Reimplement IDR and IDA using the radix tree

The IDR is very similar to the radix tree.  It has some functionality that
the radix tree did not have (alloc next free, cyclic allocation, a
callback-based for_each, destroy tree), which is readily implementable on
top of the radix tree.  A few small changes were needed in order to use a
tag to represent nodes with free space below them.  More extensive
changes were needed to support storing NULL as a valid entry in an IDR.
Plain radix trees still interpret NULL as a not-present entry.

The IDA is reimplemented as a client of the newly enhanced radix tree.  As
in the current implementation, it uses a bitmap at the last level of the
tree.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Tested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

13 files changed, 995 insertions, 1126 deletions

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3c01b89aed67..f58c0a3addc3 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -12,47 +12,28 @@
 #ifndef __IDR_H__
 #define __IDR_H__
 
-#include <linux/types.h>
-#include <linux/bitops.h>
-#include <linux/init.h>
-#include <linux/rcupdate.h>
+#include <linux/radix-tree.h>
+#include <linux/gfp.h>
+
+struct idr {
+	struct radix_tree_root	idr_rt;
+	unsigned int		idr_next;
+};
 
 /*
- * Using 6 bits at each layer allows us to allocate 7 layers out of each page.
- * 8 bits only gave us 3 layers out of every pair of pages, which is less
- * efficient except for trees with a largest element between 192-255 inclusive.
+ * The IDR API does not expose the tagging functionality of the radix tree
+ * to users.  Use tag 0 to track whether a node has free space below it.
  */
-#define IDR_BITS 6
-#define IDR_SIZE (1 << IDR_BITS)
-#define IDR_MASK ((1 << IDR_BITS)-1)
-
-struct idr_layer {
-	int			prefix;	/* the ID prefix of this idr_layer */
-	int			layer;	/* distance from leaf */
-	struct idr_layer __rcu	*ary[1<<IDR_BITS];
-	int			count;	/* When zero, we can release it */
-	union {
-		/* A zero bit means "space here" */
-		DECLARE_BITMAP(bitmap, IDR_SIZE);
-		struct rcu_head		rcu_head;
-	};
-};
+#define IDR_FREE	0
 
-struct idr {
-	struct idr_layer __rcu	*hint;	/* the last layer allocated from */
-	struct idr_layer __rcu	*top;
-	int			layers;	/* only valid w/o concurrent changes */
-	int			cur;	/* current pos for cyclic allocation */
-	spinlock_t		lock;
-	int			id_free_cnt;
-	struct idr_layer	*id_free;
-};
+/* Set the IDR flag and the IDR_FREE tag */
+#define IDR_RT_MARKER		((__force gfp_t)(3 << __GFP_BITS_SHIFT))
 
-#define IDR_INIT(name)							\
+#define IDR_INIT							\
 {									\
-	.lock			= __SPIN_LOCK_UNLOCKED(name.lock),	\
+	.idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER)			\
 }
-#define DEFINE_IDR(name)	struct idr name = IDR_INIT(name)
+#define DEFINE_IDR(name)	struct idr name = IDR_INIT
 
 /**
  * idr_get_cursor - Return the current position of the cyclic allocator
@@ -62,9 +43,9 @@ struct idr {
  * idr_alloc_cyclic() if it is free (otherwise the search will start from
  * this position).
  */
-static inline unsigned int idr_get_cursor(struct idr *idr)
+static inline unsigned int idr_get_cursor(const struct idr *idr)
 {
-	return READ_ONCE(idr->cur);
+	return READ_ONCE(idr->idr_next);
 }
 
 /**
@@ -77,7 +58,7 @@ static inline unsigned int idr_get_cursor(struct idr *idr)
  */
 static inline void idr_set_cursor(struct idr *idr, unsigned int val)
 {
-	WRITE_ONCE(idr->cur, val);
+	WRITE_ONCE(idr->idr_next, val);
 }
 
 /**
@@ -97,22 +78,31 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val)
  * period).
  */
 
