Merge branch 'block' of git://brick.kernel.dk/data/git/linux-2.6-block

* 'block' of git://brick.kernel.dk/data/git/linux-2.6-block: (67 commits)
  [PATCH] blk_queue_start_tag() shared map race fix
  [PATCH] Update axboe@suse.de email address
  [PATCH] fix creating zero sized bio mempools in low memory system
  [PATCH] CONFIG_BLOCK: blk_congestion_wait() fix
  [PATCH] CONFIG_BLOCK internal.h cleanups
  [PATCH] BLOCK: Make USB storage depend on SCSI rather than selecting it [try #6]
  [PATCH] BLOCK: Make it possible to disable the block layer [try #6]
  [PATCH] BLOCK: Remove no-longer necessary linux/buffer_head.h inclusions [try #6]
  [PATCH] BLOCK: Remove no-longer necessary linux/mpage.h inclusions [try #6]
  [PATCH] BLOCK: Move the msdos device ioctl compat stuff to the msdos driver [try #6]
  [PATCH] BLOCK: Move the Ext3 device ioctl compat stuff to the Ext3 driver [try #6]
  [PATCH] BLOCK: Move the Ext2 device ioctl compat stuff to the Ext2 driver [try #6]
  [PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the ReiserFS driver [try #6]
  [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6]
  [PATCH] BLOCK: Move the loop device ioctl compat stuff to the loop driver [try #6]
  [PATCH] BLOCK: Move __invalidate_device() to block_dev.c [try #6]
  [PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try #6]
  [PATCH] BLOCK: Remove dependence on existence of blockdev_superblock [try #6]
  [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #6]
  [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #6]
  ...

21 files changed, 429 insertions, 233 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 76bdaeab6f62..711c321a7011 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -148,6 +148,7 @@ struct bio {
 #define BIO_RW_BARRIER	2
 #define BIO_RW_FAILFAST	3
 #define BIO_RW_SYNC	4
+#define BIO_RW_META	5
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -178,6 +179,7 @@ struct bio {
 #define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
 #define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
 #define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
+#define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
 
 /*
  * will die
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cfde8b3ee919..1d79b8d4ca6d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_BLKDEV_H
 #define _LINUX_BLKDEV_H
 
+#include <linux/sched.h>
 #include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
@@ -16,6 +17,22 @@
 
 #include <asm/scatterlist.h>
 
+#ifdef CONFIG_LBD
+# include <asm/div64.h>
+# define sector_div(a, b) do_div(a, b)
+#else
+# define sector_div(n, b)( \
+{ \
+	int _res; \
+	_res = (n) % (b); \
+	(n) /= (b); \
+	_res; \
+} \
+)
+#endif
+
+#ifdef CONFIG_BLOCK
+
 struct scsi_ioctl_command;
 
 struct request_queue;
@@ -90,7 +107,7 @@ struct io_context {
 	atomic_t refcount;
 	struct task_struct *task;
 
-	int (*set_ioprio)(struct io_context *, unsigned int);
+	unsigned int ioprio_changed;
 
 	/*
 	 * For request batching
@@ -104,8 +121,7 @@ struct io_context {
 
 void put_io_context(struct io_context *ioc);
 void exit_io_context(void);
-struct io_context *current_io_context(gfp_t gfp_flags);
-struct io_context *get_io_context(gfp_t gfp_flags);
+struct io_context *get_io_context(gfp_t gfp_flags, int node);
 void copy_io_context(struct io_context **pdst, struct io_context **psrc);
 void swap_io_context(struct io_context **ioc1, struct io_context **ioc2);
 
@@ -120,6 +136,90 @@ struct request_list {
 	wait_queue_head_t wait[2];
 };
 
+/*
+ * request command types
+ */
+enum rq_cmd_type_bits {
+	REQ_TYPE_FS		= 1,	/* fs request */
+	REQ_TYPE_BLOCK_PC,		/* scsi command */
+	REQ_TYPE_SENSE,			/* sense request */
+	REQ_TYPE_PM_SUSPEND,		/* suspend request */
+	REQ_TYPE_PM_RESUME,		/* resume request */
+	REQ_TYPE_PM_SHUTDOWN,		/* shutdown request */
+	REQ_TYPE_FLUSH,			/* flush request */
+	REQ_TYPE_SPECIAL,		/* driver defined type */
+	REQ_TYPE_LINUX_BLOCK,		/* generic block layer message */
+	/*
+	 * for ATA/ATAPI devices. this really doesn't belong here, ide should
+	 * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
+	 * private REQ_LB opcodes to differentiate what type of request this is
+	 */
+	REQ_TYPE_ATA_CMD,
+	REQ_TYPE_ATA_TASK,
+	REQ_TYPE_ATA_TASKFILE,
+};
+
+/*
+ * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
+ * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
+ * SCSI cdb.
+ *
+ * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need,
+ * typically to differentiate REQ_TYPE_SPECIAL requests.
+ *
+ */
+enum {
+	/*
+	 * just examples for now
+	 */
+	REQ_LB_OP_EJECT	= 0x40,		/* eject request */
+	REQ_LB_OP_FLUSH = 0x41,		/* flush device */
+};
+
+/*
+ * request type modified bits. first three bits match BIO_RW* bits, important
+ */
+enum rq_flag_bits {
+	__REQ_RW,		/* not set, read. set, write */
+	__REQ_FAILFAST,		/* no low level driver retries */
+	__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_NOMERGE,		/* don't touch this for merging */
+	__REQ_STARTED,		/* drive already may have started this one */
+	__REQ_DONTPREP,		/* don't call prep for this one */
+	__REQ_QUEUED,		/* uses queueing */
+	__REQ_ELVPRIV,		/* elevator private data attached */
+	__REQ_FAILED,		/* set if the request failed */
+	__REQ_QUIET,		/* don't worry about errors */
+	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
+	__REQ_ORDERED_COLOR,	/* is before or after barrier */
+	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
+	__REQ_ALLOCED,		/* request came from our alloc pool */
+	__REQ_RW_META,		/* metadata io request */
+	__REQ_NR_BITS,		/* stops here */
+};
+
+#define REQ_RW		(1 << __REQ_RW)
+#define REQ_FAILFAST	(1 << __REQ_FAILFAST)
+#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_NOMERGE	(1 << __REQ_NOMERGE)
+#define REQ_STARTED	(1 << __REQ_STARTED)
+#define REQ_DONTPREP	(1 << __REQ_DONTPREP)
+#define REQ_QUEUED	(1 << __REQ_QUEUED)
+#define REQ_ELVPRIV	(1 << __REQ_ELVPRIV)
+#define REQ_FAILED	(1 << __REQ_FAILED)
+#define REQ_QUIET	(1 << __REQ_QUIET)
+#define REQ_PREEMPT	(1 << __REQ_PREEMPT)
+#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
+#define REQ_RW_SYNC	(1 << __REQ_RW_SYNC)
+#define REQ_ALLOCED	(1 << __REQ_ALLOCED)
+#define REQ_RW_META	(1 << __REQ_RW_META)
+
 #define BLK_MAX_CDB	16
 
 /*
@@ -129,30 +229,46 @@ struct request {
 	struct list_head queuelist;
 	struct list_head donelist;
 
-	unsigned long flags;		/* see REQ_ bits below */
+	request_queue_t *q;
+
+	unsigned int cmd_flags;
+	enum rq_cmd_type_bits cmd_type;
 
 	/* Maintain bio traversal state for part by part I/O submission.
 	 * hard_* are block layer internals, no driver should touch them!
 	 */
 
 	sector_t sector;		/* next sector to submit */
+	sector_t hard_sector;		/* next sector to complete */
 	unsigned long nr_sectors;	/* no. of sectors left to submit */
+	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
 	/* no. of sectors left to submit in the current segment */
 	unsigned int current_nr_sectors;
 
-	sector_t hard_sector;		/* next sector to complete */
-	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
 	/* no. of sectors left to complete in the current segment */
 	unsigned int hard_cur_sectors;
 
 	struct bio *bio;
 	struct bio *biotail;
 
+	struct hlist_node hash;	/* merge hash */
+	/*
+	 * The rb_node is only used inside the io scheduler, requests
+	 * are pruned when moved to the dispatch queue. So let the
+	 * completion_data share space with the rb_node.
+	 */
+	union {
+		struct rb_node rb_node;	/* sort/lookup */
+		void *completion_data;
+	};
+
+	/*
+	 * two pointers are available for the IO schedulers, if they need
+	 * more they have to dynamically allocate it.
+	 */
 	void *elevator_private;
-	void *completion_data;
+	void *elevator_private2;
 
-	int rq_status;	/* should split this into a few status bits */
-	int errors;
 	struct gendisk *rq_disk;
 	unsigned long start_time;
 
@@ -170,15 +286,13 @@ struct request {
 
 	unsigned short ioprio;
 
+	void *special;
+	char *buffer;
+
 	int tag;
+	int errors;
 
 	int ref_count;
-	request_queue_t *q;
-	struct request_list *rl;
-
-	struct completion *waiting;
-	void *special;
-	char *buffer;
 
 	/*
 	 * when request is used as a packet command carrier
@@ -195,80 +309,14 @@ struct request {
 	int retries;
 
 	/*
-	 * completion callback. end_io_data should be folded in with waiting
+	 * completion callback.
 	 */
 	rq_end_io_fn *end_io;
 	void *end_io_data;
 };
 
 /*
- * first three bits match BIO_RW* bits, important
- */
-enum rq_flag_bits {
-	__REQ_RW,		/* not set, read. set, write */
-	__REQ_FAILFAST,		/* no low level driver retries */
-	__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 */
-	__REQ_DONTPREP,		/* don't call prep for this one */
-	__REQ_QUEUED,		/* uses queueing */
-	__REQ_ELVPRIV,		/* elevator private data attached */
-	/*
-	 * for ATA/ATAPI devices
-	 */
-	__REQ_PC,		/* packet command (special) */
-	__REQ_BLOCK_PC,		/* queued down pc from block layer */
-	__REQ_SENSE,		/* sense retrival */
-
-	__REQ_FAILED,		/* set if the request failed */
-	__REQ_QUIET,		/* don't worry about errors */
-	__REQ_SPECIAL,		/* driver suplied command */
-	__REQ_DRIVE_CMD,
-	__REQ_DRIVE_TASK,
-	__REQ_DRIVE_TASKFILE,
-	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_PM_SUSPEND,	/* suspend request */
-	__REQ_PM_RESUME,	/* resume request */
-	__REQ_PM_SHUTDOWN,	/* shutdown request */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
-	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
-	__REQ_NR_BITS,		/* stops here */
-};
-
-#define REQ_RW		(1 << __REQ_RW)
-#define REQ_FAILFAST	(1 << __REQ_FAILFAST)
-#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)
-#define REQ_DONTPREP	(1 << __REQ_DONTPREP)
-#define REQ_QUEUED	(1 << __REQ_QUEUED)
-#define REQ_ELVPRIV	(1 << __REQ_ELVPRIV)
-#define REQ_PC		(1 << __REQ_PC)
-#define REQ_BLOCK_PC	(1 << __REQ_BLOCK_PC)
-#define REQ_SENSE	(1 << __REQ_SENSE)
-#define REQ_FAILED	(1 << __REQ_FAILED)
-#define REQ_QUIET	(1 << __REQ_QUIET)
-#define REQ_SPECIAL	(1 << __REQ_SPECIAL)
-#define REQ_DRIVE_CMD	(1 << __REQ_DRIVE_CMD)
-#define REQ_DRIVE_TASK	(1 << __REQ_DRIVE_TASK)
-#define REQ_DRIVE_TASKFILE	(1 << __REQ_DRIVE_TASKFILE)
-#define REQ_PREEMPT	(1 << __REQ_PREEMPT)
-#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_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
-#define REQ_RW_SYNC	(1 << __REQ_RW_SYNC)
-
-/*
- * State information carried for REQ_PM_SUSPEND and REQ_PM_RESUME
+ * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
  * requests. Some step values could eventually be made generic.
  */
 struct request_pm_state
@@ -432,9 +480,6 @@ struct request_queue
 	struct mutex		sysfs_lock;
 };
 
-#define RQ_INACTIVE		(-1)
-#define RQ_ACTIVE		1
-
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
@@ -490,25 +535,34 @@ enum {
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(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)
-#define blk_noretry_request(rq)	((rq)->flags & REQ_FAILFAST)
-#define blk_rq_started(rq)	((rq)->flags & REQ_STARTED)
+#define blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
+#define blk_pc_request(rq)	((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
+#define blk_special_request(rq)	((rq)->cmd_type == REQ_TYPE_SPECIAL)
+#define blk_sense_request(rq)	((rq)->cmd_type == REQ_TYPE_SENSE)
+
+#define blk_noretry_request(rq)	((rq)->cmd_flags & REQ_FAILFAST)
+#define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
 
 #define blk_account_rq(rq)	(blk_rq_started(rq) && blk_fs_request(rq))
 
-#define blk_pm_suspend_request(rq)	((rq)->flags & REQ_PM_SUSPEND)
-#define blk_pm_resume_request(rq)	((rq)->flags & REQ_PM_RESUME)
+#define blk_pm_suspend_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_SUSPEND)
+#define blk_pm_resume_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_RESUME)
 #define blk_pm_request(rq)	\
-	((rq)->flags & (REQ_PM_SUSPEND | REQ_PM_RESUME))
+	(blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
 
-#define blk_sorted_rq(rq)	((rq)->flags & REQ_SORTED)
-#define blk_barrier_rq(rq)	((rq)->flags & REQ_HARDBARRIER)
-#define blk_fua_rq(rq)		((rq)->flags & REQ_FUA)
+#define blk_sorted_rq(rq)	((rq)->cmd_flags & REQ_SORTED)
+#define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
+#define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq)		((rq)->flags & 1)
+#define rq_data_dir(rq)		((rq)->cmd_flags & 1)
+
+/*
+ * We regard a request as sync, if it's a READ or a SYNC write.
+ */
+#define rq_is_sync(rq)		(rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC)
+#define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
 
 static inline int blk_queue_full(struct request_queue *q, int rw)
 {
@@ -541,13 +595,7 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw)
 #define RQ_NOMERGE_FLAGS	\
 	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
 #define rq_mergeable(rq)	\
-	(!((rq)->flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
-
-/*
- * noop, requests are automagically marked as active/inactive by I/O
- * scheduler -- see elv_next_request
- */
-#define blk_queue_headactive(q, head_active)
+	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
 
 /*
  * q->prep_rq_fn return values
@@ -586,11 +634,6 @@ static inline void blk_queue_bounce(request_queue_t *q, struct bio **bio)
 	if ((rq->bio))			\
 		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
 
-struct sec_size {
-	unsigned block_size;
-	unsigned block_size_bits;
-};
-
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern void register_disk(struct gendisk *dev);
@@ -612,6 +655,7 @@ extern void blk_stop_queue(request_queue_t *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(request_queue_t *q);
 extern void blk_run_queue(request_queue_t *);
+extern void blk_start_queueing(request_queue_t *);
 extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *);
 extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int);
 extern int blk_rq_unmap_user(struct bio *, unsigned int);
@@ -655,16 +699,6 @@ extern void end_that_request_last(struct request *, int);
 extern void end_request(struct request *req, int uptodate);
 extern void blk_complete_request(struct request *);
 
-static inline int rq_all_done(struct request *rq, unsigned int nr_bytes)
-{
-	if (blk_fs_request(rq))
-		return (nr_bytes >= (rq->hard_nr_sectors << 9));
-	else if (blk_pc_request(rq))
-		return nr_bytes >= rq->data_len;
-
-	return 0;
-}
-
 /*
  * end_that_request_first/chunk() takes an uptodate argument. we account
  * any value <= as an io error. 0 means -EIO for compatability reasons,
@@ -679,21 +713,6 @@ static inline void blkdev_dequeue_request(struct request *req)
 }
 
 /*
- * This should be in elevator.h, but that requires pulling in rq and q
- */
-static inline void elv_dispatch_add_tail(struct request_queue *q,
-					 struct request *rq)
-{
-	if (q->last_merge == rq)
-		q->last_merge = NULL;
-	q->nr_sorted--;
-
-	q->end_sector = rq_end_sector(rq);
-	q->boundary_rq = rq;
-	list_add_tail(&rq->queuelist, &q->queue_head);
-}
-
-/*
  * Access functions for manipulating queue properties
  */
 extern request_queue_t *blk_init_queue_node(request_fn_proc *rfn,
@@ -737,7 +756,7 @@ extern void blk_put_queue(request_queue_t *);
  */
 #define blk_queue_tag_depth(q)		((q)->queue_tags->busy)
 #define blk_queue_tag_queue(q)		((q)->queue_tags->busy < (q)->queue_tags->max_depth)
-#define blk_rq_tagged(rq)		((rq)->flags & REQ_QUEUED)
+#define blk_rq_tagged(rq)		((rq)->cmd_flags & REQ_QUEUED)
 extern int blk_queue_start_tag(request_queue_t *, struct request *);
 extern struct request *blk_queue_find_tag(request_queue_t *, int);
 extern void blk_queue_end_tag(request_queue_t *, struct request *);
@@ -787,14 +806,6 @@ static inline int queue_dma_alignment(request_queue_t *q)
 	return retval;
 }
 
-static inline int bdev_dma_aligment(struct block_device *bdev)
-{
-	return queue_dma_alignment(bdev_get_queue(bdev));
-}
-
-#define blk_finished_io(nsects)	do { } while (0)
-#define blk_started_io(nsects)	do { } while (0)
-
 /* assumes size > 256 */
 static inline unsigned int blksize_bits(unsigned int size)
 {
@@ -824,24 +835,32 @@ struct work_struct;
 int kblockd_schedule_work(struct work_struct *work);
 void kblockd_flush(void);
 
-#ifdef CONFIG_LBD
-# include <asm/div64.h>
-# define sector_div(a, b) do_div(a, b)
-#else
-# define sector_div(n, b)( \
-{ \
-	int _res; \
-	_res = (n) % (b); \
-	(n) /= (b); \
-	_res; \
-} \
-)
-#endif 
-
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-*")
 
 
+#else /* CONFIG_BLOCK */
+/*
+ * stubs for when the block layer is configured out
+ */
+#define buffer_heads_over_limit 0
+
+static inline long blk_congestion_wait(int rw, long timeout)
+{
+	return io_schedule_timeout(timeout);
+}
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
+
+static inline void exit_io_context(void)
+{
+}
+
+#endif /* CONFIG_BLOCK */
+
 #endif
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 7520cc1ff9e2..b99a714fcac6 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -20,6 +20,7 @@ enum blktrace_cat {
 	BLK_TC_PC	= 1 << 9,	/* pc requests */
 	BLK_TC_NOTIFY	= 1 << 10,	/* special message */
 	BLK_TC_AHEAD	= 1 << 11,	/* readahead */
+	BLK_TC_META	= 1 << 12,	/* metadata */
 
 	BLK_TC_END	= 1 << 15,	/* only 16-bits, reminder */
 };
@@ -148,7 +149,7 @@ static inline void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 				    u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;
-	int rw = rq->flags & 0x03;
+	int rw = rq->cmd_flags & 0x03;
 
 	if (likely(!bt))
 		return;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 737e407d0cd1..131ffd37e716 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -14,6 +14,8 @@
 #include <linux/wait.h>
 #include <asm/atomic.h>
 
+#ifdef CONFIG_BLOCK
+
 enum bh_state_bits {
 	BH_Uptodate,	/* Contains valid data */
 	BH_Dirty,	/* Is dirty */
@@ -190,9 +192,7 @@ extern int buffer_heads_over_limit;
  * Generic address_space_operations implementations for buffer_head-backed
  * address_spaces.
  */
-int try_to_release_page(struct page * page, gfp_t gfp_mask);
 void block_invalidatepage(struct page *page, unsigned long offset);
-void do_invalidatepage(struct page *page, unsigned long offset);
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
 int block_read_full_page(struct page*, get_block_t*);
@@ -302,4 +302,19 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
+extern int __set_page_dirty_buffers(struct page *page);
+
+#else /* CONFIG_BLOCK */
+
+static inline void buffer_init(void) {}
+static inline int try_to_free_buffers(struct page *page) { return 1; }
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline int inode_has_buffers(struct inode *inode) { return 0; }
+static inline void invalidate_inode_buffers(struct inode *inode) {}
+static inline int remove_inode_buffers(struct inode *inode) { return 1; }
+static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) {}
+
+
+#endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h
index bea0255196c4..d61ef5951538 100644
--- a/include/linux/compat_ioctl.h
+++ b/include/linux/compat_ioctl.h
@@ -90,6 +90,7 @@ COMPATIBLE_IOCTL(FDTWADDLE)
 COMPATIBLE_IOCTL(FDFMTTRK)
 COMPATIBLE_IOCTL(FDRAWCMD)
 /* 0x12 */
+#ifdef CONFIG_BLOCK
 COMPATIBLE_IOCTL(BLKRASET)
 COMPATIBLE_IOCTL(BLKROSET)
 COMPATIBLE_IOCTL(BLKROGET)
@@ -103,6 +104,7 @@ COMPATIBLE_IOCTL(BLKTRACESETUP)
 COMPATIBLE_IOCTL(BLKTRACETEARDOWN)
 ULONG_IOCTL(BLKRASET)
 ULONG_IOCTL(BLKFRASET)
+#endif
 /* RAID */
 COMPATIBLE_IOCTL(RAID_VERSION)
 COMPATIBLE_IOCTL(GET_ARRAY_INFO)
@@ -395,12 +397,6 @@ COMPATIBLE_IOCTL(DVD_WRITE_STRUCT)
 COMPATIBLE_IOCTL(DVD_AUTH)
 /* pktcdvd */
 COMPATIBLE_IOCTL(PACKET_CTRL_CMD)
-/* Big L */
-ULONG_IOCTL(LOOP_SET_FD)
-ULONG_IOCTL(LOOP_CHANGE_FD)
-COMPATIBLE_IOCTL(LOOP_CLR_FD)
-COMPATIBLE_IOCTL(LOOP_GET_STATUS64)
-COMPATIBLE_IOCTL(LOOP_SET_STATUS64)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 1713ace808bf..b3370ef5164d 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -1,12 +1,16 @@
 #ifndef _LINUX_ELEVATOR_H
 #define _LINUX_ELEVATOR_H
 
+#include <linux/percpu.h>
+
+#ifdef CONFIG_BLOCK
+
 typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 				 struct bio *);
 
 typedef void (elevator_merge_req_fn) (request_queue_t *, struct request *, struct request *);
 
-typedef void (elevator_merged_fn) (request_queue_t *, struct request *);
+typedef void (elevator_merged_fn) (request_queue_t *, struct request *, int);
 
 typedef int (elevator_dispatch_fn) (request_queue_t *, int);
 
@@ -14,9 +18,9 @@ typedef void (elevator_add_req_fn) (request_queue_t *, struct request *);
 typedef int (elevator_queue_empty_fn) (request_queue_t *);
 typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct request *);
 typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *);
-typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *);
+typedef int (elevator_may_queue_fn) (request_queue_t *, int);
 
-typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, gfp_t);
+typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, gfp_t);
 typedef void (elevator_put_req_fn) (request_queue_t *, struct request *);
 typedef void (elevator_activate_req_fn) (request_queue_t *, struct request *);
 typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *);
@@ -82,19 +86,21 @@ struct elevator_queue
 	struct kobject kobj;
 	struct elevator_type *elevator_type;
 	struct mutex sysfs_lock;
+	struct hlist_head *hash;
 };
 
 /*
  * block elevator interface
  */
 extern void elv_dispatch_sort(request_queue_t *, struct request *);
+extern void elv_dispatch_add_tail(request_queue_t *, struct request *);
 extern void elv_add_request(request_queue_t *, struct request *, int, int);
 extern void __elv_add_request(request_queue_t *, struct request *, int, int);
 extern void elv_insert(request_queue_t *, struct request *, int);
 extern int elv_merge(request_queue_t *, struct request **, struct bio *);
 extern void elv_merge_requests(request_queue_t *, struct request *,
 			       struct request *);
-extern void elv_merged_request(request_queue_t *, struct request *);
+extern void elv_merged_request(request_queue_t *, struct request *, int);
 extern void elv_dequeue_request(request_queue_t *, struct request *);
 extern void elv_requeue_request(request_queue_t *, struct request *);
 extern int elv_queue_empty(request_queue_t *);
@@ -103,9 +109,9 @@ extern struct request *elv_former_request(request_queue_t *, struct request *);
 extern struct request *elv_latter_request(request_queue_t *, struct request *);
 extern int elv_register_queue(request_queue_t *q);
 extern void elv_unregister_queue(request_queue_t *q);
-extern int elv_may_queue(request_queue_t *, int, struct bio *);
+extern int elv_may_queue(request_queue_t *, int);
 extern void elv_completed_request(request_queue_t *, struct request *);
-extern int elv_set_request(request_queue_t *, struct request *, struct bio *, gfp_t);
+extern int elv_set_request(request_queue_t *, struct request *, gfp_t);
 extern void elv_put_request(request_queue_t *, struct request *);
 
 /*
@@ -125,6 +131,19 @@ extern void elevator_exit(elevator_t *);
 extern int elv_rq_merge_ok(struct request *, struct bio *);
 
 /*
+ * Helper functions.
+ */
+extern struct request *elv_rb_former_request(request_queue_t *, struct request *);
+extern struct request *elv_rb_latter_request(request_queue_t *, struct request *);
+
+/*
+ * rb support functions.
+ */
+extern struct request *elv_rb_add(struct rb_root *, struct request *);
+extern void elv_rb_del(struct rb_root *, struct request *);
+extern struct request *elv_rb_find(struct rb_root *, sector_t);
+
+/*
  * Return values from elevator merger
  */
 #define ELEVATOR_NO_MERGE	0
@@ -149,5 +168,42 @@ enum {
 };
 
 #define rq_end_sector(rq)	((rq)->sector + (rq)->nr_sectors)
+#define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
+
+/*
+ * Hack to reuse the donelist list_head as the fifo time holder while
+ * the request is in the io scheduler. Saves an unsigned long in rq.
+ */
+#define rq_fifo_time(rq)	((unsigned long) (rq)->donelist.next)
+#define rq_set_fifo_time(rq,exp)	((rq)->donelist.next = (void *) (exp))
+#define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
+#define rq_fifo_clear(rq)	do {		\
+	list_del_init(&(rq)->queuelist);	\
+	INIT_LIST_HEAD(&(rq)->donelist);	\
+	} while (0)
 
+/*
+ * io context count accounting
+ */
+#define elv_ioc_count_mod(name, __val)				\
+	do {							\
+		preempt_disable();				\
+		__get_cpu_var(name) += (__val);			\
+		preempt_enable();				\
+	} while (0)
+
+#define elv_ioc_count_inc(name)	elv_ioc_count_mod(name, 1)
+#define elv_ioc_count_dec(name)	elv_ioc_count_mod(name, -1)
+
+#define elv_ioc_count_read(name)				\
+({								\
+	unsigned long __val = 0;				\
+	int __cpu;						\
+	smp_wmb();						\
+	for_each_possible_cpu(__cpu)				\
+		__val += per_cpu(name, __cpu);			\
+	__val;							\
+})
+
+#endif /* CONFIG_BLOCK */
 #endif
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index 33a1aa107329..153d755376a4 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -165,41 +165,49 @@ struct ext2_group_desc
 #define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
 
 /*
- * Inode flags
+ * Inode flags (GETFLAGS/SETFLAGS)
  */
-#define	EXT2_SECRM_FL			0x00000001 /* Secure deletion */
-#define	EXT2_UNRM_FL			0x00000002 /* Undelete */
-#define	EXT2_COMPR_FL			0x00000004 /* Compress file */
-#define EXT2_SYNC_FL			0x00000008 /* Synchronous updates */
-#define EXT2_IMMUTABLE_FL		0x00000010 /* Immutable file */
-#define EXT2_APPEND_FL			0x00000020 /* writes to file may only append */
-#define EXT2_NODUMP_FL			0x00000040 /* do not dump file */
-#define EXT2_NOATIME_FL			0x00000080 /* do not update atime */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
 /* Reserved for compression usage... */
-#define EXT2_DIRTY_FL			0x00000100
-#define EXT2_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
-#define EXT2_NOCOMP_FL			0x00000400 /* Don't compress */
-#define EXT2_ECOMPR_FL			0x00000800 /* Compression error */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
 /* End compression flags --- maybe not all used */	
-#define EXT2_BTREE_FL			0x00001000 /* btree format dir */
-#define EXT2_INDEX_FL			0x00001000 /* hash-indexed directory */
-#define EXT2_IMAGIC_FL			0x00002000 /* AFS directory */
-#define EXT2_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
-#define EXT2_NOTAIL_FL			0x00008000 /* file tail should not be merged */
-#define EXT2_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
-#define EXT2_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
-#define EXT2_RESERVED_FL		0x80000000 /* reserved for ext2 lib */
-
-#define EXT2_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
-#define EXT2_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
 
 /*
  * ioctl commands
  */
-#define	EXT2_IOC_GETFLAGS		_IOR('f', 1, long)
-#define	EXT2_IOC_SETFLAGS		_IOW('f', 2, long)
-#define	EXT2_IOC_GETVERSION		_IOR('v', 1, long)
-#define	EXT2_IOC_SETVERSION		_IOW('v', 2, long)
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
 
 /*
  * Structure of an inode on the disk
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index cc08f56750da..11cca1bdc0c7 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -216,14 +216,14 @@ struct ext3_new_group_data {
 /*
  * ioctl commands
  */
-#define	EXT3_IOC_GETFLAGS		_IOR('f', 1, long)
-#define	EXT3_IOC_SETFLAGS		_IOW('f', 2, long)
+#define	EXT3_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT3_IOC_SETFLAGS		FS_IOC_SETFLAGS
 #define	EXT3_IOC_GETVERSION		_IOR('f', 3, long)
 #define	EXT3_IOC_SETVERSION		_IOW('f', 4, long)
 #define EXT3_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
 #define EXT3_IOC_GROUP_ADD		_IOW('f', 8,struct ext3_new_group_input)
-#define	EXT3_IOC_GETVERSION_OLD		_IOR('v', 1, long)
-#define	EXT3_IOC_SETVERSION_OLD		_IOW('v', 2, long)
+#define	EXT3_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
+#define	EXT3_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
 #ifdef CONFIG_JBD_DEBUG
 #define EXT3_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
 #endif
@@ -231,6 +231,23 @@ struct ext3_new_group_data {
 #define EXT3_IOC_SETRSVSZ		_IOW('f', 6, long)
 
 /*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT3_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT3_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT3_IOC32_GETVERSION		_IOR('f', 3, int)
+#define EXT3_IOC32_SETVERSION		_IOW('f', 4, int)
+#define EXT3_IOC32_GETRSVSZ		_IOR('f', 5, int)
+#define EXT3_IOC32_SETRSVSZ		_IOW('f', 6, int)
+#define EXT3_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
+#ifdef CONFIG_JBD_DEBUG
+#define EXT3_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
+#endif
+#define EXT3_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
+#define EXT3_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
+
+
+/*
  *  Mount options
  */
 struct ext3_mount_options {
@@ -812,6 +829,7 @@ extern void ext3_set_aops(struct inode *inode);
 /* ioctl.c */
 extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
 		       unsigned long);
+extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 extern int ext3_orphan_add(handle_t *, struct inode *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6eafbe309483..5baf3a153403 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -79,8 +79,8 @@ extern int dir_notify_enable;
 #define WRITE 1
 #define READA 2		/* read-ahead  - don't block if no resources */
 #define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
-#define SPECIAL 4	/* For non-blockdevice requests in request queue */
 #define READ_SYNC	(READ | (1 << BIO_RW_SYNC))
+#define READ_META	(READ | (1 << BIO_RW_META))
 #define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
 #define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
 
@@ -217,6 +217,45 @@ extern int dir_notify_enable;
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
 
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+#define FS_ECOMPR_FL			0x00000800 /* Compression error */
+/* End compression flags --- maybe not all used */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
 #define SYNC_FILE_RANGE_WAIT_BEFORE	1
 #define SYNC_FILE_RANGE_WRITE		2
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
@@ -1443,6 +1482,7 @@ extern void __init vfs_caches_init(unsigned long);
 extern void putname(const char *name);
 #endif
 
+#ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern int unregister_blkdev(unsigned int, const char *);
 extern struct block_device *bdget(dev_t);
@@ -1451,11 +1491,15 @@ extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern struct block_device *open_by_devnum(dev_t, unsigned);
 extern struct block_device *open_partition_by_devnum(dev_t, unsigned);
-extern const struct file_operations def_blk_fops;
 extern const struct address_space_operations def_blk_aops;
+#else
+static inline void bd_forget(struct inode *inode) {}
+#endif
+extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
 extern const struct file_operations bad_sock_fops;
 extern const struct file_operations def_fifo_fops;
+#ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
@@ -1471,6 +1515,7 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *);
 #define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
 #define bd_release_from_disk(bdev, disk)	bd_release(bdev)
 #endif
+#endif
 
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_HASH_SIZE	255
@@ -1484,14 +1529,19 @@ extern int chrdev_open(struct inode *, struct file *);
 extern void chrdev_show(struct seq_file *,off_t);
 
 /* fs/block_dev.c */
-#define BLKDEV_MAJOR_HASH_SIZE	255
 #define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_HASH_SIZE	255
 extern const char *__bdevname(dev_t, char *buffer);
 extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
 extern struct block_device *open_bdev_excl(const char *, int, void *);
 extern void close_bdev_excl(struct block_device *);
 extern void blkdev_show(struct seq_file *,off_t);
+#else
+#define BLKDEV_MAJOR_HASH_SIZE	0
+#endif
 
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 
@@ -1505,6 +1555,7 @@ extern const struct file_operations rdwr_fifo_fops;
 
 extern int fs_may_remount_ro(struct super_block *);
 
+#ifdef CONFIG_BLOCK
 /*
  * return READ, READA, or WRITE
  */
@@ -1516,9 +1567,10 @@ extern int fs_may_remount_ro(struct super_block *);
 #define bio_data_dir(bio)	((bio)->bi_rw & 1)
 
 extern int check_disk_change(struct block_device *);
-extern int invalidate_inodes(struct super_block *);
 extern int __invalidate_device(struct block_device *);
 extern int invalidate_partition(struct gendisk *, int);
+#endif
+extern int invalidate_inodes(struct super_block *);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 unsigned long invalidate_inode_pages(struct address_space *mapping);
@@ -1546,11 +1598,14 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping,
 extern long do_fsync(struct file *file, int datasync);
 extern void sync_supers(void);
 extern void sync_filesystems(int wait);
+extern void __fsync_super(struct super_block *sb);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
 extern int do_remount_sb(struct super_block *sb, int flags,
 			 void *data, int force);
+#ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
+#endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int permission(struct inode *, int, struct nameidata *);
 extern int generic_permission(struct inode *, int,
@@ -1633,9 +1688,11 @@ static inline void insert_inode_hash(struct inode *inode) {
 extern struct file * get_empty_filp(void);
 extern void file_move(struct file *f, struct list_head *list);
 extern void file_kill(struct file *f);
+#ifdef CONFIG_BLOCK
 struct bio;
 extern void submit_bio(int, struct bio *);
 extern int bdev_read_only(struct block_device *);
+#endif
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
@@ -1716,6 +1773,7 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
 				actor);
 }
 
+#ifdef CONFIG_BLOCK
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct block_device *bdev, const struct iovec *iov, loff_t offset,
 	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
@@ -1753,6 +1811,7 @@ static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
 	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
 				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
 }
+#endif
 
 extern const struct file_operations generic_ro_fops;
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index e4af57e87c17..41f276fdd185 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -11,6 +11,8 @@
 
 #include <linux/types.h>
 
+#ifdef CONFIG_BLOCK
+
 enum {
 /* These three have identical behaviour; use the second one if DOS FDISK gets
    confused about extended/logical partitions starting past cylinder 1023. */
@@ -420,3 +422,5 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index)
 #endif
 
 #endif
+
+#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7b703b6d4358..4edf1934e5ca 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -743,7 +743,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long
 		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
 void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
 
-int __set_page_dirty_buffers(struct page *page);
+extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
+extern void do_invalidatepage(struct page *page, unsigned long offset);
+
 int __set_page_dirty_nobuffers(struct page *page);
 int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 3ca880463c47..cc5fb75af78a 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -9,6 +9,7 @@
  * (And no, it doesn't do the #ifdef __MPAGE_H thing, and it doesn't do
  * nested includes.  Get it right in the .c file).
  */
+#ifdef CONFIG_BLOCK
 
 struct writeback_control;
 typedef int (writepage_t)(struct page *page, struct writeback_control *wbc);
@@ -21,8 +22,4 @@ int mpage_writepages(struct address_space *mapping,
 int mpage_writepage(struct page *page, get_block_t *get_block,
 		struct writeback_control *wbc);
 
-static inline int
-generic_writepages(struct address_space *mapping, struct writeback_control *wbc)
-{
-	return mpage_writepages(mapping, wbc, NULL);
-}
+#endif
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index eb3e547c8fee..c588709acbbc 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -53,6 +53,8 @@
 #include <linux/raid/md_u.h>
 #include <linux/raid/md_k.h>
 
+#ifdef CONFIG_MD
+
 /*
  * Different major versions are not compatible.
  * Different minor versions are only downward compatible.
@@ -95,5 +97,6 @@ extern void md_new_event(mddev_t *mddev);
 
 extern void md_update_sb(mddev_t * mddev);
 
+#endif /* CONFIG_MD */
 #endif 
 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index d28890295852..920b94fe31fa 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -18,6 +18,8 @@
 /* and dm-bio-list.h is not under include/linux because.... ??? */
 #include "../../../drivers/md/dm-bio-list.h"
 
+#ifdef CONFIG_BLOCK
+
 #define	LEVEL_MULTIPATH		(-4)
 #define	LEVEL_LINEAR		(-1)
 #define	LEVEL_FAULTY		(-5)
@@ -362,5 +364,6 @@ static inline void safe_put_page(struct page *p)
 	if (p) put_page(p);
 }
 
+#endif /* CONFIG_BLOCK */
 #endif
 
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index 00b340ba6612..b160fb18e8d6 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -17,5 +17,6 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 
 extern const struct file_operations ramfs_file_operations;
 extern struct vm_operations_struct generic_file_vm_ops;
+extern int __init init_rootfs(void);
 
 #endif
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 8d5382e62c08..344bc3495ddb 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -133,7 +133,7 @@ static inline void rb_set_color(struct rb_node *rb, int color)
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
 #define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
-#define RB_EMPTY_NODE(node)	(rb_parent(node) != node)
+#define RB_EMPTY_NODE(node)	(rb_parent(node) == node)
 #define RB_CLEAR_NODE(node)	(rb_set_parent(node, node))
 
 extern void rb_insert_color(struct rb_node *, struct rb_root *);
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 28493ffaafe7..9c63abffd7b2 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -807,21 +807,19 @@ struct stat_data_v1 {
 #define set_sd_v1_first_direct_byte(sdp,v) \
                                 ((sdp)->sd_first_direct_byte = cpu_to_le32(v))
 
-#include <linux/ext2_fs.h>
-
 /* inode flags stored in sd_attrs (nee sd_reserved) */
 
 /* we want common flags to have the same values as in ext2,
    so chattr(1) will work without problems */
-#define REISERFS_IMMUTABLE_FL EXT2_IMMUTABLE_FL
-#define REISERFS_APPEND_FL    EXT2_APPEND_FL
-#define REISERFS_SYNC_FL      EXT2_SYNC_FL
-#define REISERFS_NOATIME_FL   EXT2_NOATIME_FL
-#define REISERFS_NODUMP_FL    EXT2_NODUMP_FL
-#define REISERFS_SECRM_FL     EXT2_SECRM_FL
-#define REISERFS_UNRM_FL      EXT2_UNRM_FL
-#define REISERFS_COMPR_FL     EXT2_COMPR_FL
-#define REISERFS_NOTAIL_FL    EXT2_NOTAIL_FL
+#define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL
+#define REISERFS_APPEND_FL    FS_APPEND_FL
+#define REISERFS_SYNC_FL      FS_SYNC_FL
+#define REISERFS_NOATIME_FL   FS_NOATIME_FL
+#define REISERFS_NODUMP_FL    FS_NODUMP_FL
+#define REISERFS_SECRM_FL     FS_SECRM_FL
+#define REISERFS_UNRM_FL      FS_UNRM_FL
+#define REISERFS_COMPR_FL     FS_COMPR_FL
+#define REISERFS_NOTAIL_FL    FS_NOTAIL_FL
 
 /* persistent flags that file inherits from the parent directory */
 #define REISERFS_INHERIT_MASK ( REISERFS_IMMUTABLE_FL |	\
@@ -2163,15 +2161,24 @@ __u32 r5_hash(const signed char *msg, int len);
 /* prototypes from ioctl.c */
 int reiserfs_ioctl(struct inode *inode, struct file *filp,
 		   unsigned int cmd, unsigned long arg);
+long reiserfs_compat_ioctl(struct file *filp,
+		   unsigned int cmd, unsigned long arg);
 
 /* ioctl's command */
 #define REISERFS_IOC_UNPACK		_IOW(0xCD,1,long)
 /* define following flags to be the same as in ext2, so that chattr(1),
    lsattr(1) will work with us. */
-#define REISERFS_IOC_GETFLAGS		EXT2_IOC_GETFLAGS
-#define REISERFS_IOC_SETFLAGS		EXT2_IOC_SETFLAGS
-#define REISERFS_IOC_GETVERSION		EXT2_IOC_GETVERSION
-#define REISERFS_IOC_SETVERSION		EXT2_IOC_SETVERSION
+#define REISERFS_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define REISERFS_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define REISERFS_IOC_GETVERSION		FS_IOC_GETVERSION
+#define REISERFS_IOC_SETVERSION		FS_IOC_SETVERSION
+
+/* the 32 bit compat definitions with int argument */
+#define REISERFS_IOC32_UNPACK		_IOW(0xCD, 1, int)
+#define REISERFS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define REISERFS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define REISERFS_IOC32_GETVERSION	FS_IOC32_GETVERSION
+#define REISERFS_IOC32_SETVERSION	FS_IOC32_SETVERSION
 
 /* Locking primitives */
 /* Right now we are still falling back to (un)lock_kernel, but eventually that
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a06fc89cf6e5..fc4a9873ec10 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -710,7 +710,6 @@ extern unsigned int max_cache_size;
 
 
 struct io_context;			/* See blkdev.h */
-void exit_io_context(void);
 struct cpuset;
 
 #define NGROUPS_SMALL		32
diff --git a/include/linux/tty.h b/include/linux/tty.h
index ea4c2605f8da..44091c0db0b4 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -307,6 +307,9 @@ extern void tty_ldisc_put(int);
 extern void tty_wakeup(struct tty_struct *tty);
 extern void tty_ldisc_flush(struct tty_struct *tty);
 
+extern int tty_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
+		     unsigned long arg);
+
 extern struct mutex tty_mutex;
 
 /* n_tty.c */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 9d4074ecd0cd..4f4d98addb44 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -111,6 +111,8 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
 }
 
 int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
+extern int generic_writepages(struct address_space *mapping,
+			      struct writeback_control *wbc);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
 int sync_page_range(struct inode *inode, struct address_space *mapping,
 			loff_t pos, loff_t count);
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index d04d05adfa9b..c247a28259bc 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -6,7 +6,6 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 
-
 #define MSG_SIMPLE_TAG	0x20
 #define MSG_HEAD_TAG	0x21
 #define MSG_ORDERED_TAG	0x22
@@ -14,6 +13,7 @@
 #define SCSI_NO_TAG	(-1)    /* identify no tag in use */
 
 
+#ifdef CONFIG_BLOCK
 
 /**
  * scsi_get_tag_type - get the type of tag the device supports
@@ -100,7 +100,7 @@ static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 	struct scsi_device *sdev = cmd->device;
 
         if (blk_rq_tagged(req)) {
-		if (sdev->ordered_tags && req->flags & REQ_HARDBARRIER)
+		if (sdev->ordered_tags && req->cmd_flags & REQ_HARDBARRIER)
         	        *msg++ = MSG_ORDERED_TAG;
         	else
         	        *msg++ = MSG_SIMPLE_TAG;
@@ -144,4 +144,5 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth)
 	return shost->bqt ? 0 : -ENOMEM;
 }
 
+#endif /* CONFIG_BLOCK */
 #endif /* _SCSI_SCSI_TCQ_H */