Merge with rsync://rsync.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6.git

64 files changed, 1210 insertions, 597 deletions

diff --git a/include/linux/arcfb.h b/include/linux/arcfb.h
new file mode 100644
index 00000000000..721e7654dae
--- /dev/null
+++ b/include/linux/arcfb.h
@@ -0,0 +1,8 @@
+#ifndef __LINUX_ARCFB_H__
+#define __LINUX_ARCFB_H__
+
+#define FBIO_WAITEVENT		_IO('F', 0x88)
+#define FBIO_GETCONTROL2	_IOR('F', 0x89, size_t)
+
+#endif
+
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index 31d3fc25ccb..09a1451c115 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -20,7 +20,7 @@
 #define SIOCATALKDIFADDR       (SIOCPROTOPRIVATE + 0)
 
 struct atalk_addr {
-	__u16	s_net;
+	__be16	s_net;
 	__u8	s_node;
 };
 
@@ -33,8 +33,8 @@ struct sockaddr_at {
 
 struct atalk_netrange {
 	__u8	nr_phase;
-	__u16	nr_firstnet;
-	__u16	nr_lastnet;
+	__be16	nr_firstnet;
+	__be16	nr_lastnet;
 };
 
 #ifdef __KERNEL__
@@ -70,8 +70,8 @@ struct atalk_iface {
 struct atalk_sock {
 	/* struct sock has to be the first member of atalk_sock */
 	struct sock	sk;
-	unsigned short	dest_net;
-	unsigned short	src_net;
+	__be16		dest_net;
+	__be16		src_net;
 	unsigned char	dest_node;
 	unsigned char	src_node;
 	unsigned char	dest_port;
@@ -95,9 +95,9 @@ struct ddpehdr {
 		deh_hops:4,
 		deh_len:10;
 #endif
-	__u16	deh_sum;
-	__u16	deh_dnet;
-	__u16	deh_snet;
+	__be16	deh_sum;
+	__be16	deh_dnet;
+	__be16	deh_snet;
 	__u8	deh_dnode;
 	__u8	deh_snode;
 	__u8	deh_dport;
@@ -142,24 +142,24 @@ struct ddpshdr {
 
 /* AppleTalk AARP headers */
 struct elapaarp {
-	__u16	hw_type;
+	__be16	hw_type;
 #define AARP_HW_TYPE_ETHERNET		1
 #define AARP_HW_TYPE_TOKENRING		2
-	__u16	pa_type;
+	__be16	pa_type;
 	__u8	hw_len;
 	__u8	pa_len;
 #define AARP_PA_ALEN			4
-	__u16	function;
+	__be16	function;
 #define AARP_REQUEST			1
 #define AARP_REPLY			2
 #define AARP_PROBE			3
 	__u8	hw_src[ETH_ALEN]	__attribute__ ((packed));
 	__u8	pa_src_zero		__attribute__ ((packed));
-	__u16	pa_src_net		__attribute__ ((packed));
+	__be16	pa_src_net		__attribute__ ((packed));
 	__u8	pa_src_node		__attribute__ ((packed));
 	__u8	hw_dst[ETH_ALEN]	__attribute__ ((packed));
 	__u8	pa_dst_zero		__attribute__ ((packed));
-	__u16	pa_dst_net		__attribute__ ((packed));
+	__be16	pa_dst_net		__attribute__ ((packed));
 	__u8	pa_dst_node		__attribute__ ((packed));	
 };
 
diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h
index a1657fb9951..9343c89d843 100644
--- a/include/linux/auto_fs4.h
+++ b/include/linux/auto_fs4.h
@@ -23,7 +23,7 @@
 #define AUTOFS_MIN_PROTO_VERSION	3
 #define AUTOFS_MAX_PROTO_VERSION	4
 
-#define AUTOFS_PROTO_SUBVERSION		6
+#define AUTOFS_PROTO_SUBVERSION		7
 
 /* Mask for expire behaviour */
 #define AUTOFS_EXP_IMMEDIATE		1
diff --git a/include/linux/device.h b/include/linux/device.h
index df94c0de53f..7b781a72b29 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -14,6 +14,7 @@
 #include <linux/config.h>
 #include <linux/ioport.h>
 #include <linux/kobject.h>
+#include <linux/klist.h>
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/module.h>
@@ -44,14 +45,15 @@ struct device;
 struct device_driver;
 struct class;
 struct class_device;
-struct class_simple;
 
 struct bus_type {
-	char			* name;
+	const char		* name;
 
 	struct subsystem	subsys;
 	struct kset		drivers;
 	struct kset		devices;
+	struct klist		klist_devices;
+	struct klist		klist_drivers;
 
 	struct bus_attribute	* bus_attrs;
 	struct device_attribute	* dev_attrs;
@@ -98,17 +100,18 @@ extern int bus_create_file(struct bus_type *, struct bus_attribute *);
 extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
 
 struct device_driver {
-	char			* name;
+	const char		* name;
 	struct bus_type		* bus;
 
 	struct completion	unloaded;
 	struct kobject		kobj;
-	struct list_head	devices;
+	struct klist		klist_devices;
+	struct klist_node	knode_bus;
 
-	struct module 		* owner;
+	struct module		* owner;
 
 	int	(*probe)	(struct device * dev);
-	int 	(*remove)	(struct device * dev);
+	int	(*remove)	(struct device * dev);
 	void	(*shutdown)	(struct device * dev);
 	int	(*suspend)	(struct device * dev, pm_message_t state, u32 level);
 	int	(*resume)	(struct device * dev, u32 level);
@@ -137,12 +140,16 @@ struct driver_attribute driver_attr_##_name = __ATTR(_name,_mode,_show,_store)
 extern int driver_create_file(struct device_driver *, struct driver_attribute *);
 extern void driver_remove_file(struct device_driver *, struct driver_attribute *);
 
+extern int driver_for_each_device(struct device_driver * drv, struct device * start,
+				  void * data, int (*fn)(struct device *, void *));
+
 
 /*
  * device classes
  */
 struct class {
-	char			* name;
+	const char		* name;
+	struct module		* owner;
 
 	struct subsystem	subsys;
 	struct list_head	children;
@@ -185,6 +192,7 @@ struct class_device {
 	struct kobject		kobj;
 	struct class		* class;	/* required */
 	dev_t			devt;		/* dev_t, creates the sysfs "dev" */
+	struct class_device_attribute *devt_attr;
 	struct device		* dev;		/* not necessary, but nice to have */
 	void			* class_data;	/* class-specific data */
 
@@ -245,26 +253,28 @@ struct class_interface {
 extern int class_interface_register(struct class_interface *);
 extern void class_interface_unregister(struct class_interface *);
 
-/* interface for class simple stuff */
-extern struct class_simple *class_simple_create(struct module *owner, char *name);
-extern void class_simple_destroy(struct class_simple *cs);
-extern struct class_device *class_simple_device_add(struct class_simple *cs, dev_t dev, struct device *device, const char *fmt, ...)
-	__attribute__((format(printf,4,5)));
-extern int class_simple_set_hotplug(struct class_simple *, 
-	int (*hotplug)(struct class_device *dev, char **envp, int num_envp, char *buffer, int buffer_size));
-extern void class_simple_device_remove(dev_t dev);
+extern struct class *class_create(struct module *owner, char *name);
+extern void class_destroy(struct class *cls);
+extern struct class_device *class_device_create(struct class *cls, dev_t devt,
+						struct device *device, char *fmt, ...)
+					__attribute__((format(printf,4,5)));
+extern void class_device_destroy(struct class *cls, dev_t devt);
 
 
 struct device {
-	struct list_head node;		/* node in sibling list */
-	struct list_head bus_list;	/* node in bus's list */
-	struct list_head driver_list;
-	struct list_head children;
+	struct klist		klist_children;
+	struct klist_node	knode_parent;		/* node in sibling list */
+	struct klist_node	knode_driver;
+	struct klist_node	knode_bus;
 	struct device 	* parent;
 
 	struct kobject kobj;
 	char	bus_id[BUS_ID_SIZE];	/* position on parent bus */
 
+	struct semaphore	sem;	/* semaphore to synchronize calls to
+					 * its driver.
+					 */
+
 	struct bus_type	* bus;		/* type of bus device is on */
 	struct device_driver *driver;	/* which driver has allocated this
 					   device */
@@ -288,12 +298,6 @@ struct device {
 	void	(*release)(struct device * dev);
 };
 
-static inline struct device *
-list_to_dev(struct list_head *node)
-{
-	return list_entry(node, struct device, node);
-}
-
 static inline void *
 dev_get_drvdata (struct device *dev)
 {
@@ -321,7 +325,6 @@ extern int device_for_each_child(struct device *, void *,
  * Manual binding of a device to driver. See drivers/base/bus.c
  * for information on use.
  */
-extern int  driver_probe_device(struct device_driver * drv, struct device * dev);
 extern void device_bind_driver(struct device * dev);
 extern void device_release_driver(struct device * dev);
 extern int  device_attach(struct device * dev);
@@ -332,8 +335,10 @@ extern void driver_attach(struct device_driver * drv);
 
 struct device_attribute {
 	struct attribute	attr;
-	ssize_t (*show)(struct device * dev, char * buf);
-	ssize_t (*store)(struct device * dev, const char * buf, size_t count);
+	ssize_t (*show)(struct device *dev, struct device_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count);
 };
 
 #define DEVICE_ATTR(_name,_mode,_show,_store) \
@@ -360,13 +365,12 @@ extern int (*platform_notify_remove)(struct device * dev);
  */
 extern struct device * get_device(struct device * dev);
 extern void put_device(struct device * dev);
-extern struct device *device_find(const char *name, struct bus_type *bus);
 
 
 /* drivers/base/platform.c */
 
 struct platform_device {
-	char		* name;
+	const char	* name;
 	u32		id;
 	struct device	dev;
 	u32		num_resources;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 047e7222df7..73781ec165b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -315,7 +315,7 @@ extern struct efi_memory_map memmap;
  */
 static inline int efi_range_is_wc(unsigned long start, unsigned long len)
 {
-	int i;
+	unsigned long i;
 
 	for (i = 0; i < len; i += (1UL << EFI_PAGE_SHIFT)) {
 		unsigned long paddr = __pa(start + i);
diff --git a/include/linux/fb.h b/include/linux/fb.h
index b468bf49654..bc24beeed97 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -524,11 +524,11 @@ struct fb_pixmap {
 	u32 offset;		/* current offset to buffer		*/
 	u32 buf_align;		/* byte alignment of each bitmap	*/
 	u32 scan_align;		/* alignment per scanline		*/
-	u32 access_align;	/* alignment per read/write		*/
+	u32 access_align;	/* alignment per read/write (bits)	*/
 	u32 flags;		/* see FB_PIXMAP_*			*/
 	/* access methods */
-	void (*outbuf)(struct fb_info *info, u8 *addr, u8 *src, unsigned int size);
-	u8   (*inbuf) (struct fb_info *info, u8 *addr);
+	void (*writeio)(struct fb_info *info, void __iomem *dst, void *src, unsigned int size);
+	void (*readio) (struct fb_info *info, void *dst, void __iomem *src, unsigned int size);
 };
 
 
@@ -816,18 +816,9 @@ extern int unregister_framebuffer(struct fb_info *fb_info);
 extern int fb_prepare_logo(struct fb_info *fb_info);
 extern int fb_show_logo(struct fb_info *fb_info);
 extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size);
-extern void fb_iomove_buf_unaligned(struct fb_info *info, struct fb_pixmap *buf,
-				u8 *dst, u32 d_pitch, u8 *src, u32 idx,
+extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx,
 				u32 height, u32 shift_high, u32 shift_low, u32 mod);
-extern void fb_iomove_buf_aligned(struct fb_info *info, struct fb_pixmap *buf,
-				u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch,
-				u32 height);
-extern void fb_sysmove_buf_unaligned(struct fb_info *info, struct fb_pixmap *buf,
-				u8 *dst, u32 d_pitch, u8 *src, u32 idx,
-				u32 height, u32 shift_high, u32 shift_low, u32 mod);
-extern void fb_sysmove_buf_aligned(struct fb_info *info, struct fb_pixmap *buf,
-				u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch,
-				u32 height);
+extern void fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, u32 height);
 extern void fb_set_suspend(struct fb_info *info, int state);
 extern int fb_get_color_depth(struct fb_var_screeninfo *var);
 extern int fb_get_options(char *name, char **option);
diff --git a/include/linux/font.h b/include/linux/font.h
index fc2d690c9d5..8fc80a7d78a 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -25,19 +25,23 @@ struct font_desc {
 #define VGA8x16_IDX	1
 #define PEARL8x8_IDX	2
 #define VGA6x11_IDX	3
-#define SUN8x16_IDX	4
-#define SUN12x22_IDX	5
-#define ACORN8x8_IDX	6
-#define	MINI4x6_IDX	7
+#define FONT7x14_IDX	4
+#define	FONT10x18_IDX	5
+#define SUN8x16_IDX	6
+#define SUN12x22_IDX	7
+#define ACORN8x8_IDX	8
+#define	MINI4x6_IDX	9
 
 extern struct font_desc	font_vga_8x8,
-				font_vga_8x16,
-				font_pearl_8x8,
-				font_vga_6x11,
-				font_sun_8x16,
-				font_sun_12x22,
-				font_acorn_8x8,
-				font_mini_4x6;
+			font_vga_8x16,
+			font_pearl_8x8,
+			font_vga_6x11,
+			font_7x14,
+			font_10x18,
+			font_sun_8x16,
+			font_sun_12x22,
+			font_acorn_8x8,
+			font_mini_4x6;
 
 /* Find a font with a specific name */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0180102dace..e5a8db00df2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -674,6 +674,7 @@ struct file_lock {
 	struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
 	union {
 		struct nfs_lock_info	nfs_fl;
+		struct nfs4_lock_info	nfs4_fl;
 	} fl_u;
 };
 
@@ -1657,6 +1658,52 @@ static inline void simple_transaction_set(struct file *file, size_t n)
 	ar->size = n;
 }
 
+/*
+ * simple attribute files
+ *
+ * These attributes behave similar to those in sysfs:
+ *
+ * Writing to an attribute immediately sets a value, an open file can be
+ * written to multiple times.
+ *
+ * Reading from an attribute creates a buffer from the value that might get
+ * read with multiple read calls. When the attribute has been read
+ * completely, no further read calls are possible until the file is opened
+ * again.
+ *
+ * All attributes contain a text representation of a numeric value
+ * that are accessed with the get() and set() functions.
+ */
+#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
+static int __fops ## _open(struct inode *inode, struct file *file)	\
+{									\
+	__simple_attr_check_format(__fmt, 0ull);			\
+	return simple_attr_open(inode, file, __get, __set, __fmt);	\
+}									\
+static struct file_operations __fops = {				\
+	.owner	 = THIS_MODULE,						\
+	.open	 = __fops ## _open,					\
+	.release = simple_attr_close,					\
+	.read	 = simple_attr_read,					\
+	.write	 = simple_attr_write,					\
+};
+
+static inline void __attribute__((format(printf, 1, 2)))
+__simple_attr_check_format(const char *fmt, ...)
+{
+	/* don't do anything, just let the compiler check the arguments; */
+}
+
+int simple_attr_open(struct inode *inode, struct file *file,
+		     u64 (*get)(void *), void (*set)(void *, u64),
+		     const char *fmt);
+int simple_attr_close(struct inode *inode, struct file *file);
+ssize_t simple_attr_read(struct file *file, char __user *buf,
+			 size_t len, loff_t *ppos);
+ssize_t simple_attr_write(struct file *file, const char __user *buf,
+			  size_t len, loff_t *ppos);
+
+
 #ifdef CONFIG_SECURITY
 static inline char *alloc_secdata(void)
 {
diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index faaff4c6455..70f54af87b9 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -51,6 +51,7 @@ struct gianfar_platform_data {
 
 	/* board specific information */
 	u32 board_flags;
+	u32 phy_flags;
 	u32 phyid;
 	u32 interruptPHY;
 	u8 mac_addr[6];
@@ -61,9 +62,14 @@ struct gianfar_platform_data {
 #define FSL_GIANFAR_DEV_HAS_COALESCE		0x00000002
 #define FSL_GIANFAR_DEV_HAS_RMON		0x00000004
 #define FSL_GIANFAR_DEV_HAS_MULTI_INTR		0x00000008
+#define FSL_GIANFAR_DEV_HAS_CSUM		0x00000010
+#define FSL_GIANFAR_DEV_HAS_VLAN		0x00000020
+#define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH	0x00000040
+#define FSL_GIANFAR_DEV_HAS_PADDING		0x00000080
 
 /* Flags in gianfar_platform_data */
-#define FSL_GIANFAR_BRD_HAS_PHY_INTR	0x00000001	/* if not set use a timer */
+#define FSL_GIANFAR_BRD_HAS_PHY_INTR	0x00000001 /* set or use a timer */
+#define FSL_GIANFAR_BRD_IS_REDUCED	0x00000002 /* Set if RGMII, RMII */
 
 struct fsl_i2c_platform_data {
 	/* device specific information */
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
new file mode 100644
index 00000000000..7fd0576a445
--- /dev/null
+++ b/include/linux/genalloc.h
@@ -0,0 +1,40 @@
+/*
+ * 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.
+ *
+ * This code is based on the buddy allocator found in the sym53c8xx_2
+ * driver, adapted for general purpose use.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/spinlock.h>
+
+#define ALLOC_MIN_SHIFT		5 /* 32 bytes minimum */
+/*
+ *  Link between free memory chunks of a given size.
+ */
+struct gen_pool_link {
+	struct gen_pool_link *next;
+};
+
+/*
+ *  Memory pool descriptor.
+ */
+struct gen_pool {
+	spinlock_t lock;
+	unsigned long (*get_new_chunk)(struct gen_pool *);
+	struct gen_pool *next;
+	struct gen_pool_link *h;
+	unsigned long private;
+	int max_chunk_shift;
+};
+
+unsigned long gen_pool_alloc(struct gen_pool *poolp, int size);
+void gen_pool_free(struct gen_pool *mp, unsigned long ptr, int size);
+struct gen_pool *gen_pool_create(int nr_chunks, int max_chunk_shift,
+				 unsigned long (*fp)(struct gen_pool *),
+				 unsigned long data);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index af7407e8cfc..8d6bf608b19 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -39,6 +39,7 @@ struct vm_area_struct;
 #define __GFP_COMP	0x4000u	/* Add compound page metadata */
 #define __GFP_ZERO	0x8000u	/* Return zeroed page on success */
 #define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */
+#define __GFP_NORECLAIM  0x20000u /* No realy zone reclaim during allocation */
 
 #define __GFP_BITS_SHIFT 20	/* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
@@ -47,7 +48,7 @@ struct vm_area_struct;
 #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
 			__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
 			__GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
-			__GFP_NOMEMALLOC)
+			__GFP_NOMEMALLOC|__GFP_NORECLAIM)
 
 #define GFP_ATOMIC	(__GFP_HIGH)
 #define GFP_NOIO	(__GFP_WAIT)
@@ -132,5 +133,10 @@ extern void FASTCALL(free_cold_page(struct page *page));
 #define free_page(addr) free_pages((addr),0)
 
 void page_alloc_init(void);
+#ifdef CONFIG_NUMA
+void drain_remote_pages(void);
+#else
+static inline void drain_remote_pages(void) { };
+#endif
 
 #endif /* __LINUX_GFP_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6af1ae4a821..f529d144281 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -4,6 +4,7 @@
 #ifdef CONFIG_HUGETLB_PAGE
 
 #include <linux/mempolicy.h>
+#include <asm/tlbflush.h>
 
 struct ctl_table;
 
@@ -22,12 +23,6 @@ int hugetlb_report_meminfo(char *);
 int hugetlb_report_node_meminfo(int, char *);
 int is_hugepage_mem_enough(size_t);
 unsigned long hugetlb_total_pages(void);
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int write);
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len);
-int pmd_huge(pmd_t pmd);
 struct page *alloc_huge_page(void);
 void free_huge_page(struct page *);
 
@@ -35,6 +30,17 @@ extern unsigned long max_huge_pages;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;
 
+/* arch callbacks */
+
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr);
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+			      int write);
+struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+				pmd_t *pmd, int write);
+int is_aligned_hugepage_range(unsigned long addr, unsigned long len);
+int pmd_huge(pmd_t pmd);
+
 #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
@@ -48,6 +54,28 @@ extern int sysctl_hugetlb_shm_group;
 int prepare_hugepage_range(unsigned long addr, unsigned long len);
 #endif
 
+#ifndef ARCH_HAS_SETCLEAR_HUGE_PTE
+#define set_huge_pte_at(mm, addr, ptep, pte)	set_pte_at(mm, addr, ptep, pte)
+#define huge_ptep_get_and_clear(mm, addr, ptep) ptep_get_and_clear(mm, addr, ptep)
+#else
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep);
+#endif
+
+#ifndef ARCH_HAS_HUGETLB_PREFAULT_HOOK
+#define hugetlb_prefault_arch_hook(mm)		do { } while (0)
+#else
+void hugetlb_prefault_arch_hook(struct mm_struct *mm);
+#endif
+
+#ifndef ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE
+#define hugetlb_clean_stale_pgtable(pte)	BUG()
+#else
+void hugetlb_clean_stale_pgtable(pte_t *pte);
+#endif
+
 #else /* !CONFIG_HUGETLB_PAGE */
 
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
diff --git a/include/linux/hwmon-sysfs.h b/include/linux/hwmon-sysfs.h
new file mode 100644
index 00000000000..1b5018a965f
--- /dev/null
+++ b/include/linux/hwmon-sysfs.h
@@ -0,0 +1,36 @@
+/*
+ *  hwmon-sysfs.h - hardware monitoring chip driver sysfs defines
+ *
+ *  Copyright (C) 2005 Yani Ioannou <yani.ioannou@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _LINUX_HWMON_SYSFS_H
+#define _LINUX_HWMON_SYSFS_H
+
+struct sensor_device_attribute{
+	struct device_attribute dev_attr;
+	int index;
+};
+#define to_sensor_dev_attr(_dev_attr) \
+	container_of(_dev_attr, struct sensor_device_attribute, dev_attr)
+
+#define SENSOR_DEVICE_ATTR(_name,_mode,_show,_store,_index)	\
+struct sensor_device_attribute sensor_dev_attr_##_name = {	\
+	.dev_attr =	__ATTR(_name,_mode,_show,_store),	\
+	.index =	_index,					\
+}
+
+#endif /* _LINUX_HWMON_SYSFS_H */
diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h
index 89270ce5147..33f08258f22 100644
--- a/include/linux/i2c-id.h
+++ b/include/linux/i2c-id.h
@@ -108,6 +108,7 @@
 #define I2C_DRIVERID_TDA7313	62	/* TDA7313 audio processor	*/
 #define I2C_DRIVERID_MAX6900	63	/* MAX6900 real-time clock	*/
 #define I2C_DRIVERID_SAA7114H	64	/* video decoder		*/
+#define I2C_DRIVERID_DS1374	65	/* DS1374 real time clock	*/
 
 
 #define I2C_DRIVERID_EXP0	0xF0	/* experimental use id's	*/
diff --git a/include/linux/i2c-vid.h b/include/linux/i2c-vid.h
index 974835e3530..41d0635e0ba 100644
--- a/include/linux/i2c-vid.h
+++ b/include/linux/i2c-vid.h
@@ -97,3 +97,15 @@ static inline int vid_from_reg(int val, int vrm)
 		                     2050 - (val) * 50);
 	}
 }
+
+static inline int vid_to_reg(int val, int vrm)
+{
+	switch (vrm) {
+	case 91:		/* VRM 9.1 */
+	case 90:		/* VRM 9.0 */
+		return ((val >= 1100) && (val <= 1850) ?
+			((18499 - val * 10) / 25 + 5) / 10 : -1);
+	default:
+		return -1;
+	}
+}
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index ebcd745f4cd..be837b13f29 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -290,11 +290,8 @@ static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data)
  */
 struct i2c_client_address_data {
 	unsigned short *normal_i2c;
-	unsigned short *normal_i2c_range;
 	unsigned short *probe;
-	unsigned short *probe_range;
 	unsigned short *ignore;
-	unsigned short *ignore_range;
 	unsigned short *force;
 };
 
@@ -563,24 +560,15 @@ union i2c_smbus_data {
 #define I2C_CLIENT_INSMOD \
   I2C_CLIENT_MODULE_PARM(probe, \
                       "List of adapter,address pairs to scan additionally"); \
-  I2C_CLIENT_MODULE_PARM(probe_range, \
-                      "List of adapter,start-addr,end-addr triples to scan " \
-                      "additionally"); \
   I2C_CLIENT_MODULE_PARM(ignore, \
                       "List of adapter,address pairs not to scan"); \
-  I2C_CLIENT_MODULE_PARM(ignore_range, \
-                      "List of adapter,start-addr,end-addr triples not to " \
-                      "scan"); \
   I2C_CLIENT_MODULE_PARM(force, \
                       "List of adapter,address pairs to boldly assume " \
                       "to be present"); \
 	static struct i2c_client_address_data addr_data = {		\
 			.normal_i2c = 		normal_i2c,		\
-			.normal_i2c_range =	normal_i2c_range,	\
 			.probe =		probe,			\
-			.probe_range =		probe_range,		\
 			.ignore =		ignore,			\
-			.ignore_range =		ignore_range,		\
 			.force =		force,			\
 		}
 
diff --git a/include/linux/input.h b/include/linux/input.h
index 72731d7d189..9d9598ed760 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -1015,7 +1015,7 @@ static inline void input_set_abs_params(struct input_dev *dev, int axis, int min
 	dev->absbit[LONG(axis)] |= BIT(axis);
 }
 
-extern struct class_simple *input_class;
+extern struct class *input_class;
 
