[PATCH v8 01/16] hashtable: introduce a small and naive hashtable

@@ -0,0 +1,196 @@
+/*
+ * Statically sized hash table implementation
+ * (C) 2012  Sasha Levin <levinsasha928@gmail.com>
+ */
+
+#ifndef _LINUX_HASHTABLE_H
+#define _LINUX_HASHTABLE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/hash.h>
+#include <linux/rculist.h>
+
+#define DEFINE_HASHTABLE(name, bits)						\
+	struct hlist_head name[1 << (bits)] =					\
+			{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
+
+#define DECLARE_HASHTABLE(name, bits)                                   	\
+	struct hlist_head name[1 << (bits)]
+
+#define HASH_SIZE(name) (ARRAY_SIZE(name))
+#define HASH_BITS(name) ilog2(HASH_SIZE(name))
+
+/* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */
+#define hash_min(val, bits)							\
+({										\
+	sizeof(val) <= 4 ?							\
+	hash_32(val, bits) :							\
+	hash_long(val, bits);							\
+})
+
+static inline void __hash_init(struct hlist_head *ht, unsigned int sz)
+{
+	unsigned int i;
+
+	for (i = 0; i < sz; i++)
+		INIT_HLIST_HEAD(&ht[i]);
+}
+
+/**
+ * hash_init - initialize a hash table
+ * @hashtable: hashtable to be initialized
+ *
+ * Calculates the size of the hashtable from the given parameter, otherwise
+ * same as hash_init_size.
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_add - add an object to a hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add(hashtable, node, key)						\
+	hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_add_rcu - add an object to a rcu enabled hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add_rcu(hashtable, node, key)					\
+	hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_hashed - check whether an object is in any hashtable
+ * @node: the &struct hlist_node of the object to be checked
+ */
+static inline bool hash_hashed(struct hlist_node *node)
+{
+	return !hlist_unhashed(node);
+}
+
+static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz)
+{
+	unsigned int i;
+
+	for (i = 0; i < sz; i++)
+		if (!hlist_empty(&ht[i]))
+			return false;
+
+	return true;
+}
+
+/**
+ * hash_empty - check whether a hashtable is empty
+ * @hashtable: hashtable to check
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_del - remove an object from a hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del(struct hlist_node *node)
+{
+	hlist_del_init(node);
+}
+
+/**
+ * hash_del_rcu - remove an object from a rcu enabled hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del_rcu(struct hlist_node *node)
+{
+	hlist_del_init_rcu(node);
+}
+
+/**
+ * hash_for_each - iterate over a hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each(name, bkt, node, obj, member)				\
+	for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+		hlist_for_each_entry(obj, node, &name[bkt], member)
+
+/**
+ * hash_for_each_rcu - iterate over a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_rcu(name, bkt, node, obj, member)				\
+	for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+		hlist_for_each_entry_rcu(obj, node, &name[bkt], member)
+
+/**
+ * hash_for_each_safe - iterate over a hashtable safe against removal of
+ * hash entry
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_safe(name, bkt, node, tmp, obj, member)			\
+	for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+		hlist_for_each_entry_safe(obj, node, tmp, &name[bkt], member)
+
+/**
+ * hash_for_each_possible - iterate over all possible objects hashing to the
+ * same bucket
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible(name, obj, node, member, key)			\
+	hlist_for_each_entry(obj, node,	&name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_rcu - iterate over all possible objects hashing to the
+ * same bucket in an rcu enabled hashtable
+ * in a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_rcu(name, obj, node, member, key)		\
+	hlist_for_each_entry_rcu(obj, node, &name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_safe - iterate over all possible objects hashing to the
+ * same bucket safe against removals
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_safe(name, obj, node, tmp, member, key)		\
+	hlist_for_each_entry_safe(obj, node, tmp,				\
+		&name[hash_min(key, HASH_BITS(name))], member)
+
+
+#endif

@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/hashtable.h>
 
 /*
  * userns count is 1 for root user, 1 for init_uts_ns,

@@ -60,13 +61,9 @@ EXPORT_SYMBOL_GPL(init_user_ns);
  */
 
 #define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
-#define UIDHASH_SZ	(1 << UIDHASH_BITS)
-#define UIDHASH_MASK		(UIDHASH_SZ - 1)
-#define __uidhashfn(uid)	(((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
-#define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))
 
 static struct kmem_cache *uid_cachep;
-struct hlist_head uidhash_table[UIDHASH_SZ];
+static DEFINE_HASHTABLE(uidhash_table, UIDHASH_BITS);
 
