Merge branch 'for-3.3/core' of git://git.kernel.dk/linux-block

* 'for-3.3/core' of git://git.kernel.dk/linux-block: (37 commits)
  Revert "block: recursive merge requests"
  block: Stop using macro stubs for the bio data integrity calls
  blockdev: convert some macros to static inlines
  fs: remove unneeded plug in mpage_readpages()
  block: Add BLKROTATIONAL ioctl
  block: Introduce blk_set_stacking_limits function
  block: remove WARN_ON_ONCE() in exit_io_context()
  block: an exiting task should be allowed to create io_context
  block: ioc_cgroup_changed() needs to be exported
  block: recursive merge requests
  block, cfq: fix empty queue crash caused by request merge
  block, cfq: move icq creation and rq->elv.icq association to block core
  block, cfq: restructure io_cq creation path for io_context interface cleanup
  block, cfq: move io_cq exit/release to blk-ioc.c
  block, cfq: move icq cache management to block core
  block, cfq: move io_cq lookup to blk-ioc.c
  block, cfq: move cfqd->icq_list to request_queue and add request->elv.icq
  block, cfq: reorganize cfq_io_context into generic and cfq specific parts
  block: remove elevator_queue->ops
  block: reorder elevator switch sequence
  ...

Fix up conflicts in:
 - block/blk-cgroup.c
	Switch from can_attach_task to can_attach
 - block/cfq-iosched.c
	conflict with now removed cic index changes (we now use q->id instead)

block/blk-cgroup.c

@@ -1655,11 +1655,12 @@ static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	struct io_context *ioc;
 
 	cgroup_taskset_for_each(task, cgrp, tset) {
-		task_lock(task);
-		ioc = task->io_context;
-		if (ioc)
-			ioc->cgroup_changed = 1;
-		task_unlock(task);
+		/* we don't lose anything even if ioc allocation fails */
+		ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
+		if (ioc) {
+			ioc_cgroup_changed(ioc);
+			put_io_context(ioc, NULL);
+		}
 	}
 }
 

block/blk-exec.c

@@ -50,7 +50,11 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 {
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
-	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+	WARN_ON(irqs_disabled());
+	spin_lock_irq(q->queue_lock);
+
+	if (unlikely(blk_queue_dead(q))) {
+		spin_unlock_irq(q->queue_lock);
 		rq->errors = -ENXIO;
 		if (rq->end_io)
 			rq->end_io(rq, rq->errors);
@@ -59,8 +63,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
-	WARN_ON(irqs_disabled());
-	spin_lock_irq(q->queue_lock);
 	__elv_add_request(q, rq, where);
 	__blk_run_queue(q);
 	/* the queue is stopped so it won't be run */

block/blk-settings.c

@@ -104,9 +104,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
  * @lim:  the queue_limits structure to reset
  *
  * Description:
- *   Returns a queue_limit struct to its default state.  Can be used by
- *   stacking drivers like DM that stage table swaps and reuse an
- *   existing device queue.
+ *   Returns a queue_limit struct to its default state.
  */
 void blk_set_default_limits(struct queue_limits *lim)
 {
@@ -114,13 +112,12 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = BLK_DEF_MAX_SECTORS;
-	lim->max_hw_sectors = INT_MAX;
+	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
 	lim->max_discard_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
-	lim->discard_zeroes_data = 1;
+	lim->discard_zeroes_data = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -130,6 +127,27 @@ void blk_set_default_limits(struct queue_limits *lim)
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
+/**
+ * blk_set_stacking_limits - set default limits for stacking devices
+ * @lim:  the queue_limits structure to reset
+ *
+ * Description:
+ *   Returns a queue_limit struct to its default state. Should be used
+ *   by stacking drivers like DM that have no internal limits.
+ */
+void blk_set_stacking_limits(struct queue_limits *lim)
+{
+	blk_set_default_limits(lim);
+
+	/* Inherit limits from component devices */
+	lim->discard_zeroes_data = 1;
+	lim->max_segments = USHRT_MAX;
+	lim->max_hw_sectors = UINT_MAX;
+
+	lim->max_sectors = BLK_DEF_MAX_SECTORS;
+}
+EXPORT_SYMBOL(blk_set_stacking_limits);
+
 /**
  * blk_queue_make_request - define an alternate make_request function for a device
  * @q:  the request queue for the device to be affected
@@ -165,8 +183,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->nr_batching = BLK_BATCH_REQ;
 
 	blk_set_default_limits(&q->limits);
-	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
-	q->limits.discard_zeroes_data = 0;
 
 	/*
 	 * by default assume old behaviour and bounce for any highmem page

block/blk-sysfs.c

@@ -425,7 +425,7 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+	if (blk_queue_dead(q)) {
 		mutex_unlock(&q->sysfs_lock);
 		return -ENOENT;
 	}
@@ -447,7 +447,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+	if (blk_queue_dead(q)) {
 		mutex_unlock(&q->sysfs_lock);
 		return -ENOENT;
 	}
@@ -479,8 +479,12 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_sync_queue(q);
 
-	if (q->elevator)
+	if (q->elevator) {
+		spin_lock_irq(q->queue_lock);
+		ioc_clear_queue(q);
+		spin_unlock_irq(q->queue_lock);
 		elevator_exit(q->elevator);
+	}
 
 	blk_throtl_exit(q);
 
@@ -494,6 +498,8 @@ static void blk_release_queue(struct kobject *kobj)
 	blk_trace_shutdown(q);
 
 	bdi_destroy(&q->backing_dev_info);
+
+	ida_simple_remove(&blk_queue_ida, q->id);
 	kmem_cache_free(blk_requestq_cachep, q);
 }
 

block/blk-throttle.c

@@ -310,7 +310,7 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	struct request_queue *q = td->queue;
 
 	/* no throttling for dead queue */
-	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
+	if (unlikely(blk_queue_dead(q)))
 		return NULL;
 
 	rcu_read_lock();
@@ -335,7 +335,7 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	spin_lock_irq(q->queue_lock);
 
 	/* Make sure @q is still alive */
-	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+	if (unlikely(blk_queue_dead(q))) {
 		kfree(tg);
 		return NULL;
 	}

block/blk.h

 #ifndef BLK_INTERNAL_H
 #define BLK_INTERNAL_H
 
+#include <linux/idr.h>
+
 /* Amount of time in which a process may batch requests */
 #define BLK_BATCH_TIME	(HZ/50UL)
 
@@ -9,6 +11,12 @@
 
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kobj_type blk_queue_ktype;
+extern struct ida blk_queue_ida;
+
+static inline void __blk_get_queue(struct request_queue *q)
+{
+	kobject_get(&q->kobj);
+}
 
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
@@ -85,8 +93,8 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			q->flush_queue_delayed = 1;
 			return NULL;
 		}
-		if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags) ||
-		    !q->elevator->ops->elevator_dispatch_fn(q, 0))
+		if (unlikely(blk_queue_dead(q)) ||
+		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
@@ -95,16 +103,16 @@ static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->ops->elevator_activate_req_fn)
-		e->ops->elevator_activate_req_fn(q, rq);
+	if (e->type->ops.elevator_activate_req_fn)
+		e->type->ops.elevator_activate_req_fn(q, rq);
 }
 
 static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->ops->elevator_deactivate_req_fn)
-		e->ops->elevator_deactivate_req_fn(q, rq);
+	if (e->type->ops.elevator_deactivate_req_fn)
+		e->type->ops.elevator_deactivate_req_fn(q, rq);
 }
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -119,8 +127,6 @@ static inline int blk_should_fake_timeout(struct request_queue *q)
 }
 #endif
 
-struct io_context *current_io_context(gfp_t gfp_flags, int node);
-
 int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio);
 int ll_front_merge_fn(struct request_queue *q, struct request *req, 
@@ -189,6 +195,42 @@ static inline int blk_do_io_stat(struct request *rq)
 	        (rq->cmd_flags & REQ_DISCARD));
 }
 
+/*
+ * Internal io_context interface
+ */
+void get_io_context(struct io_context *ioc);
+struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
+struct io_cq *ioc_create_icq(struct request_queue *q, gfp_t gfp_mask);
+void ioc_clear_queue(struct request_queue *q);
+
+void create_io_context_slowpath(struct task_struct *task, gfp_t gfp_mask,
+				int node);
+
+/**
+ * create_io_context - try to create task->io_context
+ * @task: target task
+ * @gfp_mask: allocation mask
+ * @node: allocation node
+ *
+ * If @task->io_context is %NULL, allocate a new io_context and install it.
+ * Returns the current @task->io_context which may be %NULL if allocation
+ * failed.
+ *
+ * Note that this function can't be called with IRQ disabled because
+ * task_lock which protects @task->io_context is IRQ-unsafe.
+ */
+static inline struct io_context *create_io_context(struct task_struct *task,
+						   gfp_t gfp_mask, int node)
+{
+	WARN_ON_ONCE(irqs_disabled());
+	if (unlikely(!task->io_context))
+		create_io_context_slowpath(task, gfp_mask, node);
+	return task->io_context;
+}
+
+/*
+ * Internal throttling interface
+ */
 #ifdef CONFIG_BLK_DEV_THROTTLING
 extern bool blk_throtl_bio(struct request_queue *q, struct bio *bio);
 extern void blk_throtl_drain(struct request_queue *q);

block/bsg.c

@@ -769,12 +769,10 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 					 struct file *file)
 {
 	struct bsg_device *bd;
-	int ret;
 #ifdef BSG_DEBUG
 	unsigned char buf[32];
 #endif
-	ret = blk_get_queue(rq);
-	if (ret)
+	if (!blk_get_queue(rq))
 		return ERR_PTR(-ENXIO);
 
 	bd = bsg_alloc_device();

block/compat_ioctl.c

@@ -719,6 +719,9 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKSECTGET:
 		return compat_put_ushort(arg,
 					 queue_max_sectors(bdev_get_queue(bdev)));
+	case BLKROTATIONAL:
+		return compat_put_ushort(arg,
+					 !blk_queue_nonrot(bdev_get_queue(bdev)));
 	case BLKRASET: /* compatible, but no compat_ptr (!) */
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))

block/deadline-iosched.c

@@ -448,9 +448,7 @@ static struct elevator_type iosched_deadline = {
 
 static int __init deadline_init(void)
 {
-	elv_register(&iosched_deadline);
-
-	return 0;
+	return elv_register(&iosched_deadline);
 }
 
 static void __exit deadline_exit(void)

block/genhd.c

@@ -614,7 +614,7 @@ void add_disk(struct gendisk *disk)
 	 * Take an extra ref on queue which will be put on disk_release()
 	 * so that it sticks around as long as @disk is there.
 	 */
-	WARN_ON_ONCE(blk_get_queue(disk->queue));
+	WARN_ON_ONCE(!blk_get_queue(disk->queue));
 
 	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
 				   "bdi");

block/ioctl.c

@@ -296,6 +296,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		return put_uint(arg, bdev_discard_zeroes_data(bdev));
 	case BLKSECTGET:
 		return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev)));
+	case BLKROTATIONAL:
+		return put_ushort(arg, !blk_queue_nonrot(bdev_get_queue(bdev)));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))

block/noop-iosched.c

@@ -94,9 +94,7 @@ static struct elevator_type elevator_noop = {
 
 static int __init noop_init(void)
 {
-	elv_register(&elevator_noop);
-
-	return 0;
+	return elv_register(&elevator_noop);
 }
 
 static void __exit noop_exit(void)

drivers/block/sx8.c

@@ -619,8 +619,10 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	       host->state == HST_DEV_SCAN);
 	spin_unlock_irq(&host->lock);
 
-	DPRINTK("blk_insert_request, tag == %u\n", idx);
-	blk_insert_request(host->oob_q, crq->rq, 1, crq);
+	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
+	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->special = crq;
+	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
 	return 0;
 
@@ -658,8 +660,10 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	BUG_ON(rc < 0);
 	crq->msg_bucket = (u32) rc;
 
-	DPRINTK("blk_insert_request, tag == %u\n", idx);
-	blk_insert_request(host->oob_q, crq->rq, 1, crq);
+	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
+	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->special = crq;
+	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
 	return 0;
 }

drivers/md/dm-table.c

@@ -699,7 +699,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table,
 	while (i < dm_table_get_num_targets(table)) {
 		ti = dm_table_get_target(table, i++);
 
-		blk_set_default_limits(&ti_limits);
+		blk_set_stacking_limits(&ti_limits);
 
 		/* combine all target devices' limits */
 		if (ti->type->iterate_devices)
@@ -1221,10 +1221,10 @@ int dm_calculate_queue_limits(struct dm_table *table,
 	struct queue_limits ti_limits;
 	unsigned i = 0;
 
-	blk_set_default_limits(limits);
+	blk_set_stacking_limits(limits);
 
 	while (i < dm_table_get_num_targets(table)) {
-		blk_set_default_limits(&ti_limits);
+		blk_set_stacking_limits(&ti_limits);
 
 		ti = dm_table_get_target(table, i++);
 

drivers/md/md.c

@@ -4666,6 +4666,7 @@ static int md_alloc(dev_t dev, char *name)
 	mddev->queue->queuedata = mddev;
 
 	blk_queue_make_request(mddev->queue, md_make_request);
+	blk_set_stacking_limits(&mddev->queue->limits);
 
 	disk = alloc_disk(1 << shift);
 	if (!disk) {

drivers/scsi/scsi_scan.c

@@ -297,7 +297,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 		kfree(sdev);
 		goto out;
 	}
-	blk_get_queue(sdev->request_queue);
+	WARN_ON_ONCE(!blk_get_queue(sdev->request_queue));
 	sdev->request_queue->queuedata = sdev;
 	scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 

fs/ioprio.c

@@ -48,28 +48,12 @@ int set_task_ioprio(struct task_struct *task, int ioprio)
 	if (err)
 		return err;
 
-	task_lock(task);
-	do {
-		ioc = task->io_context;
-		/* see wmb() in current_io_context() */
-		smp_read_barrier_depends();
-		if (ioc)
-			break;
-
-		ioc = alloc_io_context(GFP_ATOMIC, -1);
-		if (!ioc) {
-			err = -ENOMEM;
-			break;
-		}
-		task->io_context = ioc;
-	} while (1);
-
-	if (!err) {
-		ioc->ioprio = ioprio;
-		ioc->ioprio_changed = 1;
+	ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
+	if (ioc) {
+		ioc_ioprio_changed(ioc, ioprio);
+		put_io_context(ioc, NULL);
 	}
 
-	task_unlock(task);
 	return err;
 }
 EXPORT_SYMBOL_GPL(set_task_ioprio);

fs/mpage.c

@@ -371,9 +371,6 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	struct blk_plug plug;
-
-	blk_start_plug(&plug);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
@@ -395,7 +392,6 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	BUG_ON(!list_empty(pages));
 	if (bio)
 		mpage_bio_submit(READ, bio);
-	blk_finish_plug(&plug);
 	return 0;
 }
 EXPORT_SYMBOL(mpage_readpages);

include/linux/bio.h

@@ -515,24 +515,64 @@ extern void bio_integrity_init(void);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
-#define bio_integrity(a)		(0)
-#define bioset_integrity_create(a, b)	(0)
-#define bio_integrity_prep(a)		(0)
-#define bio_integrity_enabled(a)	(0)
+static inline int bio_integrity(struct bio *bio)
+{
+	return 0;
+}
+
+static inline int bio_integrity_enabled(struct bio *bio)
+{
+	return 0;
+}
+
+static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
+{
+	return 0;
+}
+
+static inline void bioset_integrity_free (struct bio_set *bs)
+{
+	return;
+}
+
+static inline int bio_integrity_prep(struct bio *bio)
+{
+	return 0;
+}
+
+static inline void bio_integrity_free(struct bio *bio, struct bio_set *bs)
+{
+	return;
+}
+
 static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 				      gfp_t gfp_mask, struct bio_set *bs)
 {
 	return 0;
 }
-#define bioset_integrity_free(a)	do { } while (0)
-#define bio_integrity_free(a, b)	do { } while (0)
-#define bio_integrity_endio(a, b)	do { } while (0)
-#define bio_integrity_advance(a, b)	do { } while (0)
-#define bio_integrity_trim(a, b, c)	do { } while (0)
-#define bio_integrity_split(a, b, c)	do { } while (0)
-#define bio_integrity_set_tag(a, b, c)	do { } while (0)
-#define bio_integrity_get_tag(a, b, c)	do { } while (0)
-#define bio_integrity_init(a)		do { } while (0)
+
+static inline void bio_integrity_split(struct bio *bio, struct bio_pair *bp,
+				       int sectors)
+{
+	return;
+}
+
+static inline void bio_integrity_advance(struct bio *bio,
+					 unsigned int bytes_done)
+{
+	return;
+}
+
+static inline void bio_integrity_trim(struct bio *bio, unsigned int offset,
+				      unsigned int sectors)
+{
+	return;
+}
+
+static inline void bio_integrity_init(void)
+{
+	return;
+}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 

include/linux/blkdev.h

@@ -111,10 +111,14 @@ struct request {
 	 * Three pointers are available for the IO schedulers, if they need
 	 * more they have to dynamically allocate it.  Flush requests are
 	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the three elevator_private pointers.
+	 * space with the elevator data.
 	 */
 	union {
-		void *elevator_private[3];
+		struct {
+			struct io_cq		*icq;
+			void			*priv[2];
+		} elv;
+
 		struct {
 			unsigned int		seq;
 			struct list_head	list;
@@ -310,6 +314,12 @@ struct request_queue {
 	 */
 	unsigned long		queue_flags;
 
+	/*
+	 * ida allocated id for this queue.  Used to index queues from
+	 * ioctx.
+	 */
+	int			id;
+
 	/*
 	 * queue needs bounce pages for pages above this limit
 	 */
@@ -351,6 +361,8 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct list_head	timeout_list;
 
+	struct list_head	icq_list;
+
 	struct queue_limits	limits;
 
 	/*
@@ -387,6 +399,9 @@ struct request_queue {
 	/* Throttle data */
 	struct throtl_data *td;
 #endif
+#ifdef CONFIG_LOCKDEP
+	int			ioc_release_depth;
+#endif
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -481,6 +496,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
+#define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
@@ -660,7 +676,6 @@ extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
 extern struct request *blk_make_request(struct request_queue *, struct bio *,
 					gfp_t);
-extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
@@ -829,6 +844,7 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
+extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
 extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
@@ -859,7 +875,7 @@ extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatte
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
 
-int blk_get_queue(struct request_queue *);
+bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
@@ -1282,19 +1298,70 @@ queue_max_integrity_segments(struct request_queue *q)
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
-#define blk_integrity_rq(rq)			(0)
-#define blk_rq_count_integrity_sg(a, b)		(0)
-#define blk_rq_map_integrity_sg(a, b, c)	(0)
-#define bdev_get_integrity(a)			(0)
-#define blk_get_integrity(a)			(0)
-#define blk_integrity_compare(a, b)		(0)
-#define blk_integrity_register(a, b)		(0)
-#define blk_integrity_unregister(a)		do { } while (0)
-#define blk_queue_max_integrity_segments(a, b)	do { } while (0)
-#define queue_max_integrity_segments(a)		(0)
-#define blk_integrity_merge_rq(a, b, c)		(0)
-#define blk_integrity_merge_bio(a, b, c)	(0)
-#define blk_integrity_is_initialized(a)		(0)
+struct bio;
+struct block_device;
+struct gendisk;
+struct blk_integrity;
+
+static inline int blk_integrity_rq(struct request *rq)
+{
+	return 0;
+}
+static inline int blk_rq_count_integrity_sg(struct request_queue *q,
+					    struct bio *b)
+{
+	return 0;
+}
+static inline int blk_rq_map_integrity_sg(struct request_queue *q,
+					  struct bio *b,
+					  struct scatterlist *s)
+{
+	return 0;
+}
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
+{
+	return 0;
+}
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+	return NULL;
+}
+static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
+{
+	return 0;
+}
+static inline int blk_integrity_register(struct gendisk *d,
+					 struct blk_integrity *b)
+{
+	return 0;
+}
+static inline void blk_integrity_unregister(struct gendisk *d)
+{
+}
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+						    unsigned int segs)
+{
+}
+static inline unsigned short queue_max_integrity_segments(struct request_queue *q)
+{
+	return 0;
+}
+static inline int blk_integrity_merge_rq(struct request_queue *rq,
+					 struct request *r1,
+					 struct request *r2)
+{
+	return 0;
+}
+static inline int blk_integrity_merge_bio(struct request_queue *rq,
+					  struct request *r,
+					  struct bio *b)
+{
+	return 0;
+}
+static inline bool blk_integrity_is_initialized(struct gendisk *g)
+{
+	return 0;
+}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 

include/linux/elevator.h

@@ -5,6 +5,8 @@
 
 #ifdef CONFIG_BLOCK
 
+struct io_cq;
+
 typedef int (elevator_merge_fn) (struct request_queue *, struct request **,
 				 struct bio *);
 
@@ -24,6 +26,8 @@ typedef struct request *(elevator_request_list_fn) (struct request_queue *, stru
 typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
 typedef int (elevator_may_queue_fn) (struct request_queue *, int);
 
+typedef void (elevator_init_icq_fn) (struct io_cq *);
+typedef void (elevator_exit_icq_fn) (struct io_cq *);
 typedef int (elevator_set_req_fn) (struct request_queue *, struct request *, gfp_t);
 typedef void (elevator_put_req_fn) (struct request *);
 typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *);
@@ -56,6 +60,9 @@ struct elevator_ops
 	elevator_request_list_fn *elevator_former_req_fn;
 	elevator_request_list_fn *elevator_latter_req_fn;
 
+	elevator_init_icq_fn *elevator_init_icq_fn;	/* see iocontext.h */
+	elevator_exit_icq_fn *elevator_exit_icq_fn;	/* ditto */
+
 	elevator_set_req_fn *elevator_set_req_fn;
 	elevator_put_req_fn *elevator_put_req_fn;
 
@@ -63,7 +70,6 @@ struct elevator_ops
 
 	elevator_init_fn *elevator_init_fn;
 	elevator_exit_fn *elevator_exit_fn;
-	void (*trim)(struct io_context *);
 };
 
 #define ELV_NAME_MAX	(16)
@@ -79,11 +85,20 @@ struct elv_fs_entry {
  */
 struct elevator_type
 {
-	struct list_head list;
+	/* managed by elevator core */
+	struct kmem_cache *icq_cache;
+
+	/* fields provided by elevator implementation */
 	struct elevator_ops ops;
+	size_t icq_size;	/* see iocontext.h */
+	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
+
+	/* managed by elevator core */
+	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
+	struct list_head list;
 };
 
 /*
@@ -91,10 +106,9 @@ struct elevator_type
  */
 struct elevator_queue
 {
-	struct elevator_ops *ops;
+	struct elevator_type *type;
 	void *elevator_data;
 	struct kobject kobj;
-	struct elevator_type *elevator_type;
 	struct mutex sysfs_lock;
 	struct hlist_head *hash;
 	unsigned int registered:1;
@@ -129,7 +143,7 @@ extern void elv_drain_elevator(struct request_queue *);
 /*
  * io scheduler registration
  */
-extern void elv_register(struct elevator_type *);
+extern int elv_register(struct elevator_type *);
 extern void elv_unregister(struct elevator_type *);
 
 /*
@@ -197,22 +211,5 @@ enum {
 	INIT_LIST_HEAD(&(rq)->csd.list);	\
 	} while (0)
 
-/*
- * io context count accounting
- */
-#define elv_ioc_count_mod(name, __val) this_cpu_add(name, __val)
-#define elv_ioc_count_inc(name)	this_cpu_inc(name)
-#define elv_ioc_count_dec(name)	this_cpu_dec(name)
-
-#define elv_ioc_count_read(name)				\
-({								\
-	unsigned long __val = 0;				\
-	int __cpu;						\
-	smp_wmb();						\
-	for_each_possible_cpu(__cpu)				\
-		__val += per_cpu(name, __cpu);			\
-	__val;							\
-})
-
 #endif /* CONFIG_BLOCK */
 #endif

include/linux/fs.h

@@ -319,6 +319,7 @@ struct inodes_stat_t {
 #define BLKPBSZGET _IO(0x12,123)
 #define BLKDISCARDZEROES _IO(0x12,124)
 #define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */

include/linux/iocontext.h

@@ -3,32 +3,92 @@
 
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
+#include <linux/workqueue.h>
 
-struct cfq_queue;
-struct cfq_ttime {
-	unsigned long last_end_request;
-
-	unsigned long ttime_total;
-	unsigned long ttime_samples;
-	unsigned long ttime_mean;
+enum {
+	ICQ_IOPRIO_CHANGED,
+	ICQ_CGROUP_CHANGED,
 };
 
-struct cfq_io_context {
-	void *key;
-
-	struct cfq_queue *cfqq[2];
-
+/*
+ * An io_cq (icq) is association between an io_context (ioc) and a
+ * request_queue (q).  This is used by elevators which need to track
+ * information per ioc - q pair.
+ *
+ * Elevator can request use of icq by setting elevator_type->icq_size and
+ * ->icq_align.  Both size and align must be larger than that of struct
+ * io_cq and elevator can use the tail area for private information.  The
+ * recommended way to do this is defining a struct which contains io_cq as
+ * the first member followed by private members and using its size and
+ * align.  For example,
+ *
+ *	struct snail_io_cq {
+ *		struct io_cq	icq;
+ *		int		poke_snail;
+ *		int		feed_snail;
+ *	};
+ *
+ *	struct elevator_type snail_elv_type {
+ *		.ops =		{ ... },
+ *		.icq_size =	sizeof(struct snail_io_cq),
+ *		.icq_align =	__alignof__(struct snail_io_cq),
+ *		...
+ *	};
+ *
+ * If icq_size is set, block core will manage icq's.  All requests will
+ * have its ->elv.icq field set before elevator_ops->elevator_set_req_fn()
+ * is called and be holding a reference to the associated io_context.
+ *
+ * Whenever a new icq is created, elevator_ops->elevator_init_icq_fn() is
+ * called and, on destruction, ->elevator_exit_icq_fn().  Both functions
+ * are called with both the associated io_context and queue locks held.
+ *
+ * Elevator is allowed to lookup icq using ioc_lookup_icq() while holding
+ * queue lock but the returned icq is valid only until the queue lock is
+ * released.  Elevators can not and should not try to create or destroy
+ * icq's.
+ *
+ * As icq's are linked from both ioc and q, the locking rules are a bit
+ * complex.
+ *
+ * - ioc lock nests inside q lock.
+ *
+ * - ioc->icq_list and icq->ioc_node are protected by ioc lock.
+ *   q->icq_list and icq->q_node by q lock.
+ *
+ * - ioc->icq_tree and ioc->icq_hint are protected by ioc lock, while icq
+ *   itself is protected by q lock.  However, both the indexes and icq
+ *   itself are also RCU managed and lookup can be performed holding only
+ *   the q lock.
+ *
+ * - icq's are not reference counted.  They are destroyed when either the
+ *   ioc or q goes away.  Each request with icq set holds an extra
+ *   reference to ioc to ensure it stays until the request is completed.
+ *
+ * - Linking and unlinking icq's are performed while holding both ioc and q
+ *   locks.  Due to the lock ordering, q exit is simple but ioc exit
+ *   requires reverse-order double lock dance.
+ */
+struct io_cq {
+	struct request_queue	*q;
 	struct io_context	*ioc;
 
-	struct cfq_ttime ttime;
-
-	struct list_head queue_list;
-	struct hlist_node cic_list;
-
-	void (*dtor)(struct io_context *); /* destructor */
-	void (*exit)(struct io_context *); /* called on task exit */
-
-	struct rcu_head rcu_head;
+	/*
+	 * q_node and ioc_node link io_cq through icq_list of q and ioc
+	 * respectively.  Both fields are unused once ioc_exit_icq() is
+	 * called and shared with __rcu_icq_cache and __rcu_head which are
+	 * used for RCU free of io_cq.
+	 */
+	union {
+		struct list_head	q_node;
+		struct kmem_cache	*__rcu_icq_cache;
+	};
+	union {
+		struct hlist_node	ioc_node;
+		struct rcu_head		__rcu_head;
+	};
+
+	unsigned long		changed;
 };
 
 /*
@@ -43,11 +103,6 @@ struct io_context {
 	spinlock_t lock;
 
 	unsigned short ioprio;
-	unsigned short ioprio_changed;
-
-#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
-	unsigned short cgroup_changed;
-#endif
 
 	/*
 	 * For request batching
@@ -55,9 +110,11 @@ struct io_context {
 	int nr_batch_requests;     /* Number of requests left in the batch */
 	unsigned long last_waited; /* Time last woken after wait for request */
 
-	struct radix_tree_root radix_root;
-	struct hlist_head cic_list;
-	void __rcu *ioc_data;
+	struct radix_tree_root	icq_tree;
+	struct io_cq __rcu	*icq_hint;
+	struct hlist_head	icq_list;
+
+	struct work_struct release_work;
 };
 
 static inline struct io_context *ioc_task_link(struct io_context *ioc)
@@ -76,20 +133,17 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
 
 struct task_struct;
 #ifdef CONFIG_BLOCK
-int put_io_context(struct io_context *ioc);
+void put_io_context(struct io_context *ioc, struct request_queue *locked_q);
 void exit_io_context(struct task_struct *task);
-struct io_context *get_io_context(gfp_t gfp_flags, int node);
-struct io_context *alloc_io_context(gfp_t gfp_flags, int node);
+struct io_context *get_task_io_context(struct task_struct *task,
+				       gfp_t gfp_flags, int node);
+void ioc_ioprio_changed(struct io_context *ioc, int ioprio);
+void ioc_cgroup_changed(struct io_context *ioc);
 #else
-static inline void exit_io_context(struct task_struct *task)
-{
-}
-
 struct io_context;
-static inline int put_io_context(struct io_context *ioc)
-{
-	return 1;
-}
+static inline void put_io_context(struct io_context *ioc,
+				  struct request_queue *locked_q) { }
+static inline void exit_io_context(struct task_struct *task) { }
 #endif
 
 #endif

kernel/fork.c

@@ -873,6 +873,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 {
 #ifdef CONFIG_BLOCK
 	struct io_context *ioc = current->io_context;
+	struct io_context *new_ioc;
 
 	if (!ioc)
 		return 0;
@@ -884,11 +885,12 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 		if (unlikely(!tsk->io_context))
 			return -ENOMEM;
 	} else if (ioprio_valid(ioc->ioprio)) {
-		tsk->io_context = alloc_io_context(GFP_KERNEL, -1);
-		if (unlikely(!tsk->io_context))
+		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
+		if (unlikely(!new_ioc))
 			return -ENOMEM;
 
-		tsk->io_context->ioprio = ioc->ioprio;
+		new_ioc->ioprio = ioc->ioprio;
+		put_io_context(new_ioc, NULL);
 	}
 #endif
 	return 0;