27 files changed, 687 insertions, 52 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 90d6df1551ed..88b5dfd8ee12 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -528,12 +528,18 @@ static inline void acpi_set_cstate_limit(unsigned int new_limit) { return; }
 #ifdef CONFIG_ACPI_NUMA
 int acpi_get_pxm(acpi_handle handle);
+int acpi_get_node(acpi_handle *handle);
 #else
 static inline int acpi_get_pxm(acpi_handle handle)
 {
        return 0;
 }
+static inline int acpi_get_node(acpi_handle *handle)
+{
+        return 0;
+}
 #endif
+extern int acpi_paddr_to_node(u64 start_addr, u64 size);
 extern int pnpacpi_disabled;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index fb7e9b7ccbe3..737e407d0cd1 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -149,7 +149,6 @@ void create_empty_buffers(struct page *, unsigned long,
                        unsigned long b_state);
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
-void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
@@ -214,6 +213,7 @@ int nobh_truncate_page(struct address_space *, loff_t);
 int nobh_writepage(struct page *page, get_block_t *get_block,
                        struct writeback_control *wbc);
+void buffer_init(void);
 /*
 * inline definitions
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 08d50c53aab4..a3caf6866bae 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -31,17 +31,23 @@ struct cpu {
        struct sys_device sysdev;
 };
-extern int register_cpu(struct cpu *, int, struct node *);
+extern int register_cpu(struct cpu *cpu, int num);
 extern struct sys_device *get_cpu_sysdev(unsigned cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-extern void unregister_cpu(struct cpu *, struct node *);
+extern void unregister_cpu(struct cpu *cpu);
 #endif
 struct notifier_block;
 #ifdef CONFIG_SMP
 /* Need to know about CPUs going up/down? */
 extern int register_cpu_notifier(struct notifier_block *nb);
+#ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu_notifier(struct notifier_block *nb);
+#else
+static inline void unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
+#endif
 extern int current_in_cpu_hotplug(void);
 int cpu_up(unsigned int cpu);
@@ -73,6 +79,8 @@ extern int lock_cpu_hotplug_interruptible(void);
                { .notifier_call = fn, .priority = pri };       \
        register_cpu_notifier(&fn##_nb);                        \
 }
+#define register_hotcpu_notifier(nb)    register_cpu_notifier(nb)
+#define unregister_hotcpu_notifier(nb)  unregister_cpu_notifier(nb)
 int cpu_down(unsigned int cpu);
 #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu))
 #else
@@ -80,6 +88,8 @@ int cpu_down(unsigned int cpu);
 #define unlock_cpu_hotplug()    do { } while (0)
 #define lock_cpu_hotplug_interruptible() 0
 #define hotcpu_notifier(fn, pri)
+#define register_hotcpu_notifier(nb)
+#define unregister_hotcpu_notifier(nb)
 /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */
 static inline int cpu_is_offline(int cpu) { return 0; }
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 78b236ca04f8..272010a6078a 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -20,7 +20,7 @@
 */
 #ifndef DMAENGINE_H
 #define DMAENGINE_H
-#include <linux/config.h>
 #ifdef CONFIG_DMA_ENGINE
 #include <linux/device.h>
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 966a5b3da439..34c3a215f2cd 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -12,6 +12,9 @@
 #define FUTEX_REQUEUE           3
 #define FUTEX_CMP_REQUEUE       4
 #define FUTEX_WAKE_OP           5
+#define FUTEX_LOCK_PI           6
+#define FUTEX_UNLOCK_PI         7
+#define FUTEX_TRYLOCK_PI        8
 /*
 * Support for robust futexes: the kernel cleans up held futexes at
@@ -90,18 +93,21 @@ struct robust_list_head {
 */
 #define ROBUST_LIST_LIMIT       2048
-long do_futex(unsigned long uaddr, int op, int val,
+long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
-                unsigned long timeout, unsigned long uaddr2, int val2,
+              u32 __user *uaddr2, u32 val2, u32 val3);
-                int val3);
 extern int handle_futex_death(u32 __user *uaddr, struct task_struct *curr);
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
+extern void exit_pi_state_list(struct task_struct *curr);
 #else
 static inline void exit_robust_list(struct task_struct *curr)
 {
 }
+static inline void exit_pi_state_list(struct task_struct *curr)
+{
+}
 #endif
 #define FUTEX_OP_SET            0       /* *(int *)UADDR2 = OPARG; */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e127ef7e8da8..3a256957fb56 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -87,6 +87,7 @@ extern struct group_info init_groups;
        .lock_depth     = -1,                                           \
        .prio           = MAX_PRIO-20,                                  \
        .static_prio    = MAX_PRIO-20,                                  \
+        .normal_prio    = MAX_PRIO-20,                                  \
        .policy         = SCHED_NORMAL,                                 \
        .cpus_allowed   = CPU_MASK_ALL,                                 \
        .mm             = NULL,                                         \
@@ -122,6 +123,8 @@ extern struct group_info init_groups;
        .journal_info   = NULL,                                         \
        .cpu_timers     = INIT_CPU_TIMERS(tsk.cpu_timers),              \
        .fs_excl        = ATOMIC_INIT(0),                               \
+        .pi_lock        = SPIN_LOCK_UNLOCKED,                           \
+        INIT_RT_MUTEXES(tsk)                                            \
 }
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index cd6bd001ba4e..edfc733b1575 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -105,6 +105,9 @@ extern int allocate_resource(struct resource *root, struct resource *new,
 int adjust_resource(struct resource *res, unsigned long start,
                    unsigned long size);
+/* get registered SYSTEM_RAM resources in specified area */
+extern int find_next_system_ram(struct resource *res);
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)    __request_region(&ioport_resource, (start), (n), (name))
 #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name))
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 5653b2f23b6a..d09fbeabf1dc 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -210,11 +210,7 @@ struct kernel_ipmi_msg
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
-extern struct proc_dir_entry *proc_ipmi_root;
-#endif /* CONFIG_PROC_FS */
 /* Opaque type for a IPMI message user.  One of these is needed to
   send and receive messages. */
diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h
index c6f70660b371..c9c760700bc3 100644
--- a/include/linux/jffs2.h
+++ b/include/linux/jffs2.h
@@ -186,6 +186,7 @@ struct jffs2_raw_xref
        jint32_t hdr_crc;
        jint32_t ino;           /* inode number */
        jint32_t xid;           /* XATTR identifier number */
+        jint32_t xseqno;        /* xref sequencial number */
        jint32_t node_crc;
 } __attribute__((packed));
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 20b1cf527c60..f4284bf89758 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -30,6 +30,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
+#include <asm/scatterlist.h>
 #include <asm/io.h>
 #include <linux/ata.h>
 #include <linux/workqueue.h>
@@ -887,6 +888,9 @@ static inline unsigned int ata_tag_internal(unsigned int tag)
        return tag == ATA_MAX_QUEUE - 1;
 }
+/*
+ * device helpers
+ */
 static inline unsigned int ata_class_enabled(unsigned int class)
 {
        return class == ATA_DEV_ATA || class == ATA_DEV_ATAPI;
@@ -917,6 +921,17 @@ static inline unsigned int ata_dev_absent(const struct ata_device *dev)
        return ata_class_absent(dev->class);
 }
+/*
+ * port helpers
+ */
+static inline int ata_port_max_devices(const struct ata_port *ap)
+{
+        if (ap->flags & ATA_FLAG_SLAVE_POSS)
+                return 2;
+        return 1;
+}
 static inline u8 ata_chk_status(struct ata_port *ap)
 {
        return ap->ops->check_status(ap);
diff --git a/include/linux/list.h b/include/linux/list.h
index 37ca31b21bb7..6b74adf5297f 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -4,18 +4,11 @@
 #ifdef __KERNEL__
 #include <linux/stddef.h>
+#include <linux/poison.h>
 #include <linux/prefetch.h>
 #include <asm/system.h>
 /*
- * These are non-NULL pointers that will result in page faults
- * under normal circumstances, used to verify that nobody uses
- * non-initialized list entries.
- */
-#define LIST_POISON1  ((void *) 0x00100100)
-#define LIST_POISON2  ((void *) 0x00200200)
-/*
 * Simple doubly linked list implementation.
 *
 * Some of the internal functions ("__xxx") are useful when
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 911206386171..218501cfaeb9 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -63,6 +63,76 @@ extern int online_pages(unsigned long, unsigned long);
 /* reasonably generic interface to expand the physical pages in a zone  */
 extern int __add_pages(struct zone *zone, unsigned long start_pfn,
        unsigned long nr_pages);
+#ifdef CONFIG_NUMA
+extern int memory_add_physaddr_to_nid(u64 start);
+#else
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+        return 0;
+}
+#endif
+#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
+/*
+ * For supporting node-hotadd, we have to allocate a new pgdat.
+ *
+ * If an arch has generic style NODE_DATA(),
+ * node_data[nid] = kzalloc() works well. But it depends on the architecture.
+ *
+ * In general, generic_alloc_nodedata() is used.
+ * Now, arch_free_nodedata() is just defined for error path of node_hot_add.
+ *
+ */
+extern pg_data_t *arch_alloc_nodedata(int nid);
+extern void arch_free_nodedata(pg_data_t *pgdat);
+extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
+#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
+#define arch_alloc_nodedata(nid)        generic_alloc_nodedata(nid)
+#define arch_free_nodedata(pgdat)       generic_free_nodedata(pgdat)
+#ifdef CONFIG_NUMA
+/*
+ * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
+ * XXX: kmalloc_node() can't work well to get new node's memory at this time.
+ *      Because, pgdat for the new node is not allocated/initialized yet itself.
+ *      To use new node's memory, more consideration will be necessary.
+ */
+#define generic_alloc_nodedata(nid)                             \
+({                                                              \
+        kzalloc(sizeof(pg_data_t), GFP_KERNEL);                 \
+})
+/*
+ * This definition is just for error path in node hotadd.
+ * For node hotremove, we have to replace this.
+ */
+#define generic_free_nodedata(pgdat)    kfree(pgdat)
+extern pg_data_t *node_data[];
+static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
+{
+        node_data[nid] = pgdat;
+}
+#else /* !CONFIG_NUMA */
+/* never called */
+static inline pg_data_t *generic_alloc_nodedata(int nid)
+{
+        BUG();
+        return NULL;
+}
+static inline void generic_free_nodedata(pg_data_t *pgdat)
+{
+}
+static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
+{
+}
+#endif /* CONFIG_NUMA */
+#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
 * Stub functions for when hotplug is off
@@ -99,7 +169,8 @@ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn,
        return -ENOSYS;
 }
-extern int add_memory(u64 start, u64 size);
+extern int add_memory(int nid, u64 start, u64 size);
+extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int remove_memory(u64 start, u64 size);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a929ea197e48..c41a1299b8cf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1030,13 +1030,20 @@ static inline void vm_stat_account(struct mm_struct *mm,
 }
 #endif /* CONFIG_PROC_FS */
+static inline void
+debug_check_no_locks_freed(const void *from, unsigned long len)
+{
+        mutex_debug_check_no_locks_freed(from, len);
+        rt_mutex_debug_check_no_locks_freed(from, len);
+}
 #ifndef CONFIG_DEBUG_PAGEALLOC
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
 {
        if (!PageHighMem(page) && !enable)
-                mutex_debug_check_no_locks_freed(page_address(page),
+                debug_check_no_locks_freed(page_address(page),
-                                                 numpages * PAGE_SIZE);
+                                           numpages * PAGE_SIZE);
 }
 #endif
@@ -1065,5 +1072,7 @@ void drop_slab(void);
 extern int randomize_va_space;
 #endif
+const char *arch_vma_name(struct vm_area_struct *vma);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/node.h b/include/linux/node.h
index 254dc3de650b..81dcec84cd8f 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -26,8 +26,25 @@ struct node {
        struct sys_device       sysdev;
 };
+extern struct node node_devices[];
 extern int register_node(struct node *, int, struct node *);
 extern void unregister_node(struct node *node);
+extern int register_one_node(int nid);
+extern void unregister_one_node(int nid);
+#ifdef CONFIG_NUMA
+extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
+extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
+#else
+static inline int register_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+        return 0;
+}
+static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+        return 0;
+}
+#endif
 #define to_node(sys_device) container_of(sys_device, struct node, sysdev)
diff --git a/include/linux/nsc_gpio.h b/include/linux/nsc_gpio.h
new file mode 100644
index 000000000000..135742cfada5
--- /dev/null
+++ b/include/linux/nsc_gpio.h
@@ -0,0 +1,42 @@
+/**
+   nsc_gpio.c
+   National Semiconductor GPIO common access methods.
+   struct nsc_gpio_ops abstracts the low-level access
+   operations for the GPIO units on 2 NSC chip families; the GEODE
+   integrated CPU, and the PC-8736[03456] integrated PC-peripheral
+   chips.
+   The GPIO units on these chips have the same pin architecture, but
+   the access methods differ.  Thus, scx200_gpio and pc8736x_gpio
+   implement their own versions of these routines; and use the common
+   file-operations routines implemented in nsc_gpio module.
+   Copyright (c) 2005 Jim Cromie <jim.cromie@gmail.com>
+   NB: this work was tested on the Geode SC-1100 and PC-87366 chips.
+   NSC sold the GEODE line to AMD, and the PC-8736x line to Winbond.
+*/
+struct nsc_gpio_ops {
+        struct module*  owner;
+        u32     (*gpio_config)  (unsigned iminor, u32 mask, u32 bits);
+        void    (*gpio_dump)    (struct nsc_gpio_ops *amp, unsigned iminor);
+        int     (*gpio_get)     (unsigned iminor);
+        void    (*gpio_set)     (unsigned iminor, int state);
+        void    (*gpio_set_high)(unsigned iminor);
+        void    (*gpio_set_low) (unsigned iminor);
+        void    (*gpio_change)  (unsigned iminor);
+        int     (*gpio_current) (unsigned iminor);
+        struct device*  dev;    /* for dev_dbg() support, set in init  */
+};
+extern ssize_t nsc_gpio_write(struct file *file, const char __user *data,
+                              size_t len, loff_t *ppos);
+extern ssize_t nsc_gpio_read(struct file *file, char __user *buf,
+                             size_t len, loff_t *ppos);
+extern void nsc_gpio_dump(struct nsc_gpio_ops *amp, unsigned index);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index c2fd2d19938b..9ae6b1a75366 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1202,6 +1202,7 @@
 #define PCI_DEVICE_ID_NVIDIA_NVENET_19              0x03EF
 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA2     0x03F6
 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA3     0x03F7
+#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP65_IDE       0x0448
 #define PCI_DEVICE_ID_NVIDIA_NVENET_20              0x0450
 #define PCI_DEVICE_ID_NVIDIA_NVENET_21              0x0451
 #define PCI_DEVICE_ID_NVIDIA_NVENET_22              0x0452
@@ -2170,7 +2171,6 @@
 #define PCI_DEVICE_ID_INTEL_ICH8_4      0x2815
 #define PCI_DEVICE_ID_INTEL_ICH8_5      0x283e
 #define PCI_DEVICE_ID_INTEL_ICH8_6      0x2850
-#define PCI_DEVICE_ID_INTEL_GD31244     0x3200
 #define PCI_DEVICE_ID_INTEL_82855PM_HB  0x3340
 #define PCI_DEVICE_ID_INTEL_82830_HB    0x3575
 #define PCI_DEVICE_ID_INTEL_82830_CGC   0x3577
diff --git a/include/linux/plist.h b/include/linux/plist.h
new file mode 100644
index 000000000000..3404faef542c
--- /dev/null
+++ b/include/linux/plist.h
@@ -0,0 +1,247 @@
+/*
+ * Descending-priority-sorted double-linked list
+ *
+ * (C) 2002-2003 Intel Corp
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>.
+ *
+ * 2001-2005 (c) MontaVista Software, Inc.
+ * Daniel Walker <dwalker@mvista.com>
+ *
+ * (C) 2005 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * Simplifications of the original code by
+ * Oleg Nesterov <oleg@tv-sign.ru>
+ *
+ * Licensed under the FSF's GNU Public License v2 or later.
+ *
+ * Based on simple lists (include/linux/list.h).
+ *
+ * This is a priority-sorted list of nodes; each node has a
+ * priority from INT_MIN (highest) to INT_MAX (lowest).
+ *
+ * Addition is O(K), removal is O(1), change of priority of a node is
+ * O(K) and K is the number of RT priority levels used in the system.
+ * (1 <= K <= 99)
+ *
+ * This list is really a list of lists:
+ *
+ *  - The tier 1 list is the prio_list, different priority nodes.
+ *
+ *  - The tier 2 list is the node_list, serialized nodes.
+ *
+ * Simple ASCII art explanation:
+ *
+ * |HEAD          |
+ * |              |
+ * |prio_list.prev|<------------------------------------|
+ * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-|
+ * |10            |   |10|   |21|   |21|   |21|   |40|   (prio)
+ * |              |   |  |   |  |   |  |   |  |   |  |
+ * |              |   |  |   |  |   |  |   |  |   |  |
+ * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ * |node_list.prev|<------------------------------------|
+ *
+ * The nodes on the prio_list list are sorted by priority to simplify
+ * the insertion of new nodes. There are no nodes with duplicate
+ * priorites on the list.
+ *
+ * The nodes on the node_list is ordered by priority and can contain
+ * entries which have the same priority. Those entries are ordered
+ * FIFO
+ *
+ * Addition means: look for the prio_list node in the prio_list
+ * for the priority of the node and insert it before the node_list
+ * entry of the next prio_list node. If it is the first node of
+ * that priority, add it to the prio_list in the right position and
+ * insert it into the serialized node_list list
+ *
+ * Removal means remove it from the node_list and remove it from
+ * the prio_list if the node_list list_head is non empty. In case
+ * of removal from the prio_list it must be checked whether other
+ * entries of the same priority are on the list or not. If there
+ * is another entry of the same priority then this entry has to
+ * replace the removed entry on the prio_list. If the entry which
+ * is removed is the only entry of this priority then a simple
+ * remove from both list is sufficient.
+ *
+ * INT_MIN is the highest priority, 0 is the medium highest, INT_MAX
+ * is lowest priority.
+ *
+ * No locking is done, up to the caller.
+ *
+ */
+#ifndef _LINUX_PLIST_H_
+#define _LINUX_PLIST_H_
+#include <linux/list.h>
+#include <linux/spinlock_types.h>
+struct plist_head {
+        struct list_head prio_list;
+        struct list_head node_list;
+#ifdef CONFIG_DEBUG_PI_LIST
+        spinlock_t *lock;
+#endif
+};
+struct plist_node {
+        int                     prio;
+        struct plist_head       plist;
+};
+#ifdef CONFIG_DEBUG_PI_LIST
+# define PLIST_HEAD_LOCK_INIT(_lock)    .lock = _lock
+#else
+# define PLIST_HEAD_LOCK_INIT(_lock)
+#endif
+/**
+ * #PLIST_HEAD_INIT - static struct plist_head initializer
+ *
+ * @head:       struct plist_head variable name
+ */
+#define PLIST_HEAD_INIT(head, _lock)                    \
+{                                                       \
+        .prio_list = LIST_HEAD_INIT((head).prio_list),  \
+        .node_list = LIST_HEAD_INIT((head).node_list),  \
+        PLIST_HEAD_LOCK_INIT(&(_lock))                  \
+}
+/**
+ * #PLIST_NODE_INIT - static struct plist_node initializer
+ *
+ * @node:       struct plist_node variable name
+ * @__prio:     initial node priority
+ */
+#define PLIST_NODE_INIT(node, __prio)                   \
+{                                                       \
+        .prio  = (__prio),                              \
+        .plist = PLIST_HEAD_INIT((node).plist, NULL),   \
+}
+/**
+ * plist_head_init - dynamic struct plist_head initializer
+ *
+ * @head:       &struct plist_head pointer
+ */
+static inline void
+plist_head_init(struct plist_head *head, spinlock_t *lock)
+{
+        INIT_LIST_HEAD(&head->prio_list);
+        INIT_LIST_HEAD(&head->node_list);
+#ifdef CONFIG_DEBUG_PI_LIST
+        head->lock = lock;
+#endif
+}
+/**
+ * plist_node_init - Dynamic struct plist_node initializer
+ *
+ * @node:       &struct plist_node pointer
+ * @prio:       initial node priority
+ */
+static inline void plist_node_init(struct plist_node *node, int prio)
+{
+        node->prio = prio;
+        plist_head_init(&node->plist, NULL);
+}
+extern void plist_add(struct plist_node *node, struct plist_head *head);
+extern void plist_del(struct plist_node *node, struct plist_head *head);
+/**
+ * plist_for_each - iterate over the plist
+ *
+ * @pos1:       the type * to use as a loop counter.
+ * @head:       the head for your list.
+ */
+#define plist_for_each(pos, head)       \
+         list_for_each_entry(pos, &(head)->node_list, plist.node_list)
+/**
+ * plist_for_each_entry_safe - iterate over a plist of given type safe
+ * against removal of list entry
+ *
+ * @pos1:       the type * to use as a loop counter.
+ * @n1: another type * to use as temporary storage
+ * @head:       the head for your list.
+ */
+#define plist_for_each_safe(pos, n, head)       \
+         list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list)
+/**
+ * plist_for_each_entry - iterate over list of given type
+ *
+ * @pos:        the type * to use as a loop counter.
+ * @head:       the head for your list.
+ * @member:     the name of the list_struct within the struct.
+ */
+#define plist_for_each_entry(pos, head, mem)    \
+         list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list)
+/**
+ * plist_for_each_entry_safe - iterate over list of given type safe against
+ * removal of list entry
+ *
+ * @pos:        the type * to use as a loop counter.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @m:          the name of the list_struct within the struct.
+ */
+#define plist_for_each_entry_safe(pos, n, head, m)      \
+        list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list)
+/**
+ * plist_head_empty - return !0 if a plist_head is empty
+ *
+ * @head:       &struct plist_head pointer
+ */
+static inline int plist_head_empty(const struct plist_head *head)
+{
+        return list_empty(&head->node_list);
+}
+/**
+ * plist_node_empty - return !0 if plist_node is not on a list
+ *
+ * @node:       &struct plist_node pointer
+ */
+static inline int plist_node_empty(const struct plist_node *node)
+{
+        return plist_head_empty(&node->plist);
+}
+/* All functions below assume the plist_head is not empty. */
+/**
+ * plist_first_entry - get the struct for the first entry
+ *
+ * @ptr:        the &struct plist_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ */
+#ifdef CONFIG_DEBUG_PI_LIST
+# define plist_first_entry(head, type, member)  \
+({ \
+        WARN_ON(plist_head_empty(head)); \
+        container_of(plist_first(head), type, member); \
+})
+#else
+# define plist_first_entry(head, type, member)  \
+        container_of(plist_first(head), type, member)
+#endif
+/**
+ * plist_first - return the first node (and thus, highest priority)
+ *
+ * @head:       the &struct plist_head pointer
+ *
+ * Assumes the plist is _not_ empty.
+ */
+static inline struct plist_node* plist_first(const struct plist_head *head)
+{
+        return list_entry(head->node_list.next,
+                          struct plist_node, plist.node_list);
+}
+#endif
diff --git a/include/linux/poison.h b/include/linux/poison.h
new file mode 100644
index 000000000000..a5347c02432e
--- /dev/null
+++ b/include/linux/poison.h
@@ -0,0 +1,58 @@
+#ifndef _LINUX_POISON_H
+#define _LINUX_POISON_H
+/********** include/linux/list.h **********/
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1  ((void *) 0x00100100)
+#define LIST_POISON2  ((void *) 0x00200200)
+/********** mm/slab.c **********/
+/*
+ * Magic nums for obj red zoning.
+ * Placed in the first word before and the first word after an obj.
+ */
+#define RED_INACTIVE    0x5A2CF071UL    /* when obj is inactive */
+#define RED_ACTIVE      0x170FC2A5UL    /* when obj is active */
+/* ...and for poisoning */
+#define POISON_INUSE    0x5a    /* for use-uninitialised poisoning */
+#define POISON_FREE     0x6b    /* for use-after-free poisoning */
+#define POISON_END      0xa5    /* end-byte of poisoning */
+/********** arch/$ARCH/mm/init.c **********/
+#define POISON_FREE_INITMEM     0xcc
+/********** arch/x86_64/mm/init.c **********/
+#define POISON_FREE_INITDATA    0xba
+/********** arch/ia64/hp/common/sba_iommu.c **********/
+/*
+ * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
+ * value of "SBAIOMMU POISON\0" for spill-over poisoning.
+ */
+/********** fs/jbd/journal.c **********/
+#define JBD_POISON_FREE 0x5b
+/********** drivers/base/dmapool.c **********/
+#define POOL_POISON_FREED       0xa7    /* !inuse */
+#define POOL_POISON_ALLOCATED   0xa9    /* !initted */
+/********** drivers/atm/ **********/
+#define ATM_POISON_FREE         0x12
+/********** kernel/mutexes **********/
+#define MUTEX_DEBUG_INIT        0x11
+#define MUTEX_DEBUG_FREE        0x22
+/********** security/ **********/
+#define KEY_DESTROY             0xbd
+/********** sound/oss/ **********/
+#define OSS_POISON_FREE         0xAB
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6312758393b6..48dfe00070c7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -258,6 +258,7 @@ extern void rcu_init(void);
 extern void rcu_check_callbacks(int cpu, int user);
 extern void rcu_restart_cpu(int cpu);
 extern long rcu_batches_completed(void);
+extern long rcu_batches_completed_bh(void);
 /* Exported interfaces */
 extern void FASTCALL(call_rcu(struct rcu_head *head, 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
new file mode 100644
index 000000000000..fa4a3b82ba70
--- /dev/null
+++ b/include/linux/rtmutex.h
@@ -0,0 +1,117 @@
+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the public data structure and API definitions.
+ */
+#ifndef __LINUX_RT_MUTEX_H
+#define __LINUX_RT_MUTEX_H
+#include <linux/linkage.h>
+#include <linux/plist.h>
+#include <linux/spinlock_types.h>
+/*
+ * The rt_mutex structure
+ *
+ * @wait_lock:  spinlock to protect the structure
+ * @wait_list:  pilist head to enqueue waiters in priority order
+ * @owner:      the mutex owner
+ */
+struct rt_mutex {
+        spinlock_t              wait_lock;
+        struct plist_head       wait_list;
+        struct task_struct      *owner;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+        int                     save_state;
+        struct list_head        held_list_entry;
+        unsigned long           acquire_ip;
+        const char              *name, *file;
+        int                     line;
+        void                    *magic;
+#endif
+};
+struct rt_mutex_waiter;
+struct hrtimer_sleeper;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+ extern int rt_mutex_debug_check_no_locks_freed(const void *from,
+                                                unsigned long len);
+ extern void rt_mutex_debug_check_no_locks_held(struct task_struct *task);
+#else
+ static inline int rt_mutex_debug_check_no_locks_freed(const void *from,
+                                                       unsigned long len)
+ {
+        return 0;
+ }
+# define rt_mutex_debug_check_no_locks_held(task)       do { } while (0)
+#endif
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
+        , .name = #mutexname, .file = __FILE__, .line = __LINE__
+# define rt_mutex_init(mutex)                   __rt_mutex_init(mutex, __FUNCTION__)
+ extern void rt_mutex_debug_task_free(struct task_struct *tsk);
+#else
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
+# define rt_mutex_init(mutex)                   __rt_mutex_init(mutex, NULL)
+# define rt_mutex_debug_task_free(t)                    do { } while (0)
+#endif
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+        { .wait_lock = SPIN_LOCK_UNLOCKED \
+        , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list, mutexname.wait_lock) \
+        , .owner = NULL \
+        __DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
+#define DEFINE_RT_MUTEX(mutexname) \
+        struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
+/***
+ * rt_mutex_is_locked - is the mutex locked
+ * @lock: the mutex to be queried
+ *
+ * Returns 1 if the mutex is locked, 0 if unlocked.
+ */
+static inline int rt_mutex_is_locked(struct rt_mutex *lock)
+{
+        return lock->owner != NULL;
+}
+extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
+extern void rt_mutex_destroy(struct rt_mutex *lock);
+extern void rt_mutex_lock(struct rt_mutex *lock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
+                                                int detect_deadlock);
+extern int rt_mutex_timed_lock(struct rt_mutex *lock,
+                                        struct hrtimer_sleeper *timeout,
+                                        int detect_deadlock);
+extern int rt_mutex_trylock(struct rt_mutex *lock);
+extern void rt_mutex_unlock(struct rt_mutex *lock);
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define INIT_RT_MUTEX_DEBUG(tsk)                                       \
+        .held_list_head = LIST_HEAD_INIT(tsk.held_list_head),           \
+        .held_list_lock = SPIN_LOCK_UNLOCKED
+#else
+# define INIT_RT_MUTEX_DEBUG(tsk)
+#endif
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk)                                           \
+        .pi_waiters     = PLIST_HEAD_INIT(tsk.pi_waiters, tsk.pi_lock), \
+        INIT_RT_MUTEX_DEBUG(tsk)
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 122a25c1b997..821f0481ebe1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -73,6 +73,7 @@ struct sched_param {
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
 #include <linux/futex.h>
+#include <linux/rtmutex.h>
 #include <linux/time.h>
 #include <linux/param.h>
@@ -83,6 +84,7 @@ struct sched_param {
 #include <asm/processor.h>
 struct exec_domain;
+struct futex_pi_state;
 /*
 * List of flags we want to share for kernel threads,
@@ -123,6 +125,7 @@ extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
+extern unsigned long weighted_cpuload(const int cpu);
 /*
@@ -494,8 +497,11 @@ struct signal_struct {
 #define MAX_PRIO                (MAX_RT_PRIO + 40)
-#define rt_task(p)              (unlikely((p)->prio < MAX_RT_PRIO))
+#define rt_prio(prio)           unlikely((prio) < MAX_RT_PRIO)
+#define rt_task(p)              rt_prio((p)->prio)
 #define batch_task(p)           (unlikely((p)->policy == SCHED_BATCH))
+#define has_rt_policy(p) \
+        unlikely((p)->policy != SCHED_NORMAL && (p)->policy != SCHED_BATCH)
 /*
 * Some day this will be a full-fledged user tracking system..
@@ -558,9 +564,9 @@ enum idle_type
 /*
 * sched-domains (multiprocessor balancing) declarations:
 */
-#ifdef CONFIG_SMP
 #define SCHED_LOAD_SCALE        128UL   /* increase resolution of load */
+#ifdef CONFIG_SMP
 #define SD_LOAD_BALANCE         1       /* Do load balancing on this domain. */
 #define SD_BALANCE_NEWIDLE      2       /* Balance when about to become idle */
 #define SD_BALANCE_EXEC         4       /* Balance on exec */
@@ -569,6 +575,11 @@ enum idle_type
 #define SD_WAKE_AFFINE          32      /* Wake task to waking CPU */
 #define SD_WAKE_BALANCE         64      /* Perform balancing at task wakeup */
 #define SD_SHARE_CPUPOWER       128     /* Domain members share cpu power */
+#define SD_POWERSAVINGS_BALANCE 256     /* Balance for power savings */
+#define BALANCE_FOR_POWER       ((sched_mc_power_savings || sched_smt_power_savings) \
+                                 ? SD_POWERSAVINGS_BALANCE : 0)
 struct sched_group {
        struct sched_group *next;       /* Must be a circular list */
@@ -638,7 +649,7 @@ struct sched_domain {
 #endif
 };
-extern void partition_sched_domains(cpumask_t *partition1,
+extern int partition_sched_domains(cpumask_t *partition1,
                                    cpumask_t *partition2);
 /*
@@ -713,10 +724,13 @@ struct task_struct {
        int lock_depth;         /* BKL lock depth */
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+#ifdef CONFIG_SMP
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
        int oncpu;
 #endif
-        int prio, static_prio;
+#endif
+        int load_weight;        /* for niceness load balancing purposes */
+        int prio, static_prio, normal_prio;
        struct list_head run_list;
        prio_array_t *array;
@@ -843,6 +857,20 @@ struct task_struct {
 /* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
        spinlock_t alloc_lock;
+        /* Protection of the PI data structures: */
+        spinlock_t pi_lock;
+#ifdef CONFIG_RT_MUTEXES
+        /* PI waiters blocked on a rt_mutex held by this task */
+        struct plist_head pi_waiters;
+        /* Deadlock detection and priority inheritance handling */
+        struct rt_mutex_waiter *pi_blocked_on;
+# ifdef CONFIG_DEBUG_RT_MUTEXES
+        spinlock_t held_list_lock;
+        struct list_head held_list_head;
+# endif
+#endif
 #ifdef CONFIG_DEBUG_MUTEXES
        /* mutex deadlock detection */
        struct mutex_waiter *blocked_on;
@@ -888,6 +916,8 @@ struct task_struct {
 #ifdef CONFIG_COMPAT
        struct compat_robust_list_head __user *compat_robust_list;
 #endif
+        struct list_head pi_state_list;
+        struct futex_pi_state *pi_state_cache;
        atomic_t fs_excl;       /* holding fs exclusive resources */
        struct rcu_head rcu;
@@ -955,6 +985,7 @@ static inline void put_task_struct(struct task_struct *t)
 #define PF_SPREAD_PAGE  0x01000000      /* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB  0x02000000      /* Spread some slab caches over cpuset */
 #define PF_MEMPOLICY    0x10000000      /* Non-default NUMA mempolicy */
+#define PF_MUTEX_TESTER 0x20000000      /* Thread belongs to the rt mutex tester */
 /*
 * Only the _current_ task can read/write to tsk->flags, but other
@@ -1009,6 +1040,19 @@ static inline void idle_task_exit(void) {}
 #endif
 extern void sched_idle_next(void);
+#ifdef CONFIG_RT_MUTEXES
+extern int rt_mutex_getprio(task_t *p);
+extern void rt_mutex_setprio(task_t *p, int prio);
+extern void rt_mutex_adjust_pi(task_t *p);
+#else
+static inline int rt_mutex_getprio(task_t *p)
+{
+        return p->normal_prio;
+}
+# define rt_mutex_adjust_pi(p)          do { } while (0)
+#endif
 extern void set_user_nice(task_t *p, long nice);
 extern int task_prio(const task_t *p);
 extern int task_nice(const task_t *p);
@@ -1408,6 +1452,11 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm)
 extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
 extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
+#include <linux/sysdev.h>
+extern int sched_mc_power_savings, sched_smt_power_savings;
+extern struct sysdev_attribute attr_sched_mc_power_savings, attr_sched_smt_power_savings;
+extern int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls);
 extern void normalize_rt_tasks(void);
 #ifdef CONFIG_PM
diff --git a/include/linux/scx200.h b/include/linux/scx200.h
index a22f9e173ad2..693c0557e70b 100644
--- a/include/linux/scx200.h
+++ b/include/linux/scx200.h
@@ -49,10 +49,3 @@ extern unsigned scx200_cb_base;
 #define SCx200_REV 0x3d         /* Revision Register */
 #define SCx200_CBA 0x3e         /* Configuration Base Address Register */
 #define SCx200_CBA_SCRATCH 0x64 /* Configuration Base Address Scratchpad */
-/*
-    Local variables:
-        compile-command: "make -C ../.. bzImage modules"
-        c-basic-offset: 8
-    End:
-*/
diff --git a/include/linux/scx200_gpio.h b/include/linux/scx200_gpio.h
index 30cdd648ba79..90dd069cc145 100644
--- a/include/linux/scx200_gpio.h
+++ b/include/linux/scx200_gpio.h
@@ -1,6 +1,6 @@
 #include <linux/spinlock.h>
-u32 scx200_gpio_configure(int index, u32 set, u32 clear);
+u32 scx200_gpio_configure(unsigned index, u32 set, u32 clear);
 extern unsigned scx200_gpio_base;
 extern long scx200_gpio_shadow[2];
@@ -17,7 +17,7 @@ extern long scx200_gpio_shadow[2];
 /* returns the value of the GPIO pin */
-static inline int scx200_gpio_get(int index) {
+static inline int scx200_gpio_get(unsigned index) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_IOADDR + 0x04;
        __SCx200_GPIO_INDEX;
@@ -29,7 +29,7 @@ static inline int scx200_gpio_get(int index) {
   driven if the GPIO is configured as an output, it might not be the
   state of the GPIO right now if the GPIO is configured as an input) */
-static inline int scx200_gpio_current(int index) {
+static inline int scx200_gpio_current(unsigned index) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_INDEX;
                
@@ -38,7 +38,7 @@ static inline int scx200_gpio_current(int index) {
 /* drive the GPIO signal high */
-static inline void scx200_gpio_set_high(int index) {
+static inline void scx200_gpio_set_high(unsigned index) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_IOADDR;
        __SCx200_GPIO_SHADOW;
@@ -49,7 +49,7 @@ static inline void scx200_gpio_set_high(int index) {
 /* drive the GPIO signal low */
-static inline void scx200_gpio_set_low(int index) {
+static inline void scx200_gpio_set_low(unsigned index) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_IOADDR;
        __SCx200_GPIO_SHADOW;
@@ -60,7 +60,7 @@ static inline void scx200_gpio_set_low(int index) {
 /* drive the GPIO signal to state */
-static inline void scx200_gpio_set(int index, int state) {
+static inline void scx200_gpio_set(unsigned index, int state) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_IOADDR;
        __SCx200_GPIO_SHADOW;
@@ -73,7 +73,7 @@ static inline void scx200_gpio_set(int index, int state) {
 }
 /* toggle the GPIO signal */
-static inline void scx200_gpio_change(int index) {
+static inline void scx200_gpio_change(unsigned index) {
        __SCx200_GPIO_BANK;
        __SCx200_GPIO_IOADDR;
        __SCx200_GPIO_SHADOW;
@@ -87,10 +87,3 @@ static inline void scx200_gpio_change(int index) {
 #undef __SCx200_GPIO_SHADOW
 #undef __SCx200_GPIO_INDEX
 #undef __SCx200_GPIO_OUT
-/*
-    Local variables:
-        compile-command: "make -C ../.. bzImage modules"
-        c-basic-offset: 8
-    End:
-*/
diff --git a/include/linux/swap.h b/include/linux/swap.h
index dc3f3aa0c83e..c41e2d6d1acc 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -199,6 +199,8 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #endif
+extern int kswapd_run(int nid);
 #ifdef CONFIG_MMU
 /* linux/mm/shmem.c */
 extern int shmem_unuse(swp_entry_t entry, struct page *page);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 33785b79d548..008f04c56737 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -174,9 +174,9 @@ asmlinkage long sys_waitid(int which, pid_t pid,
                           int options, struct rusage __user *ru);
 asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options);
 asmlinkage long sys_set_tid_address(int __user *tidptr);
-asmlinkage long sys_futex(u32 __user *uaddr, int op, int val,
+asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
                        struct timespec __user *utime, u32 __user *uaddr2,
-                        int val3);
+                        u32 val3);
 asmlinkage long sys_init_module(void __user *umod, unsigned long len,
                                const char __user *uargs);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 349ef908a222..46e4d8f2771f 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -149,6 +149,7 @@ enum
        KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */
        KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */
        KERN_COMPAT_LOG=73,     /* int: print compat layer  messages */
+        KERN_MAX_LOCK_DEPTH=74,
 };
@@ -189,6 +190,7 @@ enum
        VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
        VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
        VM_PANIC_ON_OOM=33,     /* panic at out-of-memory */
+        VM_VDSO_ENABLED=34,     /* map VDSO into new processes? */
 };
diff --git a/include/linux/topology.h b/include/linux/topology.h
index a305ae2e44b6..ec1eca85290a 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -134,7 +134,8 @@
        .flags                  = SD_LOAD_BALANCE       \
                                | SD_BALANCE_NEWIDLE    \
                                | SD_BALANCE_EXEC       \
-                                | SD_WAKE_AFFINE,       \
+                                | SD_WAKE_AFFINE        \
+                                | BALANCE_FOR_POWER,    \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \