8 files changed, 562 insertions, 82 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 32f3e5ae2be5..6c695ff9caba 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -276,4 +276,7 @@ config CORDIC
           so its calculations are in fixed point. Modules can select this
           when they require this function. Module will be called cordic.
 
+config LLIST
+        bool
+
 endmenu
diff --git a/lib/Makefile b/lib/Makefile
index 892f4e282ea1..6457af4a7caf 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -115,6 +115,8 @@ obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
 
+obj-$(CONFIG_LLIST) += llist.o
+
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
 
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 37ef4b048795..2f4412e4d071 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -271,8 +271,6 @@ int __bitmap_weight(const unsigned long *bitmap, int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
-#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
-
 void bitmap_set(unsigned long *map, int start, int nr)
 {
         unsigned long *p = map + BIT_WORD(start);
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 2577b121c7c1..f193b7796449 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -197,21 +197,15 @@ static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode,
         return debugfs_create_file(name, mode, parent, value, &fops_atomic_t);
 }
 
-void cleanup_fault_attr_dentries(struct fault_attr *attr)
-{
-        debugfs_remove_recursive(attr->dir);
-}
-
-int init_fault_attr_dentries(struct fault_attr *attr, const char *name)
+struct dentry *fault_create_debugfs_attr(const char *name,
+                        struct dentry *parent, struct fault_attr *attr)
 {
         mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
         struct dentry *dir;
 
-        dir = debugfs_create_dir(name, NULL);
+        dir = debugfs_create_dir(name, parent);
         if (!dir)
-                return -ENOMEM;
-
-        attr->dir = dir;
+                return ERR_PTR(-ENOMEM);
 
         if (!debugfs_create_ul("probability", mode, dir, &attr->probability))
                 goto fail;
@@ -243,11 +237,11 @@ int init_fault_attr_dentries(struct fault_attr *attr, const char *name)
 
 #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
-        return 0;
+        return dir;
 fail:
-        debugfs_remove_recursive(attr->dir);
+        debugfs_remove_recursive(dir);
 
-        return -ENOMEM;
+        return ERR_PTR(-ENOMEM);
 }
 
 #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 577ddf805975..f352cc42f4f8 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -1,8 +1,26 @@
 /*
- * Basic general purpose allocator for managing special purpose memory
- * not managed by the regular kmalloc/kfree interface.
- * Uses for this includes on-device special memory, uncached memory
- * etc.
+ * Basic general purpose allocator for managing special purpose
+ * memory, for example, memory that is not managed by the regular
+ * kmalloc/kfree interface.  Uses for this includes on-device special
+ * memory, uncached memory etc.
+ *
+ * It is safe to use the allocator in NMI handlers and other special
+ * unblockable contexts that could otherwise deadlock on locks.  This
+ * is implemented by using atomic operations and retries on any
+ * conflicts.  The disadvantage is that there may be livelocks in
+ * extreme cases.  For better scalability, one allocator can be used
+ * for each CPU.
+ *
+ * The lockless operation only works if there is enough memory
+ * available.  If new memory is added to the pool a lock has to be
+ * still taken.  So any user relying on locklessness has to ensure
+ * that sufficient memory is preallocated.
+ *
+ * The basic atomic operation of this allocator is cmpxchg on long.
+ * On architectures that don't have NMI-safe cmpxchg implementation,
+ * the allocator can NOT be used in NMI handler.  So code uses the
+ * allocator in NMI handler should depend on
+ * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
  *
  * Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
  *
@@ -13,8 +31,109 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bitmap.h>
+#include <linux/rculist.h>
+#include <linux/interrupt.h>
 #include <linux/genalloc.h>
 
