Merge branch 'for-2.6.29' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.29' of git://git.kernel.dk/linux-2.6-block: (43 commits)
  bio: get rid of bio_vec clearing
  bounce: don't rely on a zeroed bio_vec list
  cciss: simplify parameters to deregister_disk function
  cfq-iosched: fix race between exiting queue and exiting task
  loop: Do not call loop_unplug for not configured loop device.
  loop: Flush possible running bios when loop device is released.
  alpha: remove dead BIO_VMERGE_BOUNDARY
  Get rid of CONFIG_LSF
  block: make blk_softirq_init() static
  block: use min_not_zero in blk_queue_stack_limits
  block: add one-hit cache for disk partition lookup
  cfq-iosched: remove limit of dispatch depth of max 4 times quantum
  nbd: tell the block layer that it is not a rotational device
  block: get rid of elevator_t typedef
  aio: make the lookup_ioctx() lockless
  bio: add support for inlining a number of bio_vecs inside the bio
  bio: allow individual slabs in the bio_set
  bio: move the slab pointer inside the bio_set
  bio: only mempool back the largest bio_vec slab cache
  block: don't use plugging on SSD devices
  ...

Documentation/block/biodoc.txt

@@ -914,7 +914,7 @@ I/O scheduler, a.k.a. elevator, is implemented in two layers.  Generic dispatch
 queue and specific I/O schedulers.  Unless stated otherwise, elevator is used
 to refer to both parts and I/O scheduler to specific I/O schedulers.
 
-Block layer implements generic dispatch queue in ll_rw_blk.c and elevator.c.
+Block layer implements generic dispatch queue in block/*.c.
 The generic dispatch queue is responsible for properly ordering barrier
 requests, requeueing, handling non-fs requests and all other subtleties.
 
@@ -926,8 +926,8 @@ be built inside the kernel.  Each queue can choose different one and can also
 change to another one dynamically.
 
 A block layer call to the i/o scheduler follows the convention elv_xxx(). This
-calls elevator_xxx_fn in the elevator switch (drivers/block/elevator.c). Oh,
-xxx and xxx might not match exactly, but use your imagination. If an elevator
+calls elevator_xxx_fn in the elevator switch (block/elevator.c). Oh, xxx
+and xxx might not match exactly, but use your imagination. If an elevator
 doesn't implement a function, the switch does nothing or some minimal house
 keeping work.
 

arch/alpha/include/asm/io.h

@@ -96,9 +96,6 @@ static inline dma_addr_t __deprecated isa_page_to_bus(struct page *page)
 	return page_to_phys(page);
 }
 
-/* This depends on working iommu.  */
-#define BIO_VMERGE_BOUNDARY	(alpha_mv.mv_pci_tbi ? PAGE_SIZE : 0)
-
 /* Maximum PIO space address supported?  */
 #define IO_SPACE_LIMIT 0xffff
 

arch/s390/mm/pgtable.c

@@ -263,7 +263,7 @@ int s390_enable_sie(void)
 	/* lets check if we are allowed to replace the mm */
 	task_lock(tsk);
 	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+	    tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) {
 		task_unlock(tsk);
 		return -EINVAL;
 	}
@@ -279,7 +279,7 @@ int s390_enable_sie(void)
 	/* Now lets check again if something happened */
 	task_lock(tsk);
 	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+	    tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) {
 		mmput(mm);
 		task_unlock(tsk);
 		return -EINVAL;

block/Kconfig

@@ -24,21 +24,17 @@ menuconfig BLOCK
 if BLOCK
 
 config LBD
-	bool "Support for Large Block Devices"
+	bool "Support for large block devices and files"
 	depends on !64BIT
 	help
-	  Enable block devices of size 2TB and larger.
+	  Enable block devices or files of size 2TB and larger.
 
 	  This option is required to support the full capacity of large
 	  (2TB+) block devices, including RAID, disk, Network Block Device,
 	  Logical Volume Manager (LVM) and loopback.
-
-	  For example, RAID devices are frequently bigger than the capacity
-	  of the largest individual hard drive.
-
-	  This option is not required if you have individual disk drives
-	  which total 2TB+ and you are not aggregating the capacity into
-	  a large block device (e.g. using RAID or LVM).
+
+	  This option also enables support for single files larger than
+	  2TB.
 
 	  If unsure, say N.
 
@@ -58,15 +54,6 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
-config LSF
-	bool "Support for Large Single Files"
-	depends on !64BIT
-	help
-	  Say Y here if you want to be able to handle very large files (2TB
-	  and larger), otherwise say N.
-
-	  If unsure, say Y.
-
 config BLK_DEV_BSG
 	bool "Block layer SG support v4 (EXPERIMENTAL)"
 	depends on EXPERIMENTAL

block/as-iosched.c

@@ -1339,12 +1339,12 @@ static int as_may_queue(struct request_queue *q, int rw)
 	return ret;
 }
 
-static void as_exit_queue(elevator_t *e)
+static void as_exit_queue(struct elevator_queue *e)
 {
 	struct as_data *ad = e->elevator_data;
 
 	del_timer_sync(&ad->antic_timer);
-	kblockd_flush_work(&ad->antic_work);
+	cancel_work_sync(&ad->antic_work);
 
 	BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC]));
 	BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC]));
@@ -1409,7 +1409,7 @@ as_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
-static ssize_t est_time_show(elevator_t *e, char *page)
+static ssize_t est_time_show(struct elevator_queue *e, char *page)
 {
 	struct as_data *ad = e->elevator_data;
 	int pos = 0;
@@ -1427,7 +1427,7 @@ static ssize_t est_time_show(elevator_t *e, char *page)
 }
 
 #define SHOW_FUNCTION(__FUNC, __VAR)				\
-static ssize_t __FUNC(elevator_t *e, char *page)		\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)	\
 {								\
 	struct as_data *ad = e->elevator_data;			\
 	return as_var_show(jiffies_to_msecs((__VAR)), (page));	\
@@ -1440,7 +1440,7 @@ SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[REQ_ASYNC]);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)				\
-static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct as_data *ad = e->elevator_data;				\
 	int ret = as_var_store(__PTR, (page), count);			\

block/blk-barrier.c

@@ -24,8 +24,8 @@
 int blk_queue_ordered(struct request_queue *q, unsigned ordered,
 		      prepare_flush_fn *prepare_flush_fn)
 {
-	if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) &&
-	    prepare_flush_fn == NULL) {
+	if (!prepare_flush_fn && (ordered & (QUEUE_ORDERED_DO_PREFLUSH |
+					     QUEUE_ORDERED_DO_POSTFLUSH))) {
 		printk(KERN_ERR "%s: prepare_flush_fn required\n", __func__);
 		return -EINVAL;
 	}
@@ -88,7 +88,7 @@ unsigned blk_ordered_req_seq(struct request *rq)
 		return QUEUE_ORDSEQ_DONE;
 }
 
-void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
+bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 {
 	struct request *rq;
 
@@ -99,7 +99,7 @@ void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 	q->ordseq |= seq;
 
 	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
-		return;
+		return false;
 
 	/*
 	 * Okay, sequence complete.
@@ -109,6 +109,8 @@ void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 
 	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
 		BUG();
+
+	return true;
 }
 
 static void pre_flush_end_io(struct request *rq, int error)
@@ -134,7 +136,7 @@ static void queue_flush(struct request_queue *q, unsigned which)
 	struct request *rq;
 	rq_end_io_fn *end_io;
 
-	if (which == QUEUE_ORDERED_PREFLUSH) {
+	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
 		rq = &q->pre_flush_rq;
 		end_io = pre_flush_end_io;
 	} else {
@@ -151,80 +153,110 @@ static void queue_flush(struct request_queue *q, unsigned which)
 	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 }
 
-static inline struct request *start_ordered(struct request_queue *q,
-					    struct request *rq)
+static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 {
+	struct request *rq = *rqp;
+	unsigned skip = 0;
+
 	q->orderr = 0;
 	q->ordered = q->next_ordered;
 	q->ordseq |= QUEUE_ORDSEQ_STARTED;
 
 	/*
-	 * Prep proxy barrier request.
+	 * For an empty barrier, there's no actual BAR request, which
+	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
 	 */
+	if (!rq->hard_nr_sectors) {
+		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
+				QUEUE_ORDERED_DO_POSTFLUSH);
+		/*
+		 * Empty barrier on a write-through device w/ ordered
+		 * tag has no command to issue and without any command
+		 * to issue, ordering by tag can't be used.  Drain
+		 * instead.
+		 */
+		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
+		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
+			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
+			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
+		}
+	}
+
+	/* stash away the original request */
 	elv_dequeue_request(q, rq);
 	q->orig_bar_rq = rq;
-	rq = &q->bar_rq;
-	blk_rq_init(q, rq);
-	if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
-		rq->cmd_flags |= REQ_RW;
-	if (q->ordered & QUEUE_ORDERED_FUA)
-		rq->cmd_flags |= REQ_FUA;
-	init_request_from_bio(rq, q->orig_bar_rq->bio);
-	rq->end_io = bar_end_io;
+	rq = NULL;
 
 	/*
 	 * Queue ordered sequence.  As we stack them at the head, we
 	 * need to queue in reverse order.  Note that we rely on that
 	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
-	 * request gets inbetween ordered sequence. If this request is
-	 * an empty barrier, we don't need to do a postflush ever since
-	 * there will be no data written between the pre and post flush.
-	 * Hence a single flush will suffice.
+	 * request gets inbetween ordered sequence.
 	 */
-	if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
-		queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
-	else
-		q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
+	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
+		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
+		rq = &q->post_flush_rq;
+	} else
+		skip |= QUEUE_ORDSEQ_POSTFLUSH;
 
-	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
+		rq = &q->bar_rq;
+
+		/* initialize proxy request and queue it */
+		blk_rq_init(q, rq);
+		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
+			rq->cmd_flags |= REQ_RW;
+		if (q->ordered & QUEUE_ORDERED_DO_FUA)
+			rq->cmd_flags |= REQ_FUA;
+		init_request_from_bio(rq, q->orig_bar_rq->bio);
+		rq->end_io = bar_end_io;
 
-	if (q->ordered & QUEUE_ORDERED_PREFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_PREFLUSH);
+		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	} else
+		skip |= QUEUE_ORDSEQ_BAR;
+
+	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
+		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
 		rq = &q->pre_flush_rq;
 	} else
-		q->ordseq |= QUEUE_ORDSEQ_PREFLUSH;
+		skip |= QUEUE_ORDSEQ_PREFLUSH;
 
-	if ((q->ordered & QUEUE_ORDERED_TAG) || q->in_flight == 0)
-		q->ordseq |= QUEUE_ORDSEQ_DRAIN;
-	else
+	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && q->in_flight)
 		rq = NULL;
+	else
+		skip |= QUEUE_ORDSEQ_DRAIN;
+
+	*rqp = rq;
 
-	return rq;
+	/*
+	 * Complete skipped sequences.  If whole sequence is complete,
+	 * return false to tell elevator that this request is gone.
+	 */
+	return !blk_ordered_complete_seq(q, skip, 0);
 }
 
-int blk_do_ordered(struct request_queue *q, struct request **rqp)
+bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 {
 	struct request *rq = *rqp;
 	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
 
 	if (!q->ordseq) {
 		if (!is_barrier)
-			return 1;
+			return true;
 
-		if (q->next_ordered != QUEUE_ORDERED_NONE) {
-			*rqp = start_ordered(q, rq);
-			return 1;
-		} else {
+		if (q->next_ordered != QUEUE_ORDERED_NONE)
+			return start_ordered(q, rqp);
+		else {
 			/*
-			 * This can happen when the queue switches to
-			 * ORDERED_NONE while this request is on it.
+			 * Queue ordering not supported.  Terminate
+			 * with prejudice.
 			 */
 			elv_dequeue_request(q, rq);
 			if (__blk_end_request(rq, -EOPNOTSUPP,
 					      blk_rq_bytes(rq)))
 				BUG();
 			*rqp = NULL;
-			return 0;
+			return false;
 		}
 	}
 
@@ -235,9 +267,9 @@ int blk_do_ordered(struct request_queue *q, struct request **rqp)
 	/* Special requests are not subject to ordering rules. */
 	if (!blk_fs_request(rq) &&
 	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
-		return 1;
+		return true;
 
-	if (q->ordered & QUEUE_ORDERED_TAG) {
+	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
 		/* Ordered by tag.  Blocking the next barrier is enough. */
 		if (is_barrier && rq != &q->bar_rq)
 			*rqp = NULL;
@@ -248,7 +280,7 @@ int blk_do_ordered(struct request_queue *q, struct request **rqp)
 			*rqp = NULL;
 	}
 
-	return 1;
+	return true;
 }
 
 static void bio_end_empty_barrier(struct bio *bio, int err)