 #endif
 #endif
diff --git a/include/linux/ioc4.h b/include/linux/ioc4.h
new file mode 100644
index 00000000000..3dd18b785eb
--- /dev/null
+++ b/include/linux/ioc4.h
@@ -0,0 +1,179 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 2005 Silicon Graphics, Inc.  All Rights Reserved.
+ */
+
+#ifndef _LINUX_IOC4_H
+#define _LINUX_IOC4_H
+
+#include <linux/interrupt.h>
+
+/***************
+ * Definitions *
+ ***************/
+
+/* Miscellaneous values inherent to hardware */
+
+#define IOC4_EXTINT_COUNT_DIVISOR 520	/* PCI clocks per COUNT tick */
+
+/***********************************
+ * Structures needed by subdrivers *
+ ***********************************/
+
+/* This structure fully describes the IOC4 miscellaneous registers which
+ * appear at bar[0]+0x00000 through bar[0]+0x0005c.  The corresponding
+ * PCI resource is managed by the main IOC4 driver because it contains
+ * registers of interest to many different IOC4 subdrivers.
+ */
+struct ioc4_misc_regs {
+	/* Miscellaneous IOC4 registers */
+	union ioc4_pci_err_addr_l {
+		uint32_t raw;
+		struct {
+			uint32_t valid:1;	/* Address captured */
+			uint32_t master_id:4;	/* Unit causing error
+						 * 0/1: Serial port 0 TX/RX
+						 * 2/3: Serial port 1 TX/RX
+						 * 4/5: Serial port 2 TX/RX
+						 * 6/7: Serial port 3 TX/RX
+						 * 8: ATA/ATAPI
+						 * 9-15: Undefined
+						 */
+			uint32_t mul_err:1;	/* Multiple errors occurred */
+			uint32_t addr:26;	/* Bits 31-6 of error addr */
+		} fields;
+	} pci_err_addr_l;
+	uint32_t pci_err_addr_h;	/* Bits 63-32 of error addr */
+	union ioc4_sio_int {
+		uint32_t raw;
+		struct {
+			uint8_t tx_mt:1;	/* TX ring buffer empty */
+			uint8_t rx_full:1;	/* RX ring buffer full */
+			uint8_t rx_high:1;	/* RX high-water exceeded */
+			uint8_t rx_timer:1;	/* RX timer has triggered */
+			uint8_t delta_dcd:1;	/* DELTA_DCD seen */
+			uint8_t delta_cts:1;	/* DELTA_CTS seen */
+			uint8_t intr_pass:1;	/* Interrupt pass-through */
+			uint8_t tx_explicit:1;	/* TX, MCW, or delay complete */
+		} fields[4];
+	} sio_ir;		/* Serial interrupt state */
+	union ioc4_other_int {
+		uint32_t raw;
+		struct {
+			uint32_t ata_int:1;	/* ATA port passthru */
+			uint32_t ata_memerr:1;	/* ATA halted by mem error */
+			uint32_t memerr:4;	/* Serial halted by mem err */
+			uint32_t kbd_int:1;	/* kbd/mouse intr asserted */
+			uint32_t reserved:16;	/* zero */
+			uint32_t rt_int:1;	/* INT_OUT section latch */
+			uint32_t gen_int:8;	/* Intr. from generic pins */
+		} fields;
+	} other_ir;		/* Other interrupt state */
+	union ioc4_sio_int sio_ies;	/* Serial interrupt enable set */
+	union ioc4_other_int other_ies;	/* Other interrupt enable set */
+	union ioc4_sio_int sio_iec;	/* Serial interrupt enable clear */
+	union ioc4_other_int other_iec;	/* Other interrupt enable clear */
+	union ioc4_sio_cr {
+		uint32_t raw;
+		struct {
+			uint32_t cmd_pulse:4;	/* Bytebus strobe width */
+			uint32_t arb_diag:3;	/* PCI bus requester */
+			uint32_t sio_diag_idle:1;	/* Active ser req? */
+			uint32_t ata_diag_idle:1;	/* Active ATA req? */
+			uint32_t ata_diag_active:1;	/* ATA req is winner */
+			uint32_t reserved:22;	/* zero */
+		} fields;
+	} sio_cr;
+	uint32_t unused1;
+	union ioc4_int_out {
+		uint32_t raw;
+		struct {
+			uint32_t count:16;	/* Period control */
+			uint32_t mode:3;	/* Output signal shape */
+			uint32_t reserved:11;	/* zero */
+			uint32_t diag:1;	/* Timebase control */
+			uint32_t int_out:1;	/* Current value */
+		} fields;
+	} int_out;		/* External interrupt output control */
+	uint32_t unused2;
+	union ioc4_gpcr {
+		uint32_t raw;
+		struct {
+			uint32_t dir:8;	/* Pin direction */
+			uint32_t edge:8;	/* Edge/level mode */
+			uint32_t reserved1:4;	/* zero */
+			uint32_t int_out_en:1;	/* INT_OUT enable */
+			uint32_t reserved2:11;	/* zero */
+		} fields;
+	} gpcr_s;		/* Generic PIO control set */
+	union ioc4_gpcr gpcr_c;	/* Generic PIO control clear */
+	union ioc4_gpdr {
+		uint32_t raw;
+		struct {
+			uint32_t gen_pin:8;	/* State of pins */
+			uint32_t reserved:24;
+		} fields;
+	} gpdr;			/* Generic PIO data */
+	uint32_t unused3;
+	union ioc4_gppr {
+		uint32_t raw;
+		struct {
+			uint32_t gen_pin:1;	/* Single pin state */
+			uint32_t reserved:31;
+		} fields;
+	} gppr[8];		/* Generic PIO pins */
+};
+
+/* Masks for GPCR DIR pins */
+#define IOC4_GPCR_DIR_0 0x01	/* External interrupt output */
+#define IOC4_GPCR_DIR_1 0x02	/* External interrupt input */
+#define IOC4_GPCR_DIR_2 0x04
+#define IOC4_GPCR_DIR_3 0x08	/* Keyboard/mouse presence */
+#define IOC4_GPCR_DIR_4 0x10	/* Ser. port 0 xcvr select (0=232, 1=422) */
+#define IOC4_GPCR_DIR_5 0x20	/* Ser. port 1 xcvr select (0=232, 1=422) */
+#define IOC4_GPCR_DIR_6 0x40	/* Ser. port 2 xcvr select (0=232, 1=422) */
+#define IOC4_GPCR_DIR_7 0x80	/* Ser. port 3 xcvr select (0=232, 1=422) */
+
+/* Masks for GPCR EDGE pins */
+#define IOC4_GPCR_EDGE_0 0x01
+#define IOC4_GPCR_EDGE_1 0x02	/* External interrupt input */
+#define IOC4_GPCR_EDGE_2 0x04
+#define IOC4_GPCR_EDGE_3 0x08
+#define IOC4_GPCR_EDGE_4 0x10
+#define IOC4_GPCR_EDGE_5 0x20
+#define IOC4_GPCR_EDGE_6 0x40
+#define IOC4_GPCR_EDGE_7 0x80
+
+/* One of these per IOC4 */
+struct ioc4_driver_data {
+	struct list_head idd_list;
+	unsigned long idd_bar0;
+	struct pci_dev *idd_pdev;
+	const struct pci_device_id *idd_pci_id;
+	struct __iomem ioc4_misc_regs *idd_misc_regs;
+	unsigned long count_period;
+	void *idd_serial_data;
+};
+
+/* One per submodule */
+struct ioc4_submodule {
+	struct list_head is_list;
+	char *is_name;
+	struct module *is_owner;
+	int (*is_probe) (struct ioc4_driver_data *);
+	int (*is_remove) (struct ioc4_driver_data *);
+};
+
+#define IOC4_NUM_CARDS		8	/* max cards per partition */
+
+/**********************************
+ * Functions needed by submodules *
+ **********************************/
+
+extern int ioc4_register_submodule(struct ioc4_submodule *);
+extern void ioc4_unregister_submodule(struct ioc4_submodule *);
+
+#endif				/* _LINUX_IOC4_H */
diff --git a/include/linux/ioc4_common.h b/include/linux/ioc4_common.h
deleted file mode 100644
index b03bcc46df5..00000000000
--- a/include/linux/ioc4_common.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (c) 2005 Silicon Graphics, Inc.  All Rights Reserved.
- */
-
-#ifndef _LINUX_IOC4_COMMON_H
-#define _LINUX_IOC4_COMMON_H
-
-/* prototypes */
-
-int ioc4_serial_init(void);
-
-int ioc4_serial_attach_one(struct pci_dev *pdev, const struct
-				pci_device_id *pci_id);
-int ioc4_ide_attach_one(struct pci_dev *pdev, const struct
-				pci_device_id *pci_id);
-
-#endif	/* _LINUX_IOC4_COMMON_H */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c3ff4d10166..7fc1022be9e 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -47,6 +47,10 @@ struct hw_interrupt_type {
 	void (*ack)(unsigned int irq);
 	void (*end)(unsigned int irq);
 	void (*set_affinity)(unsigned int irq, cpumask_t dest);
+	/* Currently used only by UML, might disappear one day.*/
+#ifdef CONFIG_IRQ_RELEASE_METHOD
+	void (*release)(unsigned int irq, void *dev_id);
+#endif
 };
 
 typedef struct hw_interrupt_type  hw_irq_controller;
diff --git a/include/linux/klist.h b/include/linux/klist.h
new file mode 100644
index 00000000000..eebf5e5696e
--- /dev/null
+++ b/include/linux/klist.h
@@ -0,0 +1,55 @@
+/*
+ *	klist.h - Some generic list helpers, extending struct list_head a bit.
+ *
+ *	Implementations are found in lib/klist.c
+ *
+ *
+ *	Copyright (C) 2005 Patrick Mochel
+ *
+ *	This file is rleased under the GPL v2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+
+
+struct klist {
+	spinlock_t		k_lock;
+	struct list_head	k_list;
+};
+
+
+extern void klist_init(struct klist * k);
+
+
+struct klist_node {
+	struct klist		* n_klist;
+	struct list_head	n_node;
+	struct kref		n_ref;
+	struct completion	n_removed;
+};
+
+extern void klist_add_tail(struct klist * k, struct klist_node * n);
+extern void klist_add_head(struct klist * k, struct klist_node * n);
+
+extern void klist_del(struct klist_node * n);
+extern void klist_remove(struct klist_node * n);
+
+extern int klist_node_attached(struct klist_node * n);
+
+
+struct klist_iter {
+	struct klist		* i_klist;
+	struct list_head	* i_head;
+	struct klist_node	* i_cur;
+};
+
+
+extern void klist_iter_init(struct klist * k, struct klist_iter * i);
+extern void klist_iter_init_node(struct klist * k, struct klist_iter * i, 
+				 struct klist_node * n);
+extern void klist_iter_exit(struct klist_iter * i);
+extern struct klist_node * klist_next(struct klist_iter * i);
+
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 765d660d3be..3b22304f12f 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -33,7 +33,7 @@
 extern u64 hotplug_seqnum;
 
 struct kobject {
-	char			* k_name;
+	const char		* k_name;
 	char			name[KOBJ_NAME_LEN];
 	struct kref		kref;
 	struct list_head	entry;
@@ -46,7 +46,7 @@ struct kobject {
 extern int kobject_set_name(struct kobject *, const char *, ...)
 	__attribute__((format(printf,2,3)));
 
-static inline char * kobject_name(struct kobject * kobj)
+static inline const char * kobject_name(const struct kobject * kobj)
 {
 	return kobj->k_name;
 }
@@ -57,7 +57,7 @@ extern void kobject_cleanup(struct kobject *);
 extern int kobject_add(struct kobject *);
 extern void kobject_del(struct kobject *);
 
-extern int kobject_rename(struct kobject *, char *new_name);
+extern int kobject_rename(struct kobject *, const char *new_name);
 
 extern int kobject_register(struct kobject *);
 extern void kobject_unregister(struct kobject *);
@@ -94,7 +94,7 @@ struct kobj_type {
  */
 struct kset_hotplug_ops {
 	int (*filter)(struct kset *kset, struct kobject *kobj);
-	char *(*name)(struct kset *kset, struct kobject *kobj);
+	const char *(*name)(struct kset *kset, struct kobject *kobj);
 	int (*hotplug)(struct kset *kset, struct kobject *kobj, char **envp,
 			int num_envp, char *buffer, int buffer_size);
 };
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 0d9d2257821..16d4e5a08e1 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -72,6 +72,8 @@ struct nlm_lockowner {
 	uint32_t pid;
 };
 
+struct nlm_wait;
+
 /*
  * Memory chunk for NLM client RPC request.
  */
@@ -81,6 +83,7 @@ struct nlm_rqst {
 	struct nlm_host *	a_host;		/* host handle */
 	struct nlm_args		a_args;		/* arguments */
 	struct nlm_res		a_res;		/* result */
+	struct nlm_wait *	a_block;
 	char			a_owner[NLMCLNT_OHSIZE];
 };
 
@@ -142,7 +145,9 @@ extern unsigned long		nlmsvc_timeout;
  * Lockd client functions
  */
 struct nlm_rqst * nlmclnt_alloc_call(void);
-int		  nlmclnt_block(struct nlm_host *, struct file_lock *, u32 *);
+int		  nlmclnt_prepare_block(struct nlm_rqst *req, struct nlm_host *host, struct file_lock *fl);
+void		  nlmclnt_finish_block(struct nlm_rqst *req);
+long		  nlmclnt_block(struct nlm_rqst *req, long timeout);
 int		  nlmclnt_cancel(struct nlm_host *, struct file_lock *);
 u32		  nlmclnt_grant(struct nlm_lock *);
 void		  nlmclnt_recovery(struct nlm_host *, u32);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 17518fe0b31..1813b162b0a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -691,6 +691,12 @@ extern void show_mem(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
+#ifdef CONFIG_NUMA
+extern void setup_per_cpu_pageset(void);
+#else
+static inline void setup_per_cpu_pageset(void) {}
+#endif
+
 /* prio_tree.c */
 void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
 void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e530c6c092f..4733d35d822 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,6 +63,12 @@ struct per_cpu_pageset {
 #endif
 } ____cacheline_aligned_in_smp;
 
+#ifdef CONFIG_NUMA
+#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
+#else
+#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
+#endif
+
 #define ZONE_DMA		0
 #define ZONE_NORMAL		1
 #define ZONE_HIGHMEM		2
@@ -122,8 +128,11 @@ struct zone {
 	 */
 	unsigned long		lowmem_reserve[MAX_NR_ZONES];
 
+#ifdef CONFIG_NUMA
+	struct per_cpu_pageset	*pageset[NR_CPUS];
+#else
 	struct per_cpu_pageset	pageset[NR_CPUS];
-
+#endif
 	/*
 	 * free areas of different sizes
 	 */
@@ -145,6 +154,14 @@ struct zone {
 	int			all_unreclaimable; /* All pages pinned */
 
 	/*
+	 * Does the allocator try to reclaim pages from the zone as soon
+	 * as it fails a watermark_ok() in __alloc_pages?
+	 */
+	int			reclaim_pages;
+	/* A count of how many reclaimers are scanning this zone */
+	atomic_t		reclaim_in_progress;
+
+	/*
 	 * prev_priority holds the scanning priority for this zone.  It is
 	 * defined as the scanning priority at which we achieved our reclaim
 	 * target at the previous try_to_free_pages() or balance_pgdat()
@@ -381,7 +398,7 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
 
 #include <linux/topology.h>
 /* Returns the number of the current Node. */
-#define numa_node_id()		(cpu_to_node(_smp_processor_id()))
+#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
 
 #ifndef CONFIG_DISCONTIGMEM
 
diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 9e5750079e0..3ebc36afae1 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -75,12 +75,6 @@ enum nf_ip_hook_priorities {
 #define SO_ORIGINAL_DST 80
 
 #ifdef __KERNEL__
-#ifdef CONFIG_NETFILTER_DEBUG
-void nf_debug_ip_local_deliver(struct sk_buff *skb);
-void nf_debug_ip_loopback_xmit(struct sk_buff *newskb);
-void nf_debug_ip_finish_output2(struct sk_buff *skb);
-#endif /*CONFIG_NETFILTER_DEBUG*/
-
 extern int ip_route_me_harder(struct sk_buff **pskb);
 
 /* Call this before modifying an existing IP packet: ensures it is
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h
index d84be02cb4f..694aec9b478 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_core.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h
@@ -1,7 +1,6 @@
 #ifndef _IP_CONNTRACK_CORE_H
 #define _IP_CONNTRACK_CORE_H
 #include <linux/netfilter.h>
-#include <linux/netfilter_ipv4/lockhelp.h>
 
 /* This header is used to share core functionality between the
    standalone connection tracking module, and the compatibility layer's use
@@ -47,6 +46,6 @@ static inline int ip_conntrack_confirm(struct sk_buff **pskb)
 
 extern struct list_head *ip_conntrack_hash;
 extern struct list_head ip_conntrack_expect_list;
-DECLARE_RWLOCK_EXTERN(ip_conntrack_lock);
+extern rwlock_t ip_conntrack_lock;
 #endif /* _IP_CONNTRACK_CORE_H */
 
diff --git a/include/linux/netfilter_ipv4/ip_nat.h b/include/linux/netfilter_ipv4/ip_nat.h
index 2b72b86176f..e201ec6e990 100644
--- a/include/linux/netfilter_ipv4/ip_nat.h
+++ b/include/linux/netfilter_ipv4/ip_nat.h
@@ -50,10 +50,9 @@ struct ip_nat_multi_range_compat
 
 #ifdef __KERNEL__
 #include <linux/list.h>
-#include <linux/netfilter_ipv4/lockhelp.h>
 
 /* Protects NAT hash tables, and NAT-private part of conntracks. */
-DECLARE_RWLOCK_EXTERN(ip_nat_lock);
+extern rwlock_t ip_nat_lock;
 
 /* The structure embedded in the conntrack structure. */
 struct ip_nat_info
diff --git a/include/linux/netfilter_ipv4/listhelp.h b/include/linux/netfilter_ipv4/listhelp.h
index f2ae7c5e57b..360429f4873 100644
--- a/include/linux/netfilter_ipv4/listhelp.h
+++ b/include/linux/netfilter_ipv4/listhelp.h
@@ -2,7 +2,6 @@
 #define _LISTHELP_H
 #include <linux/config.h>
 #include <linux/list.h>
-#include <linux/netfilter_ipv4/lockhelp.h>
 
 /* Header to do more comprehensive job than linux/list.h; assume list
    is first entry in structure. */
diff --git a/include/linux/netfilter_ipv4/lockhelp.h b/include/linux/netfilter_ipv4/lockhelp.h
deleted file mode 100644
index a3288633ab4..00000000000
--- a/include/linux/netfilter_ipv4/lockhelp.h
+++ /dev/null
@@ -1,129 +0,0 @@
-#ifndef _LOCKHELP_H
-#define _LOCKHELP_H
-#include <linux/config.h>
-
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <linux/interrupt.h>
-#include <linux/smp.h>
-
-/* Header to do help in lock debugging. */
-
-#ifdef CONFIG_NETFILTER_DEBUG
-struct spinlock_debug
-{
-	spinlock_t l;
-	atomic_t locked_by;
-};
-
-struct rwlock_debug
-{
-	rwlock_t l;
-	long read_locked_map;
-	long write_locked_map;
-};
-
-#define DECLARE_LOCK(l) 						\
-struct spinlock_debug l = { SPIN_LOCK_UNLOCKED, ATOMIC_INIT(-1) }
-#define DECLARE_LOCK_EXTERN(l) 			\
-extern struct spinlock_debug l
-#define DECLARE_RWLOCK(l)				\
-struct rwlock_debug l = { RW_LOCK_UNLOCKED, 0, 0 }
-#define DECLARE_RWLOCK_EXTERN(l)		\
-extern struct rwlock_debug l
-
-#define MUST_BE_LOCKED(l)						\
-do { if (atomic_read(&(l)->locked_by) != smp_processor_id())		\
-	printk("ASSERT %s:%u %s unlocked\n", __FILE__, __LINE__, #l);	\
-} while(0)
-
-#define MUST_BE_UNLOCKED(l)						\
-do { if (atomic_read(&(l)->locked_by) == smp_processor_id())		\
-	printk("ASSERT %s:%u %s locked\n", __FILE__, __LINE__, #l);	\
-} while(0)
-
-/* Write locked OK as well. */
-#define MUST_BE_READ_LOCKED(l)						    \
-do { if (!((l)->read_locked_map & (1UL << smp_processor_id()))		    \
-	 && !((l)->write_locked_map & (1UL << smp_processor_id())))	    \
-	printk("ASSERT %s:%u %s not readlocked\n", __FILE__, __LINE__, #l); \
-} while(0)
-
-#define MUST_BE_WRITE_LOCKED(l)						     \
-do { if (!((l)->write_locked_map & (1UL << smp_processor_id())))	     \
-	printk("ASSERT %s:%u %s not writelocked\n", __FILE__, __LINE__, #l); \
-} while(0)
-
-#define MUST_BE_READ_WRITE_UNLOCKED(l)					  \
-do { if ((l)->read_locked_map & (1UL << smp_processor_id()))		  \
-	printk("ASSERT %s:%u %s readlocked\n", __FILE__, __LINE__, #l);	  \
- else if ((l)->write_locked_map & (1UL << smp_processor_id()))		  \
-	 printk("ASSERT %s:%u %s writelocked\n", __FILE__, __LINE__, #l); \
-} while(0)
-
-#define LOCK_BH(lk)						\
-do {								\
-	MUST_BE_UNLOCKED(lk);					\
-	spin_lock_bh(&(lk)->l);					\
-	atomic_set(&(lk)->locked_by, smp_processor_id());	\
-} while(0)
-
-#define UNLOCK_BH(lk)				\
-do {						\
-	MUST_BE_LOCKED(lk);			\
-	atomic_set(&(lk)->locked_by, -1);	\
-	spin_unlock_bh(&(lk)->l);		\
-} while(0)
-
-#define READ_LOCK(lk) 						\
-do {								\
-	MUST_BE_READ_WRITE_UNLOCKED(lk);			\
-	read_lock_bh(&(lk)->l);					\
-	set_bit(smp_processor_id(), &(lk)->read_locked_map);	\
-} while(0)
-
-#define WRITE_LOCK(lk)							  \
-do {									  \
-	MUST_BE_READ_WRITE_UNLOCKED(lk);				  \
-	write_lock_bh(&(lk)->l);					  \
-	set_bit(smp_processor_id(), &(lk)->write_locked_map);		  \
-} while(0)
-
-#define READ_UNLOCK(lk)							\
-do {									\
-	if (!((lk)->read_locked_map & (1UL << smp_processor_id())))	\
-		printk("ASSERT: %s:%u %s not readlocked\n", 		\
-		       __FILE__, __LINE__, #lk);			\
-	clear_bit(smp_processor_id(), &(lk)->read_locked_map);		\
-	read_unlock_bh(&(lk)->l);					\
-} while(0)
-
-#define WRITE_UNLOCK(lk)					\
-do {								\
-	MUST_BE_WRITE_LOCKED(lk);				\
-	clear_bit(smp_processor_id(), &(lk)->write_locked_map);	\
-	write_unlock_bh(&(lk)->l);				\
-} while(0)
-
-#else
-#define DECLARE_LOCK(l) spinlock_t l = SPIN_LOCK_UNLOCKED
-#define DECLARE_LOCK_EXTERN(l) extern spinlock_t l
-#define DECLARE_RWLOCK(l) rwlock_t l = RW_LOCK_UNLOCKED
-#define DECLARE_RWLOCK_EXTERN(l) extern rwlock_t l
-
-#define MUST_BE_LOCKED(l)
-#define MUST_BE_UNLOCKED(l)
-#define MUST_BE_READ_LOCKED(l)
-#define MUST_BE_WRITE_LOCKED(l)
-#define MUST_BE_READ_WRITE_UNLOCKED(l)
-
-#define LOCK_BH(l) spin_lock_bh(l)
-#define UNLOCK_BH(l) spin_unlock_bh(l)
-
-#define READ_LOCK(l) read_lock_bh(l)
-#define WRITE_LOCK(l) write_lock_bh(l)
-#define READ_UNLOCK(l) read_unlock_bh(l)
-#define WRITE_UNLOCK(l) write_unlock_bh(l)
-#endif /*CONFIG_NETFILTER_DEBUG*/
-
-#endif /* _LOCKHELP_H */
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index e38407a23d0..3029cad63a0 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -14,6 +14,7 @@
 #define NETLINK_SELINUX		7	/* SELinux event notifications */
 #define NETLINK_ARPD		8
 #define NETLINK_AUDIT		9	/* auditing */
+#define NETLINK_FIB_LOOKUP	10	
 #define NETLINK_ROUTE6		11	/* af_inet6 route comm channel */
 #define NETLINK_IP6_FW		13
 #define NETLINK_DNRTMSG		14	/* DECnet routing messages */
@@ -146,7 +147,7 @@ struct netlink_callback
 	int		(*dump)(struct sk_buff * skb, struct netlink_callback *cb);
 	int		(*done)(struct netlink_callback *cb);
 	int		family;
-	long		args[4];
+	long		args[5];
 };
 
 struct netlink_notify
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5ca8a8d8ccd..5bb5b2fd7ba 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -382,6 +382,8 @@ enum {
 	NFSPROC4_CLNT_READDIR,
 	NFSPROC4_CLNT_SERVER_CAPS,
 	NFSPROC4_CLNT_DELEGRETURN,
+	NFSPROC4_CLNT_GETACL,
+	NFSPROC4_CLNT_SETACL,
 };
 
 #endif
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index dbac7f363e5..8ea249110fb 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -15,7 +15,6 @@
 #include <linux/pagemap.h>
 #include <linux/rwsem.h>
 #include <linux/wait.h>
-#include <linux/uio.h>
 
 #include <linux/nfs_fs_sb.h>
 
@@ -29,7 +28,6 @@
 #include <linux/nfs4.h>
 #include <linux/nfs_xdr.h>
 #include <linux/rwsem.h>
-#include <linux/workqueue.h>
 #include <linux/mempool.h>
 
 /*
@@ -44,13 +42,6 @@
 #define NFS_DEF_FILE_IO_BUFFER_SIZE	4096
 
 /*
- * The upper limit on timeouts for the exponential backoff algorithm.
- */
-#define NFS_WRITEBACK_DELAY		(5*HZ)
-#define NFS_WRITEBACK_LOCKDELAY		(60*HZ)
-#define NFS_COMMIT_DELAY		(5*HZ)
-
-/*
  * superblock magic number for NFS
  */
 #define NFS_SUPER_MAGIC			0x6969
@@ -60,9 +51,6 @@
  */
 #define NFS_RPC_SWAPFLAGS		(RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
 
-#define NFS_RW_SYNC		0x0001	/* O_SYNC handling */
-#define NFS_RW_SWAP		0x0002	/* This is a swap request */
-
 /*
  * When flushing a cluster of dirty pages, there can be different
  * strategies:
@@ -96,7 +84,8 @@ struct nfs_open_context {
 	int error;
 
 	struct list_head list;
-	wait_queue_head_t waitq;
+
+	__u64 dir_cookie;
 };
 
 /*
@@ -104,6 +93,8 @@ struct nfs_open_context {
  */
 struct nfs_delegation;
 
+struct posix_acl;
+
 /*
  * nfs fs inode data in memory
  */
@@ -140,7 +131,6 @@ struct nfs_inode {
 	 *
 	 *	mtime != read_cache_mtime
 	 */
-	unsigned long		readdir_timestamp;
 	unsigned long		read_cache_jiffies;
 	unsigned long		attrtimeo;
 	unsigned long		attrtimeo_timestamp;
@@ -158,6 +148,10 @@ struct nfs_inode {
 	atomic_t		data_updates;
 
 	struct nfs_access_entry	cache_access;
+#ifdef CONFIG_NFS_V3_ACL
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+#endif
 
 	/*
 	 * This is the cookie verifier used for NFSv3 readdir
@@ -183,13 +177,13 @@ struct nfs_inode {
 	wait_queue_head_t	nfs_i_wait;
 
 #ifdef CONFIG_NFS_V4
+	struct nfs4_cached_acl	*nfs4_acl;
         /* NFSv4 state */
 	struct list_head	open_states;
 	struct nfs_delegation	*delegation;
 	int			 delegation_state;
 	struct rw_semaphore	rwsem;
 #endif /* CONFIG_NFS_V4*/
-
 	struct inode		vfs_inode;
 };
 
@@ -203,6 +197,8 @@ struct nfs_inode {
 #define NFS_INO_INVALID_DATA	0x0010		/* cached data is invalid */
 #define NFS_INO_INVALID_ATIME	0x0020		/* cached atime is invalid */
 #define NFS_INO_INVALID_ACCESS	0x0040		/* cached access cred invalid */
+#define NFS_INO_INVALID_ACL	0x0080		/* cached acls are invalid */
+#define NFS_INO_REVAL_PAGECACHE	0x1000		/* must revalidate pagecache */
 
 static inline struct nfs_inode *NFS_I(struct inode *inode)
 {
@@ -294,12 +290,12 @@ extern int nfs_release(struct inode *, struct file *);
 extern int nfs_attribute_timeout(struct inode *inode);
 extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
+extern void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
 extern void nfs_begin_attr_update(struct inode *);
 extern void nfs_end_attr_update(struct inode *);
 extern void nfs_begin_data_update(struct inode *);
 extern void nfs_end_data_update(struct inode *);
-extern void nfs_end_data_update_defer(struct inode *);
 extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, struct rpc_cred *cred);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
 extern void put_nfs_open_context(struct nfs_open_context *ctx);
@@ -314,6 +310,9 @@ extern u32 root_nfs_parse_addr(char *name); /*__init*/
  * linux/fs/nfs/file.c
  */
 extern struct inode_operations nfs_file_inode_operations;
+#ifdef CONFIG_NFS_V3
+extern struct inode_operations nfs3_file_inode_operations;
+#endif /* CONFIG_NFS_V3 */
 extern struct file_operations nfs_file_operations;
 extern struct address_space_operations nfs_file_aops;
 
@@ -329,6 +328,22 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 }
 
 /*
+ * linux/fs/nfs/xattr.c
+ */
+#ifdef CONFIG_NFS_V3_ACL
+extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
+extern ssize_t nfs3_getxattr(struct dentry *, const char *, void *, size_t);
+extern int nfs3_setxattr(struct dentry *, const char *,
+			const void *, size_t, int);
+extern int nfs3_removexattr (struct dentry *, const char *name);
+#else
+# define nfs3_listxattr NULL
+# define nfs3_getxattr NULL
+# define nfs3_setxattr NULL
+# define nfs3_removexattr NULL
+#endif
+
+/*
  * linux/fs/nfs/direct.c
  */
 extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
@@ -342,6 +357,9 @@ extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf,
  * linux/fs/nfs/dir.c
  */
 extern struct inode_operations nfs_dir_inode_operations;
+#ifdef CONFIG_NFS_V3
+extern struct inode_operations nfs3_dir_inode_operations;
+#endif /* CONFIG_NFS_V3 */
 extern struct file_operations nfs_dir_operations;
 extern struct dentry_operations nfs_dentry_operations;
 
@@ -377,10 +395,10 @@ extern void nfs_commit_done(struct rpc_task *);
  */
 extern int  nfs_sync_inode(struct inode *, unsigned long, unsigned int, int);
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-extern int  nfs_commit_inode(struct inode *, unsigned long, unsigned int, int);
+extern int  nfs_commit_inode(struct inode *, int);
 #else
 static inline int
-nfs_commit_inode(struct inode *inode, unsigned long idx_start, unsigned int npages, int how)
+nfs_commit_inode(struct inode *inode, int how)
 {
 	return 0;
 }
@@ -434,11 +452,6 @@ static inline void nfs_writedata_free(struct nfs_write_data *p)
 	mempool_free(p, nfs_wdata_mempool);
 }
 
-/* Hack for future NFS swap support */
-#ifndef IS_SWAPFILE
-# define IS_SWAPFILE(inode)	(0)
-#endif
-
 /*
  * linux/fs/nfs/read.c
  */
@@ -468,6 +481,29 @@ static inline void nfs_readdata_free(struct nfs_read_data *p)
 extern void  nfs_readdata_release(struct rpc_task *task);
 
 /*
+ * linux/fs/nfs3proc.c
+ */
+#ifdef CONFIG_NFS_V3_ACL
+extern struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type);
+extern int nfs3_proc_setacl(struct inode *inode, int type,
+			    struct posix_acl *acl);
+extern int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode,
+		mode_t mode);
+extern void nfs3_forget_cached_acls(struct inode *inode);
+#else
+static inline int nfs3_proc_set_default_acl(struct inode *dir,
+					    struct inode *inode,
+					    mode_t mode)
+{
+	return 0;
+}
+
+static inline void nfs3_forget_cached_acls(struct inode *inode)
+{
+}
+#endif /* CONFIG_NFS_V3_ACL */
+
+/*
  * linux/fs/mount_clnt.c
  * (Used only by nfsroot module)
  */
@@ -515,230 +551,6 @@ extern void * nfs_root_data(void);
 
 #define NFS_JUKEBOX_RETRY_TIME (5 * HZ)
 
-#ifdef CONFIG_NFS_V4
-
-struct idmap;
-
-/*
- * In a seqid-mutating op, this macro controls which error return
- * values trigger incrementation of the seqid.
- *
- * from rfc 3010:
- * The client MUST monotonically increment the sequence number for the
- * CLOSE, LOCK, LOCKU, OPEN, OPEN_CONFIRM, and OPEN_DOWNGRADE
- * operations.  This is true even in the event that the previous
- * operation that used the sequence number received an error.  The only
- * exception to this rule is if the previous operation received one of
- * the following errors: NFSERR_STALE_CLIENTID, NFSERR_STALE_STATEID,
- * NFSERR_BAD_STATEID, NFSERR_BAD_SEQID, NFSERR_BADXDR,
- * NFSERR_RESOURCE, NFSERR_NOFILEHANDLE.
- *
- */
-#define seqid_mutating_err(err)       \
-(((err) != NFSERR_STALE_CLIENTID) &&  \
- ((err) != NFSERR_STALE_STATEID)  &&  \
- ((err) != NFSERR_BAD_STATEID)    &&  \
- ((err) != NFSERR_BAD_SEQID)      &&  \
- ((err) != NFSERR_BAD_XDR)        &&  \
- ((err) != NFSERR_RESOURCE)       &&  \
- ((err) != NFSERR_NOFILEHANDLE))
-
-enum nfs4_client_state {
-	NFS4CLNT_OK  = 0,
-};
-
-/*
- * The nfs4_client identifies our client state to the server.
- */
-struct nfs4_client {
-	struct list_head	cl_servers;	/* Global list of servers */
-	struct in_addr		cl_addr;	/* Server identifier */
-	u64			cl_clientid;	/* constant */
-	nfs4_verifier		cl_confirm;
-	unsigned long		cl_state;
-
-	u32			cl_lockowner_id;
-
-	/*
-	 * The following rwsem ensures exclusive access to the server
-	 * while we recover the state following a lease expiration.
-	 */
-	struct rw_semaphore	cl_sem;
-
-	struct list_head	cl_delegations;
-	struct list_head	cl_state_owners;
-	struct list_head	cl_unused;
-	int			cl_nunused;
-	spinlock_t		cl_lock;
-	atomic_t		cl_count;
-
-	struct rpc_clnt *	cl_rpcclient;
-	struct rpc_cred *	cl_cred;
-
-	struct list_head	cl_superblocks;	/* List of nfs_server structs */
-
-	unsigned long		cl_lease_time;
-	unsigned long		cl_last_renewal;
-	struct work_struct	cl_renewd;
-	struct work_struct	cl_recoverd;
-
-	wait_queue_head_t	cl_waitq;
-	struct rpc_wait_queue	cl_rpcwaitq;
-
-	/* used for the setclientid verifier */
-	struct timespec		cl_boot_time;
-
-	/* idmapper */
-	struct idmap *		cl_idmap;
-
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the clientid, and the callback address.
-	 */
-	char			cl_ipaddr[16];
-	unsigned char		cl_id_uniquifier;
-};
-
-/*
- * NFS4 state_owners and lock_owners are simply labels for ordered
- * sequences of RPC calls. Their sole purpose is to provide once-only
- * semantics by allowing the server to identify replayed requests.
- *
- * The ->so_sema is held during all state_owner seqid-mutating operations:
- * OPEN, OPEN_DOWNGRADE, and CLOSE. Its purpose is to properly serialize
- * so_seqid.
- */
-struct nfs4_state_owner {
-	struct list_head     so_list;	 /* per-clientid list of state_owners */
-	struct nfs4_client   *so_client;
-	u32                  so_id;      /* 32-bit identifier, unique */
-	struct semaphore     so_sema;
-	u32                  so_seqid;   /* protected by so_sema */
-	atomic_t	     so_count;
-
-	struct rpc_cred	     *so_cred;	 /* Associated cred */
-	struct list_head     so_states;
-	struct list_head     so_delegations;
-};
-
-/*
- * struct nfs4_state maintains the client-side state for a given
- * (state_owner,inode) tuple (OPEN) or state_owner (LOCK).
- *
- * OPEN:
- * In order to know when to OPEN_DOWNGRADE or CLOSE the state on the server,
- * we need to know how many files are open for reading or writing on a
- * given inode. This information too is stored here.
- *
- * LOCK: one nfs4_state (LOCK) to hold the lock stateid nfs4_state(OPEN)
- */
-
-struct nfs4_lock_state {
-	struct list_head	ls_locks;	/* Other lock stateids */
-	fl_owner_t		ls_owner;	/* POSIX lock owner */
-#define NFS_LOCK_INITIALIZED 1
-	int			ls_flags;
-	u32			ls_seqid;
-	u32			ls_id;
-	nfs4_stateid		ls_stateid;
-	atomic_t		ls_count;
-};
-
-/* bits for nfs4_state->flags */
-enum {
-	LK_STATE_IN_USE,
-	NFS_DELEGATED_STATE,
-};
-
-struct nfs4_state {
-	struct list_head open_states;	/* List of states for the same state_owner */
-	struct list_head inode_states;	/* List of states for the same inode */
-	struct list_head lock_states;	/* List of subservient lock stateids */
-
-	struct nfs4_state_owner *owner;	/* Pointer to the open owner */
-	struct inode *inode;		/* Pointer to the inode */
-
-	unsigned long flags;		/* Do we hold any locks? */
-	struct semaphore lock_sema;	/* Serializes file locking operations */
-	rwlock_t state_lock;		/* Protects the lock_states list */
-
-	nfs4_stateid stateid;
-
-	unsigned int nreaders;
-	unsigned int nwriters;
-	int state;			/* State on the server (R,W, or RW) */
-	atomic_t count;
-};
-
-
-struct nfs4_exception {
-	long timeout;
-	int retry;
-};
-
-struct nfs4_state_recovery_ops {
-	int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *);
-	int (*recover_lock)(struct nfs4_state *, struct file_lock *);
-};
-
-extern struct dentry_operations nfs4_dentry_operations;
-extern struct inode_operations nfs4_dir_inode_operations;
-
-/* nfs4proc.c */
-extern int nfs4_map_errors(int err);
-extern int nfs4_proc_setclientid(struct nfs4_client *, u32, unsigned short);
-extern int nfs4_proc_setclientid_confirm(struct nfs4_client *);
-extern int nfs4_proc_async_renew(struct nfs4_client *);
-extern int nfs4_proc_renew(struct nfs4_client *);
-extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state, mode_t mode);
-extern struct inode *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
-extern int nfs4_open_revalidate(struct inode *, struct dentry *, int);
-
-extern struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops;
-extern struct nfs4_state_recovery_ops nfs4_network_partition_recovery_ops;
-
-/* nfs4renewd.c */
-extern void nfs4_schedule_state_renewal(struct nfs4_client *);
-extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
-extern void nfs4_kill_renewd(struct nfs4_client *);
-
-/* nfs4state.c */
-extern void init_nfsv4_state(struct nfs_server *);
-extern void destroy_nfsv4_state(struct nfs_server *);
-extern struct nfs4_client *nfs4_get_client(struct in_addr *);
-extern void nfs4_put_client(struct nfs4_client *clp);
-extern int nfs4_init_client(struct nfs4_client *clp);
-extern struct nfs4_client *nfs4_find_client(struct in_addr *);
-extern u32 nfs4_alloc_lockowner_id(struct nfs4_client *);
-
-extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
-extern void nfs4_put_state_owner(struct nfs4_state_owner *);
-extern void nfs4_drop_state_owner(struct nfs4_state_owner *);
-extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
-extern void nfs4_put_open_state(struct nfs4_state *);
-extern void nfs4_close_state(struct nfs4_state *, mode_t);
-extern struct nfs4_state *nfs4_find_state(struct inode *, struct rpc_cred *, mode_t mode);
-extern void nfs4_increment_seqid(int status, struct nfs4_state_owner *sp);
-extern void nfs4_schedule_state_recovery(struct nfs4_client *);
-extern struct nfs4_lock_state *nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t);
-extern struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t);
-extern void nfs4_put_lock_state(struct nfs4_lock_state *state);
-extern void nfs4_increment_lock_seqid(int status, struct nfs4_lock_state *ls);
-extern void nfs4_notify_setlk(struct nfs4_state *, struct file_lock *, struct nfs4_lock_state *);
-extern void nfs4_notify_unlck(struct nfs4_state *, struct file_lock *, struct nfs4_lock_state *);
-extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t);
-
-
-
-struct nfs4_mount_data;
-#else
-#define init_nfsv4_state(server)  do { } while (0)
-#define destroy_nfsv4_state(server)       do { } while (0)
-#define nfs4_put_state_owner(inode, owner) do { } while (0)
-#define nfs4_put_open_state(state) do { } while (0)
-#define nfs4_close_state(a, b) do { } while (0)
-#define nfs4_renewd_prepare_shutdown(server) do { } while (0)
-#endif
-
 #endif /* __KERNEL__ */
 
 /*
diff --git a/include/linux/nfs_fs_i.h b/include/linux/nfs_fs_i.h
index e9a749588a7..e2c18dabff8 100644
--- a/include/linux/nfs_fs_i.h
+++ b/include/linux/nfs_fs_i.h
@@ -16,6 +16,11 @@ struct nfs_lock_info {
 	struct nlm_lockowner *owner;
 };
 
+struct nfs4_lock_state;
+struct nfs4_lock_info {
+	struct nfs4_lock_state *owner;
+};
+
 /*
  * Lock flag values
  */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index fc51645d61e..3d3a305488c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -10,6 +10,7 @@
 struct nfs_server {
 	struct rpc_clnt *	client;		/* RPC client handle */
 	struct rpc_clnt *	client_sys;	/* 2nd handle for FSINFO */
+	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
 	struct nfs_rpc_ops *	rpc_ops;	/* NFS protocol vector */
 	struct backing_dev_info	backing_dev_info;
 	int			flags;		/* various flags */
diff --git a/include/linux/nfs_mount.h b/include/linux/nfs_mount.h
index 0071428231f..659c7543845 100644
--- a/include/linux/nfs_mount.h
+++ b/include/linux/nfs_mount.h
@@ -58,6 +58,7 @@ struct nfs_mount_data {
 #define NFS_MOUNT_KERBEROS	0x0100	/* 3 */
 #define NFS_MOUNT_NONLM		0x0200	/* 3 */
 #define NFS_MOUNT_BROKEN_SUID	0x0400	/* 4 */
+#define NFS_MOUNT_NOACL		0x0800	/* 4 */
 #define NFS_MOUNT_STRICTLOCK	0x1000	/* reserved for NFSv4 */
 #define NFS_MOUNT_SECFLAVOUR	0x2000	/* 5 */
 #define NFS_MOUNT_FLAGMASK	0xFFFF
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 39e4895bcdb..da2e077b65e 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -20,12 +20,19 @@
 #include <asm/atomic.h>
 
 /*
+ * Valid flags for the radix tree
+ */
+#define NFS_PAGE_TAG_DIRTY	0
+#define NFS_PAGE_TAG_WRITEBACK	1
+
+/*
  * Valid flags for a dirty buffer
  */
 #define PG_BUSY			0
 #define PG_NEED_COMMIT		1
 #define PG_NEED_RESCHED		2
 
+struct nfs_inode;
 struct nfs_page {
 	struct list_head	wb_list,	/* Defines state of page: */
 				*wb_list_head;	/*      read/write/commit */
@@ -54,14 +61,17 @@ extern	void nfs_clear_request(struct nfs_page *req);
 extern	void nfs_release_request(struct nfs_page *req);
 
 
-extern	void nfs_list_add_request(struct nfs_page *, struct list_head *);
-
+extern  int nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst,
+				unsigned long idx_start, unsigned int npages);
 extern	int nfs_scan_list(struct list_head *, struct list_head *,
 			  unsigned long, unsigned int);
 extern	int nfs_coalesce_requests(struct list_head *, struct list_head *,
 				  unsigned int);
 extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
+extern  int nfs_set_page_writeback_locked(struct nfs_page *req);
+extern  void nfs_clear_page_writeback(struct nfs_page *req);
+
 
 /*
  * Lock the page of an asynchronous request without incrementing the wb_count
@@ -86,6 +96,18 @@ nfs_lock_request(struct nfs_page *req)
 	return 1;
 }
 
+/**
+ * nfs_list_add_request - Insert a request into a list
+ * @req: request
+ * @head: head of list into which to insert the request.
+ */
+static inline void
+nfs_list_add_request(struct nfs_page *req, struct list_head *head)
+{
+	list_add_tail(&req->wb_list, head);
+	req->wb_list_head = head;
+}
+
 
 /**
  * nfs_list_remove_request - Remove a request from its wb_list
@@ -96,10 +118,6 @@ nfs_list_remove_request(struct nfs_page *req)
 {
 	if (list_empty(&req->wb_list))
 		return;
-	if (!NFS_WBACK_BUSY(req)) {
-		printk(KERN_ERR "NFS: unlocked request attempted removed from list!\n");
-		BUG();
-	}
 	list_del_init(&req->wb_list);
 	req->wb_list_head = NULL;
 }
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 47037d9521c..a2bf6914ff1 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -2,6 +2,7 @@
 #define _LINUX_NFS_XDR_H
 
 #include <linux/sunrpc/xprt.h>
+#include <linux/nfsacl.h>
 
 struct nfs4_fsid {
 	__u64 major;
@@ -326,6 +327,20 @@ struct nfs_setattrargs {
 	const u32 *			bitmask;
 };
 
+struct nfs_setaclargs {
+	struct nfs_fh *			fh;
+	size_t				acl_len;
+	unsigned int			acl_pgbase;
+	struct page **			acl_pages;
+};
+
+struct nfs_getaclargs {
+	struct nfs_fh *			fh;
+	size_t				acl_len;
+	unsigned int			acl_pgbase;
+	struct page **			acl_pages;
+};
+
 struct nfs_setattrres {
 	struct nfs_fattr *              fattr;
 	const struct nfs_server *	server;
@@ -354,6 +369,20 @@ struct nfs_readdirargs {
 	struct page **		pages;
 };
 
+struct nfs3_getaclargs {
+	struct nfs_fh *		fh;
+	int			mask;
+	struct page **		pages;
+};
+
+struct nfs3_setaclargs {
+	struct inode *		inode;
+	int			mask;
+	struct posix_acl *	acl_access;
+	struct posix_acl *	acl_default;
+	struct page **		pages;
+};
+
 struct nfs_diropok {
 	struct nfs_fh *		fh;
 	struct nfs_fattr *	fattr;
@@ -477,6 +506,15 @@ struct nfs3_readdirres {
 	int			plus;
 };
 
+struct nfs3_getaclres {
+	struct nfs_fattr *	fattr;
+	int			mask;
+	unsigned int		acl_access_count;
+	unsigned int		acl_default_count;
+	struct posix_acl *	acl_access;
+	struct posix_acl *	acl_default;
+};
+
 #ifdef CONFIG_NFS_V4
 
 typedef u64 clientid4;
@@ -667,6 +705,7 @@ struct nfs_rpc_ops {
 	int	version;		/* Protocol version */
 	struct dentry_operations *dentry_ops;
 	struct inode_operations *dir_inode_ops;
+	struct inode_operations *file_inode_ops;
 
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
@@ -713,6 +752,7 @@ struct nfs_rpc_ops {
 	int	(*file_open)   (struct inode *, struct file *);
 	int	(*file_release) (struct inode *, struct file *);
 	int	(*lock)(struct file *, int, struct file_lock *);
+	void	(*clear_acl_cache)(struct inode *);
 };
 
 /*
@@ -732,4 +772,7 @@ extern struct rpc_version	nfs_version2;
 extern struct rpc_version	nfs_version3;
 extern struct rpc_version	nfs_version4;
 
+extern struct rpc_version	nfsacl_version3;
+extern struct rpc_program	nfsacl_program;
+
 #endif
diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h
new file mode 100644
index 00000000000..54487a99beb
--- /dev/null
+++ b/include/linux/nfsacl.h
@@ -0,0 +1,58 @@
+/*
+ * File: linux/nfsacl.h
+ *
+ * (C) 2003 Andreas Gruenbacher <agruen@suse.de>
+ */
+#ifndef __LINUX_NFSACL_H
+#define __LINUX_NFSACL_H
+
+#define NFS_ACL_PROGRAM	100227
+
+#define ACLPROC2_GETACL		1
+#define ACLPROC2_SETACL		2
+#define ACLPROC2_GETATTR	3
+#define ACLPROC2_ACCESS		4
+
+#define ACLPROC3_GETACL		1
+#define ACLPROC3_SETACL		2
+
+
+/* Flags for the getacl/setacl mode */
+#define NFS_ACL			0x0001
+#define NFS_ACLCNT		0x0002
+#define NFS_DFACL		0x0004
+#define NFS_DFACLCNT		0x0008
+
+/* Flag for Default ACL entries */
+#define NFS_ACL_DEFAULT		0x1000
+
+#ifdef __KERNEL__
+
+#include <linux/posix_acl.h>
+
+/* Maximum number of ACL entries over NFS */
+#define NFS_ACL_MAX_ENTRIES	1024
+
+#define NFSACL_MAXWORDS		(2*(2+3*NFS_ACL_MAX_ENTRIES))
+#define NFSACL_MAXPAGES		((2*(8+12*NFS_ACL_MAX_ENTRIES) + PAGE_SIZE-1) \
+				 >> PAGE_SHIFT)
+
+static inline unsigned int
+nfsacl_size(struct posix_acl *acl_access, struct posix_acl *acl_default)
+{
+	unsigned int w = 16;
+	w += max(acl_access ? (int)acl_access->a_count : 3, 4) * 12;
+	if (acl_default)
+		w += max((int)acl_default->a_count, 4) * 12;
+	return w;
+}
+
+extern unsigned int
+nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
+	      struct posix_acl *acl, int encode_entries, int typeflag);
+extern unsigned int
+nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
+	      struct posix_acl **pacl);
+
+#endif /* __KERNEL__ */
+#endif  /* __LINUX_NFSACL_H */
diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h
index 8f85d9a5960..4bf931d5ff5 100644
--- a/include/linux/nfsd/nfsd.h
+++ b/include/linux/nfsd/nfsd.h
@@ -15,6 +15,7 @@
 #include <linux/unistd.h>
 #include <linux/dirent.h>
 #include <linux/fs.h>
+#include <linux/posix_acl.h>
 #include <linux/mount.h>
 
 #include <linux/nfsd/debug.h>
@@ -124,6 +125,21 @@ int		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 int		nfsd_notify_change(struct inode *, struct iattr *);
 int		nfsd_permission(struct svc_export *, struct dentry *, int);
 
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+#ifdef CONFIG_NFSD_V2_ACL
+extern struct svc_version nfsd_acl_version2;
+#else
+#define nfsd_acl_version2 NULL
+#endif
+#ifdef CONFIG_NFSD_V3_ACL
+extern struct svc_version nfsd_acl_version3;
+#else
+#define nfsd_acl_version3 NULL
+#endif
+struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
+int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
+#endif
+
 
 /* 
  * NFSv4 State
diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h
index ecccef777da..130d4f588a3 100644
--- a/include/linux/nfsd/xdr.h
+++ b/include/linux/nfsd/xdr.h
@@ -169,4 +169,8 @@ int nfssvc_encode_entry(struct readdir_cd *, const char *name,
 
 int nfssvc_release_fhandle(struct svc_rqst *, u32 *, struct nfsd_fhandle *);
 
+/* Helper functions for NFSv2 ACL code */
+u32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, u32 *p, struct svc_fh *fhp);
+u32 *nfs2svc_decode_fh(u32 *p, struct svc_fh *fhp);
+
 #endif /* LINUX_NFSD_H */
diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h
index 0ae9e0ef5f6..21e18ce7ca6 100644
--- a/include/linux/nfsd/xdr3.h
+++ b/include/linux/nfsd/xdr3.h
@@ -110,6 +110,19 @@ struct nfsd3_commitargs {
 	__u32			count;
 };
 
+struct nfsd3_getaclargs {
+	struct svc_fh		fh;
+	int			mask;
+};
+
+struct posix_acl;
+struct nfsd3_setaclargs {
+	struct svc_fh		fh;
+	int			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+};
+
 struct nfsd3_attrstat {
 	__u32			status;
 	struct svc_fh		fh;
@@ -209,6 +222,14 @@ struct nfsd3_commitres {
 	struct svc_fh		fh;
 };
 
+struct nfsd3_getaclres {
+	__u32			status;
+	struct svc_fh		fh;
+	int			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+};
+
 /* dummy type for release */
 struct nfsd3_fhandle_pair {
 	__u32			dummy;
@@ -241,6 +262,7 @@ union nfsd3_xdrstore {
 	struct nfsd3_fsinfores		fsinfores;
 	struct nfsd3_pathconfres	pathconfres;
 	struct nfsd3_commitres		commitres;
+	struct nfsd3_getaclres		getaclres;
 };
 
 #define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
@@ -316,6 +338,10 @@ int nfs3svc_encode_entry(struct readdir_cd *, const char *name,
 int nfs3svc_encode_entry_plus(struct readdir_cd *, const char *name,
 				int namlen, loff_t offset, ino_t ino,
 				unsigned int);
+/* Helper functions for NFSv3 ACL code */
+u32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, u32 *p,
+				struct svc_fh *fhp);
+u32 *nfs3svc_decode_fh(u32 *p, struct svc_fh *fhp);
 
 
 #endif /* _LINUX_NFSD_XDR3_H */
diff --git a/include/linux/node.h b/include/linux/node.h
index 6e0a697e594..254dc3de650 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -27,6 +27,7 @@ struct node {
 };
 
 extern int register_node(struct node *, int, struct node *);
+extern void unregister_node(struct node *node);
 
 #define to_node(sys_device) container_of(sys_device, struct node, sysdev)
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 39ab8c6b565..f5a6695d4d2 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -61,21 +61,20 @@
 #define PG_active		 6
 #define PG_slab			 7	/* slab debug (Suparna wants this) */
 
-#define PG_highmem		 8
-#define PG_checked		 9	/* kill me in 2.5.<early>. */
-#define PG_arch_1		10
-#define PG_reserved		11
-
-#define PG_private		12	/* Has something at ->private */
-#define PG_writeback		13	/* Page is under writeback */
-#define PG_nosave		14	/* Used for system suspend/resume */
-#define PG_compound		15	/* Part of a compound page */
-
-#define PG_swapcache		16	/* Swap page: swp_entry_t in private */
-#define PG_mappedtodisk		17	/* Has blocks allocated on-disk */
-#define PG_reclaim		18	/* To be reclaimed asap */
-#define PG_nosave_free		19	/* Free, should not be written */
-#define PG_uncached		20	/* Page has been mapped as uncached */
+#define PG_checked		 8	/* kill me in 2.5.<early>. */
+#define PG_arch_1		 9
+#define PG_reserved		10
+#define PG_private		11	/* Has something at ->private */
+
+#define PG_writeback		12	/* Page is under writeback */
+#define PG_nosave		13	/* Used for system suspend/resume */
+#define PG_compound		14	/* Part of a compound page */
+#define PG_swapcache		15	/* Swap page: swp_entry_t in private */
+
+#define PG_mappedtodisk		16	/* Has blocks allocated on-disk */
+#define PG_reclaim		17	/* To be reclaimed asap */
+#define PG_nosave_free		18	/* Free, should not be written */
+#define PG_uncached		19	/* Page has been mapped as uncached */
 
 /*
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
@@ -136,8 +135,8 @@ struct page_state {
 
 extern void get_page_state(struct page_state *ret);
 extern void get_full_page_state(struct page_state *ret);
-extern unsigned long __read_page_state(unsigned offset);
-extern void __mod_page_state(unsigned offset, unsigned long delta);
+extern unsigned long __read_page_state(unsigned long offset);
+extern void __mod_page_state(unsigned long offset, unsigned long delta);
 
 #define read_page_state(member) \
 	__read_page_state(offsetof(struct page_state, member))
@@ -215,7 +214,7 @@ extern void __mod_page_state(unsigned offset, unsigned long delta);
 #define TestSetPageSlab(page)	test_and_set_bit(PG_slab, &(page)->flags)
 
 #ifdef CONFIG_HIGHMEM
-#define PageHighMem(page)	test_bit(PG_highmem, &(page)->flags)
+#define PageHighMem(page)	is_highmem(page_zone(page))
 #else
 #define PageHighMem(page)	0 /* needed to optimize away at compile time */
 #endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0422031161b..d9a25647a29 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -52,12 +52,12 @@ void release_pages(struct page **pages, int nr, int cold);
 
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
-	return alloc_pages(mapping_gfp_mask(x), 0);
+	return alloc_pages(mapping_gfp_mask(x)|__GFP_NORECLAIM, 0);
 }
 
 static inline struct page *page_cache_alloc_cold(struct address_space *x)
 {
-	return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+	return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD|__GFP_NORECLAIM, 0);
 }
 
 typedef int filler_t(void *, struct page *);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index b8b4ebf9abf..63e89e47b8e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -575,6 +575,7 @@
 #define PCI_DEVICE_ID_CT_65550		0x00e0
 #define PCI_DEVICE_ID_CT_65554		0x00e4
 #define PCI_DEVICE_ID_CT_65555		0x00e5
+#define PCI_DEVICE_ID_CT_69000		0x00c0
 
 #define PCI_VENDOR_ID_MIRO		0x1031
 #define PCI_DEVICE_ID_MIRO_36050	0x5601
diff --git a/include/linux/pfkeyv2.h b/include/linux/pfkeyv2.h
index e6b51922024..724066778af 100644
--- a/include/linux/pfkeyv2.h
+++ b/include/linux/pfkeyv2.h
@@ -245,6 +245,7 @@ struct sadb_x_nat_t_port {
 
 /* Security Association flags */
 #define SADB_SAFLAGS_PFS	1
+#define SADB_SAFLAGS_NOPMTUDISC	0x20000000
 #define SADB_SAFLAGS_DECAP_DSCP	0x40000000
 #define SADB_SAFLAGS_NOECN	0x80000000
 
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
new file mode 100644
index 00000000000..e24b74b1115
--- /dev/null
+++ b/include/linux/raid/bitmap.h
@@ -0,0 +1,273 @@
+/*
+ * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
+ *
+ * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
+ */
+#ifndef BITMAP_H
+#define BITMAP_H 1
+
+#define BITMAP_MAJOR 3
+#define BITMAP_MINOR 38
+
+/*
+ * in-memory bitmap:
+ *
+ * Use 16 bit block counters to track pending writes to each "chunk".
+ * The 2 high order bits are special-purpose, the first is a flag indicating
+ * whether a resync is needed.  The second is a flag indicating whether a
+ * resync is active.
+ * This means that the counter is actually 14 bits:
+ *
+ * +--------+--------+------------------------------------------------+
+ * | resync | resync |               counter                          |
+ * | needed | active |                                                |
+ * |  (0-1) |  (0-1) |              (0-16383)                         |
+ * +--------+--------+------------------------------------------------+
+ *
+ * The "resync needed" bit is set when:
+ *    a '1' bit is read from storage at startup.
+ *    a write request fails on some drives
+ *    a resync is aborted on a chunk with 'resync active' set
+ * It is cleared (and resync-active set) when a resync starts across all drives
+ * of the chunk.
+ *
+ *
+ * The "resync active" bit is set when:
+ *    a resync is started on all drives, and resync_needed is set.
+ *       resync_needed will be cleared (as long as resync_active wasn't already set).
+ * It is cleared when a resync completes.
+ *
+ * The counter counts pending write requests, plus the on-disk bit.
+ * When the counter is '1' and the resync bits are clear, the on-disk
+ * bit can be cleared aswell, thus setting the counter to 0.
+ * When we set a bit, or in the counter (to start a write), if the fields is
+ * 0, we first set the disk bit and set the counter to 1.
+ *
+ * If the counter is 0, the on-disk bit is clear and the stipe is clean
+ * Anything that dirties the stipe pushes the counter to 2 (at least)
+ * and sets the on-disk bit (lazily).
+ * If a periodic sweep find the counter at 2, it is decremented to 1.
+ * If the sweep find the counter at 1, the on-disk bit is cleared and the
+ * counter goes to zero.
+ *
+ * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
+ * counters as a fallback when "page" memory cannot be allocated:
+ *
+ * Normal case (page memory allocated):
+ *
+ *     page pointer (32-bit)
+ *
+ *     [ ] ------+
+ *               |
+ *               +-------> [   ][   ]..[   ] (4096 byte page == 2048 counters)
+ *                          c1   c2    c2048
+ *
+ * Hijacked case (page memory allocation failed):
+ *
+ *     hijacked page pointer (32-bit)
+ *
+ *     [		  ][		  ] (no page memory allocated)
+ *      counter #1 (16-bit) counter #2 (16-bit)
+ *
+ */
+
+#ifdef __KERNEL__
+
+#define PAGE_BITS (PAGE_SIZE << 3)
+#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
+
+typedef __u16 bitmap_counter_t;
+#define COUNTER_BITS 16
+#define COUNTER_BIT_SHIFT 4
+#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
+#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
+
+#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
+#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
+#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
+#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
+#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
+#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
+
+/* how many counters per page? */
+#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
+/* same, except a shift value for more efficient bitops */
+#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
+/* same, except a mask value for more efficient bitops */
+#define PAGE_COUNTER_MASK  (PAGE_COUNTER_RATIO - 1)
+
+#define BITMAP_BLOCK_SIZE 512
+#define BITMAP_BLOCK_SHIFT 9
+
+/* how many blocks per chunk? (this is variable) */
+#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT)
+#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT)
+#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1)
+
+/* when hijacked, the counters and bits represent even larger "chunks" */
+/* there will be 1024 chunks represented by each counter in the page pointers */
+#define PAGEPTR_BLOCK_RATIO(bitmap) \
+			(CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1)
+#define PAGEPTR_BLOCK_SHIFT(bitmap) \
+			(CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1)
+#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1)
+
+/*
+ * on-disk bitmap:
+ *
+ * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap
+ * file a page at a time. There's a superblock at the start of the file.
+ */
+
+/* map chunks (bits) to file pages - offset by the size of the superblock */
+#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3))
+
+#endif
+
+/*
+ * bitmap structures:
+ */
+
+#define BITMAP_MAGIC 0x6d746962
+
+/* use these for bitmap->flags and bitmap->sb->state bit-fields */
+enum bitmap_state {
+	BITMAP_ACTIVE = 0x001, /* the bitmap is in use */
+	BITMAP_STALE  = 0x002  /* the bitmap file is out of date or had -EIO */
+};
+
+/* the superblock at the front of the bitmap file -- little endian */
+typedef struct bitmap_super_s {
+	__u32 magic;        /*  0  BITMAP_MAGIC */
+	__u32 version;      /*  4  the bitmap major for now, could change... */
+	__u8  uuid[16];     /*  8  128 bit uuid - must match md device uuid */
+	__u64 events;       /* 24  event counter for the bitmap (1)*/
+	__u64 events_cleared;/*32  event counter when last bit cleared (2) */
+	__u64 sync_size;    /* 40  the size of the md device's sync range(3) */
+	__u32 state;        /* 48  bitmap state information */
+	__u32 chunksize;    /* 52  the bitmap chunk size in bytes */
+	__u32 daemon_sleep; /* 56  seconds between disk flushes */
+
+	__u8  pad[256 - 60]; /* set to zero */
+} bitmap_super_t;
+
+/* notes:
+ * (1) This event counter is updated before the eventcounter in the md superblock
+ *    When a bitmap is loaded, it is only accepted if this event counter is equal
+ *    to, or one greater than, the event counter in the superblock.
+ * (2) This event counter is updated when the other one is *if*and*only*if* the
+ *    array is not degraded.  As bits are not cleared when the array is degraded,
+ *    this represents the last time that any bits were cleared.
+ *    If a device is being added that has an event count with this value or
+ *    higher, it is accepted as conforming to the bitmap.
+ * (3)This is the number of sectors represented by the bitmap, and is the range that
+ *    resync happens across.  For raid1 and raid5/6 it is the size of individual
+ *    devices.  For raid10 it is the size of the array.
+ */
+
+#ifdef __KERNEL__
+
+/* the in-memory bitmap is represented by bitmap_pages */
+struct bitmap_page {
+	/*
+	 * map points to the actual memory page
+	 */
+	char *map;
+	/*
+	 * in emergencies (when map cannot be alloced), hijack the map
+	 * pointer and use it as two counters itself
+	 */
+	unsigned int hijacked:1;
+	/*
+	 * count of dirty bits on the page
+	 */
+	unsigned int  count:31;
+};
+
+/* keep track of bitmap file pages that have pending writes on them */
+struct page_list {
+	struct list_head list;
+	struct page *page;
+};
+
+/* the main bitmap structure - one per mddev */
+struct bitmap {
+	struct bitmap_page *bp;
+	unsigned long pages; /* total number of pages in the bitmap */
+	unsigned long missing_pages; /* number of pages not yet allocated */
+
+	mddev_t *mddev; /* the md device that the bitmap is for */
+
+	int counter_bits; /* how many bits per block counter */
+
+	/* bitmap chunksize -- how much data does each bit represent? */
+	unsigned long chunksize;
+	unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
+	unsigned long chunks; /* total number of data chunks for the array */
+
+	/* We hold a count on the chunk currently being synced, and drop
+	 * it when the last block is started.  If the resync is aborted
+	 * midway, we need to be able to drop that count, so we remember
+	 * the counted chunk..
+	 */
+	unsigned long syncchunk;
+
+	__u64	events_cleared;
+
+	/* bitmap spinlock */
+	spinlock_t lock;
+
+	long offset; /* offset from superblock if file is NULL */
+	struct file *file; /* backing disk file */
+	struct page *sb_page; /* cached copy of the bitmap file superblock */
+	struct page **filemap; /* list of cache pages for the file */
+	unsigned long *filemap_attr; /* attributes associated w/ filemap pages */
+	unsigned long file_pages; /* number of pages in the file */
+
+	unsigned long flags;
+
+	/*
+	 * the bitmap daemon - periodically wakes up and sweeps the bitmap
+	 * file, cleaning up bits and flushing out pages to disk as necessary
+	 */
+	unsigned long daemon_lastrun; /* jiffies of last run */
+	unsigned long daemon_sleep; /* how many seconds between updates? */
+
+	/*
+	 * bitmap_writeback_daemon waits for file-pages that have been written,
+	 * as there is no way to get a call-back when a page write completes.
+	 */
+	mdk_thread_t *writeback_daemon;
+	spinlock_t write_lock;
+	wait_queue_head_t write_wait;
+	struct list_head complete_pages;
+	mempool_t *write_pool;
+};
+
+/* the bitmap API */
+
+/* these are used only by md/bitmap */
+int  bitmap_create(mddev_t *mddev);
+void bitmap_destroy(mddev_t *mddev);
+int  bitmap_active(struct bitmap *bitmap);
+
+char *file_path(struct file *file, char *buf, int count);
+void bitmap_print_sb(struct bitmap *bitmap);
+int bitmap_update_sb(struct bitmap *bitmap);
+
+int  bitmap_setallbits(struct bitmap *bitmap);
+void bitmap_write_all(struct bitmap *bitmap);
+
+/* these are exported */
+int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors);
+void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
+		     int success);
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks);
+void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
+void bitmap_close_sync(struct bitmap *bitmap);
+
+int bitmap_unplug(struct bitmap *bitmap);
+int bitmap_daemon_work(struct bitmap *bitmap);
+#endif
+
+#endif
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index a6a67d102bf..ffa316ce4dc 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -60,7 +60,14 @@
  */
 #define MD_MAJOR_VERSION                0
 #define MD_MINOR_VERSION                90
-#define MD_PATCHLEVEL_VERSION           1
+/*
+ * MD_PATCHLEVEL_VERSION indicates kernel functionality.
+ * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
+ *     and major_version/minor_version accordingly
+ * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
+ *     in the super status byte
+ */
+#define MD_PATCHLEVEL_VERSION           2
 
 extern int register_md_personality (int p_num, mdk_personality_t *p);
 extern int unregister_md_personality (int p_num);
@@ -69,7 +76,7 @@ extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev),
 extern void md_unregister_thread (mdk_thread_t *thread);
 extern void md_wakeup_thread(mdk_thread_t *thread);
 extern void md_check_recovery(mddev_t *mddev);
-extern void md_write_start(mddev_t *mddev);
+extern void md_write_start(mddev_t *mddev, struct bio *bi);
 extern void md_write_end(mddev_t *mddev);
 extern void md_handle_safemode(mddev_t *mddev);
 extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
@@ -78,6 +85,12 @@ extern void md_unplug_mddev(mddev_t *mddev);
 
 extern void md_print_devices (void);
 
+extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
+			   sector_t sector, int size, struct page *page);
+extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+			struct page *page, int rw);
+
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 #endif 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index c9a0d4013be..8c14ba565a4 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -15,6 +15,9 @@
 #ifndef _MD_K_H
 #define _MD_K_H
 
+/* and dm-bio-list.h is not under include/linux because.... ??? */
+#include "../../../drivers/md/dm-bio-list.h"
+
 #define MD_RESERVED       0UL
 #define LINEAR            1UL
 #define RAID0             2UL
@@ -180,6 +183,10 @@ struct mdk_rdev_s
 
 	int desc_nr;			/* descriptor index in the superblock */
 	int raid_disk;			/* role of device in array */
+	int saved_raid_disk;		/* role that device used to have in the
+					 * array and could again if we did a partial
+					 * resync from the bitmap
+					 */
 
 	atomic_t	nr_pending;	/* number of pending requests.
 					 * only maintained for arrays that
@@ -252,6 +259,11 @@ struct mddev_s
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
 	sector_t			recovery_cp;
+
+	spinlock_t			write_lock;
+	wait_queue_head_t		sb_wait;	/* for waiting on superblock updates */
+	atomic_t			pending_writes;	/* number of active superblock writes */
+
 	unsigned int			safemode;	/* if set, update "clean" superblock
 							 * when no writes pending.
 							 */ 
@@ -260,6 +272,13 @@ struct mddev_s
 	atomic_t			writes_pending; 
 	request_queue_t			*queue;	/* for plugging ... */
 
+	struct bitmap                   *bitmap; /* the bitmap for the device */
+	struct file			*bitmap_file; /* the bitmap file */
+	long				bitmap_offset; /* offset from superblock of
+							* start of bitmap. May be
+							* negative, but not '0'
+							*/
+
 	struct list_head		all_mddevs;
 };
 
@@ -291,7 +310,7 @@ struct mdk_personality_s
 	int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev);
 	int (*hot_remove_disk) (mddev_t *mddev, int number);
 	int (*spare_active) (mddev_t *mddev);
-	int (*sync_request)(mddev_t *mddev, sector_t sector_nr, int go_faster);
+	sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
 	int (*resize) (mddev_t *mddev, sector_t sectors);
 	int (*reshape) (mddev_t *mddev, int raid_disks);
 	int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
@@ -334,6 +353,7 @@ typedef struct mdk_thread_s {
 	unsigned long           flags;
 	struct completion	*event;
 	struct task_struct	*tsk;
+	unsigned long		timeout;
 	const char		*name;
 } mdk_thread_t;
 
diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h
index 8ba95d67329..dc65cd43549 100644
--- a/include/linux/raid/md_p.h
+++ b/include/linux/raid/md_p.h
@@ -96,6 +96,7 @@ typedef struct mdp_device_descriptor_s {
 #define MD_SB_CLEAN		0
 #define MD_SB_ERRORS		1
 
+#define	MD_SB_BITMAP_PRESENT	8 /* bitmap may be present nearby */
 typedef struct mdp_superblock_s {
 	/*
 	 * Constant generic information
@@ -184,7 +185,7 @@ struct mdp_superblock_1 {
 	/* constant array information - 128 bytes */
 	__u32	magic;		/* MD_SB_MAGIC: 0xa92b4efc - little endian */
 	__u32	major_version;	/* 1 */
-	__u32	feature_map;	/* 0 for now */
+	__u32	feature_map;	/* bit 0 set if 'bitmap_offset' is meaningful */
 	__u32	pad0;		/* always set to 0 when writing */
 
 	__u8	set_uuid[16];	/* user-space generated. */
@@ -197,7 +198,11 @@ struct mdp_superblock_1 {
 
 	__u32	chunksize;	/* in 512byte sectors */
 	__u32	raid_disks;
-	__u8	pad1[128-96];	/* set to 0 when written */
+	__u32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
+				 * NOTE: signed, so bitmap can be before superblock
+				 * only meaningful of feature_map[0] is set.
+				 */
+	__u8	pad1[128-100];	/* set to 0 when written */
 
 	/* constant this-device information - 64 bytes */
 	__u64	data_offset;	/* sector start of data, often 0 */
diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h
index a2df5c2a42a..81da20ccec4 100644
--- a/include/linux/raid/md_u.h
+++ b/include/linux/raid/md_u.h
@@ -23,6 +23,7 @@
 #define GET_DISK_INFO		_IOR (MD_MAJOR, 0x12, mdu_disk_info_t)
 #define PRINT_RAID_DEBUG	_IO (MD_MAJOR, 0x13)
 #define RAID_AUTORUN		_IO (MD_MAJOR, 0x14)
+#define GET_BITMAP_FILE		_IOR (MD_MAJOR, 0x15, mdu_bitmap_file_t)
 