-/*
- * This is what we export.
- */
-
-void *idr_find_slowpath(struct idr *idp, int id);
 void idr_preload(gfp_t gfp_mask);
-int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask);
-int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask);
-int idr_for_each(struct idr *idp,
+int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t);
+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 *idp, int *nextid);
-void *idr_replace(struct idr *idp, void *ptr, int id);
-void idr_remove(struct idr *idp, int id);
-void idr_destroy(struct idr *idp);
-void idr_init(struct idr *idp);
-bool idr_is_empty(struct idr *idp);
+void *idr_get_next(struct idr *, int *nextid);
+void *idr_replace(struct idr *, void *, int id);
+void idr_destroy(struct idr *);
+
+static inline void idr_remove(struct idr *idr, int id)
+{
+	radix_tree_delete(&idr->idr_rt, id);
+}
+
+static inline void idr_init(struct idr *idr)
+{
+	INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER);
+	idr->idr_next = 0;
+}
+
+static inline bool idr_is_empty(const struct idr *idr)
+{
+	return radix_tree_empty(&idr->idr_rt) &&
+		radix_tree_tagged(&idr->idr_rt, IDR_FREE);
+}
 
 /**
  * idr_preload_end - end preload section started with idr_preload()
@@ -137,19 +127,14 @@ 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(struct idr *idr, int id)
+static inline void *idr_find(const struct idr *idr, int id)
 {
-	struct idr_layer *hint = rcu_dereference_raw(idr->hint);
-
-	if (hint && (id & ~IDR_MASK) == hint->prefix)
-		return rcu_dereference_raw(hint->ary[id & IDR_MASK]);
-
-	return idr_find_slowpath(idr, id);
+	return radix_tree_lookup(&idr->idr_rt, id);
 }
 
 /**
  * idr_for_each_entry - iterate over an idr's elements of a given type
- * @idp:     idr handle
+ * @idr:     idr handle
  * @entry:   the type * to use as cursor
  * @id:      id entry's key
  *
@@ -157,57 +142,60 @@ static inline void *idr_find(struct idr *idr, int id)
  * after normal terminatinon @entry is left with the value NULL.  This
  * is convenient for a "not found" value.
  */
-#define idr_for_each_entry(idp, entry, id)			\
-	for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
+#define idr_for_each_entry(idr, entry, id)			\
+	for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id)
 
 /**
- * idr_for_each_entry - continue iteration over an idr's elements of a given type
- * @idp:     idr handle
+ * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type
+ * @idr:     idr handle
  * @entry:   the type * to use as cursor
  * @id:      id entry's key
  *
  * Continue to iterate over list of given type, continuing after
  * the current position.
  */
-#define idr_for_each_entry_continue(idp, entry, id)			\
-	for ((entry) = idr_get_next((idp), &(id));			\
+#define idr_for_each_entry_continue(idr, entry, id)			\
+	for ((entry) = idr_get_next((idr), &(id));			\
 	     entry;							\
-	     ++id, (entry) = idr_get_next((idp), &(id)))
+	     ++id, (entry) = idr_get_next((idr), &(id)))
 
 /*
  * IDA - IDR based id allocator, use when translation from id to
  * pointer isn't necessary.
- *
- * IDA_BITMAP_LONGS is calculated to be one less to accommodate
- * ida_bitmap->nr_busy so that the whole struct fits in 128 bytes.
  */
 #define IDA_CHUNK_SIZE		128	/* 128 bytes per chunk */
-#define IDA_BITMAP_LONGS	(IDA_CHUNK_SIZE / sizeof(long) - 1)
+#define IDA_BITMAP_LONGS	(IDA_CHUNK_SIZE / sizeof(long))
 #define IDA_BITMAP_BITS 	(IDA_BITMAP_LONGS * sizeof(long) * 8)
 
 struct ida_bitmap {
-	long			nr_busy;
 	unsigned long		bitmap[IDA_BITMAP_LONGS];
 };
 
 struct ida {
-	struct idr		idr;
+	struct radix_tree_root	ida_rt;
 	struct ida_bitmap	*free_bitmap;
 };
 
-#define IDA_INIT(name)		{ .idr = IDR_INIT((name).idr), .free_bitmap = NULL, }
-#define DEFINE_IDA(name)	struct ida name = IDA_INIT(name)
+#define IDA_INIT	{						\
+	.ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT),		\
+}
+#define DEFINE_IDA(name)	struct ida name = IDA_INIT
 
 int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
 int ida_get_new_above(struct ida *ida, int starting_id, int *p_id);
 void ida_remove(struct ida *ida, int id);
 void ida_destroy(struct ida *ida);
-void ida_init(struct ida *ida);
 
 int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
 		   gfp_t gfp_mask);
 void ida_simple_remove(struct ida *ida, unsigned int id);
 
+static inline void ida_init(struct ida *ida)
+{
+	INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT);
+	ida->free_bitmap = NULL;
+}
+
 /**
  * ida_get_new - allocate new ID
  * @ida:	idr handle
@@ -220,11 +208,8 @@ static inline int ida_get_new(struct ida *ida, int *p_id)
 	return ida_get_new_above(ida, 0, p_id);
 }
 
-static inline bool ida_is_empty(struct ida *ida)
+static inline bool ida_is_empty(const struct ida *ida)
 {
-	return idr_is_empty(&ida->idr);
+	return radix_tree_empty(&ida->ida_rt);
 }
-
-void __init idr_init_cache(void);
-
 #endif /* __IDR_H__ */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 05f715cb8062..2ba0c1f46c84 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -105,7 +105,10 @@ struct radix_tree_node {
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-/* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */
+/* The top bits of gfp_mask are used to store the root tags and the IDR flag */
+#define ROOT_IS_IDR	((__force gfp_t)(1 << __GFP_BITS_SHIFT))
+#define ROOT_TAG_SHIFT	(__GFP_BITS_SHIFT + 1)
+
 struct radix_tree_root {
 	gfp_t			gfp_mask;
 	struct radix_tree_node	__rcu *rnode;
@@ -358,10 +361,14 @@ 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 **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *,
+			gfp_t, int end);
 
-#define RADIX_TREE_ITER_TAG_MASK	0x00FF	/* tag index in lower byte */
-#define RADIX_TREE_ITER_TAGGED		0x0100	/* lookup tagged slots */
-#define RADIX_TREE_ITER_CONTIG		0x0200	/* stop at first hole */
+enum {
+	RADIX_TREE_ITER_TAG_MASK = 0x0f,	/* tag index in lower nybble */
+	RADIX_TREE_ITER_TAGGED   = 0x10,	/* lookup tagged slots */
+	RADIX_TREE_ITER_CONTIG   = 0x20,	/* stop at first hole */
+};
 
 /**
  * radix_tree_iter_init - initialize radix tree iterator
@@ -403,6 +410,40 @@ void **radix_tree_next_chunk(const struct radix_tree_root *,
 			     struct radix_tree_iter *iter, unsigned flags);
 
 /**
+ * radix_tree_iter_lookup - look up an index in the radix tree
+ * @root: radix tree root
+ * @iter: iterator state
+ * @index: key to look up
+ *
+ * If @index is present in the radix tree, this function returns the slot
+ * containing it and updates @iter to describe the entry.  If @index is not
+ * present, it returns NULL.
+ */
+static inline void **radix_tree_iter_lookup(const struct radix_tree_root *root,
+			struct radix_tree_iter *iter, unsigned long index)
+{
+	radix_tree_iter_init(iter, index);
+	return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG);
+}
+
+/**
+ * radix_tree_iter_find - find a present entry
+ * @root: radix tree root
+ * @iter: iterator state
+ * @index: start location
+ *
+ * This function returns the slot containing the entry with the lowest index
+ * which is at least @index.  If @index is larger than any present entry, this
+ * function returns NULL.  The @iter is updated to describe the entry found.
+ */
+static inline void **radix_tree_iter_find(const struct radix_tree_root *root,
+			struct radix_tree_iter *iter, unsigned long index)
+{
+	radix_tree_iter_init(iter, index);
+	return radix_tree_next_chunk(root, iter, 0);
+}
+
+/**
  * radix_tree_iter_retry - retry this chunk of the iteration
  * @iter:	iterator state
  *
diff --git a/init/main.c b/init/main.c
index b0c9d6facef9..a65e3aad31bc 100644
--- a/init/main.c
+++ b/init/main.c
@@ -553,7 +553,7 @@ asmlinkage __visible void __init start_kernel(void)
 	if (WARN(!irqs_disabled(),
 		 "Interrupts were enabled *very* early, fixing it\n"))
 		local_irq_disable();
-	idr_init_cache();
+	radix_tree_init();
 
