Merge ../torvalds-2.6/

35 files changed, 1191 insertions, 681 deletions

diff --git a/include/linux/ata.h b/include/linux/ata.h
index d2873b732bb..94f77cce27f 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -129,6 +129,7 @@ enum {
 	ATA_CMD_READ_EXT	= 0x25,
 	ATA_CMD_WRITE		= 0xCA,
 	ATA_CMD_WRITE_EXT	= 0x35,
+	ATA_CMD_WRITE_FUA_EXT	= 0x3D,
 	ATA_CMD_PIO_READ	= 0x20,
 	ATA_CMD_PIO_READ_EXT	= 0x24,
 	ATA_CMD_PIO_WRITE	= 0x30,
@@ -137,10 +138,13 @@ enum {
 	ATA_CMD_READ_MULTI_EXT	= 0x29,
 	ATA_CMD_WRITE_MULTI	= 0xC5,
 	ATA_CMD_WRITE_MULTI_EXT	= 0x39,
+	ATA_CMD_WRITE_MULTI_FUA_EXT = 0xCE,
 	ATA_CMD_SET_FEATURES	= 0xEF,
 	ATA_CMD_PACKET		= 0xA0,
 	ATA_CMD_VERIFY		= 0x40,
 	ATA_CMD_VERIFY_EXT	= 0x42,
+ 	ATA_CMD_STANDBYNOW1	= 0xE0,
+ 	ATA_CMD_IDLEIMMEDIATE	= 0xE1,
 	ATA_CMD_INIT_DEV_PARAMS	= 0x91,
 
 	/* SETFEATURES stuff */
@@ -192,6 +196,7 @@ enum {
 	ATA_TFLAG_DEVICE	= (1 << 2), /* enable r/w to device reg */
 	ATA_TFLAG_WRITE		= (1 << 3), /* data dir: host->dev==1 (write) */
 	ATA_TFLAG_LBA		= (1 << 4), /* enable LBA */
+	ATA_TFLAG_FUA		= (1 << 5), /* enable FUA */
 };
 
 enum ata_tf_protocols {
@@ -245,7 +250,8 @@ struct ata_taskfile {
 #define ata_id_is_sata(id)	((id)[93] == 0)
 #define ata_id_rahead_enabled(id) ((id)[85] & (1 << 6))
 #define ata_id_wcache_enabled(id) ((id)[85] & (1 << 5))
-#define ata_id_has_flush(id) ((id)[83] & (1 << 12))
+#define ata_id_has_fua(id)	((id)[84] & (1 << 6))
+#define ata_id_has_flush(id)	((id)[83] & (1 << 12))
 #define ata_id_has_flush_ext(id) ((id)[83] & (1 << 13))
 #define ata_id_has_lba48(id)	((id)[83] & (1 << 10))
 #define ata_id_has_wcache(id)	((id)[82] & (1 << 5))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a18500d196e..fb098537742 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -102,7 +102,7 @@ void copy_io_context(struct io_context **pdst, struct io_context **psrc);
 void swap_io_context(struct io_context **ioc1, struct io_context **ioc2);
 
 struct request;
-typedef void (rq_end_io_fn)(struct request *);
+typedef void (rq_end_io_fn)(struct request *, int);
 
 struct request_list {
 	int count[2];
@@ -207,6 +207,7 @@ enum rq_flag_bits {
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
 	__REQ_HARDBARRIER,	/* may not be passed by drive either */
+	__REQ_FUA,		/* forced unit access */
 	__REQ_CMD,		/* is a regular fs rw request */
 	__REQ_NOMERGE,		/* don't touch this for merging */
 	__REQ_STARTED,		/* drive already may have started this one */
@@ -230,9 +231,7 @@ enum rq_flag_bits {
 	__REQ_PM_SUSPEND,	/* suspend request */
 	__REQ_PM_RESUME,	/* resume request */
 	__REQ_PM_SHUTDOWN,	/* shutdown request */
-	__REQ_BAR_PREFLUSH,	/* barrier pre-flush done */
-	__REQ_BAR_POSTFLUSH,	/* barrier post-flush */
-	__REQ_BAR_FLUSH,	/* rq is the flush request */
+	__REQ_ORDERED_COLOR,	/* is before or after barrier */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -241,6 +240,7 @@ enum rq_flag_bits {
 #define REQ_SORTED	(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
 #define REQ_HARDBARRIER	(1 << __REQ_HARDBARRIER)
+#define REQ_FUA		(1 << __REQ_FUA)
 #define REQ_CMD		(1 << __REQ_CMD)
 #define REQ_NOMERGE	(1 << __REQ_NOMERGE)
 #define REQ_STARTED	(1 << __REQ_STARTED)
@@ -260,9 +260,7 @@ enum rq_flag_bits {
 #define REQ_PM_SUSPEND	(1 << __REQ_PM_SUSPEND)
 #define REQ_PM_RESUME	(1 << __REQ_PM_RESUME)
 #define REQ_PM_SHUTDOWN	(1 << __REQ_PM_SHUTDOWN)
-#define REQ_BAR_PREFLUSH	(1 << __REQ_BAR_PREFLUSH)
-#define REQ_BAR_POSTFLUSH	(1 << __REQ_BAR_POSTFLUSH)
-#define REQ_BAR_FLUSH	(1 << __REQ_BAR_FLUSH)
+#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
 
 /*
  * State information carried for REQ_PM_SUSPEND and REQ_PM_RESUME
@@ -292,8 +290,7 @@ struct bio_vec;
 typedef int (merge_bvec_fn) (request_queue_t *, struct bio *, struct bio_vec *);
 typedef void (activity_fn) (void *data, int rw);
 typedef int (issue_flush_fn) (request_queue_t *, struct gendisk *, sector_t *);
-typedef int (prepare_flush_fn) (request_queue_t *, struct request *);
-typedef void (end_flush_fn) (request_queue_t *, struct request *);
+typedef void (prepare_flush_fn) (request_queue_t *, struct request *);
 
 enum blk_queue_state {
 	Queue_down,
@@ -335,7 +332,6 @@ struct request_queue
 	activity_fn		*activity_fn;
 	issue_flush_fn		*issue_flush_fn;
 	prepare_flush_fn	*prepare_flush_fn;
-	end_flush_fn		*end_flush_fn;
 
 	/*
 	 * Dispatch queue sorting
@@ -420,14 +416,11 @@ struct request_queue
 	/*
 	 * reserved for flush operations
 	 */
-	struct request		*flush_rq;
-	unsigned char		ordered;
-};
-
-enum {
-	QUEUE_ORDERED_NONE,
-	QUEUE_ORDERED_TAG,
-	QUEUE_ORDERED_FLUSH,
+	unsigned int		ordered, next_ordered, ordseq;
+	int			orderr, ordcolor;
+	struct request		pre_flush_rq, bar_rq, post_flush_rq;
+	struct request		*orig_bar_rq;
+	unsigned int		bi_size;
 };
 
 #define RQ_INACTIVE		(-1)
@@ -445,12 +438,51 @@ enum {
 #define QUEUE_FLAG_REENTER	6	/* Re-entrancy avoidance */
 #define QUEUE_FLAG_PLUGGED	7	/* queue is plugged */
 #define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
-#define QUEUE_FLAG_FLUSH	9	/* doing barrier flush sequence */
+
+enum {
+	/*
+	 * Hardbarrier is supported with one of the following methods.
+	 *
+	 * NONE		: hardbarrier unsupported
+	 * DRAIN	: ordering by draining is enough
+	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
+	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
+	 * TAG		: ordering by tag is enough
+	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
+	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
+	 */
+	QUEUE_ORDERED_NONE	= 0x00,
+	QUEUE_ORDERED_DRAIN	= 0x01,
+	QUEUE_ORDERED_TAG	= 0x02,
+
+	QUEUE_ORDERED_PREFLUSH	= 0x10,
+	QUEUE_ORDERED_POSTFLUSH	= 0x20,
+	QUEUE_ORDERED_FUA	= 0x40,
+
+	QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN |
+			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
+	QUEUE_ORDERED_DRAIN_FUA	= QUEUE_ORDERED_DRAIN |
+			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
+	QUEUE_ORDERED_TAG_FLUSH	= QUEUE_ORDERED_TAG |
+			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
+	QUEUE_ORDERED_TAG_FUA	= QUEUE_ORDERED_TAG |
+			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
+
+	/*
+	 * Ordered operation sequence
+	 */
+	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
+	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
+	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
+	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
+	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
+	QUEUE_ORDSEQ_DONE	= 0x20,
+};
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
-#define blk_queue_flushing(q)	test_bit(QUEUE_FLAG_FLUSH, &(q)->queue_flags)
+#define blk_queue_flushing(q)	((q)->ordseq)
 
 #define blk_fs_request(rq)	((rq)->flags & REQ_CMD)
 #define blk_pc_request(rq)	((rq)->flags & REQ_BLOCK_PC)
@@ -466,8 +498,7 @@ enum {
 
 #define blk_sorted_rq(rq)	((rq)->flags & REQ_SORTED)
 #define blk_barrier_rq(rq)	((rq)->flags & REQ_HARDBARRIER)
-#define blk_barrier_preflush(rq)	((rq)->flags & REQ_BAR_PREFLUSH)
-#define blk_barrier_postflush(rq)	((rq)->flags & REQ_BAR_POSTFLUSH)
+#define blk_fua_rq(rq)		((rq)->flags & REQ_FUA)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
@@ -560,7 +591,7 @@ extern void register_disk(struct gendisk *dev);
 extern void generic_make_request(struct bio *bio);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(request_queue_t *, struct request *);
-extern void blk_end_sync_rq(struct request *rq);
+extern void blk_end_sync_rq(struct request *rq, int error);
 extern void blk_attempt_remerge(request_queue_t *, struct request *);
 extern struct request *blk_get_request(request_queue_t *, int, gfp_t);
 extern void blk_insert_request(request_queue_t *, struct request *, int, void *);
@@ -582,8 +613,7 @@ extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_io
 extern int blk_execute_rq(request_queue_t *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(request_queue_t *, struct gendisk *,
-				  struct request *, int,
-				  void (*done)(struct request *));
+				  struct request *, int, rq_end_io_fn *);
 
 static inline request_queue_t *bdev_get_queue(struct block_device *bdev)
 {
@@ -614,7 +644,7 @@ static inline void blk_run_address_space(struct address_space *mapping)
  */
 extern int end_that_request_first(struct request *, int, int);
 extern int end_that_request_chunk(struct request *, int, int);
-extern void end_that_request_last(struct request *);
+extern void end_that_request_last(struct request *, int);
 extern void end_request(struct request *req, int uptodate);
 
 /*
@@ -665,11 +695,12 @@ extern void blk_queue_prep_rq(request_queue_t *, prep_rq_fn *pfn);
 extern void blk_queue_merge_bvec(request_queue_t *, merge_bvec_fn *);
 extern void blk_queue_dma_alignment(request_queue_t *, int);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern void blk_queue_ordered(request_queue_t *, int);
+extern int blk_queue_ordered(request_queue_t *, unsigned, prepare_flush_fn *);
 extern void blk_queue_issue_flush_fn(request_queue_t *, issue_flush_fn *);
-extern struct request *blk_start_pre_flush(request_queue_t *,struct request *);
-extern int blk_complete_barrier_rq(request_queue_t *, struct request *, int);
-extern int blk_complete_barrier_rq_locked(request_queue_t *, struct request *, int);
+extern int blk_do_ordered(request_queue_t *, struct request **);
+extern unsigned blk_ordered_cur_seq(request_queue_t *);
+extern unsigned blk_ordered_req_seq(struct request *);
+extern void blk_ordered_complete_seq(request_queue_t *, unsigned, int);
 
 extern int blk_rq_map_sg(request_queue_t *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 3b03b0b868d..993da8cc970 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -43,50 +43,38 @@ typedef struct bootmem_data {
 extern unsigned long __init bootmem_bootmap_pages (unsigned long);
 extern unsigned long __init init_bootmem (unsigned long addr, unsigned long memend);
 extern void __init free_bootmem (unsigned long addr, unsigned long size);
-extern void * __init __alloc_bootmem_limit (unsigned long size, unsigned long align, unsigned long goal, unsigned long limit);
+extern void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal);
+extern void * __init __alloc_bootmem_low(unsigned long size,
+					 unsigned long align,
+					 unsigned long goal);
+extern void * __init __alloc_bootmem_low_node(pg_data_t *pgdat,
+					      unsigned long size,
+					      unsigned long align,
+					      unsigned long goal);
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 extern void __init reserve_bootmem (unsigned long addr, unsigned long size);
 #define alloc_bootmem(x) \
 	__alloc_bootmem((x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low(x) \
-	__alloc_bootmem((x), SMP_CACHE_BYTES, 0)
+	__alloc_bootmem_low((x), SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
 	__alloc_bootmem((x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages(x) \
-	__alloc_bootmem((x), PAGE_SIZE, 0)
-
-#define alloc_bootmem_limit(x, limit)						\
-	__alloc_bootmem_limit((x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS), (limit))
-#define alloc_bootmem_low_limit(x, limit)			\
-	__alloc_bootmem_limit((x), SMP_CACHE_BYTES, 0, (limit))
-#define alloc_bootmem_pages_limit(x, limit)					\
-	__alloc_bootmem_limit((x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS), (limit))
-#define alloc_bootmem_low_pages_limit(x, limit)		\
-	__alloc_bootmem_limit((x), PAGE_SIZE, 0, (limit))
-
+	__alloc_bootmem_low((x), PAGE_SIZE, 0)
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 extern unsigned long __init free_all_bootmem (void);
-
+extern void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal);
 extern unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn);
 extern void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size);
 extern void __init free_bootmem_node (pg_data_t *pgdat, unsigned long addr, unsigned long size);
 extern unsigned long __init free_all_bootmem_node (pg_data_t *pgdat);
-extern void * __init __alloc_bootmem_node_limit (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit);
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 #define alloc_bootmem_node(pgdat, x) \
 	__alloc_bootmem_node((pgdat), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node(pgdat, x) \
 	__alloc_bootmem_node((pgdat), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages_node(pgdat, x) \
-	__alloc_bootmem_node((pgdat), (x), PAGE_SIZE, 0)
-
-#define alloc_bootmem_node_limit(pgdat, x, limit)				\
-	__alloc_bootmem_node_limit((pgdat), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS), (limit))
-#define alloc_bootmem_pages_node_limit(pgdat, x, limit)				\
-	__alloc_bootmem_node_limit((pgdat), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS), (limit))
-#define alloc_bootmem_low_pages_node_limit(pgdat, x, limit)		\
-	__alloc_bootmem_node_limit((pgdat), (x), PAGE_SIZE, 0, (limit))
-
+	__alloc_bootmem_low_node((pgdat), (x), PAGE_SIZE, 0)
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
@@ -123,15 +111,5 @@ extern void *__init alloc_large_system_hash(const char *tablename,
 #endif
 extern int __initdata hashdist;		/* Distribute hashes across NUMA nodes? */
 
-static inline void *__alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal)
-{
-	return __alloc_bootmem_limit(size, align, goal, 0);
-}
-
-static inline void *__alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align,
-				     unsigned long goal)
-{
-	return __alloc_bootmem_node_limit(pgdat, size, align, goal, 0);
-}
 
 #endif /* _LINUX_BOOTMEM_H */
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
new file mode 100644
index 00000000000..acffb8c9073
--- /dev/null
+++ b/include/linux/configfs.h
@@ -0,0 +1,205 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * configfs.h - definitions for the device driver filesystem
+ *
+ * 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., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * Based on kobject.h:
+ *      Copyright (c) 2002-2003	Patrick Mochel
+ *      Copyright (c) 2002-2003	Open Source Development Labs
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ *
+ * Please read Documentation/filesystems/configfs.txt before using the
+ * configfs interface, ESPECIALLY the parts about reference counts and
+ * item destructors.
+ */
+
+#ifndef _CONFIGFS_H_
+#define _CONFIGFS_H_
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/kref.h>
+
+#include <asm/atomic.h>
+#include <asm/semaphore.h>
+
+#define CONFIGFS_ITEM_NAME_LEN	20
+
+struct module;
+
+struct configfs_item_operations;
+struct configfs_group_operations;
+struct configfs_attribute;
+struct configfs_subsystem;
+
+struct config_item {
+	char			*ci_name;
+	char			ci_namebuf[CONFIGFS_ITEM_NAME_LEN];
+	struct kref		ci_kref;
+	struct list_head	ci_entry;
+	struct config_item	*ci_parent;
+	struct config_group	*ci_group;
+	struct config_item_type	*ci_type;
+	struct dentry		*ci_dentry;
+};
+
+extern int config_item_set_name(struct config_item *, const char *, ...);
+
+static inline char *config_item_name(struct config_item * item)
+{
+	return item->ci_name;
+}
+
+extern void config_item_init(struct config_item *);
+extern void config_item_init_type_name(struct config_item *item,
+				       const char *name,
+				       struct config_item_type *type);
+extern void config_item_cleanup(struct config_item *);
+
+extern struct config_item * config_item_get(struct config_item *);
+extern void config_item_put(struct config_item *);
+
+struct config_item_type {
+	struct module				*ct_owner;
+	struct configfs_item_operations		*ct_item_ops;
+	struct configfs_group_operations	*ct_group_ops;
+	struct configfs_attribute		**ct_attrs;
+};
+
+
+/**
+ *	group - a group of config_items of a specific type, belonging
+ *	to a specific subsystem.
+ */
+
+struct config_group {
+	struct config_item		cg_item;
+	struct list_head		cg_children;
+	struct configfs_subsystem 	*cg_subsys;
+	struct config_group		**default_groups;
+};
+
+
+extern void config_group_init(struct config_group *group);
+extern void config_group_init_type_name(struct config_group *group,
+					const char *name,
+					struct config_item_type *type);
+
+
+static inline struct config_group *to_config_group(struct config_item *item)
+{
+	return item ? container_of(item,struct config_group,cg_item) : NULL;
+}
+
+static inline struct config_group *config_group_get(struct config_group *group)
+{
+	return group ? to_config_group(config_item_get(&group->cg_item)) : NULL;
+}
+
+static inline void config_group_put(struct config_group *group)
+{
+	config_item_put(&group->cg_item);
+}
+
+extern struct config_item *config_group_find_obj(struct config_group *, const char *);
+
+
+struct configfs_attribute {
+	char			*ca_name;
+	struct module 		*ca_owner;
+	mode_t			ca_mode;
+};
+
+
+/*
+ * If allow_link() exists, the item can symlink(2) out to other
+ * items.  If the item is a group, it may support mkdir(2).
+ * Groups supply one of make_group() and make_item().  If the
+ * group supports make_group(), one can create group children.  If it
+ * supports make_item(), one can create config_item children.  If it has
+ * default_groups on group->default_groups, it has automatically created
+ * group children.  default_groups may coexist alongsize make_group() or
+ * make_item(), but if the group wishes to have only default_groups
+ * children (disallowing mkdir(2)), it need not provide either function.
+ * If the group has commit(), it supports pending and commited (active)
+ * items.
+ */
+struct configfs_item_operations {
+	void (*release)(struct config_item *);
+	ssize_t	(*show_attribute)(struct config_item *, struct configfs_attribute *,char *);
+	ssize_t	(*store_attribute)(struct config_item *,struct configfs_attribute *,const char *, size_t);
+	int (*allow_link)(struct config_item *src, struct config_item *target);
+	int (*drop_link)(struct config_item *src, struct config_item *target);
+};
+
+struct configfs_group_operations {
+	struct config_item *(*make_item)(struct config_group *group, const char *name);
+	struct config_group *(*make_group)(struct config_group *group, const char *name);
+	int (*commit_item)(struct config_item *item);
+	void (*drop_item)(struct config_group *group, struct config_item *item);
+};
+
+
+
+/**
+ * Use these macros to make defining attributes easier. See include/linux/device.h
+ * for examples..
+ */
+
+#if 0
+#define __ATTR(_name,_mode,_show,_store) { \
+	.attr = {.ca_name = __stringify(_name), .ca_mode = _mode, .ca_owner = THIS_MODULE },	\
+	.show	= _show,					\
+	.store	= _store,					\
+}
+
+#define __ATTR_RO(_name) { \
+	.attr	= { .ca_name = __stringify(_name), .ca_mode = 0444, .ca_owner = THIS_MODULE },	\
+	.show	= _name##_show,	\
+}
+
+#define __ATTR_NULL { .attr = { .name = NULL } }
+
+#define attr_name(_attr) (_attr).attr.name
+#endif
+
+
+struct configfs_subsystem {
+	struct config_group	su_group;
+	struct semaphore	su_sem;
+};
+
+static inline struct configfs_subsystem *to_configfs_subsystem(struct config_group *group)
+{
+	return group ?
+		container_of(group, struct configfs_subsystem, su_group) :
+		NULL;
+}
+
+int configfs_register_subsystem(struct configfs_subsystem *subsys);
+void configfs_unregister_subsystem(struct configfs_subsystem *subsys);
+
+#endif  /* __KERNEL__ */
+
+#endif /* _CONFIGFS_H_ */
diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h
index f5eb6b6cd10..fa75ba0d635 100644
--- a/include/linux/dm-ioctl.h
+++ b/include/linux/dm-ioctl.h
@@ -272,9 +272,9 @@ typedef char ioctl_struct[308];
 #define DM_TARGET_MSG	 _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	4
+#define DM_VERSION_MINOR	5
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2005-01-12)"
+#define DM_VERSION_EXTRA	"-ioctl (2005-10-04)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
@@ -301,8 +301,13 @@ typedef char ioctl_struct[308];
 #define DM_BUFFER_FULL_FLAG	(1 << 8) /* Out */
 
 /*
- * Set this to improve performance when you aren't going to use open_count
+ * Set this to improve performance when you aren't going to use open_count.
  */
 #define DM_SKIP_BDGET_FLAG	(1 << 9) /* In */
 
+/*
+ * Set this to avoid attempting to freeze any filesystem when suspending.
+ */
+#define DM_SKIP_LOCKFS_FLAG	(1 << 10) /* In */
+
 #endif				/* _LINUX_DM_IOCTL_H */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index a74c27e460b..fb80fa44c4d 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -130,6 +130,7 @@ extern int elv_try_last_merge(request_queue_t *, struct bio *);
 #define ELEVATOR_INSERT_FRONT	1
 #define ELEVATOR_INSERT_BACK	2
 #define ELEVATOR_INSERT_SORT	3
+#define ELEVATOR_INSERT_REQUEUE	4
 
 /*
  * return values from elevator_may_queue_fn
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc35b6ac778..115e72be25d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -302,6 +302,37 @@ struct iattr {
  */
 #include <linux/quota.h>
 
+/** 
+ * enum positive_aop_returns - aop return codes with specific semantics
+ *
+ * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
+ * 			    completed, that the page is still locked, and
+ * 			    should be considered active.  The VM uses this hint
+ * 			    to return the page to the active list -- it won't
+ * 			    be a candidate for writeback again in the near
+ * 			    future.  Other callers must be careful to unlock
+ * 			    the page if they get this return.  Returned by
+ * 			    writepage(); 
+ *
+ * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
+ *  			unlocked it and the page might have been truncated.
+ *  			The caller should back up to acquiring a new page and
+ *  			trying again.  The aop will be taking reasonable
+ *  			precautions not to livelock.  If the caller held a page
+ *  			reference, it should drop it before retrying.  Returned
+ *  			by readpage(), prepare_write(), and commit_write().
+ *
+ * address_space_operation functions return these large constants to indicate
+ * special semantics to the caller.  These are much larger than the bytes in a
+ * page to allow for functions that return the number of bytes operated on in a
+ * given page.
+ */
+
+enum positive_aop_returns {
+	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
+	AOP_TRUNCATED_PAGE	= 0x80001,
+};
+
 /*
  * oh the beauties of C type declarations.
  */
@@ -1019,6 +1050,7 @@ struct inode_operations {
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
+	void (*truncate_range)(struct inode *, loff_t, loff_t);
 };
 
 struct seq_file;
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index b76b558b03d..528959c52f1 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -14,7 +14,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 3
+#define FUSE_KERNEL_MINOR_VERSION 5
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -53,6 +53,9 @@ struct fuse_kstatfs {
 	__u64	ffree;
 	__u32	bsize;
 	__u32	namelen;
+	__u32	frsize;
+	__u32	padding;
+	__u32	spare[6];
 };
 
 #define FATTR_MODE	(1 << 0)
@@ -105,12 +108,8 @@ enum fuse_opcode {
 	FUSE_CREATE        = 35
 };
 
-/* Conservative buffer size for the client */
-#define FUSE_MAX_IN 8192
-
-#define FUSE_NAME_MAX 1024
-#define FUSE_SYMLINK_MAX 4096
-#define FUSE_XATTR_SIZE_MAX 4096
+/* The read buffer is required to be at least 8k, but may be much larger */
+#define FUSE_MIN_READ_BUFFER 8192
 
 struct fuse_entry_out {
 	__u64	nodeid;		/* Inode ID */
@@ -213,6 +212,8 @@ struct fuse_write_out {
 	__u32	padding;
 };
 
+#define FUSE_COMPAT_STATFS_SIZE 48
+
 struct fuse_statfs_out {
 	struct fuse_kstatfs st;
 };
@@ -243,9 +244,16 @@ struct fuse_access_in {
 	__u32	padding;
 };
 
-struct fuse_init_in_out {
+struct fuse_init_in {
+	__u32	major;
+	__u32	minor;
+};
+
+struct fuse_init_out {
 	__u32	major;
 	__u32	minor;
+	__u32	unused[3];
+	__u32	max_write;
 };
 
 struct fuse_in_header {
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 1056717ee50..68d82ad6b17 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -22,7 +22,7 @@ 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 *alloc_huge_page(void);
+struct page *alloc_huge_page(struct vm_area_struct *, unsigned long);
 void free_huge_page(struct page *);
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, int write_access);
@@ -97,7 +97,7 @@ static inline unsigned long hugetlb_total_pages(void)
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
 						do { } while (0)
-#define alloc_huge_page()			({ NULL; })
+#define alloc_huge_page(vma, addr)		({ NULL; })
 #define free_huge_page(p)			({ (void)(p); BUG(); })
 #define hugetlb_fault(mm, vma, addr, write)	({ BUG(); 0; })
 
diff --git a/include/linux/i2o.h b/include/linux/i2o.h
index d79c8a4bc4f..9ba80679666 100644
--- a/include/linux/i2o.h
+++ b/include/linux/i2o.h
@@ -30,6 +30,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>	/* work_struct */
+#include <linux/mempool.h>
 
 #include <asm/io.h>
 #include <asm/semaphore.h>	/* Needed for MUTEX init macros */
@@ -38,6 +39,355 @@
 #define I2O_QUEUE_EMPTY		0xffffffff
 
 /*
+ *	Cache strategies
+ */
+
+/*	The NULL strategy leaves everything up to the controller. This tends to be a
+ *	pessimal but functional choice.
+ */
+#define CACHE_NULL		0
+/*	Prefetch data when reading. We continually attempt to load the next 32 sectors
+ *	into the controller cache.
+ */
+#define CACHE_PREFETCH		1
+/*	Prefetch data when reading. We sometimes attempt to load the next 32 sectors
+ *	into the controller cache. When an I/O is less <= 8K we assume its probably
+ *	not sequential and don't prefetch (default)
+ */
+#define CACHE_SMARTFETCH	2
+/*	Data is written to the cache and then out on to the disk. The I/O must be
+ *	physically on the medium before the write is acknowledged (default without
+ *	NVRAM)
+ */
+#define CACHE_WRITETHROUGH	17
+/*	Data is written to the cache and then out on to the disk. The controller
+ *	is permitted to write back the cache any way it wants. (default if battery
+ *	backed NVRAM is present). It can be useful to set this for swap regardless of
+ *	battery state.
+ */
+#define CACHE_WRITEBACK		18
+/*	Optimise for under powered controllers, especially on RAID1 and RAID0. We
+ *	write large I/O's directly to disk bypassing the cache to avoid the extra
+ *	memory copy hits. Small writes are writeback cached
+ */
+#define CACHE_SMARTBACK		19
+/*	Optimise for under powered controllers, especially on RAID1 and RAID0. We
+ *	write large I/O's directly to disk bypassing the cache to avoid the extra
+ *	memory copy hits. Small writes are writethrough cached. Suitable for devices
+ *	lacking battery backup
+ */
+#define CACHE_SMARTTHROUGH	20
+
+/*
+ *	Ioctl structures
+ */
+
+#define 	BLKI2OGRSTRAT	_IOR('2', 1, int)
+#define 	BLKI2OGWSTRAT	_IOR('2', 2, int)
+#define 	BLKI2OSRSTRAT	_IOW('2', 3, int)
+#define 	BLKI2OSWSTRAT	_IOW('2', 4, int)
+
+/*
+ *	I2O Function codes
+ */
+
+/*
+ *	Executive Class
+ */
+#define	I2O_CMD_ADAPTER_ASSIGN		0xB3
+#define	I2O_CMD_ADAPTER_READ		0xB2
+#define	I2O_CMD_ADAPTER_RELEASE		0xB5
+#define	I2O_CMD_BIOS_INFO_SET		0xA5
+#define	I2O_CMD_BOOT_DEVICE_SET		0xA7
+#define	I2O_CMD_CONFIG_VALIDATE		0xBB
+#define	I2O_CMD_CONN_SETUP		0xCA
+#define	I2O_CMD_DDM_DESTROY		0xB1
+#define	I2O_CMD_DDM_ENABLE		0xD5
+#define	I2O_CMD_DDM_QUIESCE		0xC7
+#define	I2O_CMD_DDM_RESET		0xD9
+#define	I2O_CMD_DDM_SUSPEND		0xAF
+#define	I2O_CMD_DEVICE_ASSIGN		0xB7
+#define	I2O_CMD_DEVICE_RELEASE		0xB9
+#define	I2O_CMD_HRT_GET			0xA8
+#define	I2O_CMD_ADAPTER_CLEAR		0xBE
+#define	I2O_CMD_ADAPTER_CONNECT		0xC9
+#define	I2O_CMD_ADAPTER_RESET		0xBD
+#define	I2O_CMD_LCT_NOTIFY		0xA2
+#define	I2O_CMD_OUTBOUND_INIT		0xA1
+#define	I2O_CMD_PATH_ENABLE		0xD3
+#define	I2O_CMD_PATH_QUIESCE		0xC5
+#define	I2O_CMD_PATH_RESET		0xD7
+#define	I2O_CMD_STATIC_MF_CREATE	0xDD
+#define	I2O_CMD_STATIC_MF_RELEASE	0xDF
+#define	I2O_CMD_STATUS_GET		0xA0
+#define	I2O_CMD_SW_DOWNLOAD		0xA9
+#define	I2O_CMD_SW_UPLOAD		0xAB
+#define	I2O_CMD_SW_REMOVE		0xAD
+#define	I2O_CMD_SYS_ENABLE		0xD1
+#define	I2O_CMD_SYS_MODIFY		0xC1
+#define	I2O_CMD_SYS_QUIESCE		0xC3
+#define	I2O_CMD_SYS_TAB_SET		0xA3
+
+/*
+ * Utility Class
+ */
+#define I2O_CMD_UTIL_NOP		0x00
+#define I2O_CMD_UTIL_ABORT		0x01
+#define I2O_CMD_UTIL_CLAIM		0x09
+#define I2O_CMD_UTIL_RELEASE		0x0B
+#define I2O_CMD_UTIL_PARAMS_GET		0x06
+#define I2O_CMD_UTIL_PARAMS_SET		0x05
+#define I2O_CMD_UTIL_EVT_REGISTER	0x13
+#define I2O_CMD_UTIL_EVT_ACK		0x14
+#define I2O_CMD_UTIL_CONFIG_DIALOG	0x10
+#define I2O_CMD_UTIL_DEVICE_RESERVE	0x0D
+#define I2O_CMD_UTIL_DEVICE_RELEASE	0x0F
+#define I2O_CMD_UTIL_LOCK		0x17
+#define I2O_CMD_UTIL_LOCK_RELEASE	0x19
+#define I2O_CMD_UTIL_REPLY_FAULT_NOTIFY	0x15
+
+/*
+ * SCSI Host Bus Adapter Class
+ */
+#define I2O_CMD_SCSI_EXEC		0x81
+#define I2O_CMD_SCSI_ABORT		0x83
+#define I2O_CMD_SCSI_BUSRESET		0x27
+
+/*
+ * Bus Adapter Class
+ */
+#define I2O_CMD_BUS_ADAPTER_RESET	0x85
+#define I2O_CMD_BUS_RESET		0x87
+#define I2O_CMD_BUS_SCAN		0x89
+#define I2O_CMD_BUS_QUIESCE		0x8b
+
+/*
+ * Random Block Storage Class
+ */
+#define I2O_CMD_BLOCK_READ		0x30
+#define I2O_CMD_BLOCK_WRITE		0x31
+#define I2O_CMD_BLOCK_CFLUSH		0x37
+#define I2O_CMD_BLOCK_MLOCK		0x49
+#define I2O_CMD_BLOCK_MUNLOCK		0x4B
+#define I2O_CMD_BLOCK_MMOUNT		0x41
+#define I2O_CMD_BLOCK_MEJECT		0x43
+#define I2O_CMD_BLOCK_POWER		0x70
+
+#define I2O_CMD_PRIVATE			0xFF
+
+/* Command status values  */
+
+#define I2O_CMD_IN_PROGRESS	0x01
+#define I2O_CMD_REJECTED	0x02
+#define I2O_CMD_FAILED		0x03
+#define I2O_CMD_COMPLETED	0x04
+
+/* I2O API function return values */
+
+#define I2O_RTN_NO_ERROR			0
+#define I2O_RTN_NOT_INIT			1
+#define I2O_RTN_FREE_Q_EMPTY			2
+#define I2O_RTN_TCB_ERROR			3
+#define I2O_RTN_TRANSACTION_ERROR		4
+#define I2O_RTN_ADAPTER_ALREADY_INIT		5
+#define I2O_RTN_MALLOC_ERROR			6
+#define I2O_RTN_ADPTR_NOT_REGISTERED		7
+#define I2O_RTN_MSG_REPLY_TIMEOUT		8
+#define I2O_RTN_NO_STATUS			9
+#define I2O_RTN_NO_FIRM_VER			10
+#define	I2O_RTN_NO_LINK_SPEED			11
+
+/* Reply message status defines for all messages */
+
+#define I2O_REPLY_STATUS_SUCCESS                    	0x00
+#define I2O_REPLY_STATUS_ABORT_DIRTY                	0x01
+#define I2O_REPLY_STATUS_ABORT_NO_DATA_TRANSFER     	0x02
+#define	I2O_REPLY_STATUS_ABORT_PARTIAL_TRANSFER		0x03
+#define	I2O_REPLY_STATUS_ERROR_DIRTY			0x04
+#define	I2O_REPLY_STATUS_ERROR_NO_DATA_TRANSFER		0x05
+#define	I2O_REPLY_STATUS_ERROR_PARTIAL_TRANSFER		0x06
+#define	I2O_REPLY_STATUS_PROCESS_ABORT_DIRTY		0x08
+#define	I2O_REPLY_STATUS_PROCESS_ABORT_NO_DATA_TRANSFER	0x09
+#define	I2O_REPLY_STATUS_PROCESS_ABORT_PARTIAL_TRANSFER	0x0A
+#define	I2O_REPLY_STATUS_TRANSACTION_ERROR		0x0B
+#define	I2O_REPLY_STATUS_PROGRESS_REPORT		0x80
+
+/* Status codes and Error Information for Parameter functions */
+
+#define I2O_PARAMS_STATUS_SUCCESS		0x00
+#define I2O_PARAMS_STATUS_BAD_KEY_ABORT		0x01
+#define I2O_PARAMS_STATUS_BAD_KEY_CONTINUE   	0x02
+#define I2O_PARAMS_STATUS_BUFFER_FULL		0x03
+#define I2O_PARAMS_STATUS_BUFFER_TOO_SMALL	0x04
+#define I2O_PARAMS_STATUS_FIELD_UNREADABLE	0x05
+#define I2O_PARAMS_STATUS_FIELD_UNWRITEABLE	0x06
+#define I2O_PARAMS_STATUS_INSUFFICIENT_FIELDS	0x07
+#define I2O_PARAMS_STATUS_INVALID_GROUP_ID	0x08
+#define I2O_PARAMS_STATUS_INVALID_OPERATION	0x09
+#define I2O_PARAMS_STATUS_NO_KEY_FIELD		0x0A
+#define I2O_PARAMS_STATUS_NO_SUCH_FIELD		0x0B
+#define I2O_PARAMS_STATUS_NON_DYNAMIC_GROUP	0x0C
+#define I2O_PARAMS_STATUS_OPERATION_ERROR	0x0D
+#define I2O_PARAMS_STATUS_SCALAR_ERROR		0x0E
+#define I2O_PARAMS_STATUS_TABLE_ERROR		0x0F
+#define I2O_PARAMS_STATUS_WRONG_GROUP_TYPE	0x10
+
+/* DetailedStatusCode defines for Executive, DDM, Util and Transaction error
+ * messages: Table 3-2 Detailed Status Codes.*/
+
+#define I2O_DSC_SUCCESS                        0x0000
+#define I2O_DSC_BAD_KEY                        0x0002
+#define I2O_DSC_TCL_ERROR                      0x0003
+#define I2O_DSC_REPLY_BUFFER_FULL              0x0004
+#define I2O_DSC_NO_SUCH_PAGE                   0x0005
+#define I2O_DSC_INSUFFICIENT_RESOURCE_SOFT     0x0006
+#define I2O_DSC_INSUFFICIENT_RESOURCE_HARD     0x0007
+#define I2O_DSC_CHAIN_BUFFER_TOO_LARGE         0x0009
+#define I2O_DSC_UNSUPPORTED_FUNCTION           0x000A
+#define I2O_DSC_DEVICE_LOCKED                  0x000B
+#define I2O_DSC_DEVICE_RESET                   0x000C
+#define I2O_DSC_INAPPROPRIATE_FUNCTION         0x000D
+#define I2O_DSC_INVALID_INITIATOR_ADDRESS      0x000E
+#define I2O_DSC_INVALID_MESSAGE_FLAGS          0x000F
+#define I2O_DSC_INVALID_OFFSET                 0x0010
+#define I2O_DSC_INVALID_PARAMETER              0x0011
+#define I2O_DSC_INVALID_REQUEST                0x0012
+#define I2O_DSC_INVALID_TARGET_ADDRESS         0x0013
+#define I2O_DSC_MESSAGE_TOO_LARGE              0x0014
+#define I2O_DSC_MESSAGE_TOO_SMALL              0x0015
+#define I2O_DSC_MISSING_PARAMETER              0x0016
+#define I2O_DSC_TIMEOUT                        0x0017
+#define I2O_DSC_UNKNOWN_ERROR                  0x0018
+#define I2O_DSC_UNKNOWN_FUNCTION               0x0019
+#define I2O_DSC_UNSUPPORTED_VERSION            0x001A
+#define I2O_DSC_DEVICE_BUSY                    0x001B
+#define I2O_DSC_DEVICE_NOT_AVAILABLE           0x001C
+
+/* DetailedStatusCode defines for Block Storage Operation: Table 6-7 Detailed
+   Status Codes.*/
+
+#define I2O_BSA_DSC_SUCCESS               0x0000
+#define I2O_BSA_DSC_MEDIA_ERROR           0x0001
+#define I2O_BSA_DSC_ACCESS_ERROR          0x0002
+#define I2O_BSA_DSC_DEVICE_FAILURE        0x0003
+#define I2O_BSA_DSC_DEVICE_NOT_READY      0x0004
+#define I2O_BSA_DSC_MEDIA_NOT_PRESENT     0x0005
+#define I2O_BSA_DSC_MEDIA_LOCKED          0x0006
+#define I2O_BSA_DSC_MEDIA_FAILURE         0x0007
+#define I2O_BSA_DSC_PROTOCOL_FAILURE      0x0008
+#define I2O_BSA_DSC_BUS_FAILURE           0x0009
+#define I2O_BSA_DSC_ACCESS_VIOLATION      0x000A
+#define I2O_BSA_DSC_WRITE_PROTECTED       0x000B
+#define I2O_BSA_DSC_DEVICE_RESET          0x000C
+#define I2O_BSA_DSC_VOLUME_CHANGED        0x000D
+#define I2O_BSA_DSC_TIMEOUT               0x000E
+
+/* FailureStatusCodes, Table 3-3 Message Failure Codes */
+
+#define I2O_FSC_TRANSPORT_SERVICE_SUSPENDED             0x81
+#define I2O_FSC_TRANSPORT_SERVICE_TERMINATED            0x82
+#define I2O_FSC_TRANSPORT_CONGESTION                    0x83
+#define I2O_FSC_TRANSPORT_FAILURE                       0x84
+#define I2O_FSC_TRANSPORT_STATE_ERROR                   0x85
+#define I2O_FSC_TRANSPORT_TIME_OUT                      0x86
+#define I2O_FSC_TRANSPORT_ROUTING_FAILURE               0x87
+#define I2O_FSC_TRANSPORT_INVALID_VERSION               0x88
+#define I2O_FSC_TRANSPORT_INVALID_OFFSET                0x89
+#define I2O_FSC_TRANSPORT_INVALID_MSG_FLAGS             0x8A
+#define I2O_FSC_TRANSPORT_FRAME_TOO_SMALL               0x8B
+#define I2O_FSC_TRANSPORT_FRAME_TOO_LARGE               0x8C
+#define I2O_FSC_TRANSPORT_INVALID_TARGET_ID             0x8D
+#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_ID          0x8E
+#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_CONTEXT     0x8F
+#define I2O_FSC_TRANSPORT_UNKNOWN_FAILURE               0xFF
+
+/* Device Claim Types */
+#define	I2O_CLAIM_PRIMARY					0x01000000
+#define	I2O_CLAIM_MANAGEMENT					0x02000000
+#define	I2O_CLAIM_AUTHORIZED					0x03000000
+#define	I2O_CLAIM_SECONDARY					0x04000000
+
+/* Message header defines for VersionOffset */
+#define I2OVER15	0x0001
+#define I2OVER20	0x0002
+
+/* Default is 1.5 */
+#define I2OVERSION	I2OVER15
+
+#define SGL_OFFSET_0    I2OVERSION
+#define SGL_OFFSET_4    (0x0040 | I2OVERSION)
+#define SGL_OFFSET_5    (0x0050 | I2OVERSION)
+#define SGL_OFFSET_6    (0x0060 | I2OVERSION)
+#define SGL_OFFSET_7    (0x0070 | I2OVERSION)
+#define SGL_OFFSET_8    (0x0080 | I2OVERSION)
+#define SGL_OFFSET_9    (0x0090 | I2OVERSION)
+#define SGL_OFFSET_10   (0x00A0 | I2OVERSION)
+#define SGL_OFFSET_11   (0x00B0 | I2OVERSION)
+#define SGL_OFFSET_12   (0x00C0 | I2OVERSION)
+#define SGL_OFFSET(x)   (((x)<<4) | I2OVERSION)
+
+/* Transaction Reply Lists (TRL) Control Word structure */
+#define TRL_SINGLE_FIXED_LENGTH		0x00
+#define TRL_SINGLE_VARIABLE_LENGTH	0x40
+#define TRL_MULTIPLE_FIXED_LENGTH	0x80
+
+ /* msg header defines for MsgFlags */
+#define MSG_STATIC	0x0100
+#define MSG_64BIT_CNTXT	0x0200
+#define MSG_MULTI_TRANS	0x1000
+#define MSG_FAIL	0x2000
+#define MSG_FINAL	0x4000
+#define MSG_REPLY	0x8000
+
+ /* minimum size msg */
+#define THREE_WORD_MSG_SIZE	0x00030000
+#define FOUR_WORD_MSG_SIZE	0x00040000
+#define FIVE_WORD_MSG_SIZE	0x00050000
+#define SIX_WORD_MSG_SIZE	0x00060000
+#define SEVEN_WORD_MSG_SIZE	0x00070000
+#define EIGHT_WORD_MSG_SIZE	0x00080000
+#define NINE_WORD_MSG_SIZE	0x00090000
+#define TEN_WORD_MSG_SIZE	0x000A0000
+#define ELEVEN_WORD_MSG_SIZE	0x000B0000
+#define I2O_MESSAGE_SIZE(x)	((x)<<16)
+
+/* special TID assignments */
+#define ADAPTER_TID		0
+#define HOST_TID		1
+
+/* outbound queue defines */
+#define I2O_MAX_OUTBOUND_MSG_FRAMES	128
+#define I2O_OUTBOUND_MSG_FRAME_SIZE	128	/* in 32-bit words */
+
+/* inbound queue definitions */
+#define I2O_MSG_INPOOL_MIN		32
+#define I2O_INBOUND_MSG_FRAME_SIZE	128	/* in 32-bit words */
+
+#define I2O_POST_WAIT_OK	0
+#define I2O_POST_WAIT_TIMEOUT	-ETIMEDOUT
+
+#define I2O_CONTEXT_LIST_MIN_LENGTH	15
+#define I2O_CONTEXT_LIST_USED		0x01
+#define I2O_CONTEXT_LIST_DELETED	0x02
+
+/* timeouts */
+#define I2O_TIMEOUT_INIT_OUTBOUND_QUEUE	15
+#define I2O_TIMEOUT_MESSAGE_GET		5
+#define I2O_TIMEOUT_RESET		30
+#define I2O_TIMEOUT_STATUS_GET		5
+#define I2O_TIMEOUT_LCT_GET		360
+#define I2O_TIMEOUT_SCSI_SCB_ABORT	240
+
+/* retries */
+#define I2O_HRT_GET_TRIES		3
+#define I2O_LCT_GET_TRIES		3
+
+/* defines for max_sectors and max_phys_segments */
+#define I2O_MAX_SECTORS			1024
+#define I2O_MAX_SECTORS_LIMITED		128
+#define I2O_MAX_PHYS_SEGMENTS		MAX_PHYS_SEGMENTS
+
+/*
  *	Message structures
  */
 struct i2o_message {
@@ -58,6 +408,12 @@ struct i2o_message {
 	u32 body[0];
 };
 
+/* MFA and I2O message used by mempool */
+struct i2o_msg_mfa {
+	u32 mfa;		/* MFA returned by the controller */
+	struct i2o_message msg;	/* I2O message */
+};
+
 /*
  *	Each I2O device entity has one of these. There is one per device.
  */
@@ -130,6 +486,15 @@ struct i2o_dma {
 };
 
 /*
+ *	Contains slab cache and mempool information
+ */
+struct i2o_pool {
+	char *name;
+	kmem_cache_t *slab;
+	mempool_t *mempool;
+};
+
+/*
  *	Contains IO mapped address information
  */
 struct i2o_io {
@@ -174,8 +539,6 @@ struct i2o_controller {
 	void __iomem *irq_status;	/* Interrupt status register address */
 	void __iomem *irq_mask;	/* Interrupt mask register address */
 
-	/* Dynamic LCT related data */
-
 	struct i2o_dma status;	/* IOP status block */
 
 	struct i2o_dma hrt;	/* HW Resource Table */
@@ -188,6 +551,8 @@ struct i2o_controller {
 	struct i2o_io in_queue;	/* inbound message queue Host->IOP */
 	struct i2o_dma out_queue;	/* outbound message queue IOP->Host */
 
+	struct i2o_pool in_msg;	/* mempool for inbound messages */
+
 	unsigned int battery:1;	/* Has a battery backup */
 	unsigned int io_alloc:1;	/* An I/O resource was allocated */
 	unsigned int mem_alloc:1;	/* A memory resource was allocated */
@@ -196,7 +561,6 @@ struct i2o_controller {
 	struct resource mem_resource;	/* Mem resource allocated to the IOP */
 
 	struct device device;
-	struct class_device *classdev;	/* I2O controller class device */
 	struct i2o_device *exec;	/* Executive */
 #if BITS_PER_LONG == 64
 	spinlock_t context_list_lock;	/* lock for context_list */
@@ -247,16 +611,13 @@ struct i2o_sys_tbl {
 extern struct list_head i2o_controllers;
 
 /* Message functions */
-static inline u32 i2o_msg_get(struct i2o_controller *,
-			      struct i2o_message __iomem **);
-extern u32 i2o_msg_get_wait(struct i2o_controller *,
-			    struct i2o_message __iomem **, int);
-static inline void i2o_msg_post(struct i2o_controller *, u32);
-static inline int i2o_msg_post_wait(struct i2o_controller *, u32,
-				    unsigned long);
-extern int i2o_msg_post_wait_mem(struct i2o_controller *, u32, unsigned long,
-				 struct i2o_dma *);
-extern void i2o_msg_nop(struct i2o_controller *, u32);
+static inline struct i2o_message *i2o_msg_get(struct i2o_controller *);
+extern struct i2o_message *i2o_msg_get_wait(struct i2o_controller *, int);
+static inline void i2o_msg_post(struct i2o_controller *, struct i2o_message *);
+static inline int i2o_msg_post_wait(struct i2o_controller *,
+				    struct i2o_message *, unsigned long);
+extern int i2o_msg_post_wait_mem(struct i2o_controller *, struct i2o_message *,
+				 unsigned long, struct i2o_dma *);
 static inline void i2o_flush_reply(struct i2o_controller *, u32);
 
 /* IOP functions */
@@ -384,10 +745,10 @@ static inline u16 i2o_sg_tablesize(struct i2o_controller *c, u16 body_size)
 static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr,
 					    size_t size,
 					    enum dma_data_direction direction,
-					    u32 __iomem ** sg_ptr)
+					    u32 ** sg_ptr)
 {
 	u32 sg_flags;
-	u32 __iomem *mptr = *sg_ptr;
+	u32 *mptr = *sg_ptr;
 	dma_addr_t dma_addr;
 
 	switch (direction) {
@@ -405,16 +766,16 @@ static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr,
 	if (!dma_mapping_error(dma_addr)) {
 #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64
 		if ((sizeof(dma_addr_t) > 4) && c->pae_support) {
-			writel(0x7C020002, mptr++);
-			writel(PAGE_SIZE, mptr++);
+			*mptr++ = cpu_to_le32(0x7C020002);
+			*mptr++ = cpu_to_le32(PAGE_SIZE);
 		}
 #endif
 
-		writel(sg_flags | size, mptr++);
-		writel(i2o_dma_low(dma_addr), mptr++);
+		*mptr++ = cpu_to_le32(sg_flags | size);
+		*mptr++ = cpu_to_le32(i2o_dma_low(dma_addr));
 #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64
 		if ((sizeof(dma_addr_t) > 4) && c->pae_support)
-			writel(i2o_dma_high(dma_addr), mptr++);
+			*mptr++ = cpu_to_le32(i2o_dma_high(dma_addr));
 #endif
 		*sg_ptr = mptr;
 	}
@@ -439,10 +800,10 @@ static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr,
 static inline int i2o_dma_map_sg(struct i2o_controller *c,
 				 struct scatterlist *sg, int sg_count,
 				 enum dma_data_direction direction,
-				 u32 __iomem ** sg_ptr)
+				 u32 ** sg_ptr)
 {
 	u32 sg_flags;
-	u32 __iomem *mptr = *sg_ptr;
+	u32 *mptr = *sg_ptr;
 
 	switch (direction) {
 	case DMA_TO_DEVICE:
@@ -461,19 +822,19 @@ static inline int i2o_dma_map_sg(struct i2o_controller *c,
 
 #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64
 	if ((sizeof(dma_addr_t) > 4) && c->pae_support) {
-		writel(0x7C020002, mptr++);
-		writel(PAGE_SIZE, mptr++);
+		*mptr++ = cpu_to_le32(0x7C020002);
+		*mptr++ = cpu_to_le32(PAGE_SIZE);
 	}
 #endif
 
 	while (sg_count-- > 0) {
 		if (!sg_count)
 			sg_flags |= 0xC0000000;
-		writel(sg_flags | sg_dma_len(sg), mptr++);
-		writel(i2o_dma_low(sg_dma_address(sg)), mptr++);
+		*mptr++ = cpu_to_le32(sg_flags | sg_dma_len(sg));
+		*mptr++ = cpu_to_le32(i2o_dma_low(sg_dma_address(sg)));
 #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64
 		if ((sizeof(dma_addr_t) > 4) && c->pae_support)
-			writel(i2o_dma_high(sg_dma_address(sg)), mptr++);
+			*mptr++ = cpu_to_le32(i2o_dma_high(sg_dma_address(sg)));
 #endif
 		sg++;
 	}
@@ -563,6 +924,64 @@ static inline int i2o_dma_realloc(struct device *dev, struct i2o_dma *addr,
 	return 0;
 };
 
+/*
+ *	i2o_pool_alloc - Allocate an slab cache and mempool
+ *	@mempool: pointer to struct i2o_pool to write data into.
+ *	@name: name which is used to identify cache
+ *	@size: size of each object
+ *	@min_nr: minimum number of objects
+ *
+ *	First allocates a slab cache with name and size. Then allocates a
+ *	mempool which uses the slab cache for allocation and freeing.
+ *
+ *	Returns 0 on success or negative error code on failure.
+ */
+static inline int i2o_pool_alloc(struct i2o_pool *pool, const char *name,
+				 size_t size, int min_nr)
+{
+	pool->name = kmalloc(strlen(name) + 1, GFP_KERNEL);
+	if (!pool->name)
+		goto exit;
+	strcpy(pool->name, name);
+
+	pool->slab =
+	    kmem_cache_create(pool->name, size, 0, SLAB_HWCACHE_ALIGN, NULL,
+			      NULL);
+	if (!pool->slab)
+		goto free_name;
+
+	pool->mempool =
+	    mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab,
+			   pool->slab);
+	if (!pool->mempool)
+		goto free_slab;
+
+	return 0;
+
+      free_slab:
+	kmem_cache_destroy(pool->slab);
+
+      free_name:
+	kfree(pool->name);
+
+      exit:
+	return -ENOMEM;
+};
+
+/*
+ *	i2o_pool_free - Free slab cache and mempool again
+ *	@mempool: pointer to struct i2o_pool which should be freed
+ *
+ *	Note that you have to return all objects to the mempool again before
+ *	calling i2o_pool_free().
+ */
+static inline void i2o_pool_free(struct i2o_pool *pool)
+{
+	mempool_destroy(pool->mempool);
+	kmem_cache_destroy(pool->slab);
+	kfree(pool->name);
+};
+
 /* I2O driver (OSM) functions */
 extern int i2o_driver_register(struct i2o_driver *);
 extern void i2o_driver_unregister(struct i2o_driver *);
@@ -638,39 +1057,89 @@ extern int i2o_exec_lct_get(struct i2o_controller *);
 #define kobj_to_i2o_device(kobj) to_i2o_device(container_of(kobj, struct device, kobj))
 
 /**
+ *	i2o_out_to_virt - Turn an I2O message to a virtual address
+ *	@c: controller
+ *	@m: message engine value
+ *
+ *	Turn a receive message from an I2O controller bus address into
+ *	a Linux virtual address. The shared page frame is a linear block
+ *	so we simply have to shift the offset. This function does not
+ *	work for sender side messages as they are ioremap objects
+ *	provided by the I2O controller.
+ */
+static inline struct i2o_message *i2o_msg_out_to_virt(struct i2o_controller *c,
+						      u32 m)
+{
+	BUG_ON(m < c->out_queue.phys
+	       || m >= c->out_queue.phys + c->out_queue.len);
+
+	return c->out_queue.virt + (m - c->out_queue.phys);
+};
+
+/**
+ *	i2o_msg_in_to_virt - Turn an I2O message to a virtual address
+ *	@c: controller
+ *	@m: message engine value
+ *
+ *	Turn a send message from an I2O controller bus address into
+ *	a Linux virtual address. The shared page frame is a linear block
+ *	so we simply have to shift the offset. This function does not
+ *	work for receive side messages as they are kmalloc objects
+ *	in a different pool.
+ */
+static inline struct i2o_message __iomem *i2o_msg_in_to_virt(struct
+							     i2o_controller *c,
+							     u32 m)
+{
+	return c->in_queue.virt + m;
+};
+
+/**
  *	i2o_msg_get - obtain an I2O message from the IOP
  *	@c: I2O controller
- *	@msg: pointer to a I2O message pointer
  *
- *	This function tries to get a message slot. If no message slot is
+ *	This function tries to get a message frame. If no message frame is
  *	available do not wait until one is availabe (see also i2o_msg_get_wait).
+ *	The returned pointer to the message frame is not in I/O memory, it is
+ *	allocated from a mempool. But because a MFA is allocated from the
+ *	controller too it is guaranteed that i2o_msg_post() will never fail.
  *
- *	On a success the message is returned and the pointer to the message is
- *	set in msg. The returned message is the physical page frame offset
- *	address from the read port (see the i2o spec). If no message is
- *	available returns I2O_QUEUE_EMPTY and msg is leaved untouched.
+ *	On a success a pointer to the message frame is returned. If the message
+ *	queue is empty -EBUSY is returned and if no memory is available -ENOMEM
+ *	is returned.
  */
-static inline u32 i2o_msg_get(struct i2o_controller *c,
-			      struct i2o_message __iomem ** msg)
+static inline struct i2o_message *i2o_msg_get(struct i2o_controller *c)
 {
-	u32 m = readl(c->in_port);
-
-	if (m != I2O_QUEUE_EMPTY)
-		*msg = c->in_queue.virt + m;
+	struct i2o_msg_mfa *mmsg = mempool_alloc(c->in_msg.mempool, GFP_ATOMIC);
+	if (!mmsg)
+		return ERR_PTR(-ENOMEM);
+
+	mmsg->mfa = readl(c->in_port);
+	if (mmsg->mfa == I2O_QUEUE_EMPTY) {
+		mempool_free(mmsg, c->in_msg.mempool);
+		return ERR_PTR(-EBUSY);
+	}
 
-	return m;
+	return &mmsg->msg;
 };
 
 /**
  *	i2o_msg_post - Post I2O message to I2O controller
  *	@c: I2O controller to which the message should be send
- *	@m: the message identifier
+ *	@msg: message returned by i2o_msg_get()
  *
- *	Post the message to the I2O controller.
+ *	Post the message to the I2O controller and return immediately.
  */
-static inline void i2o_msg_post(struct i2o_controller *c, u32 m)
+static inline void i2o_msg_post(struct i2o_controller *c,
+				struct i2o_message *msg)
 {
-	writel(m, c->in_port);
+	struct i2o_msg_mfa *mmsg;
+
+	mmsg = container_of(msg, struct i2o_msg_mfa, msg);
+	memcpy_toio(i2o_msg_in_to_virt(c, mmsg->mfa), msg,
+		    (le32_to_cpu(msg->u.head[0]) >> 16) << 2);
+	writel(mmsg->mfa, c->in_port);
+	mempool_free(mmsg, c->in_msg.mempool);
 };
 
 /**
@@ -685,62 +1154,66 @@ static inline void i2o_msg_post(struct i2o_controller *c, u32 m)
  *
  *	Returns 0 on success or negative error code on failure.
  */
-static inline int i2o_msg_post_wait(struct i2o_controller *c, u32 m,
+static inline int i2o_msg_post_wait(struct i2o_controller *c,
+				    struct i2o_message *msg,
 				    unsigned long timeout)
 {
-	return i2o_msg_post_wait_mem(c, m, timeout, NULL);
+	return i2o_msg_post_wait_mem(c, msg, timeout, NULL);
 };
 
 /**
- *	i2o_flush_reply - Flush reply from I2O controller
- *	@c: I2O controller
- *	@m: the message identifier
+ *	i2o_msg_nop_mfa - Returns a fetched MFA back to the controller
+ *	@c: I2O controller from which the MFA was fetched
+ *	@mfa: MFA which should be returned
  *
- *	The I2O controller must be informed that the reply message is not needed
- *	anymore. If you forget to flush the reply, the message frame can't be
- *	used by the controller anymore and is therefore lost.
+ *	This function must be used for preserved messages, because i2o_msg_nop()
+ *	also returns the allocated memory back to the msg_pool mempool.
  */
-static inline void i2o_flush_reply(struct i2o_controller *c, u32 m)
+static inline void i2o_msg_nop_mfa(struct i2o_controller *c, u32 mfa)
 {
-	writel(m, c->out_port);
+	struct i2o_message __iomem *msg;
+	u32 nop[3] = {
+		THREE_WORD_MSG_SIZE | SGL_OFFSET_0,
+		I2O_CMD_UTIL_NOP << 24 | HOST_TID << 12 | ADAPTER_TID,
+		0x00000000
+	};
+
+	msg = i2o_msg_in_to_virt(c, mfa);
+	memcpy_toio(msg, nop, sizeof(nop));
+	writel(mfa, c->in_port);
 };
 
 /**
- *	i2o_out_to_virt - Turn an I2O message to a virtual address
- *	@c: controller
- *	@m: message engine value
+ *	i2o_msg_nop - Returns a message which is not used
+ *	@c: I2O controller from which the message was created
+ *	@msg: message which should be returned
  *
- *	Turn a receive message from an I2O controller bus address into
- *	a Linux virtual address. The shared page frame is a linear block
- *	so we simply have to shift the offset. This function does not
- *	work for sender side messages as they are ioremap objects
- *	provided by the I2O controller.
+ *	If you fetch a message via i2o_msg_get, and can't use it, you must
+ *	return the message with this function. Otherwise the MFA is lost as well
+ *	as the allocated memory from the mempool.
  */
-static inline struct i2o_message *i2o_msg_out_to_virt(struct i2o_controller *c,
-						      u32 m)
+static inline void i2o_msg_nop(struct i2o_controller *c,
+			       struct i2o_message *msg)
 {
-	BUG_ON(m < c->out_queue.phys
-	       || m >= c->out_queue.phys + c->out_queue.len);
+	struct i2o_msg_mfa *mmsg;
+	mmsg = container_of(msg, struct i2o_msg_mfa, msg);
 
-	return c->out_queue.virt + (m - c->out_queue.phys);
+	i2o_msg_nop_mfa(c, mmsg->mfa);
+	mempool_free(mmsg, c->in_msg.mempool);
 };
 
 /**
- *	i2o_msg_in_to_virt - Turn an I2O message to a virtual address
- *	@c: controller
- *	@m: message engine value
+ *	i2o_flush_reply - Flush reply from I2O controller
+ *	@c: I2O controller
+ *	@m: the message identifier
  *
- *	Turn a send message from an I2O controller bus address into
- *	a Linux virtual address. The shared page frame is a linear block
- *	so we simply have to shift the offset. This function does not
- *	work for receive side messages as they are kmalloc objects
- *	in a different pool.
+ *	The I2O controller must be informed that the reply message is not needed
+ *	anymore. If you forget to flush the reply, the message frame can't be
+ *	used by the controller anymore and is therefore lost.
  */
-static inline struct i2o_message __iomem *i2o_msg_in_to_virt(struct
-							     i2o_controller *c,
-							     u32 m)
+static inline void i2o_flush_reply(struct i2o_controller *c, u32 m)
 {
-	return c->in_queue.virt + m;
+	writel(m, c->out_port);
 };
 
 /*
@@ -779,350 +1252,5 @@ extern void i2o_dump_message(struct i2o_message *);
 extern void i2o_dump_hrt(struct i2o_controller *c);
 extern void i2o_debug_state(struct i2o_controller *c);
 
-/*
- *	Cache strategies
- */
-
-/*	The NULL strategy leaves everything up to the controller. This tends to be a
- *	pessimal but functional choice.
- */
-#define CACHE_NULL		0
-/*	Prefetch data when reading. We continually attempt to load the next 32 sectors
- *	into the controller cache.
- */
-#define CACHE_PREFETCH		1
-/*	Prefetch data when reading. We sometimes attempt to load the next 32 sectors
- *	into the controller cache. When an I/O is less <= 8K we assume its probably
- *	not sequential and don't prefetch (default)
- */
-#define CACHE_SMARTFETCH	2
-/*	Data is written to the cache and then out on to the disk. The I/O must be
- *	physically on the medium before the write is acknowledged (default without
- *	NVRAM)
- */
-#define CACHE_WRITETHROUGH	17
-/*	Data is written to the cache and then out on to the disk. The controller
- *	is permitted to write back the cache any way it wants. (default if battery
- *	backed NVRAM is present). It can be useful to set this for swap regardless of
- *	battery state.
- */
-#define CACHE_WRITEBACK		18
-/*	Optimise for under powered controllers, especially on RAID1 and RAID0. We
- *	write large I/O's directly to disk bypassing the cache to avoid the extra
- *	memory copy hits. Small writes are writeback cached
- */
-#define CACHE_SMARTBACK		19
-/*	Optimise for under powered controllers, especially on RAID1 and RAID0. We
- *	write large I/O's directly to disk bypassing the cache to avoid the extra
- *	memory copy hits. Small writes are writethrough cached. Suitable for devices
- *	lacking battery backup
- */
-#define CACHE_SMARTTHROUGH	20
-
-/*
- *	Ioctl structures
- */
-
-#define 	BLKI2OGRSTRAT	_IOR('2', 1, int)
-#define 	BLKI2OGWSTRAT	_IOR('2', 2, int)
-#define 	BLKI2OSRSTRAT	_IOW('2', 3, int)
-#define 	BLKI2OSWSTRAT	_IOW('2', 4, int)
-
-/*
- *	I2O Function codes
- */
-
-/*
- *	Executive Class
- */
-#define	I2O_CMD_ADAPTER_ASSIGN		0xB3
-#define	I2O_CMD_ADAPTER_READ		0xB2
-#define	I2O_CMD_ADAPTER_RELEASE		0xB5
-#define	I2O_CMD_BIOS_INFO_SET		0xA5
-#define	I2O_CMD_BOOT_DEVICE_SET		0xA7
-#define	I2O_CMD_CONFIG_VALIDATE		0xBB
-#define	I2O_CMD_CONN_SETUP		0xCA
-#define	I2O_CMD_DDM_DESTROY		0xB1
-#define	I2O_CMD_DDM_ENABLE		0xD5
-#define	I2O_CMD_DDM_QUIESCE		0xC7
-#define	I2O_CMD_DDM_RESET		0xD9
-#define	I2O_CMD_DDM_SUSPEND		0xAF
-#define	I2O_CMD_DEVICE_ASSIGN		0xB7
-#define	I2O_CMD_DEVICE_RELEASE		0xB9
-#define	I2O_CMD_HRT_GET			0xA8
-#define	I2O_CMD_ADAPTER_CLEAR		0xBE
-#define	I2O_CMD_ADAPTER_CONNECT		0xC9
-#define	I2O_CMD_ADAPTER_RESET		0xBD
-#define	I2O_CMD_LCT_NOTIFY		0xA2
-#define	I2O_CMD_OUTBOUND_INIT		0xA1
-#define	I2O_CMD_PATH_ENABLE		0xD3
-#define	I2O_CMD_PATH_QUIESCE		0xC5
-#define	I2O_CMD_PATH_RESET		0xD7
-#define	I2O_CMD_STATIC_MF_CREATE	0xDD
-#define	I2O_CMD_STATIC_MF_RELEASE	0xDF
-#define	I2O_CMD_STATUS_GET		0xA0
-#define	I2O_CMD_SW_DOWNLOAD		0xA9
-#define	I2O_CMD_SW_UPLOAD		0xAB
-#define	I2O_CMD_SW_REMOVE		0xAD
-#define	I2O_CMD_SYS_ENABLE		0xD1
-#define	I2O_CMD_SYS_MODIFY		0xC1
-#define	I2O_CMD_SYS_QUIESCE		0xC3
-#define	I2O_CMD_SYS_TAB_SET		0xA3
-
-/*
- * Utility Class
- */
-#define I2O_CMD_UTIL_NOP		0x00
-#define I2O_CMD_UTIL_ABORT		0x01
-#define I2O_CMD_UTIL_CLAIM		0x09
-#define I2O_CMD_UTIL_RELEASE		0x0B
-#define I2O_CMD_UTIL_PARAMS_GET		0x06
-#define I2O_CMD_UTIL_PARAMS_SET		0x05
-#define I2O_CMD_UTIL_EVT_REGISTER	0x13
-#define I2O_CMD_UTIL_EVT_ACK		0x14
-#define I2O_CMD_UTIL_CONFIG_DIALOG	0x10
-#define I2O_CMD_UTIL_DEVICE_RESERVE	0x0D
-#define I2O_CMD_UTIL_DEVICE_RELEASE	0x0F
-#define I2O_CMD_UTIL_LOCK		0x17
-#define I2O_CMD_UTIL_LOCK_RELEASE	0x19
-#define I2O_CMD_UTIL_REPLY_FAULT_NOTIFY	0x15
-
-/*
- * SCSI Host Bus Adapter Class
- */
-#define I2O_CMD_SCSI_EXEC		0x81
-#define I2O_CMD_SCSI_ABORT		0x83
-#define I2O_CMD_SCSI_BUSRESET		0x27
-
-/*
- * Bus Adapter Class
- */
-#define I2O_CMD_BUS_ADAPTER_RESET	0x85
-#define I2O_CMD_BUS_RESET		0x87
-#define I2O_CMD_BUS_SCAN		0x89
-#define I2O_CMD_BUS_QUIESCE		0x8b
-
-/*
- * Random Block Storage Class
- */
-#define I2O_CMD_BLOCK_READ		0x30
-#define I2O_CMD_BLOCK_WRITE		0x31
-#define I2O_CMD_BLOCK_CFLUSH		0x37
-#define I2O_CMD_BLOCK_MLOCK		0x49
-#define I2O_CMD_BLOCK_MUNLOCK		0x4B
-#define I2O_CMD_BLOCK_MMOUNT		0x41
-#define I2O_CMD_BLOCK_MEJECT		0x43
-#define I2O_CMD_BLOCK_POWER		0x70
-
-#define I2O_CMD_PRIVATE			0xFF
-
-/* Command status values  */
-
-#define I2O_CMD_IN_PROGRESS	0x01
-#define I2O_CMD_REJECTED	0x02
-#define I2O_CMD_FAILED		0x03
-#define I2O_CMD_COMPLETED	0x04
-
-/* I2O API function return values */
-
-#define I2O_RTN_NO_ERROR			0
-#define I2O_RTN_NOT_INIT			1
-#define I2O_RTN_FREE_Q_EMPTY			2
-#define I2O_RTN_TCB_ERROR			3
-#define I2O_RTN_TRANSACTION_ERROR		4
-#define I2O_RTN_ADAPTER_ALREADY_INIT		5
-#define I2O_RTN_MALLOC_ERROR			6
-#define I2O_RTN_ADPTR_NOT_REGISTERED		7
-#define I2O_RTN_MSG_REPLY_TIMEOUT		8
-#define I2O_RTN_NO_STATUS			9
-#define I2O_RTN_NO_FIRM_VER			10
-#define	I2O_RTN_NO_LINK_SPEED			11
-
-/* Reply message status defines for all messages */
-
-#define I2O_REPLY_STATUS_SUCCESS                    	0x00
-#define I2O_REPLY_STATUS_ABORT_DIRTY                	0x01
-#define I2O_REPLY_STATUS_ABORT_NO_DATA_TRANSFER     	0x02
-#define	I2O_REPLY_STATUS_ABORT_PARTIAL_TRANSFER		0x03
-#define	I2O_REPLY_STATUS_ERROR_DIRTY			0x04
-#define	I2O_REPLY_STATUS_ERROR_NO_DATA_TRANSFER		0x05
-#define	I2O_REPLY_STATUS_ERROR_PARTIAL_TRANSFER		0x06
-#define	I2O_REPLY_STATUS_PROCESS_ABORT_DIRTY		0x08
-#define	I2O_REPLY_STATUS_PROCESS_ABORT_NO_DATA_TRANSFER	0x09
-#define	I2O_REPLY_STATUS_PROCESS_ABORT_PARTIAL_TRANSFER	0x0A
-#define	I2O_REPLY_STATUS_TRANSACTION_ERROR		0x0B
-#define	I2O_REPLY_STATUS_PROGRESS_REPORT		0x80
-
-/* Status codes and Error Information for Parameter functions */
-
-#define I2O_PARAMS_STATUS_SUCCESS		0x00
-#define I2O_PARAMS_STATUS_BAD_KEY_ABORT		0x01
-#define I2O_PARAMS_STATUS_BAD_KEY_CONTINUE   	0x02
-#define I2O_PARAMS_STATUS_BUFFER_FULL		0x03
-#define I2O_PARAMS_STATUS_BUFFER_TOO_SMALL	0x04
-#define I2O_PARAMS_STATUS_FIELD_UNREADABLE	0x05
-#define I2O_PARAMS_STATUS_FIELD_UNWRITEABLE	0x06
-#define I2O_PARAMS_STATUS_INSUFFICIENT_FIELDS	0x07
-#define I2O_PARAMS_STATUS_INVALID_GROUP_ID	0x08
-#define I2O_PARAMS_STATUS_INVALID_OPERATION	0x09
-#define I2O_PARAMS_STATUS_NO_KEY_FIELD		0x0A
-#define I2O_PARAMS_STATUS_NO_SUCH_FIELD		0x0B
-#define I2O_PARAMS_STATUS_NON_DYNAMIC_GROUP	0x0C
-#define I2O_PARAMS_STATUS_OPERATION_ERROR	0x0D
-#define I2O_PARAMS_STATUS_SCALAR_ERROR		0x0E
-#define I2O_PARAMS_STATUS_TABLE_ERROR		0x0F
-#define I2O_PARAMS_STATUS_WRONG_GROUP_TYPE	0x10
-
-/* DetailedStatusCode defines for Executive, DDM, Util and Transaction error
- * messages: Table 3-2 Detailed Status Codes.*/
-
-#define I2O_DSC_SUCCESS                        0x0000
-#define I2O_DSC_BAD_KEY                        0x0002
-#define I2O_DSC_TCL_ERROR                      0x0003
-#define I2O_DSC_REPLY_BUFFER_FULL              0x0004
-#define I2O_DSC_NO_SUCH_PAGE                   0x0005
-#define I2O_DSC_INSUFFICIENT_RESOURCE_SOFT     0x0006
-#define I2O_DSC_INSUFFICIENT_RESOURCE_HARD     0x0007
-#define I2O_DSC_CHAIN_BUFFER_TOO_LARGE         0x0009
-#define I2O_DSC_UNSUPPORTED_FUNCTION           0x000A
-#define I2O_DSC_DEVICE_LOCKED                  0x000B
-#define I2O_DSC_DEVICE_RESET                   0x000C
-#define I2O_DSC_INAPPROPRIATE_FUNCTION         0x000D
-#define I2O_DSC_INVALID_INITIATOR_ADDRESS      0x000E
-#define I2O_DSC_INVALID_MESSAGE_FLAGS          0x000F
-#define I2O_DSC_INVALID_OFFSET                 0x0010
-#define I2O_DSC_INVALID_PARAMETER              0x0011
-#define I2O_DSC_INVALID_REQUEST                0x0012
-#define I2O_DSC_INVALID_TARGET_ADDRESS         0x0013
-#define I2O_DSC_MESSAGE_TOO_LARGE              0x0014
-#define I2O_DSC_MESSAGE_TOO_SMALL              0x0015
-#define I2O_DSC_MISSING_PARAMETER              0x0016
-#define I2O_DSC_TIMEOUT                        0x0017
-#define I2O_DSC_UNKNOWN_ERROR                  0x0018
-#define I2O_DSC_UNKNOWN_FUNCTION               0x0019
-#define I2O_DSC_UNSUPPORTED_VERSION            0x001A
-#define I2O_DSC_DEVICE_BUSY                    0x001B
-#define I2O_DSC_DEVICE_NOT_AVAILABLE           0x001C
-
-/* DetailedStatusCode defines for Block Storage Operation: Table 6-7 Detailed
-   Status Codes.*/
-
-#define I2O_BSA_DSC_SUCCESS               0x0000
-#define I2O_BSA_DSC_MEDIA_ERROR           0x0001
-#define I2O_BSA_DSC_ACCESS_ERROR          0x0002
-#define I2O_BSA_DSC_DEVICE_FAILURE        0x0003
-#define I2O_BSA_DSC_DEVICE_NOT_READY      0x0004
-#define I2O_BSA_DSC_MEDIA_NOT_PRESENT     0x0005
-#define I2O_BSA_DSC_MEDIA_LOCKED          0x0006
-#define I2O_BSA_DSC_MEDIA_FAILURE         0x0007
-#define I2O_BSA_DSC_PROTOCOL_FAILURE      0x0008
-#define I2O_BSA_DSC_BUS_FAILURE           0x0009
-#define I2O_BSA_DSC_ACCESS_VIOLATION      0x000A
-#define I2O_BSA_DSC_WRITE_PROTECTED       0x000B
-#define I2O_BSA_DSC_DEVICE_RESET          0x000C
-#define I2O_BSA_DSC_VOLUME_CHANGED        0x000D
-#define I2O_BSA_DSC_TIMEOUT               0x000E
-
-/* FailureStatusCodes, Table 3-3 Message Failure Codes */
-
-#define I2O_FSC_TRANSPORT_SERVICE_SUSPENDED             0x81
-#define I2O_FSC_TRANSPORT_SERVICE_TERMINATED            0x82
-#define I2O_FSC_TRANSPORT_CONGESTION                    0x83
-#define I2O_FSC_TRANSPORT_FAILURE                       0x84
-#define I2O_FSC_TRANSPORT_STATE_ERROR                   0x85
-#define I2O_FSC_TRANSPORT_TIME_OUT                      0x86
-#define I2O_FSC_TRANSPORT_ROUTING_FAILURE               0x87
-#define I2O_FSC_TRANSPORT_INVALID_VERSION               0x88
-#define I2O_FSC_TRANSPORT_INVALID_OFFSET                0x89
-#define I2O_FSC_TRANSPORT_INVALID_MSG_FLAGS             0x8A
-#define I2O_FSC_TRANSPORT_FRAME_TOO_SMALL               0x8B
-#define I2O_FSC_TRANSPORT_FRAME_TOO_LARGE               0x8C
-#define I2O_FSC_TRANSPORT_INVALID_TARGET_ID             0x8D
-#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_ID          0x8E
-#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_CONTEXT     0x8F
-#define I2O_FSC_TRANSPORT_UNKNOWN_FAILURE               0xFF
-
-/* Device Claim Types */
-#define	I2O_CLAIM_PRIMARY					0x01000000
-#define	I2O_CLAIM_MANAGEMENT					0x02000000
-#define	I2O_CLAIM_AUTHORIZED					0x03000000
-#define	I2O_CLAIM_SECONDARY					0x04000000
-
-/* Message header defines for VersionOffset */
-#define I2OVER15	0x0001
-#define I2OVER20	0x0002
-
-/* Default is 1.5 */
-#define I2OVERSION	I2OVER15
-
-#define SGL_OFFSET_0    I2OVERSION
-#define SGL_OFFSET_4    (0x0040 | I2OVERSION)
-#define SGL_OFFSET_5    (0x0050 | I2OVERSION)
-#define SGL_OFFSET_6    (0x0060 | I2OVERSION)
-#define SGL_OFFSET_7    (0x0070 | I2OVERSION)
-#define SGL_OFFSET_8    (0x0080 | I2OVERSION)
-#define SGL_OFFSET_9    (0x0090 | I2OVERSION)
-#define SGL_OFFSET_10   (0x00A0 | I2OVERSION)
-#define SGL_OFFSET_11   (0x00B0 | I2OVERSION)
-#define SGL_OFFSET_12   (0x00C0 | I2OVERSION)
-#define SGL_OFFSET(x)   (((x)<<4) | I2OVERSION)
-
-/* Transaction Reply Lists (TRL) Control Word structure */
-#define TRL_SINGLE_FIXED_LENGTH		0x00
-#define TRL_SINGLE_VARIABLE_LENGTH	0x40
-#define TRL_MULTIPLE_FIXED_LENGTH	0x80
-
- /* msg header defines for MsgFlags */
-#define MSG_STATIC	0x0100
-#define MSG_64BIT_CNTXT	0x0200
-#define MSG_MULTI_TRANS	0x1000
-#define MSG_FAIL	0x2000
-#define MSG_FINAL	0x4000
-#define MSG_REPLY	0x8000
-
- /* minimum size msg */
-#define THREE_WORD_MSG_SIZE	0x00030000
-#define FOUR_WORD_MSG_SIZE	0x00040000
-#define FIVE_WORD_MSG_SIZE	0x00050000
-#define SIX_WORD_MSG_SIZE	0x00060000
-#define SEVEN_WORD_MSG_SIZE	0x00070000
-#define EIGHT_WORD_MSG_SIZE	0x00080000
-#define NINE_WORD_MSG_SIZE	0x00090000
-#define TEN_WORD_MSG_SIZE	0x000A0000
-#define ELEVEN_WORD_MSG_SIZE	0x000B0000
-#define I2O_MESSAGE_SIZE(x)	((x)<<16)
-
-/* special TID assignments */
-#define ADAPTER_TID		0
-#define HOST_TID		1
-
-/* outbound queue defines */
-#define I2O_MAX_OUTBOUND_MSG_FRAMES	128
-#define I2O_OUTBOUND_MSG_FRAME_SIZE	128	/* in 32-bit words */
-
-#define I2O_POST_WAIT_OK	0
-#define I2O_POST_WAIT_TIMEOUT	-ETIMEDOUT
-
-#define I2O_CONTEXT_LIST_MIN_LENGTH	15
-#define I2O_CONTEXT_LIST_USED		0x01
-#define I2O_CONTEXT_LIST_DELETED	0x02
-
-/* timeouts */
-#define I2O_TIMEOUT_INIT_OUTBOUND_QUEUE	15
-#define I2O_TIMEOUT_MESSAGE_GET		5
-#define I2O_TIMEOUT_RESET		30
-#define I2O_TIMEOUT_STATUS_GET		5
-#define I2O_TIMEOUT_LCT_GET		360
-#define I2O_TIMEOUT_SCSI_SCB_ABORT	240
-
-/* retries */
-#define I2O_HRT_GET_TRIES		3
-#define I2O_LCT_GET_TRIES		3
-
-/* defines for max_sectors and max_phys_segments */
-#define I2O_MAX_SECTORS			1024
-#define I2O_MAX_SECTORS_LIMITED		256
-#define I2O_MAX_PHYS_SEGMENTS		MAX_PHYS_SEGMENTS
-
 #endif				/* __KERNEL__ */
 #endif				/* _I2O_H */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f04ba20712a..6c5d4c898cc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -12,7 +12,7 @@
 #include <linux/config.h>
 #include <linux/smp.h>
 
-#if !defined(CONFIG_ARCH_S390)
+#if !defined(CONFIG_S390)
 
 #include <linux/linkage.h>
 #include <linux/cache.h>
@@ -221,6 +221,17 @@ extern void note_interrupt(unsigned int irq, irq_desc_t *desc,
 extern int can_request_irq(unsigned int irq, unsigned long irqflags);
 
 extern void init_irq_proc(void);
+
+#ifdef CONFIG_AUTO_IRQ_AFFINITY
+extern int select_smp_affinity(unsigned int irq);
+#else
+static inline int
+select_smp_affinity(unsigned int irq)
+{
+	return 1;
+}
+#endif
+
 #endif
 
 extern hw_irq_controller no_irq_type;  /* needed in every arch ? */
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index dcde7adfdce..558cb4c26ec 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -498,6 +498,12 @@ struct transaction_s
 	struct journal_head	*t_checkpoint_list;
 
 	/*
+	 * Doubly-linked circular list of all buffers submitted for IO while
+	 * checkpointing. [j_list_lock]
+	 */
+	struct journal_head	*t_checkpoint_io_list;
+
+	/*
 	 * Doubly-linked circular list of temporary buffers currently undergoing
 	 * IO in the log [j_list_lock]
 	 */
@@ -843,7 +849,7 @@ extern void journal_commit_transaction(journal_t *);
 
 /* Checkpoint list management */
 int __journal_clean_checkpoint_list(journal_t *journal);
-void __journal_remove_checkpoint(struct journal_head *);
+int __journal_remove_checkpoint(struct journal_head *);
 void __journal_insert_checkpoint(struct journal_head *, transaction_t *);
 
 /* Buffer IO */
diff --git a/include/linux/key.h b/include/linux/key.h
index 53513a3be53..4d189e51bc6 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -193,14 +193,6 @@ struct key_type {
 	 */
 	int (*instantiate)(struct key *key, const void *data, size_t datalen);
 
-	/* duplicate a key of this type (optional)
-	 * - the source key will be locked against change
-	 * - the new description will be attached
-	 * - the quota will have been adjusted automatically from
-	 *   source->quotalen
-	 */
-	int (*duplicate)(struct key *key, const struct key *source);
-
 	/* update a key of this type (optional)
 	 * - this method should call key_payload_reserve() to recalculate the
 	 *   quota consumption
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e828e172ccb..a43c95f8f96 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -124,6 +124,8 @@ enum {
 	ATA_FLAG_DEBUGMSG	= (1 << 10),
 	ATA_FLAG_NO_ATAPI	= (1 << 11), /* No ATAPI support */
 
+	ATA_FLAG_SUSPENDED	= (1 << 12), /* port is suspended */
+
 	ATA_QCFLAG_ACTIVE	= (1 << 1), /* cmd not yet ack'd to scsi lyer */
 	ATA_QCFLAG_SG		= (1 << 3), /* have s/g table? */
 	ATA_QCFLAG_SINGLE	= (1 << 4), /* no s/g, just a single buffer */
@@ -436,6 +438,8 @@ extern void ata_std_ports(struct ata_ioports *ioaddr);
 extern int ata_pci_init_one (struct pci_dev *pdev, struct ata_port_info **port_info,
 			     unsigned int n_ports);
 extern void ata_pci_remove_one (struct pci_dev *pdev);
+extern int ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t state);
+extern int ata_pci_device_resume(struct pci_dev *pdev);
 #endif /* CONFIG_PCI */
 extern int ata_device_add(const struct ata_probe_ent *ent);
 extern void ata_host_set_remove(struct ata_host_set *host_set);
@@ -445,6 +449,10 @@ extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmn
 extern int ata_scsi_error(struct Scsi_Host *host);
 extern int ata_scsi_release(struct Scsi_Host *host);
 extern unsigned int ata_host_intr(struct ata_port *ap, struct ata_queued_cmd *qc);
+extern int ata_scsi_device_resume(struct scsi_device *);
+extern int ata_scsi_device_suspend(struct scsi_device *);
+extern int ata_device_resume(struct ata_port *, struct ata_device *);
+extern int ata_device_suspend(struct ata_port *, struct ata_device *);
 extern int ata_ratelimit(void);
 
 /*
@@ -480,7 +488,8 @@ extern u8   ata_bmdma_status(struct ata_port *ap);
 extern void ata_bmdma_irq_clear(struct ata_port *ap);
 extern void ata_qc_complete(struct ata_queued_cmd *qc);
 extern void ata_eng_timeout(struct ata_port *ap);
-extern void ata_scsi_simulate(u16 *id, struct scsi_cmnd *cmd,
+extern void ata_scsi_simulate(struct ata_port *ap, struct ata_device *dev,
+			      struct scsi_cmnd *cmd,
 			      void (*done)(struct scsi_cmnd *));
 extern int ata_std_bios_param(struct scsi_device *sdev,
 			      struct block_device *bdev,
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 8b67cf837ca..ed00b278cb9 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -110,14 +110,6 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
 #define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL)
 
 /*
- * Hugetlb policy. i386 hugetlb so far works with node numbers
- * instead of zone lists, so give it special interfaces for now.
- */
-extern int mpol_first_node(struct vm_area_struct *vma, unsigned long addr);
-extern int mpol_node_valid(int nid, struct vm_area_struct *vma,
-			unsigned long addr);
-
-/*
  * Tree of shared policies for a shared memory region.
  * Maintain the policies in a pseudo mm that contains vmas. The vmas
  * carry the policy. As a special twist the pseudo mm is indexed in pages, not
@@ -156,6 +148,16 @@ extern void numa_default_policy(void);
 extern void numa_policy_init(void);
 extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new);
 extern struct mempolicy default_policy;
+extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+		unsigned long addr);
+
+extern int policy_zone;
+
+static inline void check_highest_zone(int k)
+{
+	if (k > policy_zone)
+		policy_zone = k;
+}
 
 #else
 
@@ -182,17 +184,6 @@ static inline struct mempolicy *mpol_copy(struct mempolicy *old)
 	return NULL;
 }
 
-static inline int mpol_first_node(struct vm_area_struct *vma, unsigned long a)
-{
-	return numa_node_id();
-}
-
-static inline int
-mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long a)
-{
-	return 1;
-}
-
 struct shared_policy {};
 
 static inline int mpol_set_shared_policy(struct shared_policy *info,
@@ -232,6 +223,15 @@ static inline void numa_policy_rebind(const nodemask_t *old,
 {
 }
 
+static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+		unsigned long addr)
+{
+	return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+}
+
+static inline void check_highest_zone(int k)
+{
+}
 #endif /* CONFIG_NUMA */
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a06a84d347f..bc01fff3aa0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -634,14 +634,38 @@ struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
 int shmem_lock(struct file *file, int lock, struct user_struct *user);
 #else
 #define shmem_nopage filemap_nopage
-#define shmem_lock(a, b, c) 	({0;})	/* always in memory, no need to lock */
-#define shmem_set_policy(a, b)	(0)
-#define shmem_get_policy(a, b)	(NULL)
+
+static inline int shmem_lock(struct file *file, int lock,
+			     struct user_struct *user)
+{
+	return 0;
+}
+
+static inline int shmem_set_policy(struct vm_area_struct *vma,
+				   struct mempolicy *new)
+{
+	return 0;
+}
+
+static inline struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
+						 unsigned long addr)
+{
+	return NULL;
+}
 #endif
 struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags);
+extern int shmem_mmap(struct file *file, struct vm_area_struct *vma);
 
 int shmem_zero_setup(struct vm_area_struct *);
 
+#ifndef CONFIG_MMU
+extern unsigned long shmem_get_unmapped_area(struct file *file,
+					     unsigned long addr,
+					     unsigned long len,
+					     unsigned long pgoff,
+					     unsigned long flags);
+#endif
+
 static inline int can_do_mlock(void)
 {
 	if (capable(CAP_IPC_LOCK))
@@ -690,14 +714,31 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 }
 
 extern int vmtruncate(struct inode * inode, loff_t offset);
+extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
 extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
 extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
-extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
 
-static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access)
+#ifdef CONFIG_MMU
+extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
+			unsigned long address, int write_access);
+
+static inline int handle_mm_fault(struct mm_struct *mm,
+			struct vm_area_struct *vma, unsigned long address,
+			int write_access)
 {
-	return __handle_mm_fault(mm, vma, address, write_access) & (~VM_FAULT_WRITE);
+	return __handle_mm_fault(mm, vma, address, write_access) &
+				(~VM_FAULT_WRITE);
 }
+#else
+static inline int handle_mm_fault(struct mm_struct *mm,
+			struct vm_area_struct *vma, unsigned long address,
+			int write_access)
+{
+	/* should never happen if there's no MMU */
+	BUG();
+	return VM_FAULT_SIGBUS;
+}
+#endif
 
 extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
@@ -896,6 +937,8 @@ extern unsigned long do_brk(unsigned long, unsigned long);
 /* filemap.c */
 extern unsigned long page_unuse(struct page *);
 extern void truncate_inode_pages(struct address_space *, loff_t);
+extern void truncate_inode_pages_range(struct address_space *,
+				       loff_t lstart, loff_t lend);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9f22090df7d..c34f4a2c62f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -46,7 +46,6 @@ struct zone_padding {
 
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
-	int low;		/* low watermark, refill needed */
 	int high;		/* high watermark, emptying needed */
 	int batch;		/* chunk size for buddy add/remove */
 	struct list_head list;	/* the list of pages */
@@ -389,6 +388,11 @@ static inline struct zone *next_zone(struct zone *zone)
 #define for_each_zone(zone) \
 	for (zone = pgdat_list->node_zones; zone; zone = next_zone(zone))
 
+static inline int populated_zone(struct zone *zone)
+{
+	return (!!zone->present_pages);
+}
+
 static inline int is_highmem_idx(int idx)
 {
 	return (idx == ZONE_HIGHMEM);
@@ -398,6 +402,7 @@ static inline int is_normal_idx(int idx)
 {
 	return (idx == ZONE_NORMAL);
 }
+
 /**
  * is_highmem - helper function to quickly check if a struct zone is a 
  *              highmem zone or not.  This is an attempt to keep references
@@ -414,6 +419,16 @@ static inline int is_normal(struct zone *zone)
 	return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL;
 }
 
+static inline int is_dma32(struct zone *zone)
+{
+	return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
+}
+
+static inline int is_dma(struct zone *zone)
+{
+	return zone == zone->zone_pgdat->node_zones + ZONE_DMA;
+}
+
 /* These two functions are used to setup the per zone pages min values */
 struct ctl_table;
 struct file;
@@ -435,7 +450,6 @@ extern struct pglist_data contig_page_data;
 #define NODE_DATA(nid)		(&contig_page_data)
 #define NODE_MEM_MAP(nid)	mem_map
 #define MAX_NODES_SHIFT		1
-#define pfn_to_nid(pfn)		(0)
 
 #else /* CONFIG_NEED_MULTIPLE_NODES */
 
@@ -470,6 +484,10 @@ extern struct pglist_data contig_page_data;
 #define early_pfn_to_nid(nid)  (0UL)
 #endif
 
+#ifdef CONFIG_FLATMEM
+#define pfn_to_nid(pfn)		(0)
+#endif
+
 #define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
 #define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)
 
@@ -564,11 +582,6 @@ static inline int valid_section_nr(unsigned long nr)
 	return valid_section(__nr_to_section(nr));
 }
 
-/*
- * Given a kernel address, find the home node of the underlying memory.
- */
-#define kvaddr_to_nid(kaddr)	pfn_to_nid(__pa(kaddr) >> PAGE_SHIFT)
-
 static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 {
 	return __nr_to_section(pfn_to_section_nr(pfn));
@@ -598,13 +611,14 @@ static inline int pfn_valid(unsigned long pfn)
  * this restriction.
  */
 #ifdef CONFIG_NUMA
-#define pfn_to_nid		early_pfn_to_nid
-#endif
-
-#define pfn_to_pgdat(pfn)						\
+#define pfn_to_nid(pfn)							\
 ({									\
-	NODE_DATA(pfn_to_nid(pfn));					\
+	unsigned long __pfn_to_nid_pfn = (pfn);				\
+	page_to_nid(pfn_to_page(__pfn_to_nid_pfn));			\
 })
+#else
+#define pfn_to_nid(pfn)		(0)
+#endif
 
 #define early_pfn_valid(pfn)	pfn_valid(pfn)
 void sparse_init(void);
@@ -613,12 +627,6 @@ void sparse_init(void);
 #define sparse_index_init(_sec, _nid)  do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-#define early_pfn_in_nid(pfn, nid)	(early_pfn_to_nid(pfn) == (nid))
-#else
-#define early_pfn_in_nid(pfn, nid)	(1)
-#endif
-
 #ifndef early_pfn_valid
 #define early_pfn_valid(pfn)	(1)
 #endif
diff --git a/include/linux/nbd.h b/include/linux/nbd.h
index 090e210e98f..f95d51fae73 100644
--- a/include/linux/nbd.h
+++ b/include/linux/nbd.h
@@ -37,18 +37,26 @@ enum {
 /* userspace doesn't need the nbd_device structure */
 #ifdef __KERNEL__
 
+#include <linux/wait.h>
+
 /* values for flags field */
 #define NBD_READ_ONLY 0x0001
 #define NBD_WRITE_NOCHK 0x0002
 
+struct request;
+
 struct nbd_device {
 	int flags;
 	int harderror;		/* Code of hard error			*/
 	struct socket * sock;
 	struct file * file; 	/* If == NULL, device is not ready, yet	*/
 	int magic;
+
 	spinlock_t queue_lock;
 	struct list_head queue_head;/* Requests are added here...	*/
+	struct request *active_req;
+	wait_queue_head_t active_wq;
+
 	struct semaphore tx_lock;
 	struct gendisk *disk;
 	int blksize;
diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h
index 130d4f588a3..3f4f7142bbe 100644
--- a/include/linux/nfsd/xdr.h
+++ b/include/linux/nfsd/xdr.h
@@ -88,10 +88,12 @@ struct nfsd_readdirargs {
 
 struct nfsd_attrstat {
 	struct svc_fh		fh;
+	struct kstat		stat;
 };
 
 struct nfsd_diropres  {
 	struct svc_fh		fh;
+	struct kstat		stat;
 };
 
 struct nfsd_readlinkres {
@@ -101,6 +103,7 @@ struct nfsd_readlinkres {
 struct nfsd_readres {
 	struct svc_fh		fh;
 	unsigned long		count;
+	struct kstat		stat;
 };
 
 struct nfsd_readdirres {
diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h
index 3c2a71b43ba..a4322741f8b 100644
--- a/include/linux/nfsd/xdr3.h
+++ b/include/linux/nfsd/xdr3.h
@@ -126,6 +126,7 @@ struct nfsd3_setaclargs {
 struct nfsd3_attrstat {
 	__u32			status;
 	struct svc_fh		fh;
+	struct kstat            stat;
 };
 
 /* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 343083fec25..d52999c4333 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -79,13 +79,23 @@
 /*
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
  * allowed.
+ *
+ * - Fields can be modified with xxx_page_state and xxx_page_state_zone at
+ * any time safely (which protects the instance from modification by
+ * interrupt.
+ * - The __xxx_page_state variants can be used safely when interrupts are
+ * disabled.
+ * - The __xxx_page_state variants can be used if the field is only
+ * modified from process context, or only modified from interrupt context.
+ * In this case, the field should be commented here.
  */
 struct page_state {
 	unsigned long nr_dirty;		/* Dirty writeable pages */
 	unsigned long nr_writeback;	/* Pages under writeback */
 	unsigned long nr_unstable;	/* NFS unstable pages */
 	unsigned long nr_page_table_pages;/* Pages used for pagetables */
-	unsigned long nr_mapped;	/* mapped into pagetables */
+	unsigned long nr_mapped;	/* mapped into pagetables.
+					 * only modified from process context */
 	unsigned long nr_slab;		/* In slab */
 #define GET_PAGE_STATE_LAST nr_slab
 
@@ -97,32 +107,40 @@ struct page_state {
 	unsigned long pgpgout;		/* Disk writes */
 	unsigned long pswpin;		/* swap reads */
 	unsigned long pswpout;		/* swap writes */
-	unsigned long pgalloc_high;	/* page allocations */
 
+	unsigned long pgalloc_high;	/* page allocations */
 	unsigned long pgalloc_normal;
+	unsigned long pgalloc_dma32;
 	unsigned long pgalloc_dma;
+
 	unsigned long pgfree;		/* page freeings */
 	unsigned long pgactivate;	/* pages moved inactive->active */
 	unsigned long pgdeactivate;	/* pages moved active->inactive */
 
 	unsigned long pgfault;		/* faults (major+minor) */
 	unsigned long pgmajfault;	/* faults (major only) */
+
 	unsigned long pgrefill_high;	/* inspected in refill_inactive_zone */
 	unsigned long pgrefill_normal;
+	unsigned long pgrefill_dma32;
 	unsigned long pgrefill_dma;
 
 	unsigned long pgsteal_high;	/* total highmem pages reclaimed */
 	unsigned long pgsteal_normal;
+	unsigned long pgsteal_dma32;
 	unsigned long pgsteal_dma;
+
 	unsigned long pgscan_kswapd_high;/* total highmem pages scanned */
 	unsigned long pgscan_kswapd_normal;
-
+	unsigned long pgscan_kswapd_dma32;
 	unsigned long pgscan_kswapd_dma;
+
 	unsigned long pgscan_direct_high;/* total highmem pages scanned */
 	unsigned long pgscan_direct_normal;
+	unsigned long pgscan_direct_dma32;
 	unsigned long pgscan_direct_dma;
-	unsigned long pginodesteal;	/* pages reclaimed via inode freeing */
 
+	unsigned long pginodesteal;	/* pages reclaimed via inode freeing */
 	unsigned long slabs_scanned;	/* slab objects scanned */
 	unsigned long kswapd_steal;	/* pages reclaimed by kswapd */
 	unsigned long kswapd_inodesteal;/* reclaimed via kswapd inode freeing */
@@ -136,31 +154,54 @@ struct page_state {
 extern void get_page_state(struct page_state *ret);
 extern void get_page_state_node(struct page_state *ret, int node);
 extern void get_full_page_state(struct page_state *ret);
-extern unsigned long __read_page_state(unsigned long offset);
-extern void __mod_page_state(unsigned long offset, unsigned long delta);
+extern unsigned long read_page_state_offset(unsigned long offset);
+extern void mod_page_state_offset(unsigned long offset, unsigned long delta);
+extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
 
 #define read_page_state(member) \
-	__read_page_state(offsetof(struct page_state, member))
+	read_page_state_offset(offsetof(struct page_state, member))
 
 #define mod_page_state(member, delta)	\
-	__mod_page_state(offsetof(struct page_state, member), (delta))
-
-#define inc_page_state(member)	mod_page_state(member, 1UL)
-#define dec_page_state(member)	mod_page_state(member, 0UL - 1)
-#define add_page_state(member,delta) mod_page_state(member, (delta))
-#define sub_page_state(member,delta) mod_page_state(member, 0UL - (delta))
-
-#define mod_page_state_zone(zone, member, delta)				\
-	do {									\
-		unsigned offset;						\
-		if (is_highmem(zone))						\
-			offset = offsetof(struct page_state, member##_high);	\
-		else if (is_normal(zone))					\
-			offset = offsetof(struct page_state, member##_normal);	\
-		else								\
-			offset = offsetof(struct page_state, member##_dma);	\
-		__mod_page_state(offset, (delta));				\
-	} while (0)
+	mod_page_state_offset(offsetof(struct page_state, member), (delta))
+
+#define __mod_page_state(member, delta)	\
+	__mod_page_state_offset(offsetof(struct page_state, member), (delta))
+
+#define inc_page_state(member)		mod_page_state(member, 1UL)
+#define dec_page_state(member)		mod_page_state(member, 0UL - 1)
+#define add_page_state(member,delta)	mod_page_state(member, (delta))
+#define sub_page_state(member,delta)	mod_page_state(member, 0UL - (delta))
+
+#define __inc_page_state(member)	__mod_page_state(member, 1UL)
+#define __dec_page_state(member)	__mod_page_state(member, 0UL - 1)
+#define __add_page_state(member,delta)	__mod_page_state(member, (delta))
+#define __sub_page_state(member,delta)	__mod_page_state(member, 0UL - (delta))
+
+#define page_state(member) (*__page_state(offsetof(struct page_state, member)))
+
+#define state_zone_offset(zone, member)					\
+({									\
+	unsigned offset;						\
+	if (is_highmem(zone))						\
+		offset = offsetof(struct page_state, member##_high);	\
+	else if (is_normal(zone))					\
+		offset = offsetof(struct page_state, member##_normal);	\
+	else if (is_dma32(zone))					\
+		offset = offsetof(struct page_state, member##_dma32);	\
+	else								\
+		offset = offsetof(struct page_state, member##_dma);	\
+	offset;								\
+})
+
+#define __mod_page_state_zone(zone, member, delta)			\
+ do {									\
+	__mod_page_state_offset(state_zone_offset(zone, member), (delta)); \
+ } while (0)
+
+#define mod_page_state_zone(zone, member, delta)			\
+ do {									\
+	mod_page_state_offset(state_zone_offset(zone, member), (delta)); \
+ } while (0)
 
 /*
  * Manipulation of page state flags
diff --git a/include/linux/parport.h b/include/linux/parport.h
index d2a4d9e1e6d..f7ff0b0c403 100644
--- a/include/linux/parport.h
+++ b/include/linux/parport.h
@@ -242,7 +242,6 @@ enum ieee1284_phase {
 	IEEE1284_PH_FWD_IDLE,
 	IEEE1284_PH_TERMINATE,
 	IEEE1284_PH_NEGOTIATION,
-	IEEE1284_PH_HBUSY_DNA,
 	IEEE1284_PH_REV_IDLE,
 	IEEE1284_PH_HBUSY_DAVAIL,
 	IEEE1284_PH_REV_DATA,
diff --git a/include/linux/parport_pc.h b/include/linux/parport_pc.h
index c6f76247087..1cc0f6b1a49 100644
--- a/include/linux/parport_pc.h
+++ b/include/linux/parport_pc.h
@@ -79,13 +79,13 @@ static __inline__ unsigned char parport_pc_read_data(struct parport *p)
 }
 
