Make radix tree lookups safe to be performed without locks. Readers are protected against nodes being deleted by using RCU based freeing. Readers are protected against new node insertion by using memory barriers to ensure the node itself will be properly written before it is visible in the radix tree. Also introduce a lockfree gang_lookup_slot which will be used by a future patch. Index: linux-2.6/lib/radix-tree.c =================================================================== --- linux-2.6.orig/lib/radix-tree.c +++ linux-2.6/lib/radix-tree.c @@ -30,6 +30,7 @@ #include #include #include +#include #ifdef __KERNEL__ @@ -46,7 +47,9 @@ ((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_TAGS][RADIX_TREE_TAG_LONGS]; }; @@ -98,10 +101,17 @@ radix_tree_node_alloc(struct radix_tree_ 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); } /* @@ -197,6 +207,7 @@ static int radix_tree_extend(struct radi } do { + unsigned int newheight; if (!(node = radix_tree_node_alloc(root))) return -ENOMEM; @@ -209,9 +220,11 @@ static int radix_tree_extend(struct radi tag_set(node, tag, 0); } + newheight = root->height+1; + node->height = newheight; node->count = 1; - root->rnode = node; - root->height++; + rcu_assign_pointer(root->rnode, node); + root->height = newheight; } while (height > root->height); out: return 0; @@ -251,11 +264,12 @@ int radix_tree_insert(struct radix_tree_ /* 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, slot); } /* Go a level down */ @@ -285,25 +299,30 @@ static inline void **__lookup_slot(struc unsigned long index) { unsigned int height, shift; - struct radix_tree_node **slot; + struct radix_tree_node *rnode, **slot; - height = root->height; + /* Must take a copy now because root->rnode may change */ + rnode = root->rnode; + if (rnode == NULL) + return NULL; + + height = rnode->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) - return NULL; + slot = &rnode; + do { slot = (struct radix_tree_node **) ((*slot)->slots + ((index >> shift) & RADIX_TREE_MAP_MASK)); + if (*slot == NULL) + return NULL; + shift -= RADIX_TREE_MAP_SHIFT; height--; - } + } while (height > 0); return (void **)slot; } @@ -497,7 +516,7 @@ EXPORT_SYMBOL(radix_tree_tag_get); #endif static unsigned int -__lookup(struct radix_tree_root *root, void **results, unsigned long index, +__lookup(struct radix_tree_root *root, void ***results, unsigned long index, unsigned int max_items, unsigned long *next_index) { unsigned int nr_found = 0; @@ -505,12 +524,12 @@ __lookup(struct radix_tree_root *root, v struct radix_tree_node *slot; unsigned long i; - height = root->height; - if (height == 0) + slot = root->rnode; + if (!slot || slot->height == 0) goto out; + height = slot->height; shift = (height-1) * RADIX_TREE_MAP_SHIFT; - slot = root->rnode; for ( ; height > 1; height--) { @@ -534,7 +553,7 @@ __lookup(struct radix_tree_root *root, v for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) { index++; if (slot->slots[i]) { - results[nr_found++] = slot->slots[i]; + results[nr_found++] = &(slot->slots[i]); if (nr_found == max_items) goto out; } @@ -566,6 +585,43 @@ radix_tree_gang_lookup(struct radix_tree unsigned int ret = 0; while (ret < max_items) { + unsigned int nr_found, i; + unsigned long next_index; /* Index of next search */ + + if (cur_index > max_index) + break; + nr_found = __lookup(root, (void ***)results + ret, cur_index, + max_items - ret, &next_index); + for (i = 0; i < nr_found; i++) + results[ret + i] = *(((void ***)results)[ret + i]); + ret += nr_found; + if (next_index == 0) + break; + cur_index = next_index; + } + return ret; +} +EXPORT_SYMBOL(radix_tree_gang_lookup); + +/** + * radix_tree_gang_lookup_slot - perform multiple lookup on a radix tree + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * + * Same as radix_tree_gang_lookup, but returns an array of pointers + * (slots) to the stored items instead of the items themselves. + */ +unsigned int +radix_tree_gang_lookup_slot(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 cur_index = first_index; + unsigned int ret = 0; + + while (ret < max_items) { unsigned int nr_found; unsigned long next_index; /* Index of next search */ @@ -580,7 +636,8 @@ radix_tree_gang_lookup(struct radix_tree } return ret; } -EXPORT_SYMBOL(radix_tree_gang_lookup); +EXPORT_SYMBOL(radix_tree_gang_lookup_slot); + /* * FIXME: the two tag_get()s here should use find_next_bit() instead of @@ -770,12 +827,14 @@ EXPORT_SYMBOL(radix_tree_delete); */ int radix_tree_tagged(struct radix_tree_root *root, int tag) { + struct radix_tree_node *rnode; int idx; - if (!root->rnode) + rnode = root->rnode; + if (!rnode) return 0; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { - if (root->rnode->tags[tag][idx]) + if (rnode->tags[tag][idx]) return 1; } return 0; Index: linux-2.6/include/linux/radix-tree.h =================================================================== --- linux-2.6.orig/include/linux/radix-tree.h +++ linux-2.6/include/linux/radix-tree.h @@ -51,6 +51,9 @@ void *radix_tree_delete(struct radix_tre unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); +unsigned int +radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root,