 	/*
 	 * Allow workqueue creation and work item queueing/cancelling
@@ -568,7 +568,6 @@ asmlinkage __visible void __init start_kernel(void)
 	trace_init();
 
 	context_tracking_init();
-	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
diff --git a/lib/idr.c b/lib/idr.c
index 52d2979a05e8..b87056e2cc4c 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -1,1068 +1,369 @@
-/*
- * 2002-10-18  written by Jim Houston jim.houston@ccur.com
- *	Copyright (C) 2002 by Concurrent Computer Corporation
- *	Distributed under the GNU GPL license version 2.
- *
- * Modified by George Anzinger to reuse immediately and to use
- * find bit instructions.  Also removed _irq on spinlocks.
- *
- * Modified by Nadia Derbey to make it RCU safe.
- *
- * Small id to pointer translation service.
- *
- * It uses a radix tree like structure as a sparse array indexed
- * by the id to obtain the pointer.  The bitmap makes allocating
- * a new id quick.
- *
- * You call it to allocate an id (an int) an associate with that id a
- * pointer or what ever, we treat it as a (void *).  You can pass this
- * id to a user for him to pass back at a later time.  You then pass
- * that id to this code and it returns your pointer.
- */
-
-#ifndef TEST                        // to test in user space...
-#include <linux/slab.h>
-#include <linux/init.h>
+#include <linux/bitmap.h>
 #include <linux/export.h>
-#endif
-#include <linux/err.h>
-#include <linux/string.h>
 #include <linux/idr.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/percpu.h>
 
-#define MAX_IDR_SHIFT		(sizeof(int) * 8 - 1)
-#define MAX_IDR_BIT		(1U << MAX_IDR_SHIFT)
-
-/* Leave the possibility of an incomplete final layer */
-#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS)
-
-/* Number of id_layer structs to leave in free list */
-#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2)
-
-static struct kmem_cache *idr_layer_cache;
-static DEFINE_PER_CPU(struct idr_layer *, idr_preload_head);
-static DEFINE_PER_CPU(int, idr_preload_cnt);
 static DEFINE_SPINLOCK(simple_ida_lock);
 
