Merge branch 'net_sched-idr'

Chris Mi says:

====================
net/sched: Improve getting objects by indexes

Using current TC code, it is very slow to insert a lot of rules.

In order to improve the rules update rate in TC,
we introduced the following two changes:
        1) changed cls_flower to use IDR to manage the filters.
        2) changed all act_xxx modules to use IDR instead of
           a small hash table

But IDR has a limitation that it uses int. TC handle uses u32.
To make sure there is no regression, we add several new IDR APIs
to support unsigned long.

v2
==

Addressed Hannes's comment:
express idr_alloc in terms of idr_alloc_ext and most of the other functions
====================

Signed-off-by: David S. Miller <[email protected]>

include/linux/idr.h

@@ -80,19 +80,75 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val)
  */
 
 void idr_preload(gfp_t gfp_mask);
-int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t);
+
+int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
+		  unsigned long start, unsigned long end, gfp_t gfp,
+		  bool ext);
+
+/**
+ * idr_alloc - allocate an id
+ * @idr: idr handle
+ * @ptr: pointer to be associated with the new id
+ * @start: the minimum id (inclusive)
+ * @end: the maximum id (exclusive)
+ * @gfp: memory allocation flags
+ *
+ * Allocates an unused ID in the range [start, end).  Returns -ENOSPC
+ * if there are no unused IDs in that range.
+ *
+ * Note that @end is treated as max when <= 0.  This is to always allow
+ * using @start + N as @end as long as N is inside integer range.
+ *
+ * Simultaneous modifications to the @idr are not allowed and should be
+ * prevented by the user, usually with a lock.  idr_alloc() may be called
+ * concurrently with read-only accesses to the @idr, such as idr_find() and
+ * idr_for_each_entry().
+ */
+static inline int idr_alloc(struct idr *idr, void *ptr,
+			    int start, int end, gfp_t gfp)
+{
+	unsigned long id;
+	int ret;
+
+	if (WARN_ON_ONCE(start < 0))
+		return -EINVAL;
+
+	ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false);
+
+	if (ret)
+		return ret;
+
+	return id;
+}
+
+static inline int idr_alloc_ext(struct idr *idr, void *ptr,
+				unsigned long *index,
+				unsigned long start,
+				unsigned long end,
+				gfp_t gfp)
+{
+	return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true);
+}
+
 int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t);
 int idr_for_each(const struct idr *,
 		 int (*fn)(int id, void *p, void *data), void *data);
 void *idr_get_next(struct idr *, int *nextid);
+void *idr_get_next_ext(struct idr *idr, unsigned long *nextid);
 void *idr_replace(struct idr *, void *, int id);
+void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id);
 void idr_destroy(struct idr *);
 
-static inline void *idr_remove(struct idr *idr, int id)
+static inline void *idr_remove_ext(struct idr *idr, unsigned long id)
 {
 	return radix_tree_delete_item(&idr->idr_rt, id, NULL);
 }
 
+static inline void *idr_remove(struct idr *idr, int id)
+{
+	return idr_remove_ext(idr, id);
+}
+
 static inline void idr_init(struct idr *idr)
 {
 	INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER);
@@ -128,11 +184,16 @@ static inline void idr_preload_end(void)
  * This function can be called under rcu_read_lock(), given that the leaf
  * pointers lifetimes are correctly managed.
  */
-static inline void *idr_find(const struct idr *idr, int id)
+static inline void *idr_find_ext(const struct idr *idr, unsigned long id)
 {
 	return radix_tree_lookup(&idr->idr_rt, id);
 }
 
+static inline void *idr_find(const struct idr *idr, int id)
+{
+	return idr_find_ext(idr, id);
+}
+
 /**
  * idr_for_each_entry - iterate over an idr's elements of a given type
  * @idr:     idr handle
@@ -145,6 +206,8 @@ static inline void *idr_find(const struct idr *idr, int id)
  */
 #define idr_for_each_entry(idr, entry, id)			\
 	for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id)
+#define idr_for_each_entry_ext(idr, entry, id)			\
+	for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id)
 
 /**
  * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type

include/linux/radix-tree.h

@@ -357,8 +357,25 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index,
 			unsigned new_order);
 int radix_tree_join(struct radix_tree_root *, unsigned long index,
 			unsigned new_order, void *);
-void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *,
-			gfp_t, int end);
+
+void __rcu **idr_get_free_cmn(struct radix_tree_root *root,
+			      struct radix_tree_iter *iter, gfp_t gfp,
+			      unsigned long max);
+static inline void __rcu **idr_get_free(struct radix_tree_root *root,
+					struct radix_tree_iter *iter,
+					gfp_t gfp,
+					int end)
+{
+	return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX);
+}
+
+static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root,
+					    struct radix_tree_iter *iter,
+					    gfp_t gfp,
+					    unsigned long end)
+{
+	return idr_get_free_cmn(root, iter, gfp, end - 1);
+}
 
 enum {
 	RADIX_TREE_ITER_TAG_MASK = 0x0f,	/* tag index in lower nybble */

include/net/act_api.h

@@ -10,12 +10,9 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
-
-struct tcf_hashinfo {
-	struct hlist_head	*htab;
-	unsigned int		hmask;
-	spinlock_t		lock;
-	u32			index;
+struct tcf_idrinfo {
+	spinlock_t	lock;
+	struct idr	action_idr;
 };
 
 struct tc_action_ops;
@@ -25,9 +22,8 @@ struct tc_action {
 	__u32				type; /* for backward compat(TCA_OLD_COMPAT) */
 	__u32				order;
 	struct list_head		list;
-	struct tcf_hashinfo		*hinfo;
+	struct tcf_idrinfo		*idrinfo;
 
-	struct hlist_node		tcfa_head;
 	u32				tcfa_index;
 	int				tcfa_refcnt;
 	int				tcfa_bindcnt;
@@ -44,7 +40,6 @@ struct tc_action {
 	struct tc_cookie	*act_cookie;
 	struct tcf_chain	*goto_chain;
 };
-#define tcf_head	common.tcfa_head
 #define tcf_index	common.tcfa_index
 #define tcf_refcnt	common.tcfa_refcnt
 #define tcf_bindcnt	common.tcfa_bindcnt
@@ -57,27 +52,6 @@ struct tc_action {
 #define tcf_lock	common.tcfa_lock
 #define tcf_rcu		common.tcfa_rcu
 
-static inline unsigned int tcf_hash(u32 index, unsigned int hmask)
-{
-	return index & hmask;
-}
-
-static inline int tcf_hashinfo_init(struct tcf_hashinfo *hf, unsigned int mask)
-{
-	int i;
-
-	spin_lock_init(&hf->lock);
-	hf->index = 0;
-	hf->hmask = mask;
-	hf->htab = kzalloc((mask + 1) * sizeof(struct hlist_head),
-			   GFP_KERNEL);
-	if (!hf->htab)
-		return -ENOMEM;
-	for (i = 0; i < mask + 1; i++)
-		INIT_HLIST_HEAD(&hf->htab[i]);
-	return 0;
-}
-
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.
  */
@@ -126,53 +100,51 @@ struct tc_action_ops {
 };
 
 struct tc_action_net {
-	struct tcf_hashinfo *hinfo;
+	struct tcf_idrinfo *idrinfo;
 	const struct tc_action_ops *ops;
 };
 
 static inline
 int tc_action_net_init(struct tc_action_net *tn,
-		       const struct tc_action_ops *ops, unsigned int mask)
+		       const struct tc_action_ops *ops)
 {
 	int err = 0;
 
-	tn->hinfo = kmalloc(sizeof(*tn->hinfo), GFP_KERNEL);
-	if (!tn->hinfo)
+	tn->idrinfo = kmalloc(sizeof(*tn->idrinfo), GFP_KERNEL);
+	if (!tn->idrinfo)
 		return -ENOMEM;
 	tn->ops = ops;
-	err = tcf_hashinfo_init(tn->hinfo, mask);
-	if (err)
-		kfree(tn->hinfo);
+	spin_lock_init(&tn->idrinfo->lock);
+	idr_init(&tn->idrinfo->action_idr);
 	return err;
 }
 
-void tcf_hashinfo_destroy(const struct tc_action_ops *ops,
-			  struct tcf_hashinfo *hinfo);
+void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
+			 struct tcf_idrinfo *idrinfo);
 
 static inline void tc_action_net_exit(struct tc_action_net *tn)
 {
-	tcf_hashinfo_destroy(tn->ops, tn->hinfo);
-	kfree(tn->hinfo);
+	tcf_idrinfo_destroy(tn->ops, tn->idrinfo);
+	kfree(tn->idrinfo);
 }
 
 int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 		       struct netlink_callback *cb, int type,
 		       const struct tc_action_ops *ops);
-int tcf_hash_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
-u32 tcf_hash_new_index(struct tc_action_net *tn);
-bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
+int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
+bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 		    int bind);
-int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
-		    struct tc_action **a, const struct tc_action_ops *ops, int bind,
-		    bool cpustats);
-void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
-void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a);
+int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
+		   struct tc_action **a, const struct tc_action_ops *ops,
+		   int bind, bool cpustats);
+void tcf_idr_cleanup(struct tc_action *a, struct nlattr *est);
+void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
 
