From 4aff5e2333c9a1609662f2091f55c3f6fffdad36 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 10 Aug 2006 08:44:47 +0200
Subject: [PATCH] Split struct request ->flags into two parts

Right now ->flags is a bit of a mess: some are request types, and
others are just modifiers. Clean this up by splitting it into
->cmd_type and ->cmd_flags. This allows introduction of generic
Linux block message types, useful for sending generic Linux commands
to block devices.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h       | 180 ++++++++++++++++++++++++-------------------
 include/linux/blktrace_api.h |   2 +-
 2 files changed, 100 insertions(+), 82 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cfde8b3ee919..b2a412cf468f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -120,6 +120,86 @@ 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_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 BLK_MAX_CDB	16
 
 /*
@@ -129,7 +209,8 @@ struct request {
 	struct list_head queuelist;
 	struct list_head donelist;
 
-	unsigned long flags;		/* see REQ_ bits below */
+	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!
@@ -202,73 +283,7 @@ struct request {
 };
 
 /*
- * 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
@@ -490,25 +505,28 @@ 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)
 
 static inline int blk_queue_full(struct request_queue *q, int rw)
 {
@@ -541,7 +559,7 @@ 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)))
+	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
 
 /*
  * noop, requests are automagically marked as active/inactive by I/O
@@ -737,7 +755,7 @@ 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 *);
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 7520cc1ff9e2..ea48eb1b3fd3 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -148,7 +148,7 @@ 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;
-- 
cgit v1.2.3


From 9817064b68fef7e4580c6df1ea597e106b9ff88b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Fri, 28 Jul 2006 09:23:08 +0200
Subject: [PATCH] elevator: move the backmerging logic into the elevator core

Right now, every IO scheduler implements its own backmerging (except for
noop, which does no merging). That results in duplicated code for
essentially the same operation, which is never a good thing. This patch
moves the backmerging out of the io schedulers and into the elevator
core. We save 1.6kb of text and as a bonus get backmerging for noop as
well. Win-win!

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h   | 17 ++---------------
 include/linux/elevator.h |  2 ++
 2 files changed, 4 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b2a412cf468f..8f5486964671 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -229,6 +229,8 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
+	struct hlist_node hash;	/* merge hash */
+
 	void *elevator_private;
 	void *completion_data;
 
@@ -696,21 +698,6 @@ static inline void blkdev_dequeue_request(struct request *req)
 	elv_dequeue_request(req->q, 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
  */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 1713ace808bf..2c270e90b33e 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -82,12 +82,14 @@ 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);
-- 
cgit v1.2.3


From 10fd48f2376db52f08bf0420d2c4f580e39269e1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Tue, 11 Jul 2006 21:15:52 +0200
Subject: [PATCH] rbtree: fixed reversed RB_EMPTY_NODE and rb_next/prev

The conditions got reserved. Also make rb_next() and rb_prev() check
for the empty condition.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/rbtree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

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 *);
-- 
cgit v1.2.3


From 2e662b65f05d550b6799ed6bfa9963b82279e6b7 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 13 Jul 2006 11:55:04 +0200
Subject: [PATCH] elevator: abstract out the rbtree sort handling

The rbtree sort/lookup/reposition logic is mostly duplicated in
cfq/deadline/as, so move it to the elevator core. The io schedulers
still provide the actual rb root, as we don't want to impose any sort
of specific handling on the schedulers.

Introduce the helpers and rb_node in struct request to help migrate the
IO schedulers.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h   |  1 +
 include/linux/elevator.h | 18 ++++++++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8f5486964671..a905c4934a55 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -230,6 +230,7 @@ struct request {
 	struct bio *biotail;
 
 	struct hlist_node hash;	/* merge hash */
+	struct rb_node rb_node;	/* sort/lookup */
 
 	void *elevator_private;
 	void *completion_data;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2c270e90b33e..95b2a04b969c 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -6,7 +6,7 @@ typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 
 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);
 
@@ -96,7 +96,7 @@ 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 *);
@@ -126,6 +126,19 @@ extern int elevator_init(request_queue_t *, char *);
 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
  */
@@ -151,5 +164,6 @@ enum {
 };
 
 #define rq_end_sector(rq)	((rq)->sector + (rq)->nr_sectors)
+#define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 
 #endif
-- 
cgit v1.2.3


From 1fbfdfcddff4df188b24d9d05271a76a85064583 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Tue, 11 Jul 2006 21:49:15 +0200
Subject: [PATCH] elevator: introduce a way to reuse rq for internal FIFO
 handling

The io schedulers can use this instead of having to allocate space for
it themselves.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/elevator.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 95b2a04b969c..0e7b1a733919 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -166,4 +166,16 @@ 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)
+
 #endif
-- 
cgit v1.2.3


From 9e2585a8a23f3a42f815b2a638725d85a921cd65 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Fri, 28 Jul 2006 09:26:13 +0200
Subject: [PATCH] as-iosched: remove arq->is_sync member

We can track this in struct request.

Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Nick Piggin <npiggin@suse.de>
---
 include/linux/blkdev.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a905c4934a55..55ef6efe3eb5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -531,6 +531,11 @@ enum {
 
 #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)
+
 static inline int blk_queue_full(struct request_queue *q, int rw)
 {
 	if (rw == READ)
-- 
cgit v1.2.3


From ff7d145fd911266ae42af7552edc32681c01addb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Wed, 12 Jul 2006 14:04:37 +0200
Subject: [PATCH] Add one more pointer to struct request for IO scheduler usage

Then we have enough room in the request to get rid of the dynamic
allocations in CFQ/AS.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 55ef6efe3eb5..d2dc17151f6c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -232,7 +232,13 @@ struct request {
 	struct hlist_node hash;	/* merge hash */
 	struct rb_node rb_node;	/* sort/lookup */
 
+	/*
+	 * two pointers are available for the IO schedulers, if they need
+	 * more they have to dynamically allocate it.
+	 */
 	void *elevator_private;
+	void *elevator_private2;
+
 	void *completion_data;
 
 	int rq_status;	/* should split this into a few status bits */
-- 
cgit v1.2.3


From c00895ab2f08df7044e58ee01c38bf0a661ea0eb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 30 Sep 2006 20:29:12 +0200
Subject: [PATCH] Remove ->waiting member from struct request

As the comments indicates in blkdev.h, we can fold it into ->end_io_data
usage as that is really what ->waiting is. Fixup the users of
blk_end_sync_rq().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d2dc17151f6c..604f23189097 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -266,7 +266,6 @@ struct request {
 	request_queue_t *q;
 	struct request_list *rl;
 
-	struct completion *waiting;
 	void *special;
 	char *buffer;
 
@@ -285,7 +284,7 @@ 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;
-- 
cgit v1.2.3


From 49171e5c6f414d49a061b5c1c84967c2eb569822 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 10 Aug 2006 08:59:11 +0200
Subject: [PATCH] Remove struct request_list from struct request

It is always identical to &q->rq, and we only use it for detecting
whether this request came out of our mempool or not. So replace it
with an additional ->flags bit flag.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 604f23189097..d4c1dd046e27 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -180,6 +180,7 @@ enum rq_flag_bits {
 	__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_NR_BITS,		/* stops here */
 };
 
@@ -199,6 +200,7 @@ enum rq_flag_bits {
 #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 BLK_MAX_CDB	16
 
@@ -264,7 +266,6 @@ struct request {
 
 	int ref_count;
 	request_queue_t *q;
-	struct request_list *rl;
 
 	void *special;
 	char *buffer;
-- 
cgit v1.2.3


From cdd6026217c0e4cda2efce1bdc318661bef1f66f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Fri, 28 Jul 2006 09:32:07 +0200
Subject: [PATCH] Remove ->rq_status from struct request

After Christophs SCSI change, the only usage left is RQ_ACTIVE
and RQ_INACTIVE. The block layer sets RQ_INACTIVE right before freeing
the request, so any check for RQ_INACTIVE in a driver is a bug and
indicates use-after-free.

So kill/clean the remaining users, straight forward.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4c1dd046e27..8a3e309e0842 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -243,8 +243,6 @@ struct request {
 
 	void *completion_data;
 
-	int rq_status;	/* should split this into a few status bits */
-	int errors;
 	struct gendisk *rq_disk;
 	unsigned long start_time;
 
@@ -262,14 +260,16 @@ struct request {
 
 	unsigned short ioprio;
 
-	int tag;
-
-	int ref_count;
 	request_queue_t *q;
 
 	void *special;
 	char *buffer;
 
+	int tag;
+	int errors;
+
+	int ref_count;
+
 	/*
 	 * when request is used as a packet command carrier
 	 */
@@ -456,9 +456,6 @@ 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 */
-- 
cgit v1.2.3


From cb78b285c8f9d59b0d4e4f6a54c2977ce1d9b880 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Fri, 28 Jul 2006 09:32:57 +0200
Subject: [PATCH] Drop useless bio passing in may_queue/set_request API

It's not needed for anything, so kill the bio passing.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/elevator.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 0e7b1a733919..cc81645a3e18 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -14,9 +14,9 @@ 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 *);
@@ -105,9 +105,9 @@ 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 *);
 
 /*
-- 
cgit v1.2.3


From e6a1c874a064e7d07f24986aba7cd537b7f4a25d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 10 Aug 2006 09:00:21 +0200
Subject: [PATCH] struct request: shrink and optimize some more

Move some members around and unionize completion_data and rb_node since
they cannot ever be used at the same time.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8a3e309e0842..a1e288069e2e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -211,6 +211,8 @@ struct request {
 	struct list_head queuelist;
 	struct list_head donelist;
 
+	request_queue_t *q;
+
 	unsigned int cmd_flags;
 	enum rq_cmd_type_bits cmd_type;
 
@@ -219,12 +221,12 @@ struct request {
 	 */
 
 	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;
 
@@ -232,7 +234,15 @@ struct request {
 	struct bio *biotail;
 
 	struct hlist_node hash;	/* merge hash */
-	struct rb_node rb_node;	/* sort/lookup */
+	/*
+	 * 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
@@ -241,8 +251,6 @@ struct request {
 	void *elevator_private;
 	void *elevator_private2;
 
-	void *completion_data;
-
 	struct gendisk *rq_disk;
 	unsigned long start_time;
 
@@ -260,8 +268,6 @@ struct request {
 
 	unsigned short ioprio;
 
-	request_queue_t *q;
-
 	void *special;
 	char *buffer;
 
-- 
cgit v1.2.3


From fc46379daf90dce57bf765c81d3b39f55150aac2 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Tue, 29 Aug 2006 09:05:44 +0200
Subject: [PATCH] cfq-iosched: kill cfq_exit_lock

cfq_exit_lock is protecting two things now:

- The per-ioc rbtree of cfq_io_contexts

- The per-cfqd linked list of cfq_io_contexts

The per-cfqd linked list can be protected by the queue lock, as it is (by
definition) per cfqd as the queue lock is.

The per-ioc rbtree is mainly used and updated by the process itself only.
The only outside use is the io priority changing. If we move the
priority changing to not browsing the rbtree, we can remove any locking
from the rbtree updates and lookup completely. Let the sys_ioprio syscall
just mark processes as having the iopriority changed and lazily update
the private cfq io contexts the next time io is queued, and we can
remove this locking as well.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a1e288069e2e..79cb9fa8034a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -90,7 +90,7 @@ 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
-- 
cgit v1.2.3


From 4a893e837bb470867d74c05d6c6b97bba5a96185 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Sat, 22 Jul 2006 15:37:43 +0200
Subject: [PATCH] elevator: define ioc counting mechanism

None of the in-kernel primitives for handling "atomic" counting seem
to be a good fit. We need something that is essentially free for
incrementing/decrementing, while the read side may be more expensive
as we only ever need to do that when a device is removed from the
kernel.

Use a per-cpu variable for maintaining a per-cpu ioc count and define
a reading mechanism that just sums up the values.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/elevator.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index cc81645a3e18..9c5a04f6114c 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_ELEVATOR_H
 #define _LINUX_ELEVATOR_H
 
+#include <linux/percpu.h>
+
 typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 				 struct bio *);
 
@@ -178,4 +180,27 @@ enum {
 	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
-- 
cgit v1.2.3


From a3b05e8f58c95dfccbf2c824d0c68e5990571f24 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Fri, 28 Jul 2006 09:36:46 +0200
Subject: [PATCH] Kill various deprecated/unused block layer defines/functions

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 29 -----------------------------
 include/linux/fs.h     |  1 -
 2 files changed, 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79cb9fa8034a..593386162f47 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -578,12 +578,6 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_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)
-
 /*
  * q->prep_rq_fn return values
  */
@@ -621,11 +615,6 @@ 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);
@@ -690,16 +679,6 @@ 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,
@@ -807,14 +786,6 @@ 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)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6eafbe309483..9306f63bf77e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -79,7 +79,6 @@ 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 WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
 #define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
-- 
cgit v1.2.3


From b5deef901282628d88c784f4c9d2f0583ec3b355 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Wed, 19 Jul 2006 23:39:40 +0200
Subject: [PATCH] Make sure all block/io scheduler setups are node aware

Some were kmalloc_node(), some were still kmalloc(). Change them all to
kmalloc_node().

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 593386162f47..6609371c303e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -104,8 +104,7 @@ 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);
 
-- 
cgit v1.2.3


From dc72ef4ae35c2016fb594bcc85ce871376682174 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 20 Jul 2006 14:54:05 +0200
Subject: [PATCH] Add blk_start_queueing() helper

CFQ implements this on its own now, but it's really block layer
knowledge. Tells a device queue to start dispatching requests to
the driver, taking care to unplug if needed. Also fixes the issue
where as/cfq will invoke a stopped queue, which we really don't
want.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blkdev.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6609371c303e..5d8e288db163 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -635,6 +635,7 @@ 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);
-- 
cgit v1.2.3


From 5404bc7a87b9949cf61e0174b21f80e73239ab25 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Thu, 10 Aug 2006 09:01:02 +0200
Subject: [PATCH] Allow file systems to differentiate between data and meta
 reads

We can use this information for making more intelligent priority
decisions, and it will also be useful for blktrace.

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/bio.h    | 2 ++
 include/linux/blkdev.h | 3 +++
 include/linux/fs.h     | 1 +
 3 files changed, 6 insertions(+)

(limited to 'include/linux')

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 5d8e288db163..2c01a90998a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -180,6 +180,7 @@ enum rq_flag_bits {
 	__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 */
 };
 
@@ -200,6 +201,7 @@ enum rq_flag_bits {
 #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
 
@@ -543,6 +545,7 @@ enum {
  * 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)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9306f63bf77e..d68c37af4dfb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -80,6 +80,7 @@ extern int dir_notify_enable;
 #define READA 2		/* read-ahead  - don't block if no resources */
 #define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
 #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))
 
-- 
cgit v1.2.3


From 7457e6e2d7406c7009e9ad03db1335fe93b5fb71 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@suse.de>
Date: Sun, 23 Jul 2006 02:12:01 +0200
Subject: [PATCH] blktrace: support for logging metadata reads

Signed-off-by: Jens Axboe <axboe@suse.de>
---
 include/linux/blktrace_api.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index ea48eb1b3fd3..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 */
 };
-- 
cgit v1.2.3


From cf9a2ae8d49948f861b56e5333530e491a9da190 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:05:54 +0100
Subject: [PATCH] BLOCK: Move functions out of buffer code [try #6]

Move some functions out of the buffering code that aren't strictly buffering
specific.  This is a precursor to being able to disable the block layer.

 (*) Moved some stuff out of fs/buffer.c:

     (*) The file sync and general sync stuff moved to fs/sync.c.

     (*) The superblock sync stuff moved to fs/super.c.

     (*) do_invalidatepage() moved to mm/truncate.c.

     (*) try_to_release_page() moved to mm/filemap.c.

 (*) Moved some related declarations between header files:

     (*) declarations for do_invalidatepage() and try_to_release_page() moved
     	 to linux/mm.h.

     (*) __set_page_dirty_buffers() moved to linux/buffer_head.h.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/buffer_head.h | 3 +--
 include/linux/fs.h          | 1 +
 include/linux/mm.h          | 4 +++-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 737e407d0cd1..64b508e35d2a 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -190,9 +190,7 @@ 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 +300,5 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
+extern int __set_page_dirty_buffers(struct page *page);
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d68c37af4dfb..1728142ec4b6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1546,6 +1546,7 @@ 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,
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);
-- 
cgit v1.2.3


From 0d67a46df0125e20d14f12dbd3646f1f1bf23e8c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:05:56 +0100
Subject: [PATCH] BLOCK: Remove duplicate declaration of exit_io_context() [try
 #6]

Remove the duplicate declaration of exit_io_context() from linux/sched.h.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

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
-- 
cgit v1.2.3


From 07f3f05c1e3052b8656129b2a5aca9f888241a34 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 30 Sep 2006 20:52:18 +0200
Subject: [PATCH] BLOCK: Move extern declarations out of fs/*.c into header
 files [try #6]

Create a new header file, fs/internal.h, for common definitions local to the
sources in the fs/ directory.

Move extern definitions that should be in header files from fs/*.c to
fs/internal.h or other main header files where they span directories.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ramfs.h | 1 +
 include/linux/tty.h   | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

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/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 */
-- 
cgit v1.2.3


From 811d736f9e8013966e1a5a930c0db09508bdbb15 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:06:09 +0100
Subject: [PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try
 #6]

Dissociate the generic_writepages() function from the mpage stuff, moving its
declaration to linux/mm.h and actually emitting a full implementation into
mm/page-writeback.c.

The implementation is a partial duplicate of mpage_writepages() with all BIO
references removed.

It is used by NFS to do writeback.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/mpage.h     | 6 ------
 include/linux/writeback.h | 2 ++
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 3ca880463c47..517c098fde20 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -20,9 +20,3 @@ int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 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);
-}
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);
-- 
cgit v1.2.3


From 863d5b822c02d0e7215fb84ca79e9f8c3e35f04e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:06:14 +0100
Subject: [PATCH] BLOCK: Move the loop device ioctl compat stuff to the loop
 driver [try #6]

Move the loop device ioctl compat stuff from fs/compat_ioctl.c to the loop
driver so that the loop header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/compat_ioctl.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h
index bea0255196c4..98d40e08ba6e 100644
--- a/include/linux/compat_ioctl.h
+++ b/include/linux/compat_ioctl.h
@@ -395,12 +395,6 @@ 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 */
-- 
cgit v1.2.3


From 36695673b012096228ebdc1b39a6a5850daa474e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:06:16 +0100
Subject: [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6]

Move common FS-specific ioctls from linux/ext2_fs.h to linux/fs.h as FS_IOC_*
and FS_IOC32_* and have the users of them use those as a base.

Also move the GETFLAGS/SETFLAGS flags to linux/fs.h as FS_*_FL macros, and then
have the other users use them as a base.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ext2_fs.h     | 64 +++++++++++++++++++++++++--------------------
 include/linux/ext3_fs.h     | 20 +++++++++++---
 include/linux/fs.h          | 39 +++++++++++++++++++++++++++
 include/linux/reiserfs_fs.h | 28 +++++++++-----------
 4 files changed, 104 insertions(+), 47 deletions(-)

(limited to 'include/linux')

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..a7a01ff44669 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -216,20 +216,32 @@ 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
 #define EXT3_IOC_GETRSVSZ		_IOR('f', 5, long)
 #define EXT3_IOC_SETRSVSZ		_IOW('f', 6, long)
 
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#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
+
 /*
  *  Mount options
  */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1728142ec4b6..b73a47582dbe 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -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
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 28493ffaafe7..0100d6d1d84c 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 |	\
@@ -2168,10 +2166,10 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp,
 #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
 
 /* Locking primitives */
 /* Right now we are still falling back to (un)lock_kernel, but eventually that
-- 
cgit v1.2.3


From 52b499c438ff60991eb3855ca090782569b3e8cf Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:06:18 +0100
Subject: [PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the
 ReiserFS driver [try #6]

Move the ReiserFS device ioctl compat stuff from fs/compat_ioctl.c to the
ReiserFS driver so that the ReiserFS header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/reiserfs_fs.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 0100d6d1d84c..9c63abffd7b2 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -2161,6 +2161,8 @@ __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)
@@ -2171,6 +2173,13 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp,
 #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
    would evolve into real per-fs locks */
-- 
cgit v1.2.3


From 52a700c5675f399c07e6e57328291e57f13ef3bb Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Aug 2006 19:06:23 +0100
Subject: [PATCH] BLOCK: Move the Ext3 device ioctl compat stuff to the Ext3
 driver [try #6]

Move the Ext3 device ioctl compat stuff from fs/compat_ioctl.c to the Ext3
driver so that the Ext3 header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ext3_fs.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index a7a01ff44669..11cca1bdc0c7 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -233,6 +233,8 @@ struct ext3_new_group_data {
 /*
  * 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)
@@ -241,6 +243,9 @@ struct ext3_new_group_data {
 #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
@@ -824,6 +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 *);
-- 
cgit v1.2.3


From 9361401eb7619c033e2394e4f9f6d410d6719ac7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 30 Sep 2006 20:45:40 +0200
Subject: [PATCH] BLOCK: Make it possible to disable the block layer [try #6]

Make it possible to disable the block layer.  Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.

This patch does the following:

 (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
     support.