-/* the maximum ID which can be allocated given idr->layers */
-static int idr_max(int layers)
-{
-	int bits = min_t(int, layers * IDR_BITS, MAX_IDR_SHIFT);
-
-	return (1 << bits) - 1;
-}
-
-/*
- * Prefix mask for an idr_layer at @layer.  For layer 0, the prefix mask is
- * all bits except for the lower IDR_BITS.  For layer 1, 2 * IDR_BITS, and
- * so on.
- */
-static int idr_layer_prefix_mask(int layer)
-{
-	return ~idr_max(layer + 1);
-}
-
-static struct idr_layer *get_from_free_list(struct idr *idp)
-{
-	struct idr_layer *p;
-	unsigned long flags;
-
-	spin_lock_irqsave(&idp->lock, flags);
-	if ((p = idp->id_free)) {
-		idp->id_free = p->ary[0];
-		idp->id_free_cnt--;
-		p->ary[0] = NULL;
-	}
-	spin_unlock_irqrestore(&idp->lock, flags);
-	return(p);
-}
-
-/**
- * idr_layer_alloc - allocate a new idr_layer
- * @gfp_mask: allocation mask
- * @layer_idr: optional idr to allocate from
- *
- * If @layer_idr is %NULL, directly allocate one using @gfp_mask or fetch
- * one from the per-cpu preload buffer.  If @layer_idr is not %NULL, fetch
- * an idr_layer from @idr->id_free.
- *
- * @layer_idr is to maintain backward compatibility with the old alloc
- * interface - idr_pre_get() and idr_get_new*() - and will be removed
- * together with per-pool preload buffer.
- */
-static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
-{
-	struct idr_layer *new;
-
-	/* this is the old path, bypass to get_from_free_list() */
-	if (layer_idr)
-		return get_from_free_list(layer_idr);
-
-	/*
-	 * Try to allocate directly from kmem_cache.  We want to try this
-	 * before preload buffer; otherwise, non-preloading idr_alloc()
-	 * users will end up taking advantage of preloading ones.  As the
-	 * following is allowed to fail for preloaded cases, suppress
-	 * warning this time.
-	 */
-	new = kmem_cache_zalloc(idr_layer_cache, gfp_mask | __GFP_NOWARN);
-	if (new)
-		return new;
-
-	/*
-	 * Try to fetch one from the per-cpu preload buffer if in process
-	 * context.  See idr_preload() for details.
-	 */
-	if (!in_interrupt()) {
-		preempt_disable();
-		new = __this_cpu_read(idr_preload_head);
-		if (new) {
-			__this_cpu_write(idr_preload_head, new->ary[0]);
-			__this_cpu_dec(idr_preload_cnt);
-			new->ary[0] = NULL;
-		}
-		preempt_enable();
-		if (new)
-			return new;
-	}
-
-	/*
-	 * Both failed.  Try kmem_cache again w/o adding __GFP_NOWARN so
-	 * that memory allocation failure warning is printed as intended.
-	 */
-	return kmem_cache_zalloc(idr_layer_cache, gfp_mask);
-}
-
-static void idr_layer_rcu_free(struct rcu_head *head)
-{
-	struct idr_layer *layer;
-
-	layer = container_of(head, struct idr_layer, rcu_head);
-	kmem_cache_free(idr_layer_cache, layer);
-}
-
-static inline void free_layer(struct idr *idr, struct idr_layer *p)
-{
-	if (idr->hint == p)
-		RCU_INIT_POINTER(idr->hint, NULL);
-	call_rcu(&p->rcu_head, idr_layer_rcu_free);
-}
-
-/* only called when idp->lock is held */
-static void __move_to_free_list(struct idr *idp, struct idr_layer *p)
-{
-	p->ary[0] = idp->id_free;
-	idp->id_free = p;
-	idp->id_free_cnt++;
-}
-
-static void move_to_free_list(struct idr *idp, struct idr_layer *p)
-{
-	unsigned long flags;
-
-	/*
-	 * Depends on the return element being zeroed.
-	 */
-	spin_lock_irqsave(&idp->lock, flags);
-	__move_to_free_list(idp, p);
-	spin_unlock_irqrestore(&idp->lock, flags);
-}
-
-static void idr_mark_full(struct idr_layer **pa, int id)
-{
-	struct idr_layer *p = pa[0];
-	int l = 0;
-
-	__set_bit(id & IDR_MASK, p->bitmap);
-	/*
-	 * If this layer is full mark the bit in the layer above to
-	 * show that this part of the radix tree is full.  This may
-	 * complete the layer above and require walking up the radix
-	 * tree.
-	 */
-	while (bitmap_full(p->bitmap, IDR_SIZE)) {
-		if (!(p = pa[++l]))
-			break;
-		id = id >> IDR_BITS;
-		__set_bit((id & IDR_MASK), p->bitmap);
-	}
-}
-
-static int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
-{
-	while (idp->id_free_cnt < MAX_IDR_FREE) {
-		struct idr_layer *new;
-		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
-		if (new == NULL)
-			return (0);
-		move_to_free_list(idp, new);
-	}
-	return 1;
-}
-
-/**
- * sub_alloc - try to allocate an id without growing the tree depth
- * @idp: idr handle
- * @starting_id: id to start search at
- * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer
- * @gfp_mask: allocation mask for idr_layer_alloc()
- * @layer_idr: optional idr passed to idr_layer_alloc()
- *
- * Allocate an id in range [@starting_id, INT_MAX] from @idp without
- * growing its depth.  Returns
- *
- *  the allocated id >= 0 if successful,
- *  -EAGAIN if the tree needs to grow for allocation to succeed,
- *  -ENOSPC if the id space is exhausted,
- *  -ENOMEM if more idr_layers need to be allocated.
- */
-static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
-		     gfp_t gfp_mask, struct idr *layer_idr)
-{
-	int n, m, sh;
-	struct idr_layer *p, *new;
-	int l, id, oid;
-
-	id = *starting_id;
- restart:
-	p = idp->top;
-	l = idp->layers;
-	pa[l--] = NULL;
-	while (1) {
-		/*
-		 * We run around this while until we reach the leaf node...
-		 */
-		n = (id >> (IDR_BITS*l)) & IDR_MASK;
-		m = find_next_zero_bit(p->bitmap, IDR_SIZE, n);
-		if (m == IDR_SIZE) {
-			/* no space available go back to previous layer. */
-			l++;
-			oid = id;
-			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
-
-			/* if already at the top layer, we need to grow */
-			if (id > idr_max(idp->layers)) {
-				*starting_id = id;
-				return -EAGAIN;
-			}
-			p = pa[l];
-			BUG_ON(!p);
-
-			/* If we need to go up one layer, continue the
-			 * loop; otherwise, restart from the top.
-			 */
-			sh = IDR_BITS * (l + 1);
-			if (oid >> sh == id >> sh)
-				continue;
-			else
-				goto restart;
-		}
-		if (m != n) {
-			sh = IDR_BITS*l;
-			id = ((id >> sh) ^ n ^ m) << sh;
-		}
-		if ((id >= MAX_IDR_BIT) || (id < 0))
-			return -ENOSPC;
-		if (l == 0)
-			break;
-		/*
-		 * Create the layer below if it is missing.
-		 */
-		if (!p->ary[m]) {
-			new = idr_layer_alloc(gfp_mask, layer_idr);
-			if (!new)
-				return -ENOMEM;
-			new->layer = l-1;
-			new->prefix = id & idr_layer_prefix_mask(new->layer);
-			rcu_assign_pointer(p->ary[m], new);
-			p->count++;
-		}
-		pa[l--] = p;
-		p = p->ary[m];
-	}
-
-	pa[l] = p;
-	return id;
-}
-
-static int idr_get_empty_slot(struct idr *idp, int starting_id,
-			      struct idr_layer **pa, gfp_t gfp_mask,
-			      struct idr *layer_idr)
-{
-	struct idr_layer *p, *new;
-	int layers, v, id;
-	unsigned long flags;
-
-	id = starting_id;
-build_up:
-	p = idp->top;
-	layers = idp->layers;
-	if (unlikely(!p)) {
-		if (!(p = idr_layer_alloc(gfp_mask, layer_idr)))
-			return -ENOMEM;
-		p->layer = 0;
-		layers = 1;
-	}
-	/*
-	 * Add a new layer to the top of the tree if the requested
-	 * id is larger than the currently allocated space.
-	 */
-	while (id > idr_max(layers)) {
-		layers++;
-		if (!p->count) {
-			/* special case: if the tree is currently empty,
-			 * then we grow the tree by moving the top node
-			 * upwards.
-			 */
-			p->layer++;
-			WARN_ON_ONCE(p->prefix);
-			continue;
-		}
-		if (!(new = idr_layer_alloc(gfp_mask, layer_idr))) {
-			/*
-			 * The allocation failed.  If we built part of
-			 * the structure tear it down.
-			 */
-			spin_lock_irqsave(&idp->lock, flags);
-			for (new = p; p && p != idp->top; new = p) {
-				p = p->ary[0];
-				new->ary[0] = NULL;
-				new->count = 0;
-				bitmap_clear(new->bitmap, 0, IDR_SIZE);
-				__move_to_free_list(idp, new);
-			}
-			spin_unlock_irqrestore(&idp->lock, flags);
-			return -ENOMEM;
-		}
-		new->ary[0] = p;
-		new->count = 1;
-		new->layer = layers-1;
-		new->prefix = id & idr_layer_prefix_mask(new->layer);
-		if (bitmap_full(p->bitmap, IDR_SIZE))
-			__set_bit(0, new->bitmap);
-		p = new;
-	}
-	rcu_assign_pointer(idp->top, p);
-	idp->layers = layers;
-	v = sub_alloc(idp, &id, pa, gfp_mask, layer_idr);
-	if (v == -EAGAIN)
-		goto build_up;
-	return(v);
-}
-
-/*
- * @id and @pa are from a successful allocation from idr_get_empty_slot().
- * Install the user pointer @ptr and mark the slot full.
- */
-static void idr_fill_slot(struct idr *idr, void *ptr, int id,
-			  struct idr_layer **pa)
-{
-	/* update hint used for lookup, cleared from free_layer() */
-	rcu_assign_pointer(idr->hint, pa[0]);
-
-	rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], (struct idr_layer *)ptr);
-	pa[0]->count++;
-	idr_mark_full(pa, id);
-}
-
-
-/**
- * idr_preload - preload for idr_alloc()
- * @gfp_mask: allocation mask to use for preloading
- *
- * Preload per-cpu layer buffer for idr_alloc().  Can only be used from
- * process context and each idr_preload() invocation should be matched with
- * idr_preload_end().  Note that preemption is disabled while preloaded.
- *
- * The first idr_alloc() in the preloaded section can be treated as if it
- * were invoked with @gfp_mask used for preloading.  This allows using more
- * permissive allocation masks for idrs protected by spinlocks.
- *
- * For example, if idr_alloc() below fails, the failure can be treated as
- * if idr_alloc() were called with GFP_KERNEL rather than GFP_NOWAIT.
- *
- *	idr_preload(GFP_KERNEL);
- *	spin_lock(lock);
- *
- *	id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT);
- *
- *	spin_unlock(lock);
- *	idr_preload_end();
- *	if (id < 0)
- *		error;
- */
-void idr_preload(gfp_t gfp_mask)
-{
-	/*
-	 * Consuming preload buffer from non-process context breaks preload
-	 * allocation guarantee.  Disallow usage from those contexts.
-	 */
-	WARN_ON_ONCE(in_interrupt());
-	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
-
-	preempt_disable();
-
-	/*
-	 * idr_alloc() is likely to succeed w/o full idr_layer buffer and
-	 * return value from idr_alloc() needs to be checked for failure
-	 * anyway.  Silently give up if allocation fails.  The caller can
-	 * treat failures from idr_alloc() as if idr_alloc() were called
-	 * with @gfp_mask which should be enough.
-	 */
-	while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) {
-		struct idr_layer *new;
-
-		preempt_enable();
-		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
-		preempt_disable();
-		if (!new)
-			break;
-
-		/* link the new one to per-cpu preload list */
-		new->ary[0] = __this_cpu_read(idr_preload_head);
-		__this_cpu_write(idr_preload_head, new);
-		__this_cpu_inc(idr_preload_cnt);
-	}
-}
-EXPORT_SYMBOL(idr_preload);
-
 /**
- * idr_alloc - allocate new idr entry
- * @idr: the (initialized) idr
+ * 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, <= 0 for max)
- * @gfp_mask: memory allocation flags
+ * @end: the maximum id (exclusive)
+ * @gfp: memory allocation flags
  *
- * Allocate an id in [start, end) and associate it with @ptr.  If no ID is
- * available in the specified range, returns -ENOSPC.  On memory allocation
- * failure, returns -ENOMEM.
+ * 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.
  *
- * The user is responsible for exclusively synchronizing all operations
- * which may modify @idr.  However, read-only accesses such as idr_find()
- * or iteration can be performed under RCU read lock provided the user
- * destroys @ptr in RCU-safe way after removal from idr.
+ * 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_mask)
+int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
 {
-	int max = end > 0 ? end - 1 : INT_MAX;	/* inclusive upper limit */
-	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
-	int id;
-
-	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
+	void **slot;
+	struct radix_tree_iter iter;
 