-int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
 
-static inline int tcf_hash_release(struct tc_action *a, bool bind)
+static inline int tcf_idr_release(struct tc_action *a, bool bind)
 {
-	return __tcf_hash_release(a, bind, false);
+	return __tcf_idr_release(a, bind, false);
 }
 
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);

lib/idr.c

@@ -7,45 +7,32 @@
 DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
 static DEFINE_SPINLOCK(simple_ida_lock);
 
-/**
- * idr_alloc - allocate an id
- * @idr: idr handle
- * @ptr: pointer to be associated with the new id
- * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive)
- * @gfp: memory allocation flags
- *
- * Allocates an unused ID in the range [start, end).  Returns -ENOSPC
- * if there are no unused IDs in that range.
- *
- * Note that @end is treated as max when <= 0.  This is to always allow
- * using @start + N as @end as long as N is inside integer range.
- *
- * Simultaneous modifications to the @idr are not allowed and should be
- * prevented by the user, usually with a lock.  idr_alloc() may be called
- * concurrently with read-only accesses to the @idr, such as idr_find() and
- * idr_for_each_entry().
- */
-int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
+int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
+		  unsigned long start, unsigned long end, gfp_t gfp,
+		  bool ext)
 {
-	void __rcu **slot;
 	struct radix_tree_iter iter;
+	void __rcu **slot;
 
-	if (WARN_ON_ONCE(start < 0))
-		return -EINVAL;
 	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
 		return -EINVAL;
 
 	radix_tree_iter_init(&iter, start);
-	slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
+	if (ext)
+		slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end);
+	else
+		slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
 	if (IS_ERR(slot))
 		return PTR_ERR(slot);
 
 	radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
 	radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
-	return iter.index;
+
+	if (index)
+		*index = iter.index;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(idr_alloc);
+EXPORT_SYMBOL_GPL(idr_alloc_cmn);
 
 /**
  * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
@@ -134,6 +121,20 @@ void *idr_get_next(struct idr *idr, int *nextid)
 }
 EXPORT_SYMBOL(idr_get_next);
 
+void *idr_get_next_ext(struct idr *idr, unsigned long *nextid)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+
+	slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
+	if (!slot)
+		return NULL;
+
+	*nextid = iter.index;
+	return rcu_dereference_raw(*slot);
+}
+EXPORT_SYMBOL(idr_get_next_ext);
+
 /**
  * idr_replace - replace pointer for given id
  * @idr: idr handle
@@ -149,13 +150,20 @@ EXPORT_SYMBOL(idr_get_next);
  * %-EINVAL indicates that @id or @ptr were not valid.
  */
 void *idr_replace(struct idr *idr, void *ptr, int id)
+{
+	if (WARN_ON_ONCE(id < 0))
+		return ERR_PTR(-EINVAL);
+
+	return idr_replace_ext(idr, ptr, id);
+}
+EXPORT_SYMBOL(idr_replace);
+
+void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
 {
 	struct radix_tree_node *node;
 	void __rcu **slot = NULL;
 	void *entry;
 
-	if (WARN_ON_ONCE(id < 0))
-		return ERR_PTR(-EINVAL);
 	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
 		return ERR_PTR(-EINVAL);
 
@@ -167,7 +175,7 @@ void *idr_replace(struct idr *idr, void *ptr, int id)
 
 	return entry;
 }
-EXPORT_SYMBOL(idr_replace);
+EXPORT_SYMBOL(idr_replace_ext);
 
 /**
  * DOC: IDA description

lib/radix-tree.c

@@ -2137,13 +2137,13 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
 }
 EXPORT_SYMBOL(ida_pre_get);
 
-void __rcu **idr_get_free(struct radix_tree_root *root,
-			struct radix_tree_iter *iter, gfp_t gfp, int end)
+void __rcu **idr_get_free_cmn(struct radix_tree_root *root,
+			      struct radix_tree_iter *iter, gfp_t gfp,
+			      unsigned long max)
 {
 	struct radix_tree_node *node = NULL, *child;
 	void __rcu **slot = (void __rcu **)&root->rnode;
 	unsigned long maxindex, start = iter->next_index;
-	unsigned long max = end > 0 ? end - 1 : INT_MAX;
 	unsigned int shift, offset = 0;
 
  grow: