* Copyright (C) 2001 Momchil Velikov
* Portions Copyright (C) 2001 Christoph Hellwig
* Copyright (C) 2005 SGI, Christoph Lameter <clameter@sgi.com>
+ * Copyright (C) 2006 Nick Piggin
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
#include <linux/gfp.h>
#include <linux/string.h>
#include <linux/bitops.h>
+#include <linux/rcupdate.h>
#ifdef __KERNEL__
((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
struct radix_tree_node {
+ unsigned int height; /* Height from the bottom */
unsigned int count;
+ struct rcu_head rcu_head;
void *slots[RADIX_TREE_MAP_SIZE];
unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
};
};
#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long))
-#define RADIX_TREE_MAX_PATH (RADIX_TREE_INDEX_BITS/RADIX_TREE_MAP_SHIFT + 2)
+#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
+ RADIX_TREE_MAP_SHIFT))
-static unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH] __read_mostly;
+/*
+ * The height_to_maxindex array needs to be one deeper than the maximum
+ * path as height 0 holds only 1 entry.
+ */
+static unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1] __read_mostly;
/*
* Radix tree node cache.
struct radix_tree_node *ret;
gfp_t gfp_mask = root_gfp_mask(root);
- ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
+ ret = kmem_cache_alloc(radix_tree_node_cachep,
+ set_migrateflags(gfp_mask, __GFP_RECLAIMABLE));
if (ret == NULL && !(gfp_mask & __GFP_WAIT)) {
struct radix_tree_preload *rtp;
rtp->nr--;
}
}
+ BUG_ON(radix_tree_is_indirect_ptr(ret));
return ret;
}
+static void radix_tree_node_rcu_free(struct rcu_head *head)
+{
+ struct radix_tree_node *node =
+ container_of(head, struct radix_tree_node, rcu_head);
+ kmem_cache_free(radix_tree_node_cachep, node);
+}
+
static inline void
radix_tree_node_free(struct radix_tree_node *node)
{
- kmem_cache_free(radix_tree_node_cachep, node);
+ call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
}
/*
rtp = &__get_cpu_var(radix_tree_preloads);
while (rtp->nr < ARRAY_SIZE(rtp->nodes)) {
preempt_enable();
- node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
+ node = kmem_cache_alloc(radix_tree_node_cachep,
+ set_migrateflags(gfp_mask, __GFP_RECLAIMABLE));
if (node == NULL)
goto out;
preempt_disable();
out:
return ret;
}
+EXPORT_SYMBOL(radix_tree_preload);
static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
int offset)
}
do {
+ unsigned int newheight;
if (!(node = radix_tree_node_alloc(root)))
return -ENOMEM;
/* Increase the height. */
- node->slots[0] = root->rnode;
+ node->slots[0] = radix_tree_indirect_to_ptr(root->rnode);
/* Propagate the aggregated tag info into the new root */
for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
tag_set(node, tag, 0);
}
+ newheight = root->height+1;
+ node->height = newheight;
node->count = 1;
- root->rnode = node;
- root->height++;
+ node = radix_tree_ptr_to_indirect(node);
+ rcu_assign_pointer(root->rnode, node);
+ root->height = newheight;
} while (height > root->height);
out:
return 0;
int offset;
int error;
+ BUG_ON(radix_tree_is_indirect_ptr(item));
+
/* Make sure the tree is high enough. */
if (index > radix_tree_maxindex(root->height)) {
error = radix_tree_extend(root, index);
return error;
}
- slot = root->rnode;
+ slot = radix_tree_indirect_to_ptr(root->rnode);
+
height = root->height;
shift = (height-1) * RADIX_TREE_MAP_SHIFT;
/* Have to add a child node. */
if (!(slot = radix_tree_node_alloc(root)))
return -ENOMEM;
+ slot->height = height;
if (node) {
- node->slots[offset] = slot;
+ rcu_assign_pointer(node->slots[offset], slot);
node->count++;
} else
- root->rnode = slot;
+ rcu_assign_pointer(root->rnode,
+ radix_tree_ptr_to_indirect(slot));
}
/* Go a level down */
if (node) {
node->count++;
- node->slots[offset] = item;
+ rcu_assign_pointer(node->slots[offset], item);
BUG_ON(tag_get(node, 0, offset));
BUG_ON(tag_get(node, 1, offset));
} else {
- root->rnode = item;
+ rcu_assign_pointer(root->rnode, item);
BUG_ON(root_tag_get(root, 0));
BUG_ON(root_tag_get(root, 1));
}
}
EXPORT_SYMBOL(radix_tree_insert);
-static inline void **__lookup_slot(struct radix_tree_root *root,
- unsigned long index)
+/**
+ * radix_tree_lookup_slot - lookup a slot in a radix tree
+ * @root: radix tree root
+ * @index: index key
+ *
+ * Returns: the slot corresponding to the position @index in the
+ * radix tree @root. This is useful for update-if-exists operations.
