1 files changed, 697 insertions, 95 deletions

diff --git a/block/genhd.c b/block/genhd.c
index a9ec910974c..791f4194313 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -15,19 +15,18 @@
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/kobj_map.h>
-#include <linux/buffer_head.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
+#include <linux/log2.h>
+#include <linux/pm_runtime.h>
 
 #include "blk.h"
 
 static DEFINE_MUTEX(block_class_lock);
-#ifndef CONFIG_SYSFS_DEPRECATED
 struct kobject *block_depr;
-#endif
 
 /* for extended dynamic devt allocation, currently only one major is used */
-#define MAX_EXT_DEVT		(1 << MINORBITS)
+#define NR_EXT_DEVT		(1 << MINORBITS)
 
 /* For extended devt allocation.  ext_devt_mutex prevents look up
  * results from going away underneath its user.
@@ -37,6 +36,13 @@ static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
 
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr);
+static void disk_alloc_events(struct gendisk *disk);
+static void disk_add_events(struct gendisk *disk);
+static void disk_del_events(struct gendisk *disk);
+static void disk_release_events(struct gendisk *disk);
+
 /**
  * disk_get_part - get partition
  * @disk: disk to look partition from
@@ -98,7 +104,7 @@ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
 
 	if (flags & DISK_PITER_REVERSE)
 		piter->idx = ptbl->len - 1;
-	else if (flags & DISK_PITER_INCL_PART0)
+	else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
 		piter->idx = 0;
 	else
 		piter->idx = 1;
@@ -134,7 +140,8 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 	/* determine iteration parameters */
 	if (piter->flags & DISK_PITER_REVERSE) {
 		inc = -1;
-		if (piter->flags & DISK_PITER_INCL_PART0)
+		if (piter->flags & (DISK_PITER_INCL_PART0 |
+				    DISK_PITER_INCL_EMPTY_PART0))
 			end = -1;
 		else
 			end = 0;
@@ -150,7 +157,10 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
+		if (!part_nr_sects_read(part) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+		      piter->idx == 0))
 			continue;
 
 		get_device(part_to_dev(part));
@@ -184,7 +194,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 static inline int sector_in_part(struct hd_struct *part, sector_t sector)
 {
 	return part->start_sect <= sector &&
-		sector < part->start_sect + part->nr_sects;
+		sector < part->start_sect + part_nr_sects_read(part);
 }
 
 /**
@@ -237,7 +247,7 @@ static struct blk_major_name {
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 
 /* index in the above - for now: assume no multimajor ranges */
-static inline int major_to_index(int major)
+static inline int major_to_index(unsigned major)
 {
 	return major % BLKDEV_MAJOR_HASH_SIZE;
 }
@@ -401,7 +411,7 @@ static int blk_mangle_minor(int minor)
 int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 {
 	struct gendisk *disk = part_to_disk(part);
-	int idx, rc;
+	int idx;
 
 	/* in consecutive minor range? */
 	if (part->partno < disk->minors) {
@@ -410,19 +420,11 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	}
 
 	/* allocate ext devt */
-	do {
-		if (!idr_pre_get(&ext_devt_idr, GFP_KERNEL))
-			return -ENOMEM;
-		rc = idr_get_new(&ext_devt_idr, part, &idx);
-	} while (rc == -EAGAIN);
-
-	if (rc)
-		return rc;
-
-	if (idx > MAX_EXT_DEVT) {
-		idr_remove(&ext_devt_idr, idx);
-		return -EBUSY;
-	}
+	mutex_lock(&ext_devt_mutex);
+	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
+	mutex_unlock(&ext_devt_mutex);
+	if (idx < 0)
+		return idx == -ENOSPC ? -EBUSY : idx;
 
