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

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  block: don't delay blk_run_queue_async
  scsi: remove performance regression due to async queue run
  blk-throttle: Use task_subsys_state() to determine a task's blkio_cgroup
  block: rescan partitions on invalidated devices on -ENOMEDIA too
  cdrom: always check_disk_change() on open
  block: unexport DISK_EVENT_MEDIA_CHANGE for legacy/fringe drivers

25 files changed, 62 insertions, 43 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f0605ab..471fdcc 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -114,6 +114,13 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, blkio_subsys_id),
+			    struct blkio_cgroup, css);
+}
+EXPORT_SYMBOL_GPL(task_blkio_cgroup);
+
 static inline void
 blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
 {
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 10919fa..c774930 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -291,6 +291,7 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
+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);
@@ -314,6 +315,8 @@ void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
 struct cgroup;
 static inline struct blkio_cgroup *
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
+static inline struct blkio_cgroup *
+task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, void *key, dev_t dev,
diff --git a/block/blk-core.c b/block/blk-core.c
index a2e58ee..3fe00a1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -316,8 +316,10 @@ EXPORT_SYMBOL(__blk_run_queue);
  */
 void blk_run_queue_async(struct request_queue *q)
 {
-	if (likely(!blk_queue_stopped(q)))
+	if (likely(!blk_queue_stopped(q))) {
+		__cancel_delayed_work(&q->delay_work);
 		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+	}
 }
 EXPORT_SYMBOL(blk_run_queue_async);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 0475a22..252a81a 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -160,9 +160,8 @@ static void throtl_put_tg(struct throtl_grp *tg)
 }
 
 static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
-			struct cgroup *cgroup)
+			struct blkio_cgroup *blkcg)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
 	struct throtl_grp *tg = NULL;
 	void *key = td;
 	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
@@ -229,12 +228,12 @@ done:
 
 static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 {
-	struct cgroup *cgroup;
 	struct throtl_grp *tg = NULL;
+	struct blkio_cgroup *blkcg;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
-	tg = throtl_find_alloc_tg(td, cgroup);
+	blkcg = task_blkio_cgroup(current);
+	tg = throtl_find_alloc_tg(td, blkcg);
 	if (!tg)
 		tg = &td->root_tg;
 	rcu_read_unlock();
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 5b52011..ab7a9e6 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1014,10 +1014,9 @@ void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 	cfqg->needs_update = true;
 }
 
-static struct cfq_group *
-cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+static struct cfq_group * cfq_find_alloc_cfqg(struct cfq_data *cfqd,
+		struct blkio_cgroup *blkcg, int create)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
 	struct cfq_group *cfqg = NULL;
 	void *key = cfqd;
 	int i, j;
@@ -1079,12 +1078,12 @@ done:
  */
 static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 {
-	struct cgroup *cgroup;
+	struct blkio_cgroup *blkcg;
 	struct cfq_group *cfqg = NULL;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
-	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+	blkcg = task_blkio_cgroup(current);
+	cfqg = cfq_find_alloc_cfqg(cfqd, blkcg, create);
 	if (!cfqg && create)
 		cfqg = &cfqd->root_group;
 	rcu_read_unlock();
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 8066d08..e086fbb 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2547,7 +2547,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
 	disk->major = MajorNumber;
 	disk->first_minor = n << DAC960_MaxPartitionsBits;
 	disk->fops = &DAC960_BlockDeviceOperations;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
    }
   /*
     Indicate the Block Device Registration completed successfully,
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 456c0cc..8eba86b 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1736,7 +1736,6 @@ static int __init fd_probe_drives(void)
 		disk->major = FLOPPY_MAJOR;
 		disk->first_minor = drive;
 		disk->fops = &floppy_fops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 		sprintf(disk->disk_name, "fd%d", drive);
 		disk->private_data = &unit[drive];
 		set_capacity(disk, 880*2);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index c871eae..ede16c6 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1964,7 +1964,6 @@ static int __init atari_floppy_init (void)
 		unit[i].disk->first_minor = i;
 		sprintf(unit[i].disk->disk_name, "fd%d", i);
 		unit[i].disk->fops = &floppy_fops;
-		unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE;
 		unit[i].disk->private_data = &unit[i];
 		unit[i].disk->queue = blk_init_queue(do_fd_request,
 					&ataflop_lock);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 301d7a9..db8f885 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4205,7 +4205,6 @@ static int __init floppy_init(void)
 		disks[dr]->major = FLOPPY_MAJOR;
 		disks[dr]->first_minor = TOMINOR(dr);
 		disks[dr]->fops = &floppy_fops;
-		disks[dr]->events = DISK_EVENT_MEDIA_CHANGE;
 		sprintf(disks[dr]->disk_name, "fd%d", dr);
 
 		init_timer(&motor_off_timer[dr]);
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 2f2ccf6..8690e31 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -320,7 +320,6 @@ static void pcd_init_units(void)
 		disk->first_minor = unit;
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 21dfdb77..869e767 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -837,7 +837,6 @@ static void pd_probe_drive(struct pd_unit *disk)
 	p->fops = &pd_fops;
 	p->major = major;
 	p->first_minor = (disk - pd) << PD_BITS;
-	p->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->gd = p;
 	p->private_data = disk;
 	p->queue = pd_queue;
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 7adeb1e..f21b520 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -294,7 +294,6 @@ static void __init pf_init_units(void)
 		disk->first_minor = unit;
 		strcpy(disk->disk_name, pf->name);
 		disk->fops = &pf_fops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 		if (!(*drives[unit])[D_PRT])
 			pf_drive_count++;
 	}
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 24a482f..fd5adcd 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -858,7 +858,6 @@ static int __devinit swim_floppy_init(struct swim_priv *swd)
 		swd->unit[drive].disk->first_minor = drive;
 		sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
 		swd->unit[drive].disk->fops = &floppy_fops;
-		swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE;
 		swd->unit[drive].disk->private_data = &swd->unit[drive];
 		swd->unit[drive].disk->queue = swd->queue;
 		set_capacity(swd->unit[drive].disk, 2880);
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 4c10f56..773bfa7 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1163,7 +1163,6 @@ static int __devinit swim3_attach(struct macio_dev *mdev, const struct of_device
 	disk->major = FLOPPY_MAJOR;
 	disk->first_minor = i;
 	disk->fops = &floppy_fops;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = &floppy_states[i];
 	disk->queue = swim3_queue;
 	disk->flags |= GENHD_FL_REMOVABLE;
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index 68b9430..0e376d4 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -2334,7 +2334,6 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum)
 	disk->major = UB_MAJOR;
 	disk->first_minor = lun->id * UB_PARTS_PER_LUN;
 	disk->fops = &ub_bd_fops;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = lun;
 	disk->driverfs_dev = &sc->intf->dev;
 
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 645ff76..6c7fd7d 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1005,7 +1005,6 @@ static int __devinit ace_setup(struct ace_device *ace)
 	ace->gd->major = ace_major;
 	ace->gd->first_minor = ace->id * ACE_NUM_MINORS;
 	ace->gd->fops = &ace_fops;
-	ace->gd->events = DISK_EVENT_MEDIA_CHANGE;
 	ace->gd->queue = ace->queue;
 	ace->gd->private_data = ace;
 	snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a');
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 514dd8e..75fb965 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -986,6 +986,9 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t
 
 	cdinfo(CD_OPEN, "entering cdrom_open\n"); 
 
+	/* open is event synchronization point, check events first */
+	check_disk_change(bdev);
+
 	/* if this was a O_NONBLOCK open and we should honor the flags,
 	 * do a quick open without drive/disc integrity checks. */
 	cdi->use_count++;
@@ -1012,9 +1015,6 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t
 
 	cdinfo(CD_OPEN, "Use count for \"/dev/%s\" now %d\n",
 			cdi->name, cdi->use_count);
-	/* Do this on open.  Don't wait for mount, because they might
-	    not be mounting, but opening with O_NONBLOCK */
-	check_disk_change(bdev);
 	return 0;
 err_release:
 	if (CDROM_CAN(CDC_LOCK) && cdi->options & CDO_LOCK) {
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index b2b034f..3ceaf00 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -803,7 +803,6 @@ static int __devinit probe_gdrom(struct platform_device *devptr)
 		goto probe_fail_cdrom_register;
 	}
 	gd.disk->fops = &gdrom_bdops;
-	gd.disk->events = DISK_EVENT_MEDIA_CHANGE;
 	/* latch on to the interrupt */
 	err = gdrom_set_interrupt_handlers();
 	if (err)
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index 4e874c5..e427fbe 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -626,7 +626,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	gendisk->queue = q;
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE;
-	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index 643ad52..4796bbf 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -1000,7 +1000,6 @@ static struct i2o_block_device *i2o_block_device_alloc(void)
 	gd->major = I2O_MAJOR;
 	gd->queue = queue;
 	gd->fops = &i2o_block_fops;
-	gd->events = DISK_EVENT_MEDIA_CHANGE;
 	gd->private_data = dev;
 
 	dev->gd = gd;
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index 83cea9a55..1b3924c 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -236,7 +236,6 @@ tapeblock_setup_device(struct tape_device * device)
 	disk->major = tapeblock_major;
 	disk->first_minor = device->first_minor;
 	disk->fops = &tapeblock_fops;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = tape_get_device(device);
 	disk->queue = blkdat->request_queue;
 	set_capacity(disk, 0);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0bac91e..ec1803a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -74,8 +74,6 @@ struct kmem_cache *scsi_sdb_cache;
  */
 #define SCSI_QUEUE_DELAY	3
 
-static void scsi_run_queue(struct request_queue *q);
-
 /*
  * Function:	scsi_unprep_request()
  *
@@ -161,7 +159,7 @@ static int __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy)
 	blk_requeue_request(q, cmd->request);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
-	scsi_run_queue(q);
+	kblockd_schedule_work(q, &device->requeue_work);
 
 	return 0;
 }
@@ -438,7 +436,11 @@ static void scsi_run_queue(struct request_queue *q)
 			continue;
 		}
 
-		blk_run_queue_async(sdev->request_queue);
+		spin_unlock(shost->host_lock);
+		spin_lock(sdev->request_queue->queue_lock);
+		__blk_run_queue(sdev->request_queue);
+		spin_unlock(sdev->request_queue->queue_lock);
+		spin_lock(shost->host_lock);
 	}
 	/* put any unprocessed entries back */
 	list_splice(&starved_list, &shost->starved_list);
@@ -447,6 +449,16 @@ static void scsi_run_queue(struct request_queue *q)
 	blk_run_queue(q);
 }
 
+void scsi_requeue_run_queue(struct work_struct *work)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+
+	sdev = container_of(work, struct scsi_device, requeue_work);
+	q = sdev->request_queue;
+	scsi_run_queue(q);
+}
+
 /*
  * Function:	scsi_requeue_command()
  *
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 087821f..58584dc 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -242,6 +242,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	int display_failure_msg = 1, ret;
 	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
 	extern void scsi_evt_thread(struct work_struct *work);
+	extern void scsi_requeue_run_queue(struct work_struct *work);
 
 	sdev = kzalloc(sizeof(*sdev) + shost->transportt->device_size,
 		       GFP_ATOMIC);
@@ -264,6 +265,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	INIT_LIST_HEAD(&sdev->event_list);
 	spin_lock_init(&sdev->list_lock);
 	INIT_WORK(&sdev->event_work, scsi_evt_thread);
+	INIT_WORK(&sdev->requeue_work, scsi_requeue_run_queue);
 
 	sdev->sdev_gendev.parent = get_device(&starget->dev);
 	sdev->sdev_target = starget;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5147bdd..257b00e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1102,6 +1102,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (!bdev->bd_part)
 				goto out_clear;
 
+			ret = 0;
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev, mode);
 				if (ret == -ERESTARTSYS) {
@@ -1118,9 +1119,18 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					put_disk(disk);
 					goto restart;
 				}
-				if (ret)
-					goto out_clear;
 			}
+			/*
+			 * If the device is invalidated, rescan partition
+			 * if open succeeded or failed with -ENOMEDIUM.
+			 * The latter is necessary to prevent ghost
+			 * partitions on a removed medium.
+			 */
+			if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
+				rescan_partitions(disk, bdev);
+			if (ret)
+				goto out_clear;
+
 			if (!bdev->bd_openers) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
 				bdi = blk_get_backing_dev_info(bdev);
@@ -1128,8 +1138,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					bdi = &default_backing_dev_info;
 				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
-			if (bdev->bd_invalidated)
-				rescan_partitions(disk, bdev);
 		} else {
 			struct block_device *whole;
 			whole = bdget_disk(disk, 0);
@@ -1153,13 +1161,14 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		}
 	} else {
 		if (bdev->bd_contains == bdev) {
-			if (bdev->bd_disk->fops->open) {
+			ret = 0;
+			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
-				if (ret)
-					goto out_unlock_bdev;
-			}
-			if (bdev->bd_invalidated)
+			/* the same as first opener case, read comment there */
+			if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
 				rescan_partitions(bdev->bd_disk, bdev);
+			if (ret)
+				goto out_unlock_bdev;
 		}
 		/* only one opener holds refs to the module and disk */
 		module_put(disk->fops->owner);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 2d3ec50..dd82e02 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -169,6 +169,7 @@ struct scsi_device {
 				sdev_dev;
 
 	struct execute_work	ew; /* used to get process context on put */
+	struct work_struct	requeue_work;
 
 	struct scsi_dh_data	*scsi_dh_data;
 	enum scsi_device_state sdev_state;