+ *
+ * This function cannot be called under rcu_read_lock, it must be
+ * excluded from writers, as must the returned slot for subsequent
+ * use by radix_tree_deref_slot() and radix_tree_replace slot.
+ * Caller must hold tree write locked across slot lookup and
+ * replace.
+ */
+void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
{
unsigned int height, shift;
- struct radix_tree_node **slot;
-
- height = root->height;
+ struct radix_tree_node *node, **slot;
- if (index > radix_tree_maxindex(height))
+ node = root->rnode;
+ if (node == NULL)
return NULL;
- if (height == 0 && root->rnode)
+ if (!radix_tree_is_indirect_ptr(node)) {
+ if (index > 0)
+ return NULL;
return (void **)&root->rnode;
+ }
+ node = radix_tree_indirect_to_ptr(node);
+
+ height = node->height;
+ if (index > radix_tree_maxindex(height))
+ return NULL;
shift = (height-1) * RADIX_TREE_MAP_SHIFT;
- slot = &root->rnode;
- while (height > 0) {
- if (*slot == NULL)
+ do {
+ slot = (struct radix_tree_node **)
+ (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
+ node = *slot;
+ if (node == NULL)
return NULL;
- slot = (struct radix_tree_node **)
- ((*slot)->slots +
- ((index >> shift) & RADIX_TREE_MAP_MASK));
shift -= RADIX_TREE_MAP_SHIFT;
height--;
- }
+ } while (height > 0);
return (void **)slot;
}
-
-/**
- * radix_tree_lookup_slot - lookup a slot in a radix tree
- * @root: radix tree root
- * @index: index key
- *
- * Lookup the slot corresponding to the position @index in the radix tree
- * @root. This is useful for update-if-exists operations.
- */
-void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
-{
- return __lookup_slot(root, index);
-}
EXPORT_SYMBOL(radix_tree_lookup_slot);
/**
* @index: index key
*
* Lookup the item at the position @index in the radix tree @root.
+ *
+ * This function can be called under rcu_read_lock, however the caller
+ * must manage lifetimes of leaf nodes (eg. RCU may also be used to free
+ * them safely). No RCU barriers are required to access or modify the
+ * returned item, however.
*/
void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index)
{
- void **slot;
+ unsigned int height, shift;
+ struct radix_tree_node *node, **slot;
+
+ node = rcu_dereference(root->rnode);
+ if (node == NULL)
+ return NULL;
+
+ if (!radix_tree_is_indirect_ptr(node)) {
+ if (index > 0)
+ return NULL;
+ return node;
+ }
+ node = radix_tree_indirect_to_ptr(node);
+
+ height = node->height;
+ if (index > radix_tree_maxindex(height))
+ return NULL;
+
+ shift = (height-1) * RADIX_TREE_MAP_SHIFT;
+
+ do {
+ slot = (struct radix_tree_node **)
+ (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
+ node = rcu_dereference(*slot);
+ if (node == NULL)
+ return NULL;
+
+ shift -= RADIX_TREE_MAP_SHIFT;
+ height--;
+ } while (height > 0);
- slot = __lookup_slot(root, index);
- return slot != NULL ? *slot : NULL;
+ return node;
}
EXPORT_SYMBOL(radix_tree_lookup);
height = root->height;
BUG_ON(index > radix_tree_maxindex(height));
- slot = root->rnode;
+ slot = radix_tree_indirect_to_ptr(root->rnode);
shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
while (height > 0) {
void *radix_tree_tag_clear(struct radix_tree_root *root,
unsigned long index, unsigned int tag)
{
- struct radix_tree_path path[RADIX_TREE_MAX_PATH], *pathp = path;
+ /*
+ * The radix tree path needs to be one longer than the maximum path
+ * since the "list" is null terminated.
+ */
+ struct radix_tree_path path[RADIX_TREE_MAX_PATH + 1], *pathp = path;
struct radix_tree_node *slot = NULL;
unsigned int height, shift;
shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
pathp->node = NULL;
- slot = root->rnode;
+ slot = radix_tree_indirect_to_ptr(root->rnode);
while (height > 0) {
int offset;
unsigned long index, unsigned int tag)
{
unsigned int height, shift;
- struct radix_tree_node *slot;
+ struct radix_tree_node *node;
int saw_unset_tag = 0;
- height = root->height;
- if (index > radix_tree_maxindex(height))
- return 0;
-
/* check the root's tag bit */
if (!root_tag_get(root, tag))
return 0;
- if (height == 0)
- return 1;
+ node = rcu_dereference(root->rnode);
+ if (node == NULL)
+ return 0;
+
+ if (!radix_tree_is_indirect_ptr(node))
+ return (index == 0);
+ node = radix_tree_indirect_to_ptr(node);
+
+ height = node->height;
+ if (index > radix_tree_maxindex(height))
+ return 0;
shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
- slot = root->rnode;
for ( ; ; ) {
int offset;
- if (slot == NULL)
+ if (node == NULL)
return 0;
offset = (index >> shift) & RADIX_TREE_MAP_MASK;
* This is just a debug check. Later, we can bale as soon as
* we see an unset tag.
*/
- if (!tag_get(slot, tag, offset))
+ if (!tag_get(node, tag, offset))
saw_unset_tag = 1;
if (height == 1) {
- int ret = tag_get(slot, tag, offset);
+ int ret = tag_get(node, tag, offset);
BUG_ON(ret && saw_unset_tag);
return !!ret;
}
- slot = slot->slots[offset];
+ node = rcu_dereference(node->slots[offset]);
shift -= RADIX_TREE_MAP_SHIFT;
height--;
}
EXPORT_SYMBOL(radix_tree_tag_get);
#endif
+/**
+ * radix_tree_next_hole - find the next hole (not-present entry)
+ * @root: tree root
+ * @index: index key
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
+ * indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >= max_scan'
+ * will be true).
+ *
+ * radix_tree_next_hole may be called under rcu_read_lock. However, like
+ * radix_tree_gang_lookup, this will not atomically search a snapshot of the
+ * tree at a single point in time. For example, if a hole is created at index
+ * 5, then subsequently a hole is created at index 10, radix_tree_next_hole
+ * covering both indexes may return 10 if called under rcu_read_lock.
+ */
+unsigned long radix_tree_next_hole(struct radix_tree_root *root,
+ unsigned long index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ if (!radix_tree_lookup(root, index))
+ break;
+ index++;
+ if (index == 0)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(radix_tree_next_hole);
+
static unsigned int
-__lookup(struct radix_tree_root *root, void **results, unsigned long index,
+__lookup(struct radix_tree_node *slot, void **results, unsigned long index,
unsigned int max_items, unsigned long *next_index)
{
unsigned int nr_found = 0;
unsigned int shift, height;
- struct radix_tree_node *slot;
unsigned long i;
- height = root->height;
- if (height == 0) {
- if (root->rnode && index == 0)
- results[nr_found++] = root->rnode;
+ height = slot->height;
+ if (height == 0)
goto out;
- }
-
shift = (height-1) * RADIX_TREE_MAP_SHIFT;
- slot = root->rnode;
for ( ; height > 1; height--) {
-
- for (i = (index >> shift) & RADIX_TREE_MAP_MASK ;
- i < RADIX_TREE_MAP_SIZE; i++) {
+ i = (index >> shift) & RADIX_TREE_MAP_MASK;
+ for (;;) {
if (slot->slots[i] != NULL)
break;
index &= ~((1UL << shift) - 1);
index += 1UL << shift;
if (index == 0)
goto out; /* 32-bit wraparound */
+ i++;
+ if (i == RADIX_TREE_MAP_SIZE)
+ goto out;
}
- if (i == RADIX_TREE_MAP_SIZE)
- goto out;
shift -= RADIX_TREE_MAP_SHIFT;
- slot = slot->slots[i];
+ slot = rcu_dereference(slot->slots[i]);
+ if (slot == NULL)
+ goto out;
}
/* Bottom level: grab some items */
for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
+ struct radix_tree_node *node;
index++;
- if (slot->slots[i]) {
- results[nr_found++] = slot->slots[i];
+ node = slot->slots[i];
+ if (node) {
+ results[nr_found++] = rcu_dereference(node);
if (nr_found == max_items)
goto out;
}
* *@results.
*
* The implementation is naive.
+ *
+ * Like radix_tree_lookup, radix_tree_gang_lookup may be called under
+ * rcu_read_lock. In this case, rather than the returned results being
+ * an atomic snapshot of the tree at a single point in time, the semantics
+ * of an RCU protected gang lookup are as though multiple radix_tree_lookups
+ * have been issued in individual locks, and results stored in 'results'.
*/
unsigned int
radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
unsigned long first_index, unsigned int max_items)
{
- const unsigned long max_index = radix_tree_maxindex(root->height);
+ unsigned long max_index;
+ struct radix_tree_node *node;
unsigned long cur_index = first_index;
- unsigned int ret = 0;
+ unsigned int ret;
+ node = rcu_dereference(root->rnode);
+ if (!node)
+ return 0;
+
+ if (!radix_tree_is_indirect_ptr(node)) {
+ if (first_index > 0)
+ return 0;
+ results[0] = node;
+ return 1;
+ }
+ node = radix_tree_indirect_to_ptr(node);
+
+ max_index = radix_tree_maxindex(node->height);
+
+ ret = 0;
while (ret < max_items) {
unsigned int nr_found;
unsigned long next_index; /* Index of next search */
if (cur_index > max_index)
break;
- nr_found = __lookup(root, results + ret, cur_index,
+ nr_found = __lookup(node, results + ret, cur_index,
max_items - ret, &next_index);
ret += nr_found;
if (next_index == 0)
break;
cur_index = next_index;
}
+
return ret;
}
EXPORT_SYMBOL(radix_tree_gang_lookup);
* open-coding the search.
*/
static unsigned int
-__lookup_tag(struct radix_tree_root *root, void **results, unsigned long index,
+__lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index,
unsigned int max_items, unsigned long *next_index, unsigned int tag)
{
unsigned int nr_found = 0;
- unsigned int shift;
- unsigned int height = root->height;
- struct radix_tree_node *slot;
+ unsigned int shift, height;
- if (height == 0) {
- if (root->rnode && index == 0)
- results[nr_found++] = root->rnode;
+ height = slot->height;
+ if (height == 0)
goto out;
- }
-
- shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
- slot = root->rnode;
+ shift = (height-1) * RADIX_TREE_MAP_SHIFT;
- do {
- unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK;
+ while (height > 0) {
+ unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK ;
- for ( ; i < RADIX_TREE_MAP_SIZE; i++) {
- if (tag_get(slot, tag, i)) {
- BUG_ON(slot->slots[i] == NULL);
+ for (;;) {
+ if (tag_get(slot, tag, i))
break;
- }
index &= ~((1UL << shift) - 1);
index += 1UL << shift;
if (index == 0)
goto out; /* 32-bit wraparound */
+ i++;
+ if (i == RADIX_TREE_MAP_SIZE)
+ goto out;
}
- if (i == RADIX_TREE_MAP_SIZE)
- goto out;
height--;
if (height == 0) { /* Bottom level: grab some items */
unsigned long j = index & RADIX_TREE_MAP_MASK;
for ( ; j < RADIX_TREE_MAP_SIZE; j++) {
+ struct radix_tree_node *node;
index++;
- if (tag_get(slot, tag, j)) {
- BUG_ON(slot->slots[j] == NULL);
- results[nr_found++] = slot->slots[j];
+ if (!tag_get(slot, tag, j))
+ continue;
+ node = slot->slots[j];
+ /*
+ * Even though the tag was found set, we need to
+ * recheck that we have a non-NULL node, because
+ * if this lookup is lockless, it may have been
+ * subsequently deleted.
+ *
+ * Similar care must be taken in any place that
+ * lookup ->slots[x] without a lock (ie. can't
+ * rely on its value remaining the same).
