aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2010-02-09 16:34:14 +1100
committerNeilBrown <neilb@suse.de>2010-02-10 11:26:09 +1100
commitef286f6fa673cd7fb367e1b145069d8dbfcc6081 (patch)
tree957760503c1b1a417850db3204d6c010d1ce1a67
parent9eb07c259207d048e3ee8be2a77b2a4680b1edd4 (diff)
md: fix some lockdep issues between md and sysfs.
====== This fix is related to http://bugzilla.kernel.org/show_bug.cgi?id=15142 but does not address that exact issue. ====== sysfs does like attributes being removed while they are being accessed (i.e. read or written) and waits for the access to complete. As accessing some md attributes takes the same lock that is held while removing those attributes a deadlock can occur. This patch addresses 3 issues in md that could lead to this deadlock. Two relate to calling flush_scheduled_work while the lock is held. This is probably a bad idea in general and as we use schedule_work to delete various sysfs objects it is particularly bad. In one case flush_scheduled_work is called from md_alloc (called by md_probe) called from do_md_run which holds the lock. This call is only present to ensure that ->gendisk is set. However we can be sure that gendisk is always set (though possibly we couldn't when that code was originally written. This is because do_md_run is called in three different contexts: 1/ from md_ioctl. This requires that md_open has succeeded, and it fails if ->gendisk is not set. 2/ from writing a sysfs attribute. This can only happen if the mddev has been registered in sysfs which happens in md_alloc after ->gendisk has been set. 3/ from autorun_array which is only called by autorun_devices, which checks for ->gendisk to be set before calling autorun_array. So the call to md_probe in do_md_run can be removed, and the check on ->gendisk can also go. In the other case flush_scheduled_work is being called in do_md_stop, purportedly to wait for all md_delayed_delete calls (which delete the component rdevs) to complete. However there really isn't any need to wait for them - they have already been disconnected in all important ways. The third issue is that raid5->stop() removes some attribute names while the lock is held. There is already some infrastructure in place to delay attribute removal until after the lock is released (using schedule_work). So extend that infrastructure to remove the raid5_attrs_group. This does not address all lockdep issues related to the sysfs "s_active" lock. The rest can be address by splitting that lockdep context between symlinks and non-symlinks which hopefully will happen. Signed-off-by: NeilBrown <neilb@suse.de>
-rw-r--r--drivers/md/md.c14
-rw-r--r--drivers/md/raid5.c3
2 files changed, 6 insertions, 11 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index dd3dfe42d5a..a20a71e5efd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4075,8 +4075,10 @@ static void mddev_delayed_delete(struct work_struct *ws)
{
mddev_t *mddev = container_of(ws, mddev_t, del_work);
- if (mddev->private == &md_redundancy_group) {
+ if (mddev->private) {
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+ if (mddev->private != (void*)1)
+ sysfs_remove_group(&mddev->kobj, mddev->private);
if (mddev->sysfs_action)
sysfs_put(mddev->sysfs_action);
mddev->sysfs_action = NULL;
@@ -4287,10 +4289,7 @@ static int do_md_run(mddev_t * mddev)
sysfs_notify_dirent(rdev->sysfs_state);
}
- md_probe(mddev->unit, NULL, NULL);
disk = mddev->gendisk;
- if (!disk)
- return -ENOMEM;
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
@@ -4530,8 +4529,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
module_put(mddev->pers->owner);
- if (mddev->pers->sync_request)
- mddev->private = &md_redundancy_group;
+ if (mddev->pers->sync_request && mddev->private == NULL)
+ mddev->private = (void*)1;
