[PATCH 1/2] lib: Resizable, Scalable, Concurrent Hash Table

[Thomas Graf]

Generic implementation of a resizable, scalable, concurrent hash table
based on [0]. The implementation supports both, fixed size keys specified
via an offset and length, or arbitrary keys via own hash and compare
functions.

Lookups are lockless and protected as RCU read side critical sections.
Automatic growing/shrinking based on user configurable watermarks is
available while allowing concurrent lookups to take place.

Objects to be hashed must include a struct rhash_head. The reason for not
using the existing struct hlist_head is that the expansion and shrinking
will have two buckets point to a single entry which would lead in obscure
reverse chaining behaviour.

Code includes a boot selftest if CONFIG_TEST_RHASHTABLE is defined.

[0] https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf

Signed-off-by: Thomas Graf <tgraf@xxxxxxx>
---
 include/linux/rhashtable.h | 208 ++++++++++++
 lib/Kconfig.debug          |   8 +
 lib/Makefile               |   2 +-
 lib/rhashtable.c           | 783 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1000 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/rhashtable.h
 create mode 100644 lib/rhashtable.c

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
new file mode 100644
index 0000000..f784f7a
--- /dev/null
+++ b/include/linux/rhashtable.h
@@ -0,0 +1,208 @@
+/*
+ * Resizable, Scalable, Concurrent Hash Table
+ *
+ * Copyright (c) 2014 Thomas Graf <tgraf@xxxxxxx>
+ *
+ * Based on the following paper by Josh Triplett, Paul E. McKenney
+ * and Jonathan Walpole:
+ * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf
+ *
+ * Code partially derived from nft_hash:
+ * Copyright (c) 2008-2014 Patrick McHardy <kaber@xxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _LINUX_RHASHTABLE_H
+#define _LINUX_RHASHTABLE_H
+
+#include <linux/rculist.h>
+
+struct rhash_head {
+	struct rhash_head		*next;
+};
+
+#define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL)
+
+struct bucket_table {
+	size_t				size;
+	struct rhash_head __rcu		*buckets[];
+};
+
+typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
+typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 seed);
+
+struct rhashtable;
+
+/**
+ * struct rhashtable_params - Hash table construction parameters
+ * @nelem_hint: Hint on number of elements expected
+ * @key_len: Length of key
+ * @key_offset: Offset of key in struct to be hashed
+ * @head_offset: Offset of rhash_head in struct to be hashed
+ * @hash_rnd: Seed to use while hashing
+ * @max_shift: Maximum number of shifts while expanding
+ * @hashfn: Function to hash key
+ * @obj_hashfn: Function to hash object
+ * @grow_decision: If defined, may return true if table should expand
+ * @shrink_decision: If defined, may return true if table should shrink
+ * @mutex_is_held: Must return true if protecting mutex is held
+ */
+struct rhashtable_params {
+	size_t			nelem_hint;
+	size_t			key_len;
+	size_t			key_offset;
+	size_t			head_offset;
+	u32			hash_rnd;
+	size_t			max_shift;
+	rht_hashfn_t		hashfn;
+	rht_obj_hashfn_t	obj_hashfn;
+	bool			(*grow_decision)(const struct rhashtable *ht,
+						 size_t new_size);
+	bool			(*shrink_decision)(const struct rhashtable *ht,
+						   size_t new_size);
+	int			(*mutex_is_held)(void);
+};
+
+/**
+ * struct rhashtable - Hash table handle
+ * @tbl: Bucket table
+ * @nelems: Number of elements in table
+ * @shift: Current size (1 << shift)
+ * @p: Configuration parameters
+ */
+struct rhashtable {
+	struct bucket_table __rcu	*tbl;
+	size_t				nelems;
+	size_t				shift;
+	struct rhashtable_params	p;
+};
+
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_rht_mutex_is_held(const struct rhashtable *ht);
+#else
+static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
+{
+	return 1;
+}
+#endif /* CONFIG_PROVE_LOCKING */
+
+int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
+
+u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len);
+u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr);
+
+int rhashtable_insert(struct rhashtable *ht, struct rhash_head *node, gfp_t);
+bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node, gfp_t);
+
+bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size);
+bool rht_shrink_below_50(const struct rhashtable *ht, size_t new_size);
+
+int rhashtable_expand(struct rhashtable *ht, gfp_t flags);
+int rhashtable_shrink(struct rhashtable *ht, gfp_t flags);
+
+void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
+void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+				bool (*compare)(void *, void *), void *arg);
+
+void rhashtable_destroy(const struct rhashtable *ht);
+
+#define rht_dereference(p, ht) \
+	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
+
+#define rht_dereference_rcu(p, ht) \
+	rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht))
+
+/* Internal, use rht_obj() instead */
+#define rht_entry(ptr, type, member) container_of(ptr, type, member)
+#define rht_entry_safe(ptr, type, member) \
+({ \
+	typeof(ptr) __ptr = (ptr); \
+	   __ptr ? rht_entry(__ptr, type, member) : NULL; \
+})
+#define rht_entry_safe_rcu(ptr, type, member) \
+({ \
+	typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \
+	__ptr ? container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member) : NULL; \
+})
+
+/**
+ * rht_for_each - iterate over hash chain
+ * @pos:	&struct rhash_head to use as a loop cursor.
+ * @head:	head of the hash chain (struct rhash_head *)
+ * @ht:		pointer to your struct rhashtable
+ */
+#define rht_for_each(pos, head, ht) \
+	for (pos = rht_dereference(head, ht); \
+	     pos; \
+	     pos = rht_dereference((pos)->next, ht))
+
+/**
+ * rht_for_each_entry - iterate over hash chain of given type
+ * @pos:	type * to use as a loop cursor.
+ * @head:	head of the hash chain (struct rhash_head *)
+ * @ht:		pointer to your struct rhashtable
+ * @member:	name of the rhash_head within the hashable struct.
+ */
+#define rht_for_each_entry(pos, head, ht, member) \
+	for (pos = rht_entry_safe(rht_dereference(head, ht), \
+				   typeof(*(pos)), member); \
+	     pos; \
+	     pos = rht_entry_safe(rht_dereference((pos)->member.next, ht), \
+				   typeof(*(pos)), member))
+
+/**
+ * rht_for_each_entry_safe - safely iterate over hash chain of given type
+ * @pos:	type * to use as a loop cursor.
+ * @n:		type * to use for temporary next object storage
+ * @head:	head of the hash chain (struct rhash_head *)
+ * @ht:		pointer to your struct rhashtable
+ * @member:	name of the rhash_head within the hashable struct.
+ *
+ * This hash chain list-traversal primitive allows for the looped code to
+ * remove the loop cursor from the list.
+ */
+#define rht_for_each_entry_safe(pos, n, head, ht, member)		\
+	for (pos = rht_entry_safe(rht_dereference(head, ht), \
+				   typeof(*(pos)), member), \
+	     n = rht_entry_safe(rht_dereference((pos)->member.next, ht), \
+				 typeof(*(pos)), member); \
+	     pos; \
+	     pos = n, \
+	     n = rht_entry_safe(rht_dereference((pos)->member.next, ht), \
+				 typeof(*(pos)), member))
+
+/**
+ * rht_for_each_rcu - iterate over rcu hash chain
+ * @pos:	&struct rhash_head to use as a loop cursor.
+ * @head:	head of the hash chain (struct rhash_head *)
+ * @ht:		pointer to your struct rhashtable
+ *
+ * This hash chain list-traversal primitive may safely run concurrently with
+ * the _rcu fkht mutation primitives such as rht_insert() as long as the
+ * traversal is guarded by rcu_read_lock().
+ */
+#define rht_for_each_rcu(pos, head, ht) \
+	for (pos = rht_dereference_rcu(head, ht); \
+	     pos; \
+	     pos = rht_dereference_rcu((pos)->next, ht))
+
+/**
+ * rht_for_each_entry_rcu - iterate over rcu hash chain of given type
+ * @pos:	type * to use as a loop cursor.
+ * @head:	head of the hash chain (struct rhash_head *)
+ * @member:	name of the rhash_head within the hashable struct.
+ *
+ * This hash chain list-traversal primitive may safely run concurrently with
+ * the _rcu fkht mutation primitives such as rht_insert() as long as the
+ * traversal is guarded by rcu_read_lock().
+ */
+#define rht_for_each_entry_rcu(pos, head, member) \
+	for (pos = rht_entry_safe_rcu(head, typeof(*(pos)), member); \
+	     pos; \
+	     pos = rht_entry_safe_rcu((pos)->member.next, \
+				      typeof(*(pos)), member))
+
+#endif /* _LINUX_RHASHTABLE_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7a638aa..f11a2e8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1550,6 +1550,14 @@ config TEST_STRING_HELPERS
 config TEST_KSTRTOX
 	tristate "Test kstrto*() family of functions at runtime"
 
+config TEST_RHASHTABLE
+	bool "Perform selftest on resizable hash table"
+	default n
+	help
+	  Enable this option to test the rhashtable functions at boot.
+
+	  If unsure, say N.
+
 endmenu # runtime tests
 
 config PROVIDE_OHCI1394_DMA_INIT
diff --git a/lib/Makefile b/lib/Makefile
index ba967a1..fd248e4 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o percpu_ida.o hash.o
+	 percpu-refcount.o percpu_ida.o hash.o rhashtable.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
new file mode 100644
index 0000000..49eb85e
--- /dev/null
+++ b/lib/rhashtable.c
@@ -0,0 +1,783 @@
+/*
+ * Resizable, Scalable, Concurrent Hash Table
+ *
+ * Copyright (c) 2014 Thomas Graf <tgraf@xxxxxxx>
+ *
+ * Based on the following paper:
+ * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf
+ *
+ * Code partially derived from nft_hash:
+ * Copyright (c) 2008-2014 Patrick McHardy <kaber@xxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/hash.h>
+#include <linux/random.h>
+#include <linux/rhashtable.h>
+#include <linux/log2.h>
+
+#define HASH_MIN_SIZE	64UL
+
+#define ASSERT_RHT_MUTEX(HT) BUG_ON(unlikely(!lockdep_rht_mutex_is_held(HT)))
+
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
+{
+	return ht->p.mutex_is_held();
+}
+EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
+#endif
+
+/**
+ * rht_obj - cast hash head to outer object
+ * @ht:		hash table
+ * @he:		hashed node
+ */
+void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
+{
+	return (void *) he - ht->p.head_offset;
+}
+EXPORT_SYMBOL_GPL(rht_obj);
+
+static u32 __hashfn(const struct rhashtable *ht, const void *key,
+		      u32 len, u32 hsize)
+{
+	u32 h;
+
+	h = ht->p.hashfn(key, len, ht->p.hash_rnd);
+
+	return h & (hsize - 1);
+}
+
+/**
+ * rhashtable_hashfn - compute hash for key of given length
+ * @ht:		hash table to compuate for
+ * @key:	pointer to key
+ * @len:	length of key
+ *
+ * Computes the hash value using the hash function provided in the 'hashfn'
+ * of struct rhashtable_params. The returned value is guaranteed to be
+ * smaller than the number of buckets in the hash table.
+ */
+u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len)
+{
+	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+
+	return __hashfn(ht, key, len, tbl->size);
+}
+EXPORT_SYMBOL_GPL(rhashtable_hashfn);
+
+static u32 obj_hashfn(const struct rhashtable *ht, const void *ptr, u32 hsize)
+{
+	if (unlikely(!ht->p.key_len)) {
+		u32 h;
+
+		h = ht->p.obj_hashfn(ptr, ht->p.hash_rnd);
+
+		return h & (hsize - 1);
+	}
+
+	return __hashfn(ht, ptr + ht->p.key_offset, ht->p.key_len, hsize);
+}
+
+/**
+ * rhashtable_obj_hashfn - compute hash for hashed object
+ * @ht:		hash table to compuate for
+ * @ptr:	pointer to hashed object
+ *
+ * Computes the hash value using the hash function `hashfn` respectively
+ * 'obj_hashfn' depending on whether the hash table is set up to work with
+ * a fixed length key. The returned value is guaranteed to be smaller than
+ * the number of buckets in the hash table.
+ */
+u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr)
+{
+	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+
+	return obj_hashfn(ht, ptr, tbl->size);
+}
+EXPORT_SYMBOL_GPL(rhashtable_obj_hashfn);
+
+static u32 head_hashfn(const struct rhashtable *ht,
+		       const struct rhash_head *he, u32 hsize)
+{
+	return obj_hashfn(ht, rht_obj(ht, he), hsize);
+}
+
+static struct bucket_table *bucket_table_alloc(size_t nbuckets, gfp_t flags)
+{
+	struct bucket_table *tbl;
+	size_t size;
+
+	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
+	tbl = kzalloc(size, flags);
+	if (tbl == NULL)
+		tbl = vzalloc(size);
+
+	if (tbl == NULL)
+		return NULL;
+
+	tbl->size = nbuckets;
+
+	return tbl;
+}
+
+static void bucket_table_free(const struct bucket_table *tbl)
+{
+	kvfree(tbl);
+}
+
+/**
+ * rht_grow_above_75 - returns true if nelems > 0.75 * table-size
+ * @ht:		hash table
+ * @new_size:	new table size
+ */
+bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size)
+{
+	/* Expand table when exceeding 75% load */
+	return ht->nelems > (new_size / 4 * 3);
+}
+
+/**
+ * rht_shrink_below_50 - returns true if nelems < 0.3 * table-size
+ * @ht:		hash table
+ * @new_size:	new table size
+ */
+bool rht_shrink_below_50(const struct rhashtable *ht, size_t new_size)
+{
+	/* Shrink table beneath 30% load */
+	return ht->nelems < (new_size * 3 / 10);
+}
+
+static void hashtable_chain_unzip(const struct rhashtable *ht,
+				  const struct bucket_table *new_tbl,
+				  struct bucket_table *old_tbl, size_t n)
+{
+	struct rhash_head *he, *p, *next;
+	unsigned int h;
+
+	/* Old bucket empty, no work needed. */
+	p = rht_dereference(old_tbl->buckets[n], ht);
+	if (!p)
+		return;
+
+	/* Advance the old bucket pointer one or more times until it
+	 * reaches a node that doesn't hash to the same bucket as the
+	 * previous node p. Call the previous node p;
+	 */
+	h = head_hashfn(ht, p, new_tbl->size);
+	rht_for_each(he, p->next, ht) {
+		if (head_hashfn(ht, he, new_tbl->size) != h)
+			break;
+		p = he;
+	}
+	RCU_INIT_POINTER(old_tbl->buckets[n], p->next);
+
+	/* Find the subsequent node which does hash to the same
+	 * bucket as node P, or NULL if no such node exists.
+	 */
+	next = NULL;
+	if (he) {
+		rht_for_each(he, he->next, ht) {
+			if (head_hashfn(ht, he, new_tbl->size) == h) {
+				next = he;
+				break;
+			}
+		}
+	}
+
+	/* Set p's next pointer to that subsequent node pointer,
+	 * bypassing the nodes which do not hash to p's bucket
+	 */
+	RCU_INIT_POINTER(p->next, next);
+}
+
+/**
+ * rhashtable_expand - Expand hash table while allowing concurrent lookups
+ * @ht:		the hash table to expand
+ * @flags:	allocation flags
+ *
+ * A secondary bucket array is allocated and the hash entries are migrated
+ * while keeping them on both lists until the end of the RCU grace period.
+ *
+ * This function may only be called in a context where it is safe to call
+ * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
+ *
+ * The caller must ensure that no concurrent table mutations take place.
+ * It is however valid to have concurrent lookups if they are RCU protected.
+ */
+int rhashtable_expand(struct rhashtable *ht, gfp_t flags)
+{
+	struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
+	struct rhash_head *he;
+	unsigned int i, h;
+	bool complete;
+
+	ASSERT_RHT_MUTEX(ht);
+
+	if (ht->p.max_shift && ht->shift >= ht->p.max_shift)
+		return 0;
+
+	new_tbl = bucket_table_alloc(old_tbl->size * 2, flags);
+	if (new_tbl == NULL)
+		return -ENOMEM;
+
+	ht->shift++;
+
+	/* For each new bucket, search the corresponding old bucket
+	 * for the ïrst entry that hashes to the new bucket, and
+	 * link the new bucket to that entry. Since all the entries
+	 * which will end up in the new bucket appear in the same
+	 * old bucket, this constructs an entirely valid new hash
+	 * table, but with multiple buckets "zipped" together into a
+	 * single imprecise chain.
+	 */
+	for (i = 0; i < new_tbl->size; i++) {
+		h = i & (old_tbl->size - 1);
+		rht_for_each(he, old_tbl->buckets[h], ht) {
+			if (head_hashfn(ht, he, new_tbl->size) == i) {
+				RCU_INIT_POINTER(new_tbl->buckets[i], he);
+				break;
+			}
+		}
+	}
+
+	/* Publish the new table pointer. Lookups may now traverse
+	 * the new table, but they will not beneït from any
+	 * additional efïciency until later steps unzip the buckets.
+	 */
+	rcu_assign_pointer(ht->tbl, new_tbl);
+
+	/* Unzip interleaved hash chains */
+	do {
+		/* Wait for readers. All new readers will see the new
+		 * table, and thus no references to the old table will
+		 * remain.
+		 */
+		synchronize_rcu();
+
+		/* For each bucket in the old table (each of which
+		 * contains items from multiple buckets of the new
+		 * table): ...
+		 */
+		complete = true;
+		for (i = 0; i < old_tbl->size; i++) {
+			hashtable_chain_unzip(ht, new_tbl, old_tbl, i);
+			if (old_tbl->buckets[i] != NULL)
+				complete = false;
+		}
+	} while (!complete);
+
+	bucket_table_free(old_tbl);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_expand);
+
+/**
+ * rhashtable_shrink - Shrink hash table while allowing concurrent lookups
+ * @ht:		the hash table to shrink
+ * @flags:	allocation flags
+ *
+ * This function may only be called in a context where it is safe to call
+ * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
+ *
+ * The caller must ensure that no concurrent table mutations take place.
+ * It is however valid to have concurrent lookups if they are RCU protected.
+ */
+int rhashtable_shrink(struct rhashtable *ht, gfp_t flags)
+{
+	struct bucket_table *ntbl, *tbl = rht_dereference(ht->tbl, ht);
+	struct rhash_head __rcu **pprev;
+	unsigned int i;
+
+	ASSERT_RHT_MUTEX(ht);
+
+	if (tbl->size <= HASH_MIN_SIZE)
+		return 0;
+
+	ntbl = bucket_table_alloc(tbl->size / 2, flags);
+	if (ntbl == NULL)
+		return -ENOMEM;
+
+	ht->shift--;
+
+	/* Link each bucket in the new table to the ïrst bucket
+	 * in the old table that contains entries which will hash
+	 * to the new bucket.
+	 */
+	for (i = 0; i < ntbl->size; i++) {
+		ntbl->buckets[i] = tbl->buckets[i];
+
+		/* Link each bucket in the new table to the ïrst bucket
+		 * in the old table that contains entries which will hash
+		 * to the new bucket.
+		 */
+		for (pprev = &ntbl->buckets[i]; *pprev != NULL;
+		     pprev = &rht_dereference(*pprev, ht)->next)
+			;
+		RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]);
+	}
+
+	/* Publish the new, valid hash table */
+	rcu_assign_pointer(ht->tbl, ntbl);
+
+	/* Wait for readers. No new readers will have references to the
+	 * old hash table.
+	 */
+	synchronize_rcu();
+
+	bucket_table_free(tbl);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_shrink);
+
+/**
+ * rhashtable_insert - insert object into hash hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @flags:	allocation flags (table expansion)
+ *
+ * Will automatically grow the table via rhashtable_expand() if the the
+ * grow_decision function specified at rhashtable_init() returns true.
+ *
+ * The caller must ensure that no concurrent table mutations occur. It is
+ * however valid to have concurrent lookups if they are RCU protected.
+ */
+int rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
+		      gfp_t flags)
+{
+	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
+	u32 hash;
+
+	ASSERT_RHT_MUTEX(ht);
+
+	hash = head_hashfn(ht, obj, tbl->size);
+	RCU_INIT_POINTER(obj->next, tbl->buckets[hash]);
+	rcu_assign_pointer(tbl->buckets[hash], obj);
+	ht->nelems++;
+
+	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
+		rhashtable_expand(ht, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_insert);
+
+/**
+ * rhashtable_remove - remove object into the hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @flags:	allocation flags (table expansion)
+ *
+ * Since the hash chain is single linked, the removal operation needs to
+ * walk the bucket chain upon removal. The removal operation is thus
+ * considerable slow if the hash table is not correctly sized.
+ *
+ * Will automatically shrink the table via rhashtable_expand() if the the
+ * shrink_decision function specified at rhashtable_init() returns true.
+ *
+ * The caller must ensure that no concurrent table mutations occur. It is
+ * however valid to have concurrent lookups if they are RCU protected.
+ */
+bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj,
+		       gfp_t flags)
+{
+	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
+	struct rhash_head __rcu **pprev;
+	struct rhash_head *he;
+	u32 h;
+
+	ASSERT_RHT_MUTEX(ht);
+
+	h = head_hashfn(ht, obj, tbl->size);
+
+	pprev = &tbl->buckets[h];
+	rht_for_each(he, tbl->buckets[h], ht) {
+		if (he != obj) {
+			pprev = &he->next;
+			continue;
+		}
+
+		RCU_INIT_POINTER(*pprev, he->next);
+		ht->nelems--;
+
+		if (ht->p.shrink_decision &&
+		    ht->p.shrink_decision(ht, tbl->size))
+			rhashtable_shrink(ht, flags);
+
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(rhashtable_remove);
+
+/**
+ * rhashtable_lookup - lookup key in hash table
+ * @ht:		hash table
+ * @key:	pointer to key
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. The first matching entry is returned.
+ *
+ * This lookup function may only be used for fixed key hash table (key_len
+ * paramter set). It will BUG() if used inappropriately.
+ *
+ * Lookups may occur in parallel with hash mutations as long as the lookup is
+ * guarded by rcu_read_lock(). The caller must take care of this.
+ */
+void *rhashtable_lookup(const struct rhashtable *ht, const void *key)
+{
+	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+	struct rhash_head *he;
+	u32 h;
+
+	BUG_ON(!ht->p.key_len);
+
+	h = __hashfn(ht, key, ht->p.key_len, tbl->size);
+	rht_for_each_rcu(he, tbl->buckets[h], ht) {
+		if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key,
+			   ht->p.key_len))
+			continue;
+		return (void *) he - ht->p.head_offset;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(rhashtable_lookup);
+
+/**
+ * rhashtable_lookup_compare - search hash table with compare function
+ * @ht:		hash table
+ * @hash:	hash value of desired entry
+ * @compare:	compare function, must return true on match
+ * @arg:	argument passed on to compare function
+ *
+ * Traverses the bucket chain behind the provided hash value and calls the
+ * specified compare function for each entry.
+ *
+ * Lookups may occur in parallel with hash mutations as long as the lookup is
+ * guarded by rcu_read_lock(). The caller must take care of this.
+ *
+ * Returns the first entry on which the compare function returned true.
+ */
+void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+				bool (*compare)(void *, void *), void *arg)
+{
+	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+	struct rhash_head *he;
+
+	if (unlikely(hash >= tbl->size))
+		return NULL;
+
+	rht_for_each_rcu(he, tbl->buckets[hash], ht) {
+		if (!compare(rht_obj(ht, he), arg))
+			continue;
+		return (void *) he - ht->p.head_offset;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
+
+static size_t rounded_hashtable_size(unsigned int nelem)
+{
+	return max(roundup_pow_of_two(nelem * 4 / 3), HASH_MIN_SIZE);
+}
+
+/**
+ * rhashtable_init - initialize a new hash table
+ * @ht:		hash table to be initialized
+ * @params:	configuration parameters
+ *
+ * Initializes a new hash table based on the provided configuration
+ * parameters. A table can be configured either with a variable or
+ * fixed length key:
+ *
+ * Configuration Example 1: Fixed length keys
+ * struct test_obj {
+ *	int			key;
+ *	void *			my_member;
+ *	struct rhash_head	node;
+ * };
+ *
+ * struct rhashtable_params params = {
+ *	.head_offset = offsetof(struct test_obj, node),
+ *	.key_offset = offsetof(struct test_obj, key),
+ *	.key_len = sizeof(int),
+ *	.hashfn = arch_fast_hash,
+ *	.mutex_is_held = &my_mutex_is_held,
+ * };
+ *
+ * Configuration Example 2: Variable length keys
+ * struct test_obj {
+ *	[...]
+ *	struct rhash_head	node;
+ * };
+ *
+ * u32 my_hash_fn(const void *data, u32 seed)
+ * {
+ *	struct test_obj *obj = data;
+ *
+ *	return [... hash ...];
+ * }
+ *
+ * struct rhashtable_params params = {
+ *	.head_offset = offsetof(struct test_obj, node),
+ *	.hashfn = arch_fast_hash,
+ *	.obj_hashfn = my_hash_fn,
+ *	.mutex_is_held = &my_mutex_is_held,
+ * };
+ */
+int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
+{
+	struct bucket_table *tbl;
+	size_t size;
+
+	size = HASH_MIN_SIZE;
+
+	if ((params->key_len && !params->hashfn) ||
+	    (!params->key_len && !params->obj_hashfn))
+		return -EINVAL;
+
+	if (params->nelem_hint)
+		size = rounded_hashtable_size(params->nelem_hint);
+
+	tbl = bucket_table_alloc(size, GFP_KERNEL);
+	if (tbl == NULL)
+		return -ENOMEM;
+
+	ht->shift = ilog2(tbl->size);
+
+	memset(ht, 0, sizeof(*ht));
+	memcpy(&ht->p, params, sizeof(*params));
+	RCU_INIT_POINTER(ht->tbl, tbl);
+
+	if (!ht->p.hash_rnd)
+		get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_init);
+
+/**
+ * rhashtable_destroy - destroy hash table
+ * @ht:		the hash table to destroy
+ *
+ * Frees the bucket array.
+ *
+ * Locking must be provided by the caller.
+ */
+void rhashtable_destroy(const struct rhashtable *ht)
+{
+	const struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
+
+	ASSERT_RHT_MUTEX(ht);
+
+	bucket_table_free(tbl);
+}
+EXPORT_SYMBOL_GPL(rhashtable_destroy);
+
+/**************************************************************************
+ * Self Test
+ **************************************************************************/
+
+#ifdef CONFIG_TEST_RHASHTABLE
+
+#define TEST_HT_SIZE	8
+#define TEST_ENTRIES	2048
+#define TEST_PTR	((void *) 0xdeadbeef)
+#define TEST_NEXPANDS	4
+
+static int test_mutex_is_held(void)
+{
+	return 1;
+}
+
+struct test_obj {
+	void			*ptr;
+	int			value;
+	struct rhash_head	node;
+};
+
+static int __init test_rht_lookup(struct rhashtable *ht)
+{
+	unsigned int i;
+
+	for (i = 0; i < TEST_ENTRIES * 2; i++) {
+		struct test_obj *obj;
+		bool expected = !(i % 2);
+		u32 key = i;
+
+		obj = rhashtable_lookup(ht, &key);
+
+		if (expected && !obj) {
+			pr_warn("Test failed: Could not find key %u\n", key);
+			return -ENOENT;
+		} else if (!expected && obj) {
+			pr_warn("Test failed: Unexpected entry found for key %u\n",
+				key);
+			return -EEXIST;
+		} else if (expected && obj) {
+			if (obj->ptr != TEST_PTR || obj->value != i) {
+				pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n",
+					obj->ptr, TEST_PTR, obj->value, i);
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void test_bucket_stats(struct rhashtable *ht,
+				     struct bucket_table *tbl,
+				     bool quiet)
+{
+	unsigned int cnt, i, total = 0;
+	struct test_obj *obj;
+
+	for (i = 0; i < tbl->size; i++) {
+		cnt = 0;
+		if (!quiet)
+			pr_info(" [%#4x/%zu]", i, tbl->size);
+		rht_for_each_entry_rcu(obj, tbl->buckets[i], node) {
+			cnt++;
+			total++;
+			if (!quiet)
+				pr_cont(" [%p],", obj);
+		}
+
+		if (!quiet)
+			pr_cont("\n  [%#x] first element: %p, chain length: %u\n",
+				i, tbl->buckets[i], cnt);
+	}
+
+	pr_info("  Traversal complete: counted=%u, nelems=%zu, entries=%d\n",
+		total, ht->nelems, TEST_ENTRIES);
+}
+
+static int __init test_rhashtable(struct rhashtable *ht)
+{
+	struct bucket_table *tbl;
+	struct test_obj *obj, *next;
+	int err;
+	unsigned int i;
+
+	/*
+	 * Insertion Test:
+	 * Insert TEST_ENTRIES into table with all keys even numbers
+	 */
+	pr_info("  Adding %d keys\n", TEST_ENTRIES);
+	for (i = 0; i < TEST_ENTRIES; i++) {
+		struct test_obj *obj;
+
+		obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+		if (!obj) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		obj->ptr = TEST_PTR;
+		obj->value = i * 2;
+
+		err = rhashtable_insert(ht, &obj->node, GFP_KERNEL);
+		if (err < 0) {
+			pr_warn("Test failed: Could not add entry %d\n", err);
+			kfree(obj);
+			goto error;
+		}
+	}
+
+	rcu_read_lock();
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+	test_bucket_stats(ht, tbl, true);
+	test_rht_lookup(ht);
+	rcu_read_unlock();
+
+	for (i = 0; i < TEST_NEXPANDS; i++) {
+		pr_info("  Table expansion iteration %u...\n", i);
+		rhashtable_expand(ht, GFP_KERNEL);
+
+		rcu_read_lock();
+		pr_info("  Verifying lookups...\n");
+		test_rht_lookup(ht);
+		rcu_read_unlock();
+	}
+
+	for (i = 0; i < TEST_NEXPANDS; i++) {
+		pr_info("  Table shrinkage iteration %u...\n", i);
+		rhashtable_shrink(ht, GFP_KERNEL);
+
+		rcu_read_lock();
+		pr_info("  Verifying lookups...\n");
+		test_rht_lookup(ht);
+		rcu_read_unlock();
+	}
+
+	pr_info("  Deleting %d keys\n", TEST_ENTRIES);
+	for (i = 0; i < TEST_ENTRIES; i++) {
+		u32 key = i * 2;
+
+		obj = rhashtable_lookup(ht, &key);
+		BUG_ON(!obj);
+
+		rhashtable_remove(ht, &obj->node, GFP_KERNEL);
+		kfree(obj);
+	}
+
+	return 0;
+
+error:
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+	for (i = 0; i < tbl->size; i++)
+		rht_for_each_entry_safe(obj, next, tbl->buckets[i], ht, node)
+			kfree(obj);
+
+	return err;
+}
+
+static int __init test_rht_init(void)
+{
+	struct rhashtable ht;
+	struct rhashtable_params params = {
+		.nelem_hint = TEST_HT_SIZE,
+		.head_offset = offsetof(struct test_obj, node),
+		.key_offset = offsetof(struct test_obj, value),
+		.key_len = sizeof(int),
+		.hashfn = arch_fast_hash,
+		.mutex_is_held = &test_mutex_is_held,
+		.grow_decision = rht_grow_above_75,
+		.shrink_decision = rht_shrink_below_50,
+	};
+	int err;
+
+	pr_info("Running resizable hashtable tests...\n");
+
+	err = rhashtable_init(&ht, &params);
+	if (err < 0) {
+		pr_warn("Test failed: Unable to initialize hashtable: %d\n",
+			err);
+		return err;
+	}
+
+	err = test_rhashtable(&ht);
+
+	rhashtable_destroy(&ht);
+
+	return err;
+}
+
+subsys_initcall(test_rht_init);
+
+#endif /* CONFIG_TEST_RHASHTABLE */
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/