1 files changed, 104 insertions, 90 deletions

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 886866bee8b2..cf314ce2fd17 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -130,9 +130,9 @@ static inline u16 nft_reg_load16(u32 *sreg)
 	return *(u16 *)sreg;
 }
 
-static inline void nft_reg_store64(u32 *dreg, u64 val)
+static inline void nft_reg_store64(u64 *dreg, u64 val)
 {
-	put_unaligned(val, (u64 *)dreg);
+	put_unaligned(val, dreg);
 }
 
 static inline u64 nft_reg_load64(u32 *sreg)
@@ -205,14 +205,13 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
 }
 
 int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
-unsigned int nft_parse_register(const struct nlattr *attr);
 int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg);
 
-int nft_validate_register_load(enum nft_registers reg, unsigned int len);
-int nft_validate_register_store(const struct nft_ctx *ctx,
-				enum nft_registers reg,
-				const struct nft_data *data,
-				enum nft_data_types type, unsigned int len);
+int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len);
+int nft_parse_register_store(const struct nft_ctx *ctx,
+			     const struct nlattr *attr, u8 *dreg,
+			     const struct nft_data *data,
+			     enum nft_data_types type, unsigned int len);
 
 /**
  *	struct nft_userdata - user defined data associated with an object
@@ -240,6 +239,10 @@ struct nft_set_elem {
 		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
 		struct nft_data	val;
 	} key;
+	union {
+		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
+		struct nft_data val;
+	} data;
 	void			*priv;
 };
 
@@ -368,7 +371,8 @@ struct nft_set_ops {
 	int				(*init)(const struct nft_set *set,
 						const struct nft_set_desc *desc,
 						const struct nlattr * const nla[]);
-	void				(*destroy)(const struct nft_set *set);
+	void				(*destroy)(const struct nft_ctx *ctx,
+						   const struct nft_set *set);
 	void				(*gc_init)(const struct nft_set *set);
 
 	unsigned int			elemsize;
@@ -398,6 +402,7 @@ void nft_unregister_set(struct nft_set_type *type);
  *
  *	@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
@@ -424,6 +429,7 @@ void nft_unregister_set(struct nft_set_type *type);
 struct nft_set {
 	struct list_head		list;
 	struct list_head		bindings;
+	refcount_t			refs;
 	struct nft_table		*table;
 	possible_net_t			net;
 	char				*name;
@@ -442,7 +448,8 @@ struct nft_set {
 	unsigned char			*udata;
 	/* 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;
@@ -460,6 +467,11 @@ 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);
@@ -493,6 +505,7 @@ struct nft_set_binding {
 };
 
 enum nft_trans_phase;
+void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set);
 void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 			      struct nft_set_binding *binding,
 			      enum nft_trans_phase phase);
@@ -661,62 +674,8 @@ void *nft_set_elem_init(const struct nft_set *set,
 			u64 timeout, u64 expiration, gfp_t gfp);
 void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 			  bool destroy_expr);
-
-/**
- *	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;
-}
+void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
+				const struct nft_set *set, void *elem);
 
 struct nft_expr_ops;
 /**
@@ -752,6 +711,7 @@ struct nft_expr_type {
 
 enum nft_trans_phase {
 	NFT_TRANS_PREPARE,
+	NFT_TRANS_PREPARE_ERROR,
 	NFT_TRANS_ABORT,
 	NFT_TRANS_COMMIT,
 	NFT_TRANS_RELEASE
@@ -1008,6 +968,29 @@ int __nft_release_basechain(struct nft_ctx *ctx);
 
 unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
 
+static inline bool nft_use_inc(u32 *use)
+{
+	if (*use == UINT_MAX)
+		return false;
+
+	(*use)++;
+
+	return true;
+}
+
+static inline void nft_use_dec(u32 *use)
+{
+	WARN_ON_ONCE((*use)-- == 0);
+}
+
+/* For error and abort path: restore use counter to previous state. */
+static inline void nft_use_inc_restore(u32 *use)
+{
+	WARN_ON_ONCE(!nft_use_inc(use));
+}
+
+#define nft_use_dec_restore	nft_use_dec
+
 /**
  *	struct nft_table - nf_tables table
  *
@@ -1077,8 +1060,8 @@ struct nft_object {
 	struct list_head		list;
 	struct rhlist_head		rhlhead;
 	struct nft_object_hash_key	key;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	const struct nft_object_ops	*ops ____cacheline_aligned;
@@ -1180,8 +1163,8 @@ struct nft_flowtable {
 	int				hooknum;
 	int				priority;
 	int				ops_len;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	struct nf_hook_ops		*ops ____cacheline_aligned;
@@ -1320,45 +1303,37 @@ 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);
 }
 
 /**
  *	struct nft_trans - nf_tables object update in transaction
  *
  *	@list: used internally
+ *	@binding_list: list of objects with possible bindings
  *	@msg_type: message type
  *	@put_net: ctx->net needs to be put
  *	@ctx: transaction context
@@ -1366,6 +1341,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
  */
 struct nft_trans {
 	struct list_head		list;
+	struct list_head		binding_list;
 	int				msg_type;
 	bool				put_net;
 	struct nft_ctx			ctx;
@@ -1416,13 +1392,10 @@ struct nft_trans_chain {
 
 struct nft_trans_table {
 	bool				update;
-	bool				enable;
 };
 
 #define nft_trans_table_update(trans)	\
 	(((struct nft_trans_table *)trans->data)->update)
-#define nft_trans_table_enable(trans)	\
-	(((struct nft_trans_table *)trans->data)->enable)
 
 struct nft_trans_elem {
 	struct nft_set			*set;
@@ -1457,6 +1430,35 @@ struct nft_trans_flowtable {
 #define nft_trans_flowtable(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flowtable)
 
+#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);
+
+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);
 
@@ -1468,4 +1470,16 @@ void nf_tables_trans_destroy_flush_work(void);
 int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result);
 __be64 nf_jiffies64_to_msecs(u64 input);
 
+struct nftables_pernet {
+	struct list_head	tables;
+	struct list_head	commit_list;
+	struct list_head	binding_list;
+	struct list_head	module_list;
+	struct list_head	notify_list;
+	struct mutex		commit_mutex;
+	unsigned int		base_seq;
+	u8			validate_state;
+	unsigned int		gc_seq;
+};
+
 #endif /* _NET_NF_TABLES_H */