 /*
  * The uidhash_lock is mostly taken from process context, but it is

@@ -92,22 +89,22 @@ struct user_struct root_user = {
 /*
  * These routines must be called with the uidhash spinlock held!
  */
-static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
+static void uid_hash_insert(struct user_struct *up)
 {
-	hlist_add_head(&up->uidhash_node, hashent);
+	hash_add(uidhash_table, &up->uidhash_node, __kuid_val(up->uid));
 }
 
 static void uid_hash_remove(struct user_struct *up)
 {
-	hlist_del_init(&up->uidhash_node);
+	hash_del(&up->uidhash_node);
 }
 
-static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid)
 {
 	struct user_struct *user;
 	struct hlist_node *h;
 
-	hlist_for_each_entry(user, h, hashent, uidhash_node) {
+	hash_for_each_possible(uidhash_table, user, h, uidhash_node, __kuid_val(uid)) {
 		if (uid_eq(user->uid, uid)) {
 			atomic_inc(&user->__count);
 			return user;

@@ -143,7 +140,7 @@ struct user_struct *find_user(kuid_t uid)
 	unsigned long flags;
 
 	spin_lock_irqsave(&uidhash_lock, flags);
-	ret = uid_hash_find(uid, uidhashentry(uid));
+	ret = uid_hash_find(uid);
 	spin_unlock_irqrestore(&uidhash_lock, flags);
 	return ret;
 }

@@ -164,11 +161,10 @@ void free_uid(struct user_struct *up)
 
 struct user_struct *alloc_uid(kuid_t uid)
 {
-	struct hlist_head *hashent = uidhashentry(uid);
 	struct user_struct *up, *new;
 
 	spin_lock_irq(&uidhash_lock);
-	up = uid_hash_find(uid, hashent);
+	up = uid_hash_find(uid);
 	spin_unlock_irq(&uidhash_lock);
 
 	if (!up) {

@@ -184,13 +180,13 @@ struct user_struct *alloc_uid(kuid_t uid)
 		 * on adding the same user already..
 		 */
 		spin_lock_irq(&uidhash_lock);
-		up = uid_hash_find(uid, hashent);
+		up = uid_hash_find(uid);
 		if (up) {
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
 		} else {
-			uid_hash_insert(new, hashent);
+			uid_hash_insert(new);
 			up = new;
 		}
 		spin_unlock_irq(&uidhash_lock);

@@ -204,17 +200,12 @@ out_unlock:
 
 static int __init uid_cache_init(void)
 {
-	int n;
-
 	uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
 			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
-	for(n = 0; n < UIDHASH_SZ; ++n)
-		INIT_HLIST_HEAD(uidhash_table + n);
-
 	/* Insert the root user immediately (init already runs as root) */
 	spin_lock_irq(&uidhash_lock);
-	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
+	uid_hash_insert(&root_user);
 	spin_unlock_irq(&uidhash_lock);
 
 	return 0;

@@ -33,7 +33,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/swap.h>
 #include <linux/ksm.h>
-#include <linux/hash.h>
+#include <linux/hashtable.h>
 #include <linux/freezer.h>
 #include <linux/oom.h>
 

@@ -156,9 +156,8 @@ struct rmap_item {
 static struct rb_root root_stable_tree = RB_ROOT;
 static struct rb_root root_unstable_tree = RB_ROOT;
 
-#define MM_SLOTS_HASH_SHIFT 10
-#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT)
-static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS];
+#define MM_SLOTS_HASH_BITS 10
+static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
 
 static struct mm_slot ksm_mm_head = {
 	.mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list),

@@ -275,26 +274,21 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
-	struct mm_slot *mm_slot;
-	struct hlist_head *bucket;
 	struct hlist_node *node;
+	struct mm_slot *slot;
+
+	hash_for_each_possible(mm_slots_hash, slot, node, link, (unsigned long)mm) 
+		if (slot->mm == mm)
+			return slot;
 
-	bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
-	hlist_for_each_entry(mm_slot, node, bucket, link) {
-		if (mm == mm_slot->mm)
-			return mm_slot;
-	}
 	return NULL;
 }
 
 static void insert_to_mm_slots_hash(struct mm_struct *mm,
 				    struct mm_slot *mm_slot)
 {
-	struct hlist_head *bucket;
-
-	bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
 	mm_slot->mm = mm;
-	hlist_add_head(&mm_slot->link, bucket);
+	hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
 }
 
 static inline int in_stable_tree(struct rmap_item *rmap_item)

