Commit fa70d2e2 authored by Mike Snitzer's avatar Mike Snitzer Committed by Jens Axboe

block: allow gendisk's request_queue registration to be deferred

Since I can remember DM has forced the block layer to allow the
allocation and initialization of the request_queue to be distinct
operations.  Reason for this is block/genhd.c:add_disk() has requires
that the request_queue (and associated bdi) be tied to the gendisk
before add_disk() is called -- because add_disk() also deals with
exposing the request_queue via blk_register_queue().

DM's dynamic creation of arbitrary device types (and associated
request_queue types) requires the DM device's gendisk be available so
that DM table loads can establish a master/slave relationship with
subordinate devices that are referenced by loaded DM tables -- using
bd_link_disk_holder().  But until these DM tables, and their associated
subordinate devices, are known DM cannot know what type of request_queue
it needs -- nor what its queue_limits should be.

This chicken and egg scenario has created all manner of problems for DM
and, at times, the block layer.

Summary of changes:

- Add device_add_disk_no_queue_reg() and add_disk_no_queue_reg() variant
  that drivers may use to add a disk without also calling
  blk_register_queue().  Driver must call blk_register_queue() once its
  request_queue is fully initialized.

- Return early from blk_unregister_queue() if QUEUE_FLAG_REGISTERED
  is not set.  It won't be set if driver used add_disk_no_queue_reg()
  but driver encounters an error and must del_gendisk() before calling
  blk_register_queue().

- Export blk_register_queue().

These changes allow DM to use add_disk_no_queue_reg() to anchor its
gendisk as the "master" for master/slave relationships DM must establish
with subordinate devices referenced in DM tables that get loaded.  Once
all "slave" devices for a DM device are known its request_queue can be
properly initialized and then advertised via sysfs -- important
improvement being that no request_queue resource initialization
performed by blk_register_queue() is missed for DM devices anymore.
Signed-off-by: default avatarMike Snitzer <snitzer@redhat.com>
Reviewed-by: default avatarMing Lei <ming.lei@redhat.com>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 667257e8
...@@ -921,6 +921,7 @@ int blk_register_queue(struct gendisk *disk) ...@@ -921,6 +921,7 @@ int blk_register_queue(struct gendisk *disk)
mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_lock);
return ret; return ret;
} }
EXPORT_SYMBOL_GPL(blk_register_queue);
void blk_unregister_queue(struct gendisk *disk) void blk_unregister_queue(struct gendisk *disk)
{ {
...@@ -929,6 +930,10 @@ void blk_unregister_queue(struct gendisk *disk) ...@@ -929,6 +930,10 @@ void blk_unregister_queue(struct gendisk *disk)
if (WARN_ON(!q)) if (WARN_ON(!q))
return; return;
/* Return early if disk->queue was never registered. */
if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
return;
/* /*
* Protect against the 'queue' kobj being accessed * Protect against the 'queue' kobj being accessed
* while/after it is removed. * while/after it is removed.
......
...@@ -629,16 +629,18 @@ static void register_disk(struct device *parent, struct gendisk *disk) ...@@ -629,16 +629,18 @@ static void register_disk(struct device *parent, struct gendisk *disk)
} }
/** /**
* device_add_disk - add partitioning information to kernel list * __device_add_disk - add disk information to kernel list
* @parent: parent device for the disk * @parent: parent device for the disk
* @disk: per-device partitioning information * @disk: per-device partitioning information
* @register_queue: register the queue if set to true
* *
* This function registers the partitioning information in @disk * This function registers the partitioning information in @disk
* with the kernel. * with the kernel.
* *
* FIXME: error handling * FIXME: error handling
*/ */
void device_add_disk(struct device *parent, struct gendisk *disk) static void __device_add_disk(struct device *parent, struct gendisk *disk,
bool register_queue)
{ {
dev_t devt; dev_t devt;
int retval; int retval;
...@@ -682,7 +684,8 @@ void device_add_disk(struct device *parent, struct gendisk *disk) ...@@ -682,7 +684,8 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
exact_match, exact_lock, disk); exact_match, exact_lock, disk);
} }
register_disk(parent, disk); register_disk(parent, disk);
blk_register_queue(disk); if (register_queue)
blk_register_queue(disk);
/* /*
* Take an extra ref on queue which will be put on disk_release() * Take an extra ref on queue which will be put on disk_release()
...@@ -693,8 +696,19 @@ void device_add_disk(struct device *parent, struct gendisk *disk) ...@@ -693,8 +696,19 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
disk_add_events(disk); disk_add_events(disk);
blk_integrity_add(disk); blk_integrity_add(disk);
} }
void device_add_disk(struct device *parent, struct gendisk *disk)
{
__device_add_disk(parent, disk, true);
}
EXPORT_SYMBOL(device_add_disk); EXPORT_SYMBOL(device_add_disk);
void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
{
__device_add_disk(parent, disk, false);
}
EXPORT_SYMBOL(device_add_disk_no_queue_reg);
void del_gendisk(struct gendisk *disk) void del_gendisk(struct gendisk *disk)
{ {
struct disk_part_iter piter; struct disk_part_iter piter;
......
...@@ -395,6 +395,11 @@ static inline void add_disk(struct gendisk *disk) ...@@ -395,6 +395,11 @@ static inline void add_disk(struct gendisk *disk)
{ {
device_add_disk(NULL, disk); device_add_disk(NULL, disk);
} }
extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk);
static inline void add_disk_no_queue_reg(struct gendisk *disk)
{
device_add_disk_no_queue_reg(NULL, disk);
}
extern void del_gendisk(struct gendisk *gp); extern void del_gendisk(struct gendisk *gp);
extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct gendisk *get_gendisk(dev_t dev, int *partno);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment