Merge branch 'for-2.6.40/core' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.40/core' of git://git.kernel.dk/linux-2.6-block: (40 commits)
  cfq-iosched: free cic_index if cfqd allocation fails
  cfq-iosched: remove unused 'group_changed' in cfq_service_tree_add()
  cfq-iosched: reduce bit operations in cfq_choose_req()
  cfq-iosched: algebraic simplification in cfq_prio_to_maxrq()
  blk-cgroup: Initialize ioc->cgroup_changed at ioc creation time
  block: move bd_set_size() above rescan_partitions() in __blkdev_get()
  block: call elv_bio_merged() when merged
  cfq-iosched: Make IO merge related stats per cpu
  cfq-iosched: Fix a memory leak of per cpu stats for root group
  backing-dev: Kill set but not used var in  bdi_debug_stats_show()
  block: get rid of on-stack plugging debug checks
  blk-throttle: Make no throttling rule group processing lockless
  blk-cgroup: Make cgroup stat reset path blkg->lock free for dispatch stats
  blk-cgroup: Make 64bit per cpu stats safe on 32bit arch
  blk-throttle: Make dispatch stats per cpu
  blk-throttle: Free up a group only after one rcu grace period
  blk-throttle: Use helper function to add root throtl group to lists
  blk-throttle: Introduce a helper function to fill in device details
  blk-throttle: Dynamically allocate root group
  blk-cgroup: Allow sleeping while dynamically allocating a group
  ...

Documentation/ABI/testing/sysfs-block

@@ -142,3 +142,67 @@ Description:
 		with the previous I/O request are enabled. When set to 2,
 		all merge tries are disabled. The default value is 0 -
 		which enables all types of merge tries.
+
+What:		/sys/block/<disk>/discard_alignment
+Date:		May 2011
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Devices that support discard functionality may
+		internally allocate space in units that are bigger than
+		the exported logical block size. The discard_alignment
+		parameter indicates how many bytes the beginning of the
+		device is offset from the internal allocation unit's
+		natural alignment.
+
+What:		/sys/block/<disk>/<partition>/discard_alignment
+Date:		May 2011
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Devices that support discard functionality may
+		internally allocate space in units that are bigger than
+		the exported logical block size. The discard_alignment
+		parameter indicates how many bytes the beginning of the
+		partition is offset from the internal allocation unit's
+		natural alignment.
+
+What:		/sys/block/<disk>/queue/discard_granularity
+Date:		May 2011
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Devices that support discard functionality may
+		internally allocate space using units that are bigger
+		than the logical block size. The discard_granularity
+		parameter indicates the size of the internal allocation
+		unit in bytes if reported by the device. Otherwise the
+		discard_granularity will be set to match the device's
+		physical block size. A discard_granularity of 0 means
+		that the device does not support discard functionality.
+
+What:		/sys/block/<disk>/queue/discard_max_bytes
+Date:		May 2011
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Devices that support discard functionality may have
+		internal limits on the number of bytes that can be
+		trimmed or unmapped in a single operation. Some storage
+		protocols also have inherent limits on the number of
+		blocks that can be described in a single command. The
+		discard_max_bytes parameter is set by the device driver
+		to the maximum number of bytes that can be discarded in
+		a single operation. Discard requests issued to the
+		device must not exceed this limit. A discard_max_bytes
+		value of 0 means that the device does not support
+		discard functionality.
+
+What:		/sys/block/<disk>/queue/discard_zeroes_data
+Date:		May 2011
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Devices that support discard functionality may return
+		stale or random data when a previously discarded block
+		is read back. This can cause problems if the filesystem
+		expects discarded blocks to be explicitly cleared. If a
+		device reports that it deterministically returns zeroes
+		when a discarded area is read the discard_zeroes_data
+		parameter will be set to one. Otherwise it will be 0 and
+		the result of reading a discarded area is undefined.

block/blk-cgroup.h

@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/u64_stats_sync.h>
 
 enum blkio_policy_id {
 	BLKIO_POLICY_PROP = 0,		/* Proportional Bandwidth division */
@@ -36,22 +37,15 @@ enum stat_type {
 	 * request completion for IOs doen by this cgroup. This may not be
 	 * accurate when NCQ is turned on. */
 	BLKIO_STAT_SERVICE_TIME = 0,
-	/* Total bytes transferred */
-	BLKIO_STAT_SERVICE_BYTES,
-	/* Total IOs serviced, post merge */
-	BLKIO_STAT_SERVICED,
 	/* Total time spent waiting in scheduler queue in ns */
 	BLKIO_STAT_WAIT_TIME,
-	/* Number of IOs merged */
-	BLKIO_STAT_MERGED,
 	/* Number of IOs queued up */
 	BLKIO_STAT_QUEUED,
 	/* All the single valued stats go below this */
 	BLKIO_STAT_TIME,
-	BLKIO_STAT_SECTORS,
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Time not charged to this cgroup */
 	BLKIO_STAT_UNACCOUNTED_TIME,
-#ifdef CONFIG_DEBUG_BLK_CGROUP
 	BLKIO_STAT_AVG_QUEUE_SIZE,
 	BLKIO_STAT_IDLE_TIME,
 	BLKIO_STAT_EMPTY_TIME,
@@ -60,6 +54,18 @@ enum stat_type {
 #endif
 };
 
+/* Per cpu stats */
+enum stat_type_cpu {
+	BLKIO_STAT_CPU_SECTORS,
+	/* Total bytes transferred */
+	BLKIO_STAT_CPU_SERVICE_BYTES,
+	/* Total IOs serviced, post merge */
+	BLKIO_STAT_CPU_SERVICED,
+	/* Number of IOs merged */
+	BLKIO_STAT_CPU_MERGED,
+	BLKIO_STAT_CPU_NR
+};
+
 enum stat_sub_type {
 	BLKIO_STAT_READ = 0,
 	BLKIO_STAT_WRITE,
@@ -116,11 +122,11 @@ struct blkio_cgroup {
 struct blkio_group_stats {
 	/* total disk time and nr sectors dispatched by this group */
 	uint64_t time;
-	uint64_t sectors;
-	/* Time not charged to this cgroup */
-	uint64_t unaccounted_time;
 	uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
 #ifdef CONFIG_DEBUG_BLK_CGROUP
+	/* Time not charged to this cgroup */
+	uint64_t unaccounted_time;
+
 	/* Sum of number of IOs queued across all samples */
 	uint64_t avg_queue_size_sum;
 	/* Count of samples taken for average */
@@ -145,6 +151,13 @@ struct blkio_group_stats {
 #endif
 };
 
+/* Per cpu blkio group stats */
+struct blkio_group_stats_cpu {
+	uint64_t sectors;
+	uint64_t stat_arr_cpu[BLKIO_STAT_CPU_NR][BLKIO_STAT_TOTAL];
+	struct u64_stats_sync syncp;
+};
+
 struct blkio_group {
 	/* An rcu protected unique identifier for the group */
 	void *key;
@@ -160,6 +173,8 @@ struct blkio_group {
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
 	struct blkio_group_stats stats;
+	/* Per cpu stats pointer */
+	struct blkio_group_stats_cpu __percpu *stats_cpu;
 };
 
 struct blkio_policy_node {
@@ -295,6 +310,7 @@ extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 	struct blkio_group *blkg, void *key, dev_t dev,
 	enum blkio_policy_id plid);
+extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
@@ -322,6 +338,8 @@ static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, void *key, dev_t dev,
 		enum blkio_policy_id plid) {}
 
+static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
+
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 

block/blk-core.c

@@ -569,8 +569,6 @@ int blk_get_queue(struct request_queue *q)
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
 	if (rq->cmd_flags & REQ_ELVPRIV)
 		elv_put_request(q, rq);
 	mempool_free(rq, q->rq.rq_pool);
@@ -1110,14 +1108,6 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
-	/*
-	 * Debug stuff, kill later
-	 */
-	if (!rq_mergeable(req)) {
-		blk_dump_rq_flags(req, "back");
-		return false;
-	}
-
 	if (!ll_back_merge_fn(q, req, bio))
 		return false;
 
@@ -1132,6 +1122,7 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	drive_stat_acct(req, 0);
+	elv_bio_merged(q, req, bio);
 	return true;
 }
 
@@ -1141,14 +1132,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	sector_t sector;
 
-	/*
-	 * Debug stuff, kill later
-	 */
-	if (!rq_mergeable(req)) {
-		blk_dump_rq_flags(req, "front");
-		return false;
-	}
-
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
 
@@ -1173,6 +1156,7 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	drive_stat_acct(req, 0);
+	elv_bio_merged(q, req, bio);
 	return true;
 }
 
@@ -1258,14 +1242,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	el_ret = elv_merge(q, &req, bio);
 	if (el_ret == ELEVATOR_BACK_MERGE) {
-		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
 		if (bio_attempt_back_merge(q, req, bio)) {
 			if (!attempt_back_merge(q, req))
 				elv_merged_request(q, req, el_ret);
 			goto out_unlock;
 		}
 	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
 		if (bio_attempt_front_merge(q, req, bio)) {
 			if (!attempt_front_merge(q, req))
 				elv_merged_request(q, req, el_ret);
@@ -1320,10 +1302,6 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
-		/*
-		 * Debug flag, kill later
-		 */
-		req->cmd_flags |= REQ_ON_PLUG;
 		list_add_tail(&req->queuelist, &plug->list);
 		drive_stat_acct(req, 1);
 	} else {
@@ -1550,7 +1528,8 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		blk_throtl_bio(q, &bio);
+		if (blk_throtl_bio(q, &bio))
+			goto end_io;
 
 		/*
 		 * If bio = NULL, bio has been throttled and will be submitted
@@ -2748,7 +2727,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	while (!list_empty(&list)) {
 		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
-		BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
 		BUG_ON(!rq->q);
 		if (rq->q != q) {
 			/*
@@ -2760,8 +2738,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 			depth = 0;
 			spin_lock(q->queue_lock);
 		}
-		rq->cmd_flags &= ~REQ_ON_PLUG;
-
 		/*
 		 * rq is already accounted, so use raw insert
 		 */

block/blk-exec.c

@@ -56,7 +56,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	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 plugged+unplugged */
+	/* the queue is stopped so it won't be run */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
 	spin_unlock_irq(q->queue_lock);

block/blk-flush.c

@@ -212,13 +212,19 @@ static void flush_end_io(struct request *flush_rq, int error)
 	}
 
 	/*
-	 * Moving a request silently to empty queue_head may stall the
-	 * queue.  Kick the queue in those cases.  This function is called
-	 * from request completion path and calling directly into
-	 * request_fn may confuse the driver.  Always use kblockd.
+	 * Kick the queue to avoid stall for two cases:
+	 * 1. Moving a request silently to empty queue_head may stall the
+	 * queue.
+	 * 2. When flush request is running in non-queueable queue, the
+	 * queue is hold. Restart the queue after flush request is finished
+	 * to avoid stall.
+	 * This function is called from request completion path and calling
+	 * directly into request_fn may confuse the driver.  Always use
+	 * kblockd.
 	 */
-	if (queued)
+	if (queued || q->flush_queue_delayed)
 		blk_run_queue_async(q);
+	q->flush_queue_delayed = 0;
 }
 
 /**

block/blk-ioc.c

@@ -96,6 +96,9 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
 		INIT_HLIST_HEAD(&ret->cic_list);
 		ret->ioc_data = NULL;
+#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
+		ret->cgroup_changed = 0;
+#endif
 	}
 
 	return ret;

block/blk-lib.c

@@ -9,17 +9,20 @@
 
 #include "blk.h"
 
-static void blkdev_discard_end_io(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
+struct bio_batch {
+	atomic_t		done;
+	unsigned long		flags;
+	struct completion	*wait;
+};
 
-	if (bio->bi_private)
-		complete(bio->bi_private);
+static void bio_batch_end_io(struct bio *bio, int err)
+{
+	struct bio_batch *bb = bio->bi_private;
 
