implement in-kernel gendisk events handling

Currently, media presence polling for removeable block devices is done
from userland.  There are several issues with this.

* Polling is done by periodically opening the device.  For SCSI
  devices, the command sequence generated by such action involves a
  few different commands including TEST_UNIT_READY.  This behavior,
  while perfectly legal, is different from Windows which only issues
  single command, GET_EVENT_STATUS_NOTIFICATION.  Unfortunately, some
  ATAPI devices lock up after being periodically queried such command
  sequences.

* There is no reliable and unintrusive way for a userland program to
  tell whether the target device is safe for media presence polling.
  For example, polling for media presence during an on-going burning
  session can make it fail.  The polling program can avoid this by
  opening the device with O_EXCL but then it risks making a valid
  exclusive user of the device fail w/ -EBUSY.

* Userland polling is unnecessarily heavy and in-kernel implementation
  is lighter and better coordinated (workqueue, timer slack).

This patch implements framework for in-kernel disk event handling,
which includes media presence polling.

* bdops->check_events() is added, which supercedes ->media_changed().
  It should check whether there's any pending event and return if so.
  Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and
  DISK_EVENT_EJECT_REQUEST.  ->check_events() is guaranteed not to be
  called parallelly.

* gendisk->events and ->async_events are added.  These should be
  initialized by block driver before passing the device to add_disk().
  The former contains the mask of all supported events and the latter
  the mask of all events which the device can report without polling.
  /sys/block/*/events[_async] export these to userland.

* Kernel parameter block.events_dfl_poll_msecs controls the system
  polling interval (default is 0 which means disable) and
  /sys/block/*/events_poll_msecs control polling intervals for
  individual devices (default is -1 meaning use system setting).  Note
  that if a device can report all supported events asynchronously and
  its polling interval isn't explicitly set, the device won't be
  polled regardless of the system polling interval.

* If a device is opened exclusively with write access, event checking
  is automatically disabled until all write exclusive accesses are
  released.

* There are event 'clearing' events.  For example, both of currently
  defined events are cleared after the device has been successfully
  opened.  This information is passed to ->check_events() callback
  using @clearing argument as a hint.

* Event checking is always performed from system_nrt_wq and timer
  slack is set to 25% for polling.

* Nothing changes for drivers which implement ->media_changed() but
  not ->check_events().  Going forward, all drivers will be converted
  to ->check_events() and ->media_change() will be dropped.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

fs/block_dev.c

@@ -948,10 +948,11 @@ int check_disk_change(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	const struct block_device_operations *bdops = disk->fops;
+	unsigned int events;
 
-	if (!bdops->media_changed)
-		return 0;
-	if (!bdops->media_changed(bdev->bd_disk))
+	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
+				   DISK_EVENT_EJECT_REQUEST);
+	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return 0;
 
 	flush_disk(bdev);
@@ -1158,9 +1159,10 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 
 	if (whole) {
 		/* finish claiming */
+		mutex_lock(&bdev->bd_mutex);
 		spin_lock(&bdev_lock);
 
-		if (res == 0) {
+		if (!res) {
 			BUG_ON(!bd_may_claim(bdev, whole, holder));
 			/*
 			 * Note that for a whole device bd_holders
@@ -1180,6 +1182,20 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		wake_up_bit(&whole->bd_claiming, 0);
 
 		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().
+		 */
+		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+			bdev->bd_write_holder = true;
+			disk_block_events(bdev->bd_disk);
+		}
+
+		mutex_unlock(&bdev->bd_mutex);
 		bdput(whole);
 	}
 
@@ -1353,12 +1369,23 @@ int blkdev_put(struct block_device *bdev, fmode_t mode)
 
 		spin_unlock(&bdev_lock);
 
-		/* if this was the last claim, holder link should go too */
-		if (bdev_free)
+		/*
+		 * If this was the last claim, remove holder link and
+		 * unblock evpoll if it was a write holder.
+		 */
+		if (bdev_free) {
 			bd_unlink_disk_holder(bdev);
+			if (bdev->bd_write_holder) {
+				disk_unblock_events(bdev->bd_disk);
+				bdev->bd_write_holder = false;
+			} else
+				disk_check_events(bdev->bd_disk);
+		}
 
 		mutex_unlock(&bdev->bd_mutex);
-	}
+	} else
+		disk_check_events(bdev->bd_disk);
+
 	return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);

include/linux/blkdev.h

@@ -1251,6 +1251,9 @@ struct block_device_operations {
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t,
 						void **, unsigned long *);
+	unsigned int (*check_events) (struct gendisk *disk,
+				      unsigned int clearing);
+	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
 	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);

include/linux/fs.h

@@ -662,6 +662,7 @@ struct block_device {
 	void *			bd_claiming;
 	void *			bd_holder;
 	int			bd_holders;
+	bool			bd_write_holder;
 #ifdef CONFIG_SYSFS
 	struct gendisk *	bd_holder_disk;	/* for sysfs slave linkng */
 #endif

include/linux/genhd.h

@@ -127,6 +127,11 @@ struct hd_struct {
 #define GENHD_FL_EXT_DEVT			64 /* allow extended devt */
 #define GENHD_FL_NATIVE_CAPACITY		128
 
+enum {
+	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
+	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
+};
+
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
@@ -143,6 +148,8 @@ struct disk_part_tbl {
 	struct hd_struct __rcu *part[];
 };
 
+struct disk_events;
+
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
 	 * don't use directly.  Use disk_devt() and disk_max_parts().
@@ -154,6 +161,10 @@ struct gendisk {
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, mode_t *mode);
+
+	unsigned int events;		/* supported events */
+	unsigned int async_events;	/* async events, subset of all */
+
 	/* Array of pointers to partitions indexed by partno.
 	 * Protected with matching bdev lock but stat and other
 	 * non-critical accesses use RCU.  Always access through
@@ -171,8 +182,8 @@ struct gendisk {
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
-
 	atomic_t sync_io;		/* RAID */
+	struct disk_events *ev;
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity *integrity;
 #endif
@@ -405,6 +416,11 @@ static inline int get_disk_ro(struct gendisk *disk)
 	return disk->part0.policy;
 }
 
+extern void disk_block_events(struct gendisk *disk);
+extern void disk_unblock_events(struct gendisk *disk);
+extern void disk_check_events(struct gendisk *disk);
+extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
+
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk);
 extern void rand_initialize_disk(struct gendisk *disk);