 	*devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx));
 	return 0;
@@ -500,6 +502,72 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
+static void register_disk(struct gendisk *disk)
+{
+	struct device *ddev = disk_to_dev(disk);
+	struct block_device *bdev;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+	int err;
+
+	ddev->parent = disk->driverfs_dev;
+
+	dev_set_name(ddev, "%s", disk->disk_name);
+
+	/* delay uevents, until we scanned partition table */
+	dev_set_uevent_suppress(ddev, 1);
+
+	if (device_add(ddev))
+		return;
+	if (!sysfs_deprecated) {
+		err = sysfs_create_link(block_depr, &ddev->kobj,
+					kobject_name(&ddev->kobj));
+		if (err) {
+			device_del(ddev);
+			return;
+		}
+	}
+
+	/*
+	 * avoid probable deadlock caused by allocating memory with
+	 * GFP_KERNEL in runtime_resume callback of its all ancestor
+	 * devices
+	 */
+	pm_runtime_set_memalloc_noio(ddev, true);
+
+	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
+
+	/* No minors to use for partitions */
+	if (!disk_part_scan_enabled(disk))
+		goto exit;
+
+	/* No such device (e.g., media were just removed) */
+	if (!get_capacity(disk))
+		goto exit;
+
+	bdev = bdget_disk(disk, 0);
+	if (!bdev)
+		goto exit;
+
+	bdev->bd_invalidated = 1;
+	err = blkdev_get(bdev, FMODE_READ, NULL);
+	if (err < 0)
+		goto exit;
+	blkdev_put(bdev, FMODE_READ);
+
+exit:
+	/* announce disk after possible partitions are created */
+	dev_set_uevent_suppress(ddev, 0);
+	kobject_uevent(&ddev->kobj, KOBJ_ADD);
+
+	/* announce possible partitions */
+	disk_part_iter_init(&piter, disk, 0);
+	while ((part = disk_part_iter_next(&piter)))
+		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+	disk_part_iter_exit(&piter);
+}
+
 /**
  * add_disk - add partitioning information to kernel list
  * @disk: per-device partitioning information
@@ -537,28 +605,69 @@ void add_disk(struct gendisk *disk)
 	disk->major = MAJOR(devt);
 	disk->first_minor = MINOR(devt);
 
+	disk_alloc_events(disk);
+
+	/* Register BDI before referencing it from bdev */
+	bdi = &disk->queue->backing_dev_info;
+	bdi_register_dev(bdi, disk_devt(disk));
+
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
 	register_disk(disk);
 	blk_register_queue(disk);
 
-	bdi = &disk->queue->backing_dev_info;
-	bdi_register_dev(bdi, disk_devt(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));
+
 	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
 				   "bdi");
 	WARN_ON(retval);
-}
 
+	disk_add_events(disk);
+}
 EXPORT_SYMBOL(add_disk);
-EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
 
-void unlink_gendisk(struct gendisk *disk)
+void del_gendisk(struct gendisk *disk)
 {
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+
+	disk_del_events(disk);
+
+	/* invalidate stuff */
+	disk_part_iter_init(&piter, disk,
+			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
+	while ((part = disk_part_iter_next(&piter))) {
+		invalidate_partition(disk, part->partno);
+		delete_partition(disk, part->partno);
+	}
+	disk_part_iter_exit(&piter);
+
+	invalidate_partition(disk, 0);
+	set_capacity(disk, 0);
+	disk->flags &= ~GENHD_FL_UP;
+
 	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
 	bdi_unregister(&disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
 	blk_unregister_region(disk_devt(disk), disk->minors);
+
+	part_stat_set_all(&disk->part0, 0);
+	disk->part0.stamp = 0;
+
+	kobject_put(disk->part0.holder_dir);
+	kobject_put(disk->slave_dir);
+	disk->driverfs_dev = NULL;
+	if (!sysfs_deprecated)
+		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
+	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
+	device_del(disk_to_dev(disk));
+	blk_free_devt(disk_to_dev(disk)->devt);
 }
+EXPORT_SYMBOL(del_gendisk);
 
 /**
  * get_gendisk - get partitioning information for a given device
@@ -592,6 +701,7 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 
 	return disk;
 }
+EXPORT_SYMBOL(get_gendisk);
 
 /**
  * bdget_disk - do bdget() by gendisk and partition number
@@ -640,7 +750,7 @@ void __init printk_all_partitions(void)
 
 		/*
 		 * Don't show empty devices or things that have been
-		 * surpressed
+		 * suppressed
 		 */
 		if (get_capacity(disk) == 0 ||
 		    (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO))
@@ -655,10 +765,11 @@ void __init printk_all_partitions(void)
 		while ((part = disk_part_iter_next(&piter))) {
 			bool is_part0 = part == &disk->part0;
 
-			printk("%s%s %10llu %s", is_part0 ? "" : "  ",
+			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
-			       (unsigned long long)part->nr_sects >> 1,
-			       disk_name(disk, part->partno, name_buf));
+			       (unsigned long long)part_nr_sects_read(part) >> 1
+			       , disk_name(disk, part->partno, name_buf),
+			       part->info ? part->info->uuid : "");
 			if (is_part0) {
 				if (disk->driverfs_dev != NULL &&
 				    disk->driverfs_dev->driver != NULL)
@@ -722,10 +833,10 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v)
 
 static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
 {
-	static void *p;
+	void *p;
 
 	p = disk_seqf_start(seqf, pos);
-	if (!IS_ERR(p) && p && !*pos)
+	if (!IS_ERR_OR_NULL(p) && !*pos)
 		seq_puts(seqf, "major minor  #blocks  name\n\n");
 	return p;
 }
@@ -738,7 +849,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_partitionable(sgp) &&
+	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
@@ -749,7 +860,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	while ((part = disk_part_iter_next(&piter)))
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
 			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
-			   (unsigned long long)part->nr_sects >> 1,
+			   (unsigned long long)part_nr_sects_read(part) >> 1,
 			   disk_name(sgp, part->partno, buf));
 	disk_part_iter_exit(&piter);
 
@@ -798,10 +909,9 @@ static int __init genhd_device_init(void)
 
 	register_blkdev(BLOCK_EXT_MAJOR, "blkext");
 
-#ifndef CONFIG_SYSFS_DEPRECATED
 	/* create top-level block dir */
-	block_depr = kobject_create_and_add("block", NULL);
-#endif
+	if (!sysfs_deprecated)
+		block_depr = kobject_create_and_add("block", NULL);
 	return 0;
 }
 
@@ -848,13 +958,35 @@ static ssize_t disk_capability_show(struct device *dev,
 	return sprintf(buf, "%x\n", disk->flags);
 }
 
+static ssize_t disk_alignment_offset_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
+}
+
+static ssize_t disk_discard_alignment_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
+		   NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -871,8 +1003,11 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_removable.attr,
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -886,19 +1021,11 @@ static struct attribute_group disk_attr_group = {
 	.attrs = disk_attrs,
 };
 
-static struct attribute_group *disk_attr_groups[] = {
+static const struct attribute_group *disk_attr_groups[] = {
 	&disk_attr_group,
 	NULL
 };
 
-static void disk_free_ptbl_rcu_cb(struct rcu_head *head)
-{
-	struct disk_part_tbl *ptbl =
-		container_of(head, struct disk_part_tbl, rcu_head);
-
-	kfree(ptbl);
-}
-
 /**
  * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way
  * @disk: disk to replace part_tbl for
@@ -919,7 +1046,7 @@ static void disk_replace_part_tbl(struct gendisk *disk,
 
 	if (old_ptbl) {
 		rcu_assign_pointer(old_ptbl->last_lookup, NULL);
-		call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb);
+		kfree_rcu(old_ptbl, rcu_head);
 	}
 }
 
@@ -958,7 +1085,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	if (!new_ptbl)
 		return -ENOMEM;
 