 /* configuration */
 #define CLEAR_ARRAY		_IO (MD_MAJOR, 0x20)
@@ -36,6 +37,7 @@
 #define HOT_ADD_DISK		_IO (MD_MAJOR, 0x28)
 #define SET_DISK_FAULTY		_IO (MD_MAJOR, 0x29)
 #define HOT_GENERATE_ERROR	_IO (MD_MAJOR, 0x2a)
+#define SET_BITMAP_FILE		_IOW (MD_MAJOR, 0x2b, int)
 
 /* usage */
 #define RUN_ARRAY		_IOW (MD_MAJOR, 0x30, mdu_param_t)
@@ -106,6 +108,11 @@ typedef struct mdu_start_info_s {
 
 } mdu_start_info_t;
 
+typedef struct mdu_bitmap_file_s
+{
+	char pathname[4096];
+} mdu_bitmap_file_t;
+
 typedef struct mdu_param_s
 {
 	int			personality;	/* 1,2,3,4 */
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
index abbfdd9afe1..9d93cf12e89 100644
--- a/include/linux/raid/raid1.h
+++ b/include/linux/raid/raid1.h
@@ -36,12 +36,21 @@ struct r1_private_data_s {
 	spinlock_t		device_lock;
 
 	struct list_head	retry_list;
+	/* queue pending writes and submit them on unplug */
+	struct bio_list		pending_bio_list;
+	/* queue of writes that have been unplugged */
+	struct bio_list		flushing_bio_list;
+
 	/* for use when syncing mirrors: */
 
 	spinlock_t		resync_lock;
-	int nr_pending;
-	int barrier;
+	int			nr_pending;
+	int			barrier;
 	sector_t		next_resync;
+	int			fullsync;  /* set to 1 if a full sync is needed,
+					    * (fresh device added).
+					    * Cleared when a sync completes.
+					    */
 
 	wait_queue_head_t	wait_idle;
 	wait_queue_head_t	wait_resume;
@@ -85,14 +94,17 @@ struct r1bio_s {
 	int			read_disk;
 
 	struct list_head	retry_list;
+	struct bitmap_update	*bitmap_update;
 	/*
 	 * if the IO is in WRITE direction, then multiple bios are used.
 	 * We choose the number when they are allocated.
 	 */
 	struct bio		*bios[0];
+	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
 };
 
 /* bits for r1bio.state */
 #define	R1BIO_Uptodate	0
 #define	R1BIO_IsSync	1
+#define	R1BIO_Degraded	2
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4dbb109022f..b58afd97a18 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -201,8 +201,8 @@ extern unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
-extern void arch_unmap_area(struct vm_area_struct *area);
-extern void arch_unmap_area_topdown(struct vm_area_struct *area);
+extern void arch_unmap_area(struct mm_struct *, unsigned long);
+extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 
 #define set_mm_counter(mm, member, value) (mm)->_##member = (value)
 #define get_mm_counter(mm, member) ((mm)->_##member)
@@ -218,9 +218,10 @@ struct mm_struct {
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
 				unsigned long pgoff, unsigned long flags);
-	void (*unmap_area) (struct vm_area_struct *area);
-	unsigned long mmap_base;		/* base of mmap area */
-	unsigned long free_area_cache;		/* first hole */
+	void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
+        unsigned long mmap_base;		/* base of mmap area */
+        unsigned long cached_hole_size;         /* if non-zero, the largest hole below free_area_cache */
+	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cc04f5cd228..d7c839a2184 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -193,7 +193,6 @@ struct skb_shared_info {
  *	@nfcache: Cache info
  *	@nfct: Associated connection, if any
  *	@nfctinfo: Relationship of this skb to the connection
- *	@nf_debug: Netfilter debugging
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *      @private: Data which is private to the HIPPI implementation
  *	@tc_index: Traffic control index
@@ -264,9 +263,6 @@ struct sk_buff {
 	__u32			nfcache;
 	__u32			nfctinfo;
 	struct nf_conntrack	*nfct;
-#ifdef CONFIG_NETFILTER_DEBUG
-        unsigned int		nf_debug;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif
@@ -1219,15 +1215,6 @@ static inline void nf_reset(struct sk_buff *skb)
 {
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
-#ifdef CONFIG_NETFILTER_DEBUG
-	skb->nf_debug = 0;
-#endif
-}
-static inline void nf_reset_debug(struct sk_buff *skb)
-{
-#ifdef CONFIG_NETFILTER_DEBUG
-	skb->nf_debug = 0;
-#endif
 }
 
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/include/linux/smp.h b/include/linux/smp.h
index dcf1db3b35d..9dfa3ee769a 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -92,10 +92,7 @@ void smp_prepare_boot_cpu(void);
 /*
  *	These macros fold the SMP functionality into a single CPU system
  */
-
-#if !defined(__smp_processor_id) || !defined(CONFIG_PREEMPT)
-# define smp_processor_id()			0
-#endif
+#define raw_smp_processor_id()			0
 #define hard_smp_processor_id()			0
 #define smp_call_function(func,info,retry,wait)	({ 0; })
 #define on_each_cpu(func,info,retry,wait)	({ func(info); 0; })
@@ -106,30 +103,25 @@ static inline void smp_send_reschedule(int cpu) { }
 #endif /* !SMP */
 
 /*
- * DEBUG_PREEMPT support: check whether smp_processor_id() is being
- * used in a preemption-safe way.
+ * smp_processor_id(): get the current CPU ID.
  *
- * An architecture has to enable this debugging code explicitly.
- * It can do so by renaming the smp_processor_id() macro to
- * __smp_processor_id().  This should only be done after some minimal
- * testing, because usually there are a number of false positives
- * that an architecture will trigger.
+ * if DEBUG_PREEMPT is enabled the we check whether it is
+ * used in a preemption-safe way. (smp_processor_id() is safe
+ * if it's used in a preemption-off critical section, or in
+ * a thread that is bound to the current CPU.)
  *
- * To fix a false positive (i.e. smp_processor_id() use that the
- * debugging code reports but which use for some reason is legal),
- * change the smp_processor_id() reference to _smp_processor_id(),
- * which is the nondebug variant.  NOTE: don't use this to hack around
- * real bugs.
+ * NOTE: raw_smp_processor_id() is for internal use only
+ * (smp_processor_id() is the preferred variant), but in rare
+ * instances it might also be used to turn off false positives
+ * (i.e. smp_processor_id() use that the debugging code reports but
+ * which use for some reason is legal). Don't use this to hack around
+ * the warning message, as your code might not work under PREEMPT.
  */
-#ifdef __smp_processor_id
-# if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
-   extern unsigned int smp_processor_id(void);
-# else
-#  define smp_processor_id() __smp_processor_id()
-# endif
-# define _smp_processor_id() __smp_processor_id()
+#ifdef CONFIG_DEBUG_PREEMPT
+  extern unsigned int debug_smp_processor_id(void);
+# define smp_processor_id() debug_smp_processor_id()
 #else
-# define _smp_processor_id() smp_processor_id()
+# define smp_processor_id() raw_smp_processor_id()
 #endif
 
 #define get_cpu()		({ preempt_disable(); smp_processor_id(); })
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 2709caf4d12..ab151bbb66d 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -111,6 +111,11 @@ struct rpc_procinfo {
 struct rpc_clnt *rpc_create_client(struct rpc_xprt *xprt, char *servname,
 				struct rpc_program *info,
 				u32 version, rpc_authflavor_t authflavor);
+struct rpc_clnt *rpc_new_client(struct rpc_xprt *xprt, char *servname,
+				struct rpc_program *info,
+				u32 version, rpc_authflavor_t authflavor);
+struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
+				struct rpc_program *, int);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
 int		rpc_shutdown_client(struct rpc_clnt *);
 int		rpc_destroy_client(struct rpc_clnt *);
@@ -129,6 +134,7 @@ void		rpc_clnt_sigmask(struct rpc_clnt *clnt, sigset_t *oldset);
 void		rpc_clnt_sigunmask(struct rpc_clnt *clnt, sigset_t *oldset);
 void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 size_t		rpc_max_payload(struct rpc_clnt *);
+int		rpc_ping(struct rpc_clnt *clnt, int flags);
 
 static __inline__
 int rpc_call(struct rpc_clnt *clnt, u32 proc, void *argp, void *resp, int flags)
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 99d17ed7ceb..4d77e90d0b3 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -31,7 +31,6 @@ struct rpc_wait_queue;
 struct rpc_wait {
 	struct list_head	list;		/* wait queue links */
 	struct list_head	links;		/* Links to related tasks */
-	wait_queue_head_t	waitq;		/* sync: sleep on this q */
 	struct rpc_wait_queue *	rpc_waitq;	/* RPC wait queue we're on */
 };
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 37003970cf2..5af8800e0ce 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -185,6 +185,17 @@ xdr_ressize_check(struct svc_rqst *rqstp, u32 *p)
 	return vec->iov_len <= PAGE_SIZE;
 }
 
+static inline struct page *
+svc_take_res_page(struct svc_rqst *rqstp)
+{
+	if (rqstp->rq_arghi <= rqstp->rq_argused)
+		return NULL;
+	rqstp->rq_arghi--;
+	rqstp->rq_respages[rqstp->rq_resused] =
+		rqstp->rq_argpages[rqstp->rq_arghi];
+	return rqstp->rq_respages[rqstp->rq_resused++];
+}
+
 static inline int svc_take_page(struct svc_rqst *rqstp)
 {
 	if (rqstp->rq_arghi <= rqstp->rq_argused)
@@ -240,9 +251,10 @@ struct svc_deferred_req {
 };
 
 /*
- * RPC program
+ * List of RPC programs on the same transport endpoint
  */
 struct svc_program {
+	struct svc_program *	pg_next;	/* other programs (same xprt) */
 	u32			pg_prog;	/* program number */
 	unsigned int		pg_lovers;	/* lowest version */
 	unsigned int		pg_hivers;	/* lowest version */
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 541dcf838ab..34ec3e8d99b 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -146,7 +146,8 @@ extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
 extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, int, int);
 extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, int);
-extern int read_bytes_from_xdr_buf(struct xdr_buf *buf, int base, void *obj, int len);
+extern int read_bytes_from_xdr_buf(struct xdr_buf *, int, void *, int);
+extern int write_bytes_to_xdr_buf(struct xdr_buf *, int, void *, int);
 
 /*
  * Helper structure for copying from an sk_buff.
@@ -160,7 +161,7 @@ typedef struct {
 
 typedef size_t (*skb_read_actor_t)(skb_reader_t *desc, void *to, size_t len);
 
-extern void xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int,
+extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int,
 		skb_reader_t *, skb_read_actor_t);
 
 struct socket;
@@ -168,6 +169,22 @@ struct sockaddr;
 extern int xdr_sendpages(struct socket *, struct sockaddr *, int,
 		struct xdr_buf *, unsigned int, int);
 
+extern int xdr_encode_word(struct xdr_buf *, int, u32);
+extern int xdr_decode_word(struct xdr_buf *, int, u32 *);
+
+struct xdr_array2_desc;
+typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem);
+struct xdr_array2_desc {
+	unsigned int elem_size;
+	unsigned int array_len;
+	xdr_xcode_elem_t xcode;
+};
+
+extern int xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
+                             struct xdr_array2_desc *desc);
+extern int xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
+			     struct xdr_array2_desc *desc);
+
 /*
  * Provide some simple tools for XDR buffer overflow-checking etc.
  */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3bbc41be9bd..2343f999e6e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -172,7 +172,8 @@ extern int rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
 /* linux/mm/vmscan.c */
-extern int try_to_free_pages(struct zone **, unsigned int, unsigned int);
+extern int try_to_free_pages(struct zone **, unsigned int);
+extern int zone_reclaim(struct zone *, unsigned int, unsigned int);
 extern int shrink_all_memory(int);
 extern int vm_swappiness;
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 38b58b30814..392da5a6dac 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -16,13 +16,13 @@ struct kobject;
 struct module;
 
 struct attribute {
-	char			* name;
+	const char		* name;
 	struct module 		* owner;
 	mode_t			mode;
 };
 
 struct attribute_group {
-	char			* name;
+	const char		* name;
 	struct attribute	** attrs;
 };
 
@@ -73,6 +73,7 @@ struct sysfs_dirent {
 	int			s_type;
 	umode_t			s_mode;
 	struct dentry		* s_dentry;
+	struct iattr		* s_iattr;
 };
 
 #define SYSFS_ROOT		0x0001
@@ -105,11 +106,11 @@ sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode);
 extern void
 sysfs_remove_file(struct kobject *, const struct attribute *);
 
-extern int 
-sysfs_create_link(struct kobject * kobj, struct kobject * target, char * name);
+extern int
+sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name);
 
 extern void
-sysfs_remove_link(struct kobject *, char * name);
+sysfs_remove_link(struct kobject *, const char * name);
 
 int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr);
 int sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr);
@@ -153,12 +154,12 @@ static inline void sysfs_remove_file(struct kobject * k, const struct attribute
 	;
 }
 
-static inline int sysfs_create_link(struct kobject * k, struct kobject * t, char * n)
+static inline int sysfs_create_link(struct kobject * k, struct kobject * t, const char * n)
 {
 	return 0;
 }
 
-static inline void sysfs_remove_link(struct kobject * k, char * name)
+static inline void sysfs_remove_link(struct kobject * k, const char * name)
 {
 	;
 }
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 2d1ac505853..3d508bf0840 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -287,15 +287,14 @@ struct usb_bus {
 
 	struct dentry *usbfs_dentry;	/* usbfs dentry entry for the bus */
 
-	struct class_device class_dev;	/* class device for this bus */
+	struct class_device *class_dev;	/* class device for this bus */
+	struct kref kref;		/* handles reference counting this bus */
 	void (*release)(struct usb_bus *bus);	/* function to destroy this bus's memory */
 #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 	struct mon_bus *mon_bus;	/* non-null when associated */
 	int monitored;			/* non-zero when monitored */
 #endif
 };
-#define	to_usb_bus(d) container_of(d, struct usb_bus, class_dev)
-
 
 /* -------------------------------------------------------------------------- */
 
diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index d68391a9b9f..f0d423300d8 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -196,6 +196,7 @@ struct xfrm_usersa_info {
 	__u8				flags;
 #define XFRM_STATE_NOECN	1
 #define XFRM_STATE_DECAP_DSCP	2
+#define XFRM_STATE_NOPMTUDISC	4
 };
 
 struct xfrm_usersa_id {