 	return (void *)set->data;
 }
 
+static inline bool nft_set_gc_is_pending(const struct nft_set *s)
+{
+	return refcount_read(&s->refs) != 1;
+}
+
 static inline struct nft_set *nft_set_container_of(const void *priv)
 {
 	return (void *)priv - offsetof(struct nft_set, data);
@@ -561,7 +570,6 @@ struct nft_set *nft_set_lookup_global(const struct net *net,
 
 struct nft_set_ext *nft_set_catchall_lookup(const struct net *net,
 					    const struct nft_set *set);
-void *nft_set_catchall_gc(const struct nft_set *set);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
@@ -776,62 +784,6 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
 				const struct nft_set *set, void *elem);
 
-/**
- *	struct nft_set_gc_batch_head - nf_tables set garbage collection batch
- *
- *	@rcu: rcu head
- *	@set: set the elements belong to
- *	@cnt: count of elements
- */
-struct nft_set_gc_batch_head {
-	struct rcu_head			rcu;
-	const struct nft_set		*set;
-	unsigned int			cnt;
-};
-
-#define NFT_SET_GC_BATCH_SIZE	((PAGE_SIZE -				  \
-				  sizeof(struct nft_set_gc_batch_head)) / \
-				 sizeof(void *))
-
-/**
- *	struct nft_set_gc_batch - nf_tables set garbage collection batch
- *
- * 	@head: GC batch head
- * 	@elems: garbage collection elements
- */
-struct nft_set_gc_batch {
-	struct nft_set_gc_batch_head	head;
-	void				*elems[NFT_SET_GC_BATCH_SIZE];
-};
-
-struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
-						gfp_t gfp);
-void nft_set_gc_batch_release(struct rcu_head *rcu);
-
-static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb)
-{
-	if (gcb != NULL)
-		call_rcu(&gcb->head.rcu, nft_set_gc_batch_release);
-}
-
-static inline struct nft_set_gc_batch *
-nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb,
-		       gfp_t gfp)
-{
-	if (gcb != NULL) {
-		if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems))
-			return gcb;
-		nft_set_gc_batch_complete(gcb);
-	}
-	return nft_set_gc_batch_alloc(set, gfp);
-}
-
-static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
-					void *elem)
-{
-	gcb->elems[gcb->head.cnt++] = elem;
-}
-
 struct nft_expr_ops;
 /**
  *	struct nft_expr_type - nf_tables expression type
@@ -1490,39 +1442,30 @@ static inline void nft_set_elem_change_active(const struct net *net,
 
 #endif /* IS_ENABLED(CONFIG_NF_TABLES) */
 
-/*
- * We use a free bit in the genmask field to indicate the element
- * is busy, meaning it is currently being processed either by
- * the netlink API or GC.
- *
- * Even though the genmask is only a single byte wide, this works
- * because the extension structure if fully constant once initialized,
- * so there are no non-atomic write accesses unless it is already
- * marked busy.
- */
-#define NFT_SET_ELEM_BUSY_MASK	(1 << 2)
+#define NFT_SET_ELEM_DEAD_MASK	(1 << 2)
 
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-#define NFT_SET_ELEM_BUSY_BIT	2
+#define NFT_SET_ELEM_DEAD_BIT	2
 #elif defined(__BIG_ENDIAN_BITFIELD)
-#define NFT_SET_ELEM_BUSY_BIT	(BITS_PER_LONG - BITS_PER_BYTE + 2)
+#define NFT_SET_ELEM_DEAD_BIT	(BITS_PER_LONG - BITS_PER_BYTE + 2)
 #else
 #error
 #endif
 
-static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext)
+static inline void nft_set_elem_dead(struct nft_set_ext *ext)
 {
 	unsigned long *word = (unsigned long *)ext;
 
 	BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
-	return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word);
+	set_bit(NFT_SET_ELEM_DEAD_BIT, word);
 }
 
-static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
+static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext)
 {
 	unsigned long *word = (unsigned long *)ext;
 
-	clear_bit(NFT_SET_ELEM_BUSY_BIT, word);
+	BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
+	return test_bit(NFT_SET_ELEM_DEAD_BIT, word);
 }
 
 /**
@@ -1656,6 +1599,39 @@ struct nft_trans_flowtable {
 #define nft_trans_flowtable_flags(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flags)
 
+#define NFT_TRANS_GC_BATCHCOUNT	256
+
+struct nft_trans_gc {
+	struct list_head	list;
+	struct net		*net;
+	struct nft_set		*set;
+	u32			seq;
+	u16			count;
+	void			*priv[NFT_TRANS_GC_BATCHCOUNT];
+	struct rcu_head		rcu;
+};
+
+struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set,
+					unsigned int gc_seq, gfp_t gfp);
+void nft_trans_gc_destroy(struct nft_trans_gc *trans);
+
+struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc,
+					      unsigned int gc_seq, gfp_t gfp);
+void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc);
+
+struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp);
+void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans);
+
+void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv);
+
+struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
+						 unsigned int gc_seq);
+struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc);
+
+void nft_setelem_data_deactivate(const struct net *net,
+				 const struct nft_set *set,
+				 struct nft_set_elem *elem);
+
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);
 
@@ -1683,6 +1659,7 @@ struct nftables_pernet {
 	u64			table_handle;
 	unsigned int		base_seq;
 	u8			validate_state;
+	unsigned int		gc_seq;
 };
 
 extern unsigned int nf_tables_net_id;