+static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
+{
+        unsigned long val, nval;
+
+        nval = *addr;
+        do {
+                val = nval;
+                if (val & mask_to_set)
+                        return -EBUSY;
+                cpu_relax();
+        } while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);
+
+        return 0;
+}
+
+static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
+{
+        unsigned long val, nval;
+
+        nval = *addr;
+        do {
+                val = nval;
+                if ((val & mask_to_clear) != mask_to_clear)
+                        return -EBUSY;
+                cpu_relax();
+        } while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);
+
+        return 0;
+}
+
+/*
+ * bitmap_set_ll - set the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Set @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users set the same bit, one user will return remain bits, otherwise
+ * return 0.
+ */
+static int bitmap_set_ll(unsigned long *map, int start, int nr)
+{
+        unsigned long *p = map + BIT_WORD(start);
+        const int size = start + nr;
+        int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+        unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+        while (nr - bits_to_set >= 0) {
+                if (set_bits_ll(p, mask_to_set))
+                        return nr;
+                nr -= bits_to_set;
+                bits_to_set = BITS_PER_LONG;
+                mask_to_set = ~0UL;
+                p++;
+        }
+        if (nr) {
+                mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+                if (set_bits_ll(p, mask_to_set))
+                        return nr;
+        }
+
+        return 0;
+}
+
+/*
+ * bitmap_clear_ll - clear the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Clear @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users clear the same bit, one user will return remain bits,
+ * otherwise return 0.
+ */
+static int bitmap_clear_ll(unsigned long *map, int start, int nr)
+{
+        unsigned long *p = map + BIT_WORD(start);
+        const int size = start + nr;
+        int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+        unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+        while (nr - bits_to_clear >= 0) {
+                if (clear_bits_ll(p, mask_to_clear))
+                        return nr;
+                nr -= bits_to_clear;
+                bits_to_clear = BITS_PER_LONG;
+                mask_to_clear = ~0UL;
+                p++;
+        }
+        if (nr) {
+                mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+                if (clear_bits_ll(p, mask_to_clear))
+                        return nr;
+        }
+
+        return 0;
+}
 
 /**
  * gen_pool_create - create a new special memory pool
@@ -30,7 +149,7 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
 
         pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
         if (pool != NULL) {
-                rwlock_init(&pool->lock);
+                spin_lock_init(&pool->lock);
                 INIT_LIST_HEAD(&pool->chunks);
                 pool->min_alloc_order = min_alloc_order;
         }
@@ -63,14 +182,14 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
         if (unlikely(chunk == NULL))
                 return -ENOMEM;
 
-        spin_lock_init(&chunk->lock);
         chunk->phys_addr = phys;
         chunk->start_addr = virt;
         chunk->end_addr = virt + size;
+        atomic_set(&chunk->avail, size);
 
-        write_lock(&pool->lock);
-        list_add(&chunk->next_chunk, &pool->chunks);
-        write_unlock(&pool->lock);
+        spin_lock(&pool->lock);
+        list_add_rcu(&chunk->next_chunk, &pool->chunks);
+        spin_unlock(&pool->lock);
 
         return 0;
 }
@@ -85,19 +204,19 @@ EXPORT_SYMBOL(gen_pool_add_virt);
  */
 phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 {
-        struct list_head *_chunk;
         struct gen_pool_chunk *chunk;
+        phys_addr_t paddr = -1;
 
-        read_lock(&pool->lock);
-        list_for_each(_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
-
-                if (addr >= chunk->start_addr && addr < chunk->end_addr)
-                        return chunk->phys_addr + addr - chunk->start_addr;
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+                if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+                        paddr = chunk->phys_addr + (addr - chunk->start_addr);
+                        break;
+                }
         }
-        read_unlock(&pool->lock);
+        rcu_read_unlock();
 
-        return -1;
+        return paddr;
 }
 EXPORT_SYMBOL(gen_pool_virt_to_phys);
 
@@ -115,7 +234,6 @@ void gen_pool_destroy(struct gen_pool *pool)
         int order = pool->min_alloc_order;
         int bit, end_bit;
 
-
         list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
                 chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
                 list_del(&chunk->next_chunk);
@@ -137,44 +255,50 @@ EXPORT_SYMBOL(gen_pool_destroy);
  * @size: number of bytes to allocate from the pool
  *
  * Allocate the requested number of bytes from the specified pool.
- * Uses a first-fit algorithm.
+ * Uses a first-fit algorithm. Can not be used in NMI handler on
+ * architectures without NMI-safe cmpxchg implementation.
  */
 unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 {
-        struct list_head *_chunk;
         struct gen_pool_chunk *chunk;
-        unsigned long addr, flags;
+        unsigned long addr = 0;
         int order = pool->min_alloc_order;
-        int nbits, start_bit, end_bit;
+        int nbits, start_bit = 0, end_bit, remain;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
 
         if (size == 0)
                 return 0;
 
         nbits = (size + (1UL << order) - 1) >> order;
-
-        read_lock(&pool->lock);
-        list_for_each(_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+                if (size > atomic_read(&chunk->avail))
+                        continue;
 
                 end_bit = (chunk->end_addr - chunk->start_addr) >> order;
-
-                spin_lock_irqsave(&chunk->lock, flags);
-                start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0,
-                                                nbits, 0);
-                if (start_bit >= end_bit) {
-                        spin_unlock_irqrestore(&chunk->lock, flags);
+retry:
+                start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit,
+                                                       start_bit, nbits, 0);
+                if (start_bit >= end_bit)
                         continue;
+                remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
+                if (remain) {
+                        remain = bitmap_clear_ll(chunk->bits, start_bit,
+                                                 nbits - remain);
+                        BUG_ON(remain);
+                        goto retry;
                 }
 
                 addr = chunk->start_addr + ((unsigned long)start_bit << order);
-
-                bitmap_set(chunk->bits, start_bit, nbits);
-                spin_unlock_irqrestore(&chunk->lock, flags);
-                read_unlock(&pool->lock);
-                return addr;
+                size = nbits << order;
+                atomic_sub(size, &chunk->avail);
+                break;
         }
-        read_unlock(&pool->lock);
-        return 0;
+        rcu_read_unlock();
+        return addr;
 }
 EXPORT_SYMBOL(gen_pool_alloc);
 
@@ -184,33 +308,95 @@ EXPORT_SYMBOL(gen_pool_alloc);
  * @addr: starting address of memory to free back to pool
  * @size: size in bytes of memory to free
  *
- * Free previously allocated special memory back to the specified pool.
+ * Free previously allocated special memory back to the specified
+ * pool.  Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
  */
 void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
 {
-        struct list_head *_chunk;
         struct gen_pool_chunk *chunk;
-        unsigned long flags;
         int order = pool->min_alloc_order;
-        int bit, nbits;
+        int start_bit, nbits, remain;
 
-        nbits = (size + (1UL << order) - 1) >> order;
-
-        read_lock(&pool->lock);
-        list_for_each(_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
 
+        nbits = (size + (1UL << order) - 1) >> order;
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
                 if (addr >= chunk->start_addr && addr < chunk->end_addr) {
                         BUG_ON(addr + size > chunk->end_addr);
-                        spin_lock_irqsave(&chunk->lock, flags);
-                        bit = (addr - chunk->start_addr) >> order;
-                        while (nbits--)
-                                __clear_bit(bit++, chunk->bits);
-                        spin_unlock_irqrestore(&chunk->lock, flags);
-                        break;
+                        start_bit = (addr - chunk->start_addr) >> order;
+                        remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
+                        BUG_ON(remain);
+                        size = nbits << order;
+                        atomic_add(size, &chunk->avail);
+                        rcu_read_unlock();
+                        return;
                 }
         }
-        BUG_ON(nbits > 0);
-        read_unlock(&pool->lock);
+        rcu_read_unlock();
+        BUG();
 }
 EXPORT_SYMBOL(gen_pool_free);
+
+/**
+ * gen_pool_for_each_chunk - call func for every chunk of generic memory pool
+ * @pool:       the generic memory pool
+ * @func:       func to call
+ * @data:       additional data used by @func
+ *
+ * Call @func for every chunk of generic memory pool.  The @func is
+ * called with rcu_read_lock held.
+ */
+void gen_pool_for_each_chunk(struct gen_pool *pool,
+        void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data),
+        void *data)
+{
+        struct gen_pool_chunk *chunk;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk)
+                func(pool, chunk, data);
+        rcu_read_unlock();
+}
+EXPORT_SYMBOL(gen_pool_for_each_chunk);
+
+/**
+ * gen_pool_avail - get available free space of the pool
+ * @pool: pool to get available free space
+ *
+ * Return available free space of the specified pool.
+ */
+size_t gen_pool_avail(struct gen_pool *pool)
+{
+        struct gen_pool_chunk *chunk;
+        size_t avail = 0;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+                avail += atomic_read(&chunk->avail);
+        rcu_read_unlock();
+        return avail;
+}
+EXPORT_SYMBOL_GPL(gen_pool_avail);
+
+/**
+ * gen_pool_size - get size in bytes of memory managed by the pool
+ * @pool: pool to get size
+ *
+ * Return size in bytes of memory managed by the pool.
+ */
+size_t gen_pool_size(struct gen_pool *pool)
+{
+        struct gen_pool_chunk *chunk;
+        size_t size = 0;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+                size += chunk->end_addr - chunk->start_addr;
+        rcu_read_unlock();
+        return size;
+}
+EXPORT_SYMBOL_GPL(gen_pool_size);
diff --git a/lib/idr.c b/lib/idr.c
index e15502e8b21e..db040ce3fa73 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -34,8 +34,10 @@
 #include <linux/err.h>
 #include <linux/string.h>
 #include <linux/idr.h>
+#include <linux/spinlock.h>
 
 static struct kmem_cache *idr_layer_cache;
+static DEFINE_SPINLOCK(simple_ida_lock);
 
 static struct idr_layer *get_from_free_list(struct idr *idp)
 {
@@ -926,6 +928,71 @@ void ida_destroy(struct ida *ida)
 EXPORT_SYMBOL(ida_destroy);
 
 /**
+ * ida_simple_get - get a new id.
+ * @ida: the (initialized) ida.
+ * @start: the minimum id (inclusive, < 0x8000000)
+ * @end: the maximum id (exclusive, < 0x8000000 or 0)
+ * @gfp_mask: memory allocation flags
+ *
+ * Allocates an id in the range start <= id < end, or returns -ENOSPC.
+ * On memory allocation failure, returns -ENOMEM.
+ *
+ * Use ida_simple_remove() to get rid of an id.
+ */
+int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
+                   gfp_t gfp_mask)
+{
+        int ret, id;
+        unsigned int max;
+
+        BUG_ON((int)start < 0);
+        BUG_ON((int)end < 0);
+
+        if (end == 0)
+                max = 0x80000000;
+        else {
+                BUG_ON(end < start);
+                max = end - 1;
+        }
+
+again:
+        if (!ida_pre_get(ida, gfp_mask))
+                return -ENOMEM;
+
+        spin_lock(&simple_ida_lock);
+        ret = ida_get_new_above(ida, start, &id);
+        if (!ret) {
+                if (id > max) {
+                        ida_remove(ida, id);
+                        ret = -ENOSPC;
+                } else {
+                        ret = id;
+                }
+        }
+        spin_unlock(&simple_ida_lock);
+
+        if (unlikely(ret == -EAGAIN))
+                goto again;
+
+        return ret;
+}
+EXPORT_SYMBOL(ida_simple_get);
+
+/**
+ * ida_simple_remove - remove an allocated id.
+ * @ida: the (initialized) ida.
+ * @id: the id returned by ida_simple_get.
+ */
+void ida_simple_remove(struct ida *ida, unsigned int id)
+{
+        BUG_ON((int)id < 0);
+        spin_lock(&simple_ida_lock);
+        ida_remove(ida, id);
+        spin_unlock(&simple_ida_lock);
+}
+EXPORT_SYMBOL(ida_simple_remove);
+
+/**
  * ida_init - initialize ida handle
  * @ida:        ida handle
  *
diff --git a/lib/llist.c b/lib/llist.c
new file mode 100644
index 000000000000..da445724fa1f
--- /dev/null
+++ b/lib/llist.c
@@ -0,0 +1,129 @@
+/*
+ * Lock-less NULL terminated single linked list
+ *
+ * The basic atomic operation of this list is cmpxchg on long.  On
+ * architectures that don't have NMI-safe cmpxchg implementation, the
+ * list can NOT be used in NMI handler.  So code uses the list in NMI
+ * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
+ *
+ * Copyright 2010,2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * 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;
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/llist.h>
+
+#include <asm/system.h>
+
+/**
+ * llist_add - add a new entry
+ * @new:        new entry to be added
+ * @head:       the head for your lock-less list
+ */
+void llist_add(struct llist_node *new, struct llist_head *head)
+{
+        struct llist_node *entry, *old_entry;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
+
+        entry = head->first;
+        do {
+                old_entry = entry;
+                new->next = entry;
+                cpu_relax();
+        } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry);
+}
+EXPORT_SYMBOL_GPL(llist_add);
+
+/**
+ * llist_add_batch - add several linked entries in batch
+ * @new_first:  first entry in batch to be added
+ * @new_last:   last entry in batch to be added
+ * @head:       the head for your lock-less list
+ */
+void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
+                     struct llist_head *head)
+{
+        struct llist_node *entry, *old_entry;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
+
+        entry = head->first;
+        do {
+                old_entry = entry;
+                new_last->next = entry;
+                cpu_relax();
+        } while ((entry = cmpxchg(&head->first, old_entry, new_first)) != old_entry);
+}
+EXPORT_SYMBOL_GPL(llist_add_batch);
+
+/**
+ * llist_del_first - delete the first entry of lock-less list
+ * @head:       the head for your lock-less list
+ *
+ * If list is empty, return NULL, otherwise, return the first entry
+ * deleted, this is the newest added one.
+ *
+ * Only one llist_del_first user can be used simultaneously with
+ * multiple llist_add users without lock.  Because otherwise
+ * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add,
+ * llist_add) sequence in another user may change @head->first->next,
+ * but keep @head->first.  If multiple consumers are needed, please
+ * use llist_del_all or use lock between consumers.
+ */
+struct llist_node *llist_del_first(struct llist_head *head)
+{
+        struct llist_node *entry, *old_entry, *next;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
+
+        entry = head->first;
+        do {
+                if (entry == NULL)
+                        return NULL;
+                old_entry = entry;
+                next = entry->next;
+                cpu_relax();
+        } while ((entry = cmpxchg(&head->first, old_entry, next)) != old_entry);
+
+        return entry;
+}
+EXPORT_SYMBOL_GPL(llist_del_first);
+
+/**
+ * llist_del_all - delete all entries from lock-less list
+ * @head:       the head of lock-less list to delete all entries
+ *
+ * If list is empty, return NULL, otherwise, delete all entries and
+ * return the pointer to the first entry.  The order of entries
+ * deleted is from the newest to the oldest added one.
+ */
+struct llist_node *llist_del_all(struct llist_head *head)
+{
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+        BUG_ON(in_nmi());
+#endif
+
+        return xchg(&head->first, NULL);
+}
+EXPORT_SYMBOL_GPL(llist_del_all);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7ea2e033d715..a2f9da59c197 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -823,8 +823,8 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_prev_hole);
 
 static unsigned int
-__lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
-        unsigned int max_items, unsigned long *next_index)
+__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices,
+        unsigned long index, unsigned int max_items, unsigned long *next_index)
 {
         unsigned int nr_found = 0;
         unsigned int shift, height;
@@ -857,12 +857,16 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
 
         /* Bottom level: grab some items */
         for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-                index++;
                 if (slot->slots[i]) {
-                        results[nr_found++] = &(slot->slots[i]);
-                        if (nr_found == max_items)
+                        results[nr_found] = &(slot->slots[i]);
+                        if (indices)
+                                indices[nr_found] = index;
+                        if (++nr_found == max_items) {
+                                index++;
                                 goto out;
+                        }
                 }
+                index++;
         }
 out:
         *next_index = index;
@@ -918,8 +922,8 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 
                 if (cur_index > max_index)
                         break;
-                slots_found = __lookup(node, (void ***)results + ret, cur_index,
-                                        max_items - ret, &next_index);
+                slots_found = __lookup(node, (void ***)results + ret, NULL,
+                                cur_index, max_items - ret, &next_index);
                 nr_found = 0;
                 for (i = 0; i < slots_found; i++) {
                         struct radix_tree_node *slot;
@@ -944,6 +948,7 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *      radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree
  *      @root:          radix tree root
  *      @results:       where the results of the lookup are placed
+ *      @indices:       where their indices should be placed (but usually NULL)
  *      @first_index:   start the lookup from this key
  *      @max_items:     place up to this many items at *results
  *
@@ -958,7 +963,8 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *      protection, radix_tree_deref_slot may fail requiring a retry.
  */
 unsigned int
-radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
+radix_tree_gang_lookup_slot(struct radix_tree_root *root,
+                        void ***results, unsigned long *indices,
                         unsigned long first_index, unsigned int max_items)
 {
         unsigned long max_index;
@@ -974,6 +980,8 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
                 if (first_index > 0)
                         return 0;
                 results[0] = (void **)&root->rnode;
+                if (indices)
+                        indices[0] = 0;
                 return 1;
         }
         node = indirect_to_ptr(node);
@@ -987,8 +995,9 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
 
                 if (cur_index > max_index)
                         break;
-                slots_found = __lookup(node, results + ret, cur_index,
-                                        max_items - ret, &next_index);
+                slots_found = __lookup(node, results + ret,
+                                indices ? indices + ret : NULL,
+                                cur_index, max_items - ret, &next_index);
                 ret += slots_found;
                 if (next_index == 0)
                         break;
@@ -1194,6 +1203,98 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
 
+#if defined(CONFIG_SHMEM) && defined(CONFIG_SWAP)
+#include <linux/sched.h> /* for cond_resched() */
+
+/*
+ * This linear search is at present only useful to shmem_unuse_inode().
+ */
+static unsigned long __locate(struct radix_tree_node *slot, void *item,
+                              unsigned long index, unsigned long *found_index)
+{
+        unsigned int shift, height;
+        unsigned long i;
+
+        height = slot->height;
+        shift = (height-1) * RADIX_TREE_MAP_SHIFT;
+
+        for ( ; height > 1; height--) {
+                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;
+                }
+
+                shift -= RADIX_TREE_MAP_SHIFT;
+                slot = rcu_dereference_raw(slot->slots[i]);
+                if (slot == NULL)
+                        goto out;
+        }
+
+        /* Bottom level: check items */
+        for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+                if (slot->slots[i] == item) {
+                        *found_index = index + i;
+                        index = 0;
+                        goto out;
+                }
+        }
+        index += RADIX_TREE_MAP_SIZE;
+out:
+        return index;
+}
+
+/**
+ *      radix_tree_locate_item - search through radix tree for item
+ *      @root:          radix tree root
+ *      @item:          item to be found
+ *
+ *      Returns index where item was found, or -1 if not found.
+ *      Caller must hold no lock (since this time-consuming function needs
+ *      to be preemptible), and must check afterwards if item is still there.
+ */
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+        struct radix_tree_node *node;
+        unsigned long max_index;
+        unsigned long cur_index = 0;
+        unsigned long found_index = -1;
+
+        do {
+                rcu_read_lock();
+                node = rcu_dereference_raw(root->rnode);
+                if (!radix_tree_is_indirect_ptr(node)) {
+                        rcu_read_unlock();
+                        if (node == item)
+                                found_index = 0;
+                        break;
+                }
+
+                node = indirect_to_ptr(node);
+                max_index = radix_tree_maxindex(node->height);
+                if (cur_index > max_index)
+                        break;
+
+                cur_index = __locate(node, item, cur_index, &found_index);
+                rcu_read_unlock();
+                cond_resched();
+        } while (cur_index != 0 && cur_index <= max_index);
+
+        return found_index;
+}
+#else
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+        return -1;
+}
+#endif /* CONFIG_SHMEM && CONFIG_SWAP */
 
 /**
  *      radix_tree_shrink    -    shrink height of a radix tree to minimal