-	INIT_RCU_HEAD(&new_ptbl->rcu_head);
 	new_ptbl->len = target;
 
 	for (i = 0; i < len; i++)
@@ -972,19 +1098,34 @@ static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
 	free_part_stats(&disk->part0);
+	free_part_info(&disk->part0);
+	if (disk->queue)
+		blk_put_queue(disk->queue);
 	kfree(disk);
 }
 struct class block_class = {
 	.name		= "block",
 };
 
+static char *block_devnode(struct device *dev, umode_t *mode,
+			   kuid_t *uid, kgid_t *gid)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (disk->devnode)
+		return disk->devnode(disk, mode);
+	return NULL;
+}
+
 static struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
+	.devnode	= block_devnode,
 };
 
 #ifdef CONFIG_PROC_FS
@@ -1010,31 +1151,31 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 				"wsect wuse running use aveq"
 				"\n\n");
 	*/
- 
-	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_PART0);
+
+	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
 		cpu = part_stat_lock();
 		part_round_stats(cpu, hd);
 		part_stat_unlock();
-		seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
-			   "%u %lu %lu %llu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
+			   "%u %lu %lu %lu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[0]),
-			   part_stat_read(hd, merges[0]),
-			   (unsigned long long)part_stat_read(hd, sectors[0]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[0])),
-			   part_stat_read(hd, ios[1]),
-			   part_stat_read(hd, merges[1]),
-			   (unsigned long long)part_stat_read(hd, sectors[1]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
-			   hd->in_flight,
+			   part_stat_read(hd, ios[READ]),
+			   part_stat_read(hd, merges[READ]),
+			   part_stat_read(hd, sectors[READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
+			   part_stat_read(hd, ios[WRITE]),
+			   part_stat_read(hd, merges[WRITE]),
+			   part_stat_read(hd, sectors[WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
+			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
 			);
 	}
 	disk_part_iter_exit(&piter);
- 
+
 	return 0;
 }
 
@@ -1066,29 +1207,6 @@ static int __init proc_genhd_init(void)
 module_init(proc_genhd_init);
 #endif /* CONFIG_PROC_FS */
 
-static void media_change_notify_thread(struct work_struct *work)
-{
-	struct gendisk *gd = container_of(work, struct gendisk, async_notify);
-	char event[] = "MEDIA_CHANGE=1";
-	char *envp[] = { event, NULL };
-
-	/*
-	 * set enviroment vars to indicate which event this is for
-	 * so that user space will know to go check the media status.
-	 */
-	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
-	put_device(gd->driverfs_dev);
-}
-
-#if 0
-void genhd_media_change_notify(struct gendisk *disk)
-{
-	get_device(disk->driverfs_dev);
-	schedule_work(&disk->async_notify);
-}
-EXPORT_SYMBOL_GPL(genhd_media_change_notify);
-#endif  /*  0  */
-
 dev_t blk_lookup_devt(const char *name, int partno)
 {
 	dev_t devt = MKDEV(0, 0);
@@ -1126,7 +1244,7 @@ EXPORT_SYMBOL(blk_lookup_devt);
 
 struct gendisk *alloc_disk(int minors)
 {
-	return alloc_disk_node(minors, -1);
+	return alloc_disk_node(minors, NUMA_NO_NODE);
 }
 EXPORT_SYMBOL(alloc_disk);
 
@@ -1134,8 +1252,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 {
 	struct gendisk *disk;
 
-	disk = kmalloc_node(sizeof(struct gendisk),
-				GFP_KERNEL | __GFP_ZERO, node_id);
+	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
 	if (disk) {
 		if (!init_part_stats(&disk->part0)) {
 			kfree(disk);
@@ -1149,13 +1266,23 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 		}
 		disk->part_tbl->part[0] = &disk->part0;
 
+		/*
+		 * set_capacity() and get_capacity() currently don't use
+		 * seqcounter to read/update the part0->nr_sects. Still init
+		 * the counter as we can read the sectors in IO submission
+		 * patch using seqence counters.
+		 *
+		 * TODO: Ideally set_capacity() and get_capacity() should be
+		 * converted to make use of bd_mutex and sequence counters.
+		 */
+		seqcount_init(&disk->part0.nr_sects_seq);
+		hd_ref_init(&disk->part0);
+
 		disk->minors = minors;
 		rand_initialize_disk(disk);
 		disk_to_dev(disk)->class = &block_class;
 		disk_to_dev(disk)->type = &disk_type;
 		device_initialize(disk_to_dev(disk));
-		INIT_WORK(&disk->async_notify,
-			media_change_notify_thread);
 	}
 	return disk;
 }
@@ -1190,6 +1317,16 @@ void put_disk(struct gendisk *disk)
 
 EXPORT_SYMBOL(put_disk);
 
+static void set_disk_ro_uevent(struct gendisk *gd, int ro)
+{
+	char event[] = "DISK_RO=1";
+	char *envp[] = { event, NULL };
+
+	if (!ro)
+		event[8] = '0';
+	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
+}
+
 void set_device_ro(struct block_device *bdev, int flag)
 {
 	bdev->bd_part->policy = flag;
@@ -1202,8 +1339,12 @@ void set_disk_ro(struct gendisk *disk, int flag)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
-	disk_part_iter_init(&piter, disk,
-			    DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0);
+	if (disk->part0.policy != flag) {
+		set_disk_ro_uevent(disk, flag);
+		disk->part0.policy = flag;
+	}
+
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
 		part->policy = flag;
 	disk_part_iter_exit(&piter);
@@ -1226,10 +1367,471 @@ int invalidate_partition(struct gendisk *disk, int partno)
 	struct block_device *bdev = bdget_disk(disk, partno);
 	if (bdev) {
 		fsync_bdev(bdev);
-		res = __invalidate_device(bdev);
+		res = __invalidate_device(bdev, true);
 		bdput(bdev);
 	}
 	return res;
 }
 
 EXPORT_SYMBOL(invalidate_partition);
+
+/*
+ * Disk events - monitor disk events like media change and eject request.
+ */
+struct disk_events {
+	struct list_head	node;		/* all disk_event's */
+	struct gendisk		*disk;		/* the associated disk */
+	spinlock_t		lock;
+
+	struct mutex		block_mutex;	/* protects blocking */
+	int			block;		/* event blocking depth */
+	unsigned int		pending;	/* events already sent out */
+	unsigned int		clearing;	/* events being cleared */
+
+	long			poll_msecs;	/* interval, -1 for default */
+	struct delayed_work	dwork;
+};
+
+static const char *disk_events_strs[] = {
+	[ilog2(DISK_EVENT_MEDIA_CHANGE)]	= "media_change",
+	[ilog2(DISK_EVENT_EJECT_REQUEST)]	= "eject_request",
+};
+
+static char *disk_uevents[] = {
+	[ilog2(DISK_EVENT_MEDIA_CHANGE)]	= "DISK_MEDIA_CHANGE=1",
+	[ilog2(DISK_EVENT_EJECT_REQUEST)]	= "DISK_EJECT_REQUEST=1",
+};
+
+/* list of all disk_events */
+static DEFINE_MUTEX(disk_events_mutex);
+static LIST_HEAD(disk_events);
+
+/* disable in-kernel polling by default */
+static unsigned long disk_events_dfl_poll_msecs	= 0;
+
+static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
+{
+	struct disk_events *ev = disk->ev;
+	long intv_msecs = 0;
+
+	/*
+	 * If device-specific poll interval is set, always use it.  If
+	 * the default is being used, poll iff there are events which
+	 * can't be monitored asynchronously.
+	 */
+	if (ev->poll_msecs >= 0)
+		intv_msecs = ev->poll_msecs;
+	else if (disk->events & ~disk->async_events)
+		intv_msecs = disk_events_dfl_poll_msecs;
+
+	return msecs_to_jiffies(intv_msecs);
+}
+
+/**
+ * disk_block_events - block and flush disk event checking
+ * @disk: disk to block events for
+ *
+ * On return from this function, it is guaranteed that event checking
+ * isn't in progress and won't happen until unblocked by
+ * disk_unblock_events().  Events blocking is counted and the actual
+ * unblocking happens after the matching number of unblocks are done.
+ *
+ * Note that this intentionally does not block event checking from
+ * disk_clear_events().
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void disk_block_events(struct gendisk *disk)
+{
+	struct disk_events *ev = disk->ev;
+	unsigned long flags;
+	bool cancel;
+
+	if (!ev)
+		return;
+
+	/*
+	 * Outer mutex ensures that the first blocker completes canceling
+	 * the event work before further blockers are allowed to finish.
+	 */
+	mutex_lock(&ev->block_mutex);
+
+	spin_lock_irqsave(&ev->lock, flags);
+	cancel = !ev->block++;
+	spin_unlock_irqrestore(&ev->lock, flags);
+
+	if (cancel)
+		cancel_delayed_work_sync(&disk->ev->dwork);
+
+	mutex_unlock(&ev->block_mutex);
+}
+
+static void __disk_unblock_events(struct gendisk *disk, bool check_now)
+{
+	struct disk_events *ev = disk->ev;
+	unsigned long intv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ev->lock, flags);
+
+	if (WARN_ON_ONCE(ev->block <= 0))
+		goto out_unlock;
+
+	if (--ev->block)
+		goto out_unlock;
+
+	/*
+	 * Not exactly a latency critical operation, set poll timer
+	 * slack to 25% and kick event check.
+	 */
+	intv = disk_events_poll_jiffies(disk);
+	set_timer_slack(&ev->dwork.timer, intv / 4);
+	if (check_now)
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, 0);
+	else if (intv)
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, intv);
+out_unlock:
+	spin_unlock_irqrestore(&ev->lock, flags);
+}
+
+/**
+ * disk_unblock_events - unblock disk event checking
+ * @disk: disk to unblock events for
+ *
+ * Undo disk_block_events().  When the block count reaches zero, it
+ * starts events polling if configured.
+ *
+ * CONTEXT:
+ * Don't care.  Safe to call from irq context.
+ */
+void disk_unblock_events(struct gendisk *disk)
+{
+	if (disk->ev)
+		__disk_unblock_events(disk, false);
+}
+
+/**
+ * disk_flush_events - schedule immediate event checking and flushing
+ * @disk: disk to check and flush events for
+ * @mask: events to flush
+ *
+ * Schedule immediate event checking on @disk if not blocked.  Events in
+ * @mask are scheduled to be cleared from the driver.  Note that this
+ * doesn't clear the events from @disk->ev.
+ *
+ * CONTEXT:
+ * If @mask is non-zero must be called with bdev->bd_mutex held.
+ */
+void disk_flush_events(struct gendisk *disk, unsigned int mask)
+{
+	struct disk_events *ev = disk->ev;
+
+	if (!ev)
+		return;
+
+	spin_lock_irq(&ev->lock);
+	ev->clearing |= mask;
+	if (!ev->block)
+		mod_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, 0);
+	spin_unlock_irq(&ev->lock);
+}
+
+/**
+ * disk_clear_events - synchronously check, clear and return pending events
+ * @disk: disk to fetch and clear events from
+ * @mask: mask of events to be fetched and clearted
+ *
+ * Disk events are synchronously checked and pending events in @mask
+ * are cleared and returned.  This ignores the block count.
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
+{
+	const struct block_device_operations *bdops = disk->fops;
+	struct disk_events *ev = disk->ev;
+	unsigned int pending;
+	unsigned int clearing = mask;
+
+	if (!ev) {
+		/* for drivers still using the old ->media_changed method */
+		if ((mask & DISK_EVENT_MEDIA_CHANGE) &&
+		    bdops->media_changed && bdops->media_changed(disk))
+			return DISK_EVENT_MEDIA_CHANGE;
+		return 0;
+	}
+
+	disk_block_events(disk);
+
+	/*
+	 * store the union of mask and ev->clearing on the stack so that the
+	 * race with disk_flush_events does not cause ambiguity (ev->clearing
+	 * can still be modified even if events are blocked).
+	 */
+	spin_lock_irq(&ev->lock);
+	clearing |= ev->clearing;
+	ev->clearing = 0;
+	spin_unlock_irq(&ev->lock);
+
+	disk_check_events(ev, &clearing);
+	/*
+	 * if ev->clearing is not 0, the disk_flush_events got called in the
+	 * middle of this function, so we want to run the workfn without delay.
+	 */
+	__disk_unblock_events(disk, ev->clearing ? true : false);
+
+	/* then, fetch and clear pending events */
+	spin_lock_irq(&ev->lock);
+	pending = ev->pending & mask;
+	ev->pending &= ~mask;
+	spin_unlock_irq(&ev->lock);
+	WARN_ON_ONCE(clearing & mask);
+
+	return pending;
+}
+
+/*
+ * Separate this part out so that a different pointer for clearing_ptr can be
+ * passed in for disk_clear_events.
+ */
+static void disk_events_workfn(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct disk_events *ev = container_of(dwork, struct disk_events, dwork);
+
+	disk_check_events(ev, &ev->clearing);
+}
+
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr)
+{
+	struct gendisk *disk = ev->disk;
+	char *envp[ARRAY_SIZE(disk_uevents) + 1] = { };
+	unsigned int clearing = *clearing_ptr;
+	unsigned int events;
+	unsigned long intv;
+	int nr_events = 0, i;
+
+	/* check events */
+	events = disk->fops->check_events(disk, clearing);
+
+	/* accumulate pending events and schedule next poll if necessary */
+	spin_lock_irq(&ev->lock);
+
+	events &= ~ev->pending;
+	ev->pending |= events;
+	*clearing_ptr &= ~clearing;
+
+	intv = disk_events_poll_jiffies(disk);
+	if (!ev->block && intv)
+		queue_delayed_work(system_freezable_power_efficient_wq,
+				&ev->dwork, intv);
+
+	spin_unlock_irq(&ev->lock);
+
+	/*
+	 * Tell userland about new events.  Only the events listed in
+	 * @disk->events are reported.  Unlisted events are processed the
+	 * same internally but never get reported to userland.
+	 */
+	for (i = 0; i < ARRAY_SIZE(disk_uevents); i++)
+		if (events & disk->events & (1 << i))
+			envp[nr_events++] = disk_uevents[i];
+
+	if (nr_events)
+		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+}
+
+/*
+ * A disk events enabled device has the following sysfs nodes under
+ * its /sys/block/X/ directory.
+ *
+ * events		: list of all supported events
+ * events_async		: list of events which can be detected w/o polling
+ * events_poll_msecs	: polling interval, 0: disable, -1: system default
+ */
+static ssize_t __disk_events_show(unsigned int events, char *buf)
+{
+	const char *delim = "";
+	ssize_t pos = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++)
+		if (events & (1 << i)) {
+			pos += sprintf(buf + pos, "%s%s",
+				       delim, disk_events_strs[i]);
+			delim = " ";
+		}
+	if (pos)
+		pos += sprintf(buf + pos, "\n");
+	return pos;
+}
+
+static ssize_t disk_events_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return __disk_events_show(disk->events, buf);
+}
+
+static ssize_t disk_events_async_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return __disk_events_show(disk->async_events, buf);
+}
+
+static ssize_t disk_events_poll_msecs_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%ld\n", disk->ev->poll_msecs);
+}
+
+static ssize_t disk_events_poll_msecs_store(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	long intv;
+
+	if (!count || !sscanf(buf, "%ld", &intv))
+		return -EINVAL;
+
+	if (intv < 0 && intv != -1)
+		return -EINVAL;
+
+	disk_block_events(disk);
+	disk->ev->poll_msecs = intv;
+	__disk_unblock_events(disk, true);
+
+	return count;
+}
+
+static const DEVICE_ATTR(events, S_IRUGO, disk_events_show, NULL);
+static const DEVICE_ATTR(events_async, S_IRUGO, disk_events_async_show, NULL);
+static const DEVICE_ATTR(events_poll_msecs, S_IRUGO|S_IWUSR,
+			 disk_events_poll_msecs_show,
+			 disk_events_poll_msecs_store);
+
+static const struct attribute *disk_events_attrs[] = {
+	&dev_attr_events.attr,
+	&dev_attr_events_async.attr,
+	&dev_attr_events_poll_msecs.attr,
+	NULL,
+};
+
+/*
+ * The default polling interval can be specified by the kernel
+ * parameter block.events_dfl_poll_msecs which defaults to 0
+ * (disable).  This can also be modified runtime by writing to
+ * /sys/module/block/events_dfl_poll_msecs.
+ */
+static int disk_events_set_dfl_poll_msecs(const char *val,
+					  const struct kernel_param *kp)
+{
+	struct disk_events *ev;
+	int ret;
+
+	ret = param_set_ulong(val, kp);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&disk_events_mutex);
+
+	list_for_each_entry(ev, &disk_events, node)
+		disk_flush_events(ev->disk, 0);
+
+	mutex_unlock(&disk_events_mutex);
+
+	return 0;
+}
+
+static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = {
+	.set	= disk_events_set_dfl_poll_msecs,
+	.get	= param_get_ulong,
+};
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX	"block."
+
+module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops,
+		&disk_events_dfl_poll_msecs, 0644);
+
+/*
+ * disk_{alloc|add|del|release}_events - initialize and destroy disk_events.
+ */
+static void disk_alloc_events(struct gendisk *disk)
+{
+	struct disk_events *ev;
+
+	if (!disk->fops->check_events)
+		return;
+
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev) {
+		pr_warn("%s: failed to initialize events\n", disk->disk_name);
+		return;
+	}
+
+	INIT_LIST_HEAD(&ev->node);
+	ev->disk = disk;
+	spin_lock_init(&ev->lock);
+	mutex_init(&ev->block_mutex);
+	ev->block = 1;
+	ev->poll_msecs = -1;
+	INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn);
+
+	disk->ev = ev;
+}
+
+static void disk_add_events(struct gendisk *disk)
+{
+	if (!disk->ev)
+		return;
+
+	/* FIXME: error handling */
+	if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0)
+		pr_warn("%s: failed to create sysfs files for events\n",
+			disk->disk_name);
+
+	mutex_lock(&disk_events_mutex);
+	list_add_tail(&disk->ev->node, &disk_events);
+	mutex_unlock(&disk_events_mutex);
+
+	/*
+	 * Block count is initialized to 1 and the following initial
+	 * unblock kicks it into action.
+	 */
+	__disk_unblock_events(disk, true);
+}
+
+static void disk_del_events(struct gendisk *disk)
+{
+	if (!disk->ev)
+		return;
+
+	disk_block_events(disk);
+
+	mutex_lock(&disk_events_mutex);
+	list_del_init(&disk->ev->node);
+	mutex_unlock(&disk_events_mutex);
+
+	sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs);
+}
+
+static void disk_release_events(struct gendisk *disk)
+{
+	/* the block count should be 1 from disk_del_events() */
+	WARN_ON_ONCE(disk->ev && disk->ev->block != 1);
+	kfree(disk->ev);
+}