+ */
+ if (node) {
+ node = rcu_dereference(node);
+ results[nr_found++] = node;
if (nr_found == max_items)
goto out;
}
}
}
shift -= RADIX_TREE_MAP_SHIFT;
- slot = slot->slots[i];
- } while (height > 0);
+ slot = rcu_dereference(slot->slots[i]);
+ if (slot == NULL)
+ break;
+ }
out:
*next_index = index;
return nr_found;
unsigned long first_index, unsigned int max_items,
unsigned int tag)
{
- const unsigned long max_index = radix_tree_maxindex(root->height);
+ struct radix_tree_node *node;
+ unsigned long max_index;
unsigned long cur_index = first_index;
- unsigned int ret = 0;
+ unsigned int ret;
/* check the root's tag bit */
if (!root_tag_get(root, tag))
return 0;
+ node = rcu_dereference(root->rnode);
+ if (!node)
+ return 0;
+
+ if (!radix_tree_is_indirect_ptr(node)) {
+ if (first_index > 0)
+ return 0;
+ results[0] = node;
+ return 1;
+ }
+ node = radix_tree_indirect_to_ptr(node);
+
+ max_index = radix_tree_maxindex(node->height);
+
+ ret = 0;
while (ret < max_items) {
unsigned int nr_found;
unsigned long next_index; /* Index of next search */
if (cur_index > max_index)
break;
- nr_found = __lookup_tag(root, results + ret, cur_index,
+ nr_found = __lookup_tag(node, results + ret, cur_index,
max_items - ret, &next_index, tag);
ret += nr_found;
if (next_index == 0)
break;
cur_index = next_index;
}
+
return ret;
}
EXPORT_SYMBOL(radix_tree_gang_lookup_tag);
static inline void radix_tree_shrink(struct radix_tree_root *root)
{
/* try to shrink tree height */
- while (root->height > 0 &&
- root->rnode->count == 1 &&
- root->rnode->slots[0]) {
+ while (root->height > 0) {
struct radix_tree_node *to_free = root->rnode;
+ void *newptr;
+
+ BUG_ON(!radix_tree_is_indirect_ptr(to_free));
+ to_free = radix_tree_indirect_to_ptr(to_free);
+
+ /*
+ * The candidate node has more than one child, or its child
+ * is not at the leftmost slot, we cannot shrink.
+ */
+ if (to_free->count != 1)
+ break;
+ if (!to_free->slots[0])
+ break;
- root->rnode = to_free->slots[0];
+ /*
+ * We don't need rcu_assign_pointer(), since we are simply
+ * moving the node from one part of the tree to another. If
+ * it was safe to dereference the old pointer to it
+ * (to_free->slots[0]), it will be safe to dereference the new
+ * one (root->rnode).
+ */
+ newptr = to_free->slots[0];
+ if (root->height > 1)
+ newptr = radix_tree_ptr_to_indirect(newptr);
+ root->rnode = newptr;
root->height--;
/* must only free zeroed nodes into the slab */
tag_clear(to_free, 0, 0);
*/
void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
{
- struct radix_tree_path path[RADIX_TREE_MAX_PATH], *pathp = path;
+ /*
+ * The radix tree path needs to be one longer than the maximum path
+ * since the "list" is null terminated.
+ */
+ struct radix_tree_path path[RADIX_TREE_MAX_PATH + 1], *pathp = path;
struct radix_tree_node *slot = NULL;
+ struct radix_tree_node *to_free;
unsigned int height, shift;
int tag;
int offset;
goto out;
slot = root->rnode;
- if (height == 0 && root->rnode) {
+ if (height == 0) {
root_tag_clear_all(root);
root->rnode = NULL;
goto out;
}
+ slot = radix_tree_indirect_to_ptr(slot);
shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
pathp->node = NULL;
radix_tree_tag_clear(root, index, tag);
}
+ to_free = NULL;
/* Now free the nodes we do not need anymore */
while (pathp->node) {
pathp->node->slots[pathp->offset] = NULL;
pathp->node->count--;
+ /*
+ * Queue the node for deferred freeing after the
+ * last reference to it disappears (set NULL, above).
+ */
+ if (to_free)
+ radix_tree_node_free(to_free);
if (pathp->node->count) {
- if (pathp->node == root->rnode)
+ if (pathp->node ==
+ radix_tree_indirect_to_ptr(root->rnode))
radix_tree_shrink(root);
goto out;
}
/* Node with zero slots in use so free it */
- radix_tree_node_free(pathp->node);
-
+ to_free = pathp->node;
pathp--;
+
}
root_tag_clear_all(root);
root->height = 0;
root->rnode = NULL;
+ if (to_free)
+ radix_tree_node_free(to_free);
out:
return slot;
height_to_maxindex[i] = __maxindex(i);
}
-#ifdef CONFIG_HOTPLUG_CPU
static int radix_tree_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
struct radix_tree_preload *rtp;
/* Free per-cpu pool of perloaded nodes */
- if (action == CPU_DEAD) {
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
rtp = &per_cpu(radix_tree_preloads, cpu);
while (rtp->nr) {
kmem_cache_free(radix_tree_node_cachep,
}
return NOTIFY_OK;
}
-#endif /* CONFIG_HOTPLUG_CPU */
void __init radix_tree_init(void)
{
radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
sizeof(struct radix_tree_node), 0,
- SLAB_PANIC, radix_tree_node_ctor, NULL);
+ SLAB_PANIC, radix_tree_node_ctor);
radix_tree_init_maxindex();
hotcpu_notifier(radix_tree_callback, 0);
}
git.samba.org / sfrench / cifs-2.6.git / blobdiff