-	/* sanity checks */
 	if (WARN_ON_ONCE(start < 0))
 		return -EINVAL;
-	if (unlikely(max < start))
-		return -ENOSPC;
+	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
+		return -EINVAL;
 
-	/* allocate id */
-	id = idr_get_empty_slot(idr, start, pa, gfp_mask, NULL);
-	if (unlikely(id < 0))
-		return id;
-	if (unlikely(id > max))
-		return -ENOSPC;
+	radix_tree_iter_init(&iter, start);
+	slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
+	if (IS_ERR(slot))
+		return PTR_ERR(slot);
 
-	idr_fill_slot(idr, ptr, id, pa);
-	return id;
+	radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
+	radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
+	return iter.index;
 }
 EXPORT_SYMBOL_GPL(idr_alloc);
 
 /**
  * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
- * @idr: the (initialized) idr
+ * @idr: idr handle
  * @ptr: pointer to be associated with the new id
  * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive, <= 0 for max)
- * @gfp_mask: memory allocation flags
- *
- * Essentially the same as idr_alloc, but prefers to allocate progressively
- * higher ids if it can. If the "cur" counter wraps, then it will start again
- * at the "start" end of the range and allocate one that has already been used.
- */
-int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end,
-			gfp_t gfp_mask)
-{
-	int id;
-
-	id = idr_alloc(idr, ptr, max(start, idr->cur), end, gfp_mask);
-	if (id == -ENOSPC)
-		id = idr_alloc(idr, ptr, start, end, gfp_mask);
-
-	if (likely(id >= 0))
-		idr->cur = id + 1;
-	return id;
-}
-EXPORT_SYMBOL(idr_alloc_cyclic);
-
-static void idr_remove_warning(int id)
-{
-	WARN(1, "idr_remove called for id=%d which is not allocated.\n", id);
-}
-
-static void sub_remove(struct idr *idp, int shift, int id)
-{
-	struct idr_layer *p = idp->top;
-	struct idr_layer **pa[MAX_IDR_LEVEL + 1];
-	struct idr_layer ***paa = &pa[0];
-	struct idr_layer *to_free;
-	int n;
-
-	*paa = NULL;
-	*++paa = &idp->top;
-
-	while ((shift > 0) && p) {
-		n = (id >> shift) & IDR_MASK;
-		__clear_bit(n, p->bitmap);
-		*++paa = &p->ary[n];
-		p = p->ary[n];
-		shift -= IDR_BITS;
-	}
-	n = id & IDR_MASK;
-	if (likely(p != NULL && test_bit(n, p->bitmap))) {
-		__clear_bit(n, p->bitmap);
-		RCU_INIT_POINTER(p->ary[n], NULL);
-		to_free = NULL;
-		while(*paa && ! --((**paa)->count)){
-			if (to_free)
-				free_layer(idp, to_free);
-			to_free = **paa;
-			**paa-- = NULL;
-		}
-		if (!*paa)
-			idp->layers = 0;
-		if (to_free)
-			free_layer(idp, to_free);
-	} else
-		idr_remove_warning(id);
-}
-
-/**
- * idr_remove - remove the given id and free its slot
- * @idp: idr handle
- * @id: unique key
- */
-void idr_remove(struct idr *idp, int id)
-{
-	struct idr_layer *p;
-	struct idr_layer *to_free;
-
-	if (id < 0)
-		return;
-
-	if (id > idr_max(idp->layers)) {
-		idr_remove_warning(id);
-		return;
-	}
-
-	sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
-	if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
-	    idp->top->ary[0]) {
-		/*
-		 * Single child at leftmost slot: we can shrink the tree.
-		 * This level is not needed anymore since when layers are
-		 * inserted, they are inserted at the top of the existing
-		 * tree.
-		 */
-		to_free = idp->top;
-		p = idp->top->ary[0];
-		rcu_assign_pointer(idp->top, p);
-		--idp->layers;
-		to_free->count = 0;
-		bitmap_clear(to_free->bitmap, 0, IDR_SIZE);
-		free_layer(idp, to_free);
-	}
-}
-EXPORT_SYMBOL(idr_remove);
-
-static void __idr_remove_all(struct idr *idp)
-{
-	int n, id, max;
-	int bt_mask;
-	struct idr_layer *p;
-	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
-	struct idr_layer **paa = &pa[0];
-
-	n = idp->layers * IDR_BITS;
-	*paa = idp->top;
-	RCU_INIT_POINTER(idp->top, NULL);
-	max = idr_max(idp->layers);
-
-	id = 0;
-	while (id >= 0 && id <= max) {
-		p = *paa;
-		while (n > IDR_BITS && p) {
-			n -= IDR_BITS;
-			p = p->ary[(id >> n) & IDR_MASK];
-			*++paa = p;
-		}
-
-		bt_mask = id;
-		id += 1 << n;
-		/* Get the highest bit that the above add changed from 0->1. */
-		while (n < fls(id ^ bt_mask)) {
-			if (*paa)
-				free_layer(idp, *paa);
-			n += IDR_BITS;
-			--paa;
-		}
-	}
-	idp->layers = 0;
-}
-
-/**
- * idr_destroy - release all cached layers within an idr tree
- * @idp: idr handle
- *
- * Free all id mappings and all idp_layers.  After this function, @idp is
- * completely unused and can be freed / recycled.  The caller is
- * responsible for ensuring that no one else accesses @idp during or after
- * idr_destroy().
+ * @end: the maximum id (exclusive)
+ * @gfp: memory allocation flags
  *
- * A typical clean-up sequence for objects stored in an idr tree will use
- * idr_for_each() to free all objects, if necessary, then idr_destroy() to
- * free up the id mappings and cached idr_layers.
+ * Allocates an ID larger than th