@@ -647,7 +641,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 		ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
 						struct mm_slot, mm_list);
 		if (ksm_test_exit(mm)) {
-			hlist_del(&mm_slot->link);
+			hash_del(&mm_slot->link);
 			list_del(&mm_slot->mm_list);
 			spin_unlock(&ksm_mmlist_lock);
 

@@ -1392,7 +1386,7 @@ next_mm:
 		 * or when all VM_MERGEABLE areas have been unmapped (and
 		 * mmap_sem then protects against race with MADV_MERGEABLE).
 		 */
-		hlist_del(&slot->link);
+		hash_del(&slot->link);
 		list_del(&slot->mm_list);
 		spin_unlock(&ksm_mmlist_lock);
 

@@ -1559,7 +1553,7 @@ void __ksm_exit(struct mm_struct *mm)
 	mm_slot = get_mm_slot(mm);
 	if (mm_slot && ksm_scan.mm_slot != mm_slot) {
 		if (!mm_slot->rmap_list) {
-			hlist_del(&mm_slot->link);
+			hash_del(&mm_slot->link);
 			list_del(&mm_slot->mm_list);
 			easy_to_free = 1;
 		} else {

@@ -2038,6 +2032,7 @@ static int __init ksm_init(void)
 	 */
 	hotplug_memory_notifier(ksm_memory_callback, 100);
 #endif
+
 	return 0;
 
 out_free:

@@ -41,6 +41,7 @@
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
 #include <linux/idr.h>
+#include <linux/hashtable.h>
 
 #include "workqueue_sched.h"
 

@@ -82,8 +83,6 @@ enum {
 	NR_WORKER_POOLS		= 2,		/* # worker pools per gcwq */
 
 	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */
-	BUSY_WORKER_HASH_SIZE	= 1 << BUSY_WORKER_HASH_ORDER,
-	BUSY_WORKER_HASH_MASK	= BUSY_WORKER_HASH_SIZE - 1,
 
 	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
 	IDLE_WORKER_TIMEOUT	= 300 * HZ,	/* keep idle ones for 5 mins */

@@ -180,7 +179,7 @@ struct global_cwq {
 	unsigned int		flags;		/* L: GCWQ_* flags */
 
 	/* workers are chained either in busy_hash or pool idle_list */
-	struct hlist_head	busy_hash[BUSY_WORKER_HASH_SIZE];
+	DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
 						/* L: hash of busy workers */
 
 	struct worker_pool	pools[NR_WORKER_POOLS];

@@ -285,8 +284,7 @@ EXPORT_SYMBOL_GPL(system_freezable_wq);
 	     (pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++)
 
 #define for_each_busy_worker(worker, i, pos, gcwq)			\
-	for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)			\
-		hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
+	hash_for_each(gcwq->busy_hash, i, pos, worker, hentry)
 
 static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask,
 				  unsigned int sw)

@@ -857,63 +855,6 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
 }
 
 /**
- * busy_worker_head - return the busy hash head for a work
- * @gcwq: gcwq of interest
- * @work: work to be hashed
- *
- * Return hash head of @gcwq for @work.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to the hash head.
- */
-static struct hlist_head *busy_worker_head(struct global_cwq *gcwq,
-					   struct work_struct *work)
-{
-	const int base_shift = ilog2(sizeof(struct work_struct));
-	unsigned long v = (unsigned long)work;
-
-	/* simple shift and fold hash, do we need something better? */
-	v >>= base_shift;
-	v += v >> BUSY_WORKER_HASH_ORDER;
-	v &= BUSY_WORKER_HASH_MASK;
-
-	return &gcwq->busy_hash[v];
-}
-
-/**
- * __find_worker_executing_work - find worker which is executing a work
- * @gcwq: gcwq of interest
- * @bwh: hash head as returned by busy_worker_head()
- * @work: work to find worker for
- *
- * Find a worker which is executing @work on @gcwq.  @bwh should be
- * the hash head obtained by calling busy_worker_head() with the same
- * work.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to worker which is executing @work if found, NULL
- * otherwise.
- */
-static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
-						   struct hlist_head *bwh,
-						   struct work_struct *work)
-{
-	struct worker *worker;
-	struct hlist_node *tmp;
-
-	hlist_for_each_entry(worker, tmp, bwh, hentry)
-		if (worker->current_work == work)
-			return worker;
-	return NULL;
-}
-
-/**
  * find_worker_executing_work - find worker which is executing a work
  * @gcwq: gcwq of interest
  * @work: work to find worker for