+	if (err && (err != -EOPNOTSUPP))
+		clear_bit(BIO_UPTODATE, &bb->flags);
+	if (atomic_dec_and_test(&bb->done))
+		complete(bb->wait);
 	bio_put(bio);
 }
 
@@ -41,6 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
 	unsigned int max_discard_sectors;
+	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
 
@@ -67,7 +71,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		type |= REQ_SECURE;
 	}
 
-	while (nr_sects && !ret) {
+	atomic_set(&bb.done, 1);
+	bb.flags = 1 << BIO_UPTODATE;
+	bb.wait = &wait;
+
+	while (nr_sects) {
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
 			ret = -ENOMEM;
@@ -75,9 +83,9 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		}
 
 		bio->bi_sector = sector;
-		bio->bi_end_io = blkdev_discard_end_io;
+		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
-		bio->bi_private = &wait;
+		bio->bi_private = &bb;
 
 		if (nr_sects > max_discard_sectors) {
 			bio->bi_size = max_discard_sectors << 9;
@@ -88,45 +96,21 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			nr_sects = 0;
 		}
 
-		bio_get(bio);
+		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+	}
 
+	/* Wait for bios in-flight */
+	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion(&wait);
 
-		if (bio_flagged(bio, BIO_EOPNOTSUPP))
-			ret = -EOPNOTSUPP;
-		else if (!bio_flagged(bio, BIO_UPTODATE))
-			ret = -EIO;
-		bio_put(bio);
-	}
+	if (!test_bit(BIO_UPTODATE, &bb.flags))
+		ret = -EIO;
 
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
-struct bio_batch
-{
-	atomic_t 		done;
-	unsigned long 		flags;
-	struct completion 	*wait;
-};
-
-static void bio_batch_end_io(struct bio *bio, int err)
-{
-	struct bio_batch *bb = bio->bi_private;
-
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bb->flags);
-		else
-			clear_bit(BIO_UPTODATE, &bb->flags);
-	}
-	if (bb)
-		if (atomic_dec_and_test(&bb->done))
-			complete(bb->wait);
-	bio_put(bio);
-}
-
 /**
  * blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:	blockdev to issue
@@ -151,7 +135,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	bb.flags = 1 << BIO_UPTODATE;
 	bb.wait = &wait;
 
-submit:
 	ret = 0;
 	while (nr_sects != 0) {
 		bio = bio_alloc(gfp_mask,
@@ -168,9 +151,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
-			if (sz == 0)
-				/* bio has maximum size possible */
-				break;
 			ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
 			nr_sects -= ret >> 9;
 			sector += ret >> 9;
@@ -190,16 +170,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		/* One of bios in the batch was completed with error.*/
 		ret = -EIO;
 
-	if (ret)
-		goto out;
-
-	if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
-	if (nr_sects != 0)
-		goto submit;
-out:
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);

block/blk-settings.c

@@ -120,7 +120,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
-	lim->discard_zeroes_data = -1;
+	lim->discard_zeroes_data = 1;
 	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;
@@ -166,6 +166,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 
 	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
@@ -790,6 +791,12 @@ void blk_queue_flush(struct request_queue *q, unsigned int flush)
 }
 EXPORT_SYMBOL_GPL(blk_queue_flush);
 
+void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
+{
+	q->flush_not_queueable = !queueable;
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;

block/blk-sysfs.c

@@ -152,7 +152,8 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->limits.max_discard_sectors << 9, page);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)q->limits.max_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)

block/blk.h

@@ -62,7 +62,28 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return rq;
 		}
 
-		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+		/*
+		 * Flush request is running and flush request isn't queueable
+		 * in the drive, we can hold the queue till flush request is
+		 * finished. Even we don't do this, driver can't dispatch next
+		 * requests and will requeue them. And this can improve
+		 * throughput too. For example, we have request flush1, write1,
+		 * flush 2. flush1 is dispatched, then queue is hold, write1
+		 * isn't inserted to queue. After flush1 is finished, flush2
+		 * will be dispatched. Since disk cache is already clean,
+		 * flush2 will be finished very soon, so looks like flush2 is
+		 * folded to flush1.
+		 * Since the queue is hold, a flag is set to indicate the queue
+		 * should be restarted later. Please see flush_end_io() for
+		 * details.
+		 */
+		if (q->flush_pending_idx != q->flush_running_idx &&
+				!queue_flush_queueable(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))
 			return NULL;
 	}
 }

block/elevator.c

@@ -155,13 +155,8 @@ static struct elevator_type *elevator_get(const char *name)
 
 	e = elevator_find(name);
 	if (!e) {
-		char elv[ELV_NAME_MAX + strlen("-iosched")];
-
 		spin_unlock(&elv_list_lock);
-
-		snprintf(elv, sizeof(elv), "%s-iosched", name);
-
-		request_module("%s", elv);
+		request_module("%s-iosched", name);
 		spin_lock(&elv_list_lock);
 		e = elevator_find(name);
 	}
@@ -421,8 +416,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	struct list_head *entry;
 	int stop_flags;
 
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
 
@@ -661,8 +654,6 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	rq->q = q;
 
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
 	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||

drivers/ata/libata-scsi.c

@@ -1089,21 +1089,21 @@ static int atapi_drain_needed(struct request *rq)
 static int ata_scsi_dev_config(struct scsi_device *sdev,
 			       struct ata_device *dev)
 {
+	struct request_queue *q = sdev->request_queue;
+
 	if (!ata_id_has_unload(dev->id))
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
-	blk_queue_max_hw_sectors(sdev->request_queue, dev->max_sectors);
+	blk_queue_max_hw_sectors(q, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
-		struct request_queue *q = sdev->request_queue;
 		void *buf;
 
 		sdev->sector_size = ATA_SECT_SIZE;
 
 		/* set DMA padding */
-		blk_queue_update_dma_pad(sdev->request_queue,
-					 ATA_DMA_PAD_SZ - 1);
+		blk_queue_update_dma_pad(q, ATA_DMA_PAD_SZ - 1);
 
 		/* configure draining */
 		buf = kmalloc(ATAPI_MAX_DRAIN, q->bounce_gfp | GFP_KERNEL);
@@ -1131,8 +1131,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 			"sector_size=%u > PAGE_SIZE, PIO may malfunction\n",
 			sdev->sector_size);
 
-	blk_queue_update_dma_alignment(sdev->request_queue,
-				       sdev->sector_size - 1);
+	blk_queue_update_dma_alignment(q, sdev->sector_size - 1);
 
 	if (dev->flags & ATA_DFLAG_AN)
 		set_bit(SDEV_EVT_MEDIA_CHANGE, sdev->supported_events);
@@ -1145,6 +1144,8 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
 	}
 
+	blk_queue_flush_queueable(q, false);
+
 	dev->sdev = sdev;
 	return 0;
 }

drivers/block/paride/pcd.c

@@ -320,6 +320,8 @@ static void pcd_init_units(void)
 		disk->first_minor = unit;
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
+		disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 

drivers/cdrom/viocd.c

@@ -625,7 +625,9 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	blk_queue_max_hw_sectors(q, 4096 / 512);
 	gendisk->queue = q;
 	gendisk->fops = &viocd_fops;
-	gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE;
+	gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
+			 GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;

drivers/ide/ide-cd.c

@@ -1781,7 +1781,8 @@ static int ide_cd_probe(ide_drive_t *drive)
 
 	ide_cd_read_toc(drive, &sense);
 	g->fops = &idecd_ops;
-	g->flags |= GENHD_FL_REMOVABLE;
+	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+	g->events = DISK_EVENT_MEDIA_CHANGE;
 	add_disk(g);
 	return 0;
 

drivers/scsi/sr.c

@@ -636,7 +636,7 @@ static int sr_probe(struct device *dev)
 	disk->first_minor = minor;
 	sprintf(disk->disk_name, "sr%d", minor);
 	disk->fops = &sr_bdops;
-	disk->flags = GENHD_FL_CD;
+	disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
 
 	blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);

fs/block_dev.c

@@ -1238,6 +1238,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 	res = __blkdev_get(bdev, mode, 0);
 
 	if (whole) {
+		struct gendisk *disk = whole->bd_disk;
+
 		/* finish claiming */
 		mutex_lock(&bdev->bd_mutex);
 		spin_lock(&bdev_lock);
@@ -1264,15 +1266,16 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		spin_unlock(&bdev_lock);
 
 		/*
-		 * Block event polling for write claims.  Any write
-		 * holder makes the write_holder state stick until all
-		 * are released.  This is good enough and tracking
-		 * individual writeable reference is too fragile given
-		 * the way @mode is used in blkdev_get/put().
+		 * Block event polling for write claims if requested.  Any
+		 * write holder makes the write_holder state stick until
+		 * all are released.  This is good enough and tracking
+		 * individual writeable reference is too fragile given the
+		 * way @mode is used in blkdev_get/put().
 		 */
-		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+		if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
+		    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
 			bdev->bd_write_holder = true;
-			disk_block_events(bdev->bd_disk);
+			disk_block_events(disk);
 		}
 
 		mutex_unlock(&bdev->bd_mutex);

fs/partitions/check.c

@@ -255,7 +255,11 @@ ssize_t part_discard_alignment_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%u\n", p->discard_alignment);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%u\n",
+			queue_limit_discard_alignment(&disk->queue->limits,
+							p->start_sect));
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -449,8 +453,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	p->start_sect = start;
 	p->alignment_offset =
 		queue_limit_alignment_offset(&disk->queue->limits, start);
-	p->discard_alignment =
-		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);

include/linux/blk_types.h

@@ -151,7 +151,6 @@ enum rq_flag_bits {
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
-	__REQ_ON_PLUG,		/* on plug list */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -192,6 +191,5 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
-#define REQ_ON_PLUG		(1 << __REQ_ON_PLUG)
 
 #endif /* __LINUX_BLK_TYPES_H */

include/linux/blkdev.h

@@ -257,7 +257,7 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		cluster;
-	signed char		discard_zeroes_data;
+	unsigned char		discard_zeroes_data;
 };
 
 struct request_queue
@@ -364,6 +364,8 @@ struct request_queue
 	 * for flush operations
 	 */
 	unsigned int		flush_flags;
+	unsigned int		flush_not_queueable:1;
+	unsigned int		flush_queue_delayed:1;
 	unsigned int		flush_pending_idx:1;
 	unsigned int		flush_running_idx:1;
 	unsigned long		flush_pending_since;
@@ -843,6 +845,7 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
+extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
@@ -1066,13 +1069,16 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 {
 	unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1);
 
+	if (!lim->max_discard_sectors)
+		return 0;
+
 	return (lim->discard_granularity + lim->discard_alignment - alignment)
 		& (lim->discard_granularity - 1);
 }
 
 static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
 {
-	if (q->limits.discard_zeroes_data == 1)
+	if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
 		return 1;
 
 	return 0;
@@ -1111,6 +1117,11 @@ static inline unsigned int block_size(struct block_device *bdev)
 	return bdev->bd_block_size;
 }
 
+static inline bool queue_flush_queueable(struct request_queue *q)
+{
+	return !q->flush_not_queueable;
+}
+
 typedef struct {struct page *v;} Sector;
 
 unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);

include/linux/genhd.h

@@ -100,7 +100,6 @@ struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
 	sector_t alignment_offset;
-	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
@@ -127,6 +126,7 @@ struct hd_struct {
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	32
 #define GENHD_FL_EXT_DEVT			64 /* allow extended devt */
 #define GENHD_FL_NATIVE_CAPACITY		128
+#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	256
 
 enum {
 	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */

mm/backing-dev.c

@@ -63,10 +63,10 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
-	unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+	unsigned long nr_dirty, nr_io, nr_more_io;
 	struct inode *inode;
 
-	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
+	nr_dirty = nr_io = nr_more_io = 0;
 	spin_lock(&inode_wb_list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;