 #ifdef DEBUG_PARPORT
-extern __inline__ void dump_parport_state (char *str, struct parport *p)
+static inline void dump_parport_state (char *str, struct parport *p)
 {
 	/* here's hoping that reading these ports won't side-effect anything underneath */
 	unsigned char ecr = inb (ECONTROL (p));
 	unsigned char dcr = inb (CONTROL (p));
 	unsigned char dsr = inb (STATUS (p));
-	static char *ecr_modes[] = {"SPP", "PS2", "PPFIFO", "ECP", "xXx", "yYy", "TST", "CFG"};
+	static const char *const ecr_modes[] = {"SPP", "PS2", "PPFIFO", "ECP", "xXx", "yYy", "TST", "CFG"};
 	const struct parport_pc_private *priv = p->physport->private_data;
 	int i;
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 96a0403f61f..a213e999de3 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -394,6 +394,13 @@
 #define PCI_DEVICE_ID_NS_87410		0xd001
 #define PCI_DEVICE_ID_NS_CS5535_IDE	0x002d
 
+#define PCI_DEVICE_ID_NS_CS5535_HOST_BRIDGE  0x0028
+#define PCI_DEVICE_ID_NS_CS5535_ISA_BRIDGE   0x002b
+#define PCI_DEVICE_ID_NS_CS5535_IDE          0x002d
+#define PCI_DEVICE_ID_NS_CS5535_AUDIO        0x002e
+#define PCI_DEVICE_ID_NS_CS5535_USB          0x002f
+#define PCI_DEVICE_ID_NS_CS5535_VIDEO        0x0030
+
 #define PCI_VENDOR_ID_TSENG		0x100c
 #define PCI_DEVICE_ID_TSENG_W32P_2	0x3202
 #define PCI_DEVICE_ID_TSENG_W32P_b	0x3205
@@ -496,6 +503,9 @@
 
 #define PCI_DEVICE_ID_AMD_CS5536_IDE	0x209A
 
+#define PCI_DEVICE_ID_AMD_LX_VIDEO  0x2081
+#define PCI_DEVICE_ID_AMD_LX_AES    0x2082
+
 #define PCI_VENDOR_ID_TRIDENT		0x1023
 #define PCI_DEVICE_ID_TRIDENT_4DWAVE_DX	0x2000
 #define PCI_DEVICE_ID_TRIDENT_4DWAVE_NX	0x2001
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index 13e7c4b6236..b6e0bcad84e 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -71,8 +71,8 @@
  */
 #define MD_PATCHLEVEL_VERSION           3
 
-extern int register_md_personality (int p_num, mdk_personality_t *p);
-extern int unregister_md_personality (int p_num);
+extern int register_md_personality (struct mdk_personality *p);
+extern int unregister_md_personality (struct mdk_personality *p);
 extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev),
 				mddev_t *mddev, const char *name);
 extern void md_unregister_thread (mdk_thread_t *thread);
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 46629a275ba..617b9506c76 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -18,62 +18,19 @@
 /* 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
-#define RAID1             3UL
-#define RAID5             4UL
-#define TRANSLUCENT       5UL
-#define HSM               6UL
-#define MULTIPATH         7UL
-#define RAID6		  8UL
-#define	RAID10		  9UL
-#define FAULTY		  10UL
-#define MAX_PERSONALITY   11UL
-
 #define	LEVEL_MULTIPATH		(-4)
 #define	LEVEL_LINEAR		(-1)
 #define	LEVEL_FAULTY		(-5)
 
+/* we need a value for 'no level specified' and 0
+ * means 'raid0', so we need something else.  This is
+ * for internal use only
+ */
+#define	LEVEL_NONE		(-1000000)
+
 #define MaxSector (~(sector_t)0)
 #define MD_THREAD_NAME_MAX 14
 
-static inline int pers_to_level (int pers)
-{
-	switch (pers) {
-		case FAULTY:		return LEVEL_FAULTY;
-		case MULTIPATH:		return LEVEL_MULTIPATH;
-		case HSM:		return -3;
-		case TRANSLUCENT:	return -2;
-		case LINEAR:		return LEVEL_LINEAR;
-		case RAID0:		return 0;
-		case RAID1:		return 1;
-		case RAID5:		return 5;
-		case RAID6:		return 6;
-		case RAID10:		return 10;
-	}
-	BUG();
-	return MD_RESERVED;
-}
-
-static inline int level_to_pers (int level)
-{
-	switch (level) {
-		case LEVEL_FAULTY: return FAULTY;
-		case LEVEL_MULTIPATH: return MULTIPATH;
-		case -3: return HSM;
-		case -2: return TRANSLUCENT;
-		case LEVEL_LINEAR: return LINEAR;
-		case 0: return RAID0;
-		case 1: return RAID1;
-		case 4:
-		case 5: return RAID5;
-		case 6: return RAID6;
-		case 10: return RAID10;
-	}
-	return MD_RESERVED;
-}
-
 typedef struct mddev_s mddev_t;
 typedef struct mdk_rdev_s mdk_rdev_t;
 
@@ -138,14 +95,16 @@ struct mdk_rdev_s
 	atomic_t	read_errors;	/* number of consecutive read errors that
 					 * we have tried to ignore.
 					 */
+	atomic_t	corrected_errors; /* number of corrected read errors,
+					   * for reporting to userspace and storing
+					   * in superblock.
+					   */
 };
 
-typedef struct mdk_personality_s mdk_personality_t;
-
 struct mddev_s
 {
 	void				*private;
-	mdk_personality_t		*pers;
+	struct mdk_personality		*pers;
 	dev_t				unit;
 	int				md_minor;
 	struct list_head 		disks;
@@ -164,6 +123,7 @@ struct mddev_s
 	int				chunk_size;
 	time_t				ctime, utime;
 	int				level, layout;
+	char				clevel[16];
 	int				raid_disks;
 	int				max_disks;
 	sector_t			size; /* used size of component devices */
@@ -183,6 +143,11 @@ struct mddev_s
 	sector_t			resync_mismatches; /* count of sectors where
 							    * parity/replica mismatch found
 							    */
+	/* if zero, use the system-wide default */
+	int				sync_speed_min;
+	int				sync_speed_max;
+
+	int				ok_start_degraded;
 	/* recovery/resync flags 
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started
@@ -265,9 +230,11 @@ static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sect
         atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
 }
 
-struct mdk_personality_s
+struct mdk_personality
 {
 	char *name;
+	int level;
+	struct list_head list;
 	struct module *owner;
 	int (*make_request)(request_queue_t *q, struct bio *bio);
 	int (*run)(mddev_t *mddev);
@@ -305,8 +272,6 @@ static inline char * mdname (mddev_t * mddev)
 	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
 }
 
-extern mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr);
-
 /*
  * iterates through some rdev ringlist. It's safe to remove the
  * current 'rdev'. Dont touch 'tmp' though.
@@ -366,5 +331,10 @@ do {									\
 	__wait_event_lock_irq(wq, condition, lock, cmd);		\
 } while (0)
 
+static inline void safe_put_page(struct page *p)
+{
+	if (p) put_page(p);
+}
+
 #endif
 
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
index 292b98f2b40..9d5494aaac0 100644
--- a/include/linux/raid/raid1.h
+++ b/include/linux/raid/raid1.h
@@ -45,6 +45,8 @@ struct r1_private_data_s {
 
 	spinlock_t		resync_lock;
 	int			nr_pending;
+	int			nr_waiting;
+	int			nr_queued;
 	int			barrier;
 	sector_t		next_resync;
 	int			fullsync;  /* set to 1 if a full sync is needed,
@@ -52,11 +54,12 @@ struct r1_private_data_s {
 					    * Cleared when a sync completes.
 					    */
 
-	wait_queue_head_t	wait_idle;
-	wait_queue_head_t	wait_resume;
+	wait_queue_head_t	wait_barrier;
 
 	struct pool_info	*poolinfo;
 
+	struct page		*tmppage;
+
 	mempool_t *r1bio_pool;
 	mempool_t *r1buf_pool;
 };
@@ -106,6 +109,13 @@ struct r1bio_s {
 	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
 };
 
+/* when we get a read error on a read-only array, we redirect to another
+ * device without failing the first device, or trying to over-write to
+ * correct the read error.  To keep track of bad blocks on a per-bio
+ * level, we store IO_BLOCKED in the appropriate 'bios' pointer
+ */
+#define IO_BLOCKED ((struct bio*)1)
+
 /* bits for r1bio.state */
 #define	R1BIO_Uptodate	0
 #define	R1BIO_IsSync	1
diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h
index 60708789c8f..b1103298a8c 100644
--- a/include/linux/raid/raid10.h
+++ b/include/linux/raid/raid10.h
@@ -35,18 +35,26 @@ struct r10_private_data_s {
 	sector_t chunk_mask;
 
 	struct list_head	retry_list;
-	/* for use when syncing mirrors: */
+	/* queue pending writes and submit them on unplug */
+	struct bio_list		pending_bio_list;
+
 
 	spinlock_t		resync_lock;
 	int nr_pending;
+	int nr_waiting;
+	int nr_queued;
 	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;
+	wait_queue_head_t	wait_barrier;
 
 	mempool_t *r10bio_pool;
 	mempool_t *r10buf_pool;
+	struct page		*tmppage;
 };
 
 typedef struct r10_private_data_s conf_t;
@@ -96,8 +104,16 @@ struct r10bio_s {
 	} devs[0];
 };
 
+/* when we get a read error on a read-only array, we redirect to another
+ * device without failing the first device, or trying to over-write to
+ * correct the read error.  To keep track of bad blocks on a per-bio
+ * level, we store IO_BLOCKED in the appropriate 'bios' pointer
+ */
+#define IO_BLOCKED ((struct bio*)1)
+
 /* bits for r10bio.state */
 #define	R10BIO_Uptodate	0
 #define	R10BIO_IsSync	1
 #define	R10BIO_IsRecover 2
+#define	R10BIO_Degraded 3
 #endif
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index f025ba6fb14..394da8207b3 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -126,7 +126,7 @@
  */
 
 struct stripe_head {
-	struct stripe_head	*hash_next, **hash_pprev; /* hash pointers */
+	struct hlist_node	hash;
 	struct list_head	lru;			/* inactive_list or handle_list */
 	struct raid5_private_data	*raid_conf;
 	sector_t		sector;			/* sector of this row */
@@ -152,7 +152,6 @@ struct stripe_head {
 #define	R5_Insync	3	/* rdev && rdev->in_sync at start */
 #define	R5_Wantread	4	/* want to schedule a read */
 #define	R5_Wantwrite	5
-#define	R5_Syncio	6	/* this io need to be accounted as resync io */
 #define	R5_Overlap	7	/* There is a pending overlapping request on this block */
 #define	R5_ReadError	8	/* seen a read error here recently */
 #define	R5_ReWrite	9	/* have tried to over-write the readerror */
@@ -205,7 +204,7 @@ struct disk_info {
 };
 
 struct raid5_private_data {
-	struct stripe_head	**stripe_hashtbl;
+	struct hlist_head	*stripe_hashtbl;
 	mddev_t			*mddev;
 	struct disk_info	*spare;
 	int			chunk_size, level, algorithm;
@@ -228,6 +227,8 @@ struct raid5_private_data {
 					    * Cleared when a sync completes.
 					    */
 
+	struct page 		*spare_page; /* Used when checking P/Q in raid6 */
+
 	/*
 	 * Free stripes pool
 	 */
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index e0a4faa9610..953b6df5d03 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -5,6 +5,16 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev);
 struct super_block *ramfs_get_sb(struct file_system_type *fs_type,
 	 int flags, const char *dev_name, void *data);
 
+#ifndef CONFIG_MMU
+extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
+						   unsigned long addr,
+						   unsigned long len,
+						   unsigned long pgoff,
+						   unsigned long flags);
+
+extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
+#endif
+
 extern struct file_operations ramfs_file_operations;
 extern struct vm_operations_struct generic_file_vm_ops;
 
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 33261f1d223..9d6fbeef210 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -71,6 +71,7 @@ void __anon_vma_link(struct vm_area_struct *);
  * rmap interfaces called when adding or removing pte of page
  */
 void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
+void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
 void page_add_file_rmap(struct page *);
 void page_remove_rmap(struct page *);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b0ad6f30679..7da33619d5d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -254,25 +254,12 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
  * The mm counters are not protected by its page_table_lock,
  * so must be incremented atomically.
  */
-#ifdef ATOMIC64_INIT
-#define set_mm_counter(mm, member, value) atomic64_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic64_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic64_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic64_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic64_dec(&(mm)->_##member)
-typedef atomic64_t mm_counter_t;
-#else /* !ATOMIC64_INIT */
-/*
- * The counters wrap back to 0 at 2^32 * PAGE_SIZE,
- * that is, at 16TB if using 4kB page size.
- */
-#define set_mm_counter(mm, member, value) atomic_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic_dec(&(mm)->_##member)
-typedef atomic_t mm_counter_t;
-#endif /* !ATOMIC64_INIT */
+#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
+typedef atomic_long_t mm_counter_t;
 
 #else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
 /*
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index a61c04f804b..5dc94e777fa 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -14,11 +14,7 @@
 typedef struct pbe {
 	unsigned long address;		/* address of the copy */
 	unsigned long orig_address;	/* original address of page */
-	swp_entry_t swap_address;	
-
-	struct pbe *next;	/* also used as scratch space at
-				 * end of page (see link, diskpage)
-				 */
+	struct pbe *next;
 } suspend_pagedir_t;
 
 #define for_each_pbe(pbe, pblist) \
@@ -77,6 +73,6 @@ unsigned long get_safe_page(gfp_t gfp_mask);
  * XXX: We try to keep some more pages free so that I/O operations succeed
  * without paging. Might this be more?
  */
-#define PAGES_FOR_IO	512
+#define PAGES_FOR_IO	1024
 
 #endif /* _LINUX_SWSUSP_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 508668f840b..556617bcf7a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -172,7 +172,6 @@ extern void swap_setup(void);
 
 /* linux/mm/vmscan.c */
 extern int try_to_free_pages(struct zone **, gfp_t);
-extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 extern int shrink_all_memory(int);
 extern int vm_swappiness;
 
@@ -210,6 +209,7 @@ extern unsigned int nr_swapfiles;
 extern struct swap_info_struct swap_info[];
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
+extern swp_entry_t get_swap_page_of_type(int type);
 extern int swap_duplicate(swp_entry_t);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern void swap_free(swp_entry_t);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 343d883d69c..64a36ba43b2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -60,12 +60,6 @@ struct writeback_control {
 };
 
 /*
- * ->writepage() return values (make these much larger than a pagesize, in
- * case some fs is returning number-of-bytes-written from writepage)
- */
-#define WRITEPAGE_ACTIVATE	0x80000	/* IO was not started: activate page */
-
-/*
  * fs/fs-writeback.c
  */	
 void writeback_inodes(struct writeback_control *wbc);