 (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
     an item that uses the block layer.  This includes:

     (*) Block I/O tracing.

     (*) Disk partition code.

     (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.

     (*) The SCSI layer.  As far as I can tell, even SCSI chardevs use the
     	 block layer to do scheduling.  Some drivers that use SCSI facilities -
     	 such as USB storage - end up disabled indirectly from this.

     (*) Various block-based device drivers, such as IDE and the old CDROM
     	 drivers.

     (*) MTD blockdev handling and FTL.

     (*) JFFS - which uses set_bdev_super(), something it could avoid doing by
     	 taking a leaf out of JFFS2's book.

 (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
     linux/elevator.h contingent on CONFIG_BLOCK being set.  sector_div() is,
     however, still used in places, and so is still available.

 (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
     parts of linux/fs.h.

 (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.

 (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.

 (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
     is not enabled.

 (*) fs/no-block.c is created to hold out-of-line stubs and things that are
     required when CONFIG_BLOCK is not set:

     (*) Default blockdev file operations (to give error ENODEV on opening).

 (*) Makes some /proc changes:

     (*) /proc/devices does not list any blockdevs.

     (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.

 (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.

 (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
     given command other than Q_SYNC or if a special device is specified.

 (*) In init/do_mounts.c, no reference is made to the blockdev routines if
     CONFIG_BLOCK is not defined.  This does not prohibit NFS roots or JFFS2.

 (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
     error ENOSYS by way of cond_syscall if so).

 (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
     CONFIG_BLOCK is not set, since they can't then happen.

Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h       | 50 +++++++++++++++++++++++++++++++-------------
 include/linux/buffer_head.h  | 16 ++++++++++++++
 include/linux/compat_ioctl.h |  2 ++
 include/linux/elevator.h     |  3 +++
 include/linux/fs.h           | 25 +++++++++++++++++++---
 include/linux/genhd.h        |  4 ++++
 include/linux/mpage.h        |  3 +++
 include/linux/raid/md.h      |  3 +++
 include/linux/raid/md_k.h    |  3 +++
 9 files changed, 92 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c01a90998a7..3e36107d342a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -16,6 +16,22 @@
 
 #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;
@@ -818,24 +834,30 @@ 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 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/buffer_head.h b/include/linux/buffer_head.h
index 64b508e35d2a..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 */
@@ -301,4 +303,18 @@ static inline void lock_buffer(struct buffer_head *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 98d40e08ba6e..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)
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 9c5a04f6114c..b3370ef5164d 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -3,6 +3,8 @@
 
 #include <linux/percpu.h>
 
+#ifdef CONFIG_BLOCK
+
 typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 				 struct bio *);
 
@@ -203,4 +205,5 @@ enum {
 	__val;							\
 })
 
+#endif /* CONFIG_BLOCK */
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b73a47582dbe..5baf3a153403 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1482,6 +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);
@@ -1490,11 +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);
@@ -1510,6 +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
@@ -1523,14 +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);
 
@@ -1544,6 +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
  */
@@ -1555,9 +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);
@@ -1590,7 +1603,9 @@ 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,
@@ -1673,9 +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);
@@ -1756,6 +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,
@@ -1793,6 +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/mpage.h b/include/linux/mpage.h
index 517c098fde20..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);
@@ -20,3 +21,5 @@ int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
 		struct writeback_control *wbc);
+
+#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
 
-- 
cgit v1.2.3


From bcfd8d36151e531e1c6c731f1fbf792509a1c494 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@osdl.org>
Date: Thu, 31 Aug 2006 12:56:06 +0200
Subject: [PATCH] CONFIG_BLOCK: blk_congestion_wait() fix

Don't just do nothing: it'll cause busywaits all over writeback and page
reclaim.

For now, take a fixed-length nap.  Will improve when NFS starts waking up
throttled processes.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3e36107d342a..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>
@@ -848,7 +849,7 @@ void kblockd_flush(void);
 
 static inline long blk_congestion_wait(int rw, long timeout)
 {
-	return timeout;
+	return io_schedule_timeout(timeout);
 }
 
 static inline long nr_blockdev_pages(void)
@@ -856,7 +857,9 @@ static inline long nr_blockdev_pages(void)
 	return 0;
 }
 
-static inline void exit_io_context(void) {}
+static inline void exit_io_context(void)
+{
+}
 
 #endif /* CONFIG_BLOCK */
 
-- 
cgit v1.2.3