summaryrefslogtreecommitdiff
path: root/fs/block_dev.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2010-12-08 20:57:37 +0100
committerJens Axboe <jaxboe@fusionio.com>2010-12-16 17:53:38 +0100
commit77ea887e433ad8389d416826936c110fa7910f80 (patch)
treeac9d32aabcebf5a465acae2066b12c9335b5ca6f /fs/block_dev.c
parentd2bf1b6723ed0eab378363649d15b7893bf14e91 (diff)
downloadlwn-77ea887e433ad8389d416826936c110fa7910f80.tar.gz
lwn-77ea887e433ad8389d416826936c110fa7910f80.zip
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>
Diffstat (limited to 'fs/block_dev.c')
-rw-r--r--fs/block_dev.c41
1 files changed, 34 insertions, 7 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c1c1b8c3fb99..6017389711ee 100644
--- a/fs/block_dev.c
+++ b/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);