@@ -932,8 +873,14 @@ static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
 static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
 						 struct work_struct *work)
 {
-	return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work),
-					    work);
+	struct worker *worker;
+	struct hlist_node *tmp;
+
+	hash_for_each_possible(gcwq->busy_hash, worker, tmp, hentry, (unsigned long)work)
+		if (worker->current_work == work)
+			return worker;
+
+	return NULL;
 }
 
 /**

@@ -2160,7 +2107,6 @@ __acquires(&gcwq->lock)
 	struct cpu_workqueue_struct *cwq = get_work_cwq(work);
 	struct worker_pool *pool = worker->pool;
 	struct global_cwq *gcwq = pool->gcwq;
-	struct hlist_head *bwh = busy_worker_head(gcwq, work);
 	bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE;
 	work_func_t f = work->func;
 	int work_color;

@@ -2192,7 +2138,7 @@ __acquires(&gcwq->lock)
 	 * already processing the work.  If so, defer the work to the
 	 * currently executing one.
 	 */
-	collision = __find_worker_executing_work(gcwq, bwh, work);
+	collision = find_worker_executing_work(gcwq, work);
 	if (unlikely(collision)) {
 		move_linked_works(work, &collision->scheduled, NULL);
 		return;

@@ -2200,7 +2146,7 @@ __acquires(&gcwq->lock)
 
 	/* claim and dequeue */
 	debug_work_deactivate(work);
-	hlist_add_head(&worker->hentry, bwh);
+	hash_add(gcwq->busy_hash, &worker->hentry, (unsigned long)worker);
 	worker->current_work = work;
 	worker->current_cwq = cwq;
 	work_color = get_work_color(work);

@@ -2258,7 +2204,7 @@ __acquires(&gcwq->lock)
 		worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
 
 	/* we're done with it, release */
-	hlist_del_init(&worker->hentry);
+	hash_del(&worker->hentry);
 	worker->current_work = NULL;
 	worker->current_cwq = NULL;
 	cwq_dec_nr_in_flight(cwq, work_color);

@@ -3823,7 +3769,6 @@ out_unlock:
 static int __init init_workqueues(void)
 {
 	unsigned int cpu;
-	int i;
 
 	/* make sure we have enough bits for OFFQ CPU number */
 	BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) <

@@ -3841,8 +3786,7 @@ static int __init init_workqueues(void)
 		gcwq->cpu = cpu;
 		gcwq->flags |= GCWQ_DISASSOCIATED;
 
-		for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)
-			INIT_HLIST_HEAD(&gcwq->busy_hash[i]);
+		hash_init(gcwq->busy_hash);
 
 		for_each_worker_pool(pool, gcwq) {
 			pool->gcwq = gcwq;

@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/static_key.h>
+#include <linux/hashtable.h>
 
 extern struct tracepoint * const __start___tracepoints_ptrs[];
 extern struct tracepoint * const __stop___tracepoints_ptrs[];

@@ -49,8 +50,7 @@ static LIST_HEAD(tracepoint_module_list);
  * Protected by tracepoints_mutex.
  */
 #define TRACEPOINT_HASH_BITS 6
-#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
-static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+static DEFINE_HASHTABLE(tracepoint_table, TRACEPOINT_HASH_BITS);
 
 /*
  * Note about RCU :

@@ -191,16 +191,15 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
  */
 static struct tracepoint_entry *get_tracepoint(const char *name)
 {
-	struct hlist_head *head;
 	struct hlist_node *node;
 	struct tracepoint_entry *e;
 	u32 hash = jhash(name, strlen(name), 0);
 
-	head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, node, head, hlist) {
+	hash_for_each_possible(tracepoint_table, e, node, hlist, hash) {
 		if (!strcmp(name, e->name))
 			return e;
 	}
+
 	return NULL;
 }
 

@@ -210,19 +209,13 @@ static struct tracepoint_entry *get_tracepoint(const char *name)
  */
 static struct tracepoint_entry *add_tracepoint(const char *name)
 {
-	struct hlist_head *head;
-	struct hlist_node *node;
 	struct tracepoint_entry *e;
 	size_t name_len = strlen(name) + 1;
 	u32 hash = jhash(name, name_len-1, 0);
 
-	head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			printk(KERN_NOTICE
-				"tracepoint %s busy\n", name);
-			return ERR_PTR(-EEXIST);	/* Already there */
-		}
+	if (get_tracepoint(name)) {
+		printk(KERN_NOTICE "tracepoint %s busy\n", name);
+		return ERR_PTR(-EEXIST);	/* Already there */
 	}
 	/*
 	 * Using kmalloc here to allocate a variable length element. Could

@@ -234,7 +227,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
 	memcpy(&e->name[0], name, name_len);
 	e->funcs = NULL;
 	e->refcount = 0;
-	hlist_add_head(&e->hlist, head);
+	hash_add(tracepoint_table, &e->hlist, hash);
 	return e;
 }
 

@@ -244,7 +237,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
  */
 static inline void remove_tracepoint(struct tracepoint_entry *e)
 {
-	hlist_del(&e->hlist);
+	hash_del(&e->hlist);
 	kfree(e);
 }
 

@@ -34,6 +34,7 @@
 #include <linux/jhash.h>
 #include <linux/errno.h>
 #include <net/9p/9p.h>
+#include <linux/hashtable.h>
 
 /**
  * struct errormap - map string errors from Plan 9 to Linux numeric ids

@@ -50,8 +51,8 @@ struct errormap {
 	struct hlist_node list;
 };
 
-#define ERRHASHSZ		32
-static struct hlist_head hash_errmap[ERRHASHSZ];
+#define ERR_HASH_BITS 5
+static DEFINE_HASHTABLE(hash_errmap, ERR_HASH_BITS);
 
 /* FixMe - reduce to a reasonable size */
 static struct errormap errmap[] = {

@@ -193,18 +194,14 @@ static struct errormap errmap[] = {
 int p9_error_init(void)
 {
 	struct errormap *c;
-	int bucket;
-
-	/* initialize hash table */
-	for (bucket = 0; bucket < ERRHASHSZ; bucket++)
-		INIT_HLIST_HEAD(&hash_errmap[bucket]);
+	u32 hash;
 
 	/* load initial error map into hash table */
 	for (c = errmap; c->name != NULL; c++) {
 		c->namelen = strlen(c->name);
-		bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
+		hash = jhash(c->name, c->namelen, 0);
 		INIT_HLIST_NODE(&c->list);
-		hlist_add_head(&c->list, &hash_errmap[bucket]);
+		hash_add(hash_errmap, &c->list, hash);
 	}
 
 	return 1;

@@ -223,13 +220,13 @@ int p9_errstr2errno(char *errstr, int len)
 	int errno;
 	struct hlist_node *p;
 	struct errormap *c;
-	int bucket;
+	u32 hash;
 
 	errno = 0;
 	p = NULL;
 	c = NULL;
-	bucket = jhash(errstr, len, 0) % ERRHASHSZ;
-	hlist_for_each_entry(c, p, &hash_errmap[bucket], list) {
+	hash = jhash(errstr, len, 0);
+	hash_for_each_possible(hash_errmap, c, p, list, hash) {
 		if (c->namelen == len && !memcmp(c->name, errstr, len)) {
 			errno = c->val;
 			break;

@@ -61,7 +61,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
+#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
 
 void blk_insert_flush(struct request *rq);
 void blk_abort_flushes(struct request_queue *q);

@@ -46,11 +46,6 @@ static LIST_HEAD(elv_list);
 /*
  * Merge hash stuff.
  */
-static const int elv_hash_shift = 6;
-#define ELV_HASH_BLOCK(sec)	((sec) >> 3)
-#define ELV_HASH_FN(sec)	\
-		(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
-#define ELV_HASH_ENTRIES	(1 << elv_hash_shift)
 #define rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))
 
 /*

@@ -142,7 +137,6 @@ static struct elevator_queue *elevator_alloc(struct request_queue *q,
 				  struct elevator_type *e)
 {
 	struct elevator_queue *eq;
-	int i;
 
 	eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (unlikely(!eq))

@@ -151,14 +145,7 @@ static struct elevator_queue *elevator_alloc(struct request_queue *q,
 	eq->type = e;
 	kobject_init(&eq->kobj, &elv_ktype);
 	mutex_init(&eq->sysfs_lock);
-
-	eq->hash = kmalloc_node(sizeof(struct hlist_head) * ELV_HASH_ENTRIES,
-					GFP_KERNEL, q->node);
-	if (!eq->hash)
-		goto err;
-
-	for (i = 0; i < ELV_HASH_ENTRIES; i++)
-		INIT_HLIST_HEAD(&eq->hash[i]);
+	hash_init(eq->hash);
 
 	return eq;
 err:

@@ -173,7 +160,6 @@ static void elevator_release(struct kobject *kobj)
 
 	e = container_of(kobj, struct elevator_queue, kobj);
 	elevator_put(e->type);
-	kfree(e->hash);
 	kfree(e);
 }
 

@@ -240,7 +226,7 @@ EXPORT_SYMBOL(elevator_exit);
 
 static inline void __elv_rqhash_del(struct request *rq)
 {
-	hlist_del_init(&rq->hash);
+	hash_del(&rq->hash);
 }
 
 static void elv_rqhash_del(struct request_queue *q, struct request *rq)

@@ -254,7 +240,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
 	struct elevator_queue *e = q->elevator;
 
 	BUG_ON(ELV_ON_HASH(rq));
-	hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
+	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
 }
 
 static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)

@@ -266,11 +252,10 @@ static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
 static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
 {
 	struct elevator_queue *e = q->elevator;
-	struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
 	struct hlist_node *entry, *next;
 	struct request *rq;
 
-	hlist_for_each_entry_safe(rq, entry, next, hash_list, hash) {
+	hash_for_each_possible_safe(e->hash, rq, entry, next, hash, offset) {
 		BUG_ON(!ELV_ON_HASH(rq));
 
 		if (unlikely(!rq_mergeable(rq))) {

@@ -2,6 +2,7 @@
 #define _LINUX_ELEVATOR_H
 
 #include <linux/percpu.h>
+#include <linux/hashtable.h>
 
 #ifdef CONFIG_BLOCK
 

@@ -96,6 +97,8 @@ struct elevator_type
 	struct list_head list;
 };
 
+#define ELV_HASH_BITS 6
+
 /*
  * each queue has an elevator_queue associated with it
  */

@@ -105,8 +108,8 @@ struct elevator_queue
 	void *elevator_data;
 	struct kobject kobj;
 	struct mutex sysfs_lock;
-	struct hlist_head *hash;
 	unsigned int registered:1;
+	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
 };
 
 /*

@@ -28,6 +28,7 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
+#include <linux/hashtable.h>
 #include <asm/ioctls.h>
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/cache.h>

@@ -524,19 +525,18 @@ EXPORT_SYMBOL_GPL(cache_purge);
  * it to be revisited when cache info is available
  */
 
-#define	DFR_HASHSIZE	(PAGE_SIZE/sizeof(struct list_head))
-#define	DFR_HASH(item)	((((long)item)>>4 ^ (((long)item)>>13)) % DFR_HASHSIZE)
+#define	DFR_HASH_BITS	9
 
 #define	DFR_MAX	300	/* ??? */
 
 static DEFINE_SPINLOCK(cache_defer_lock);
 static LIST_HEAD(cache_defer_list);
-static struct hlist_head cache_defer_hash[DFR_HASHSIZE];
+static DEFINE_HASHTABLE(cache_defer_hash, DFR_HASH_BITS);
 static int cache_defer_cnt;
 
 static void __unhash_deferred_req(struct cache_deferred_req *dreq)
 {
-	hlist_del_init(&dreq->hash);
+	hash_del(&dreq->hash);
 	if (!list_empty(&dreq->recent)) {
 		list_del_init(&dreq->recent);
 		cache_defer_cnt--;

@@ -545,10 +545,7 @@ static void __unhash_deferred_req(struct cache_deferred_req *dreq)
 
 static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item)
 {
-	int hash = DFR_HASH(item);
-
-	INIT_LIST_HEAD(&dreq->recent);
-	hlist_add_head(&dreq->hash, &cache_defer_hash[hash]);
+	hash_add(cache_defer_hash, &dreq->hash, (unsigned long)item);
 }
 
 static void setup_deferral(struct cache_deferred_req *dreq,

@@ -600,7 +597,7 @@ static void cache_wait_req(struct cache_req *req, struct cache_head *item)
 		 * to clean up
 		 */
 		spin_lock(&cache_defer_lock);
-		if (!hlist_unhashed(&sleeper.handle.hash)) {
+		if (hash_hashed(&sleeper.handle.hash)) {
 			__unhash_deferred_req(&sleeper.handle);
 			spin_unlock(&cache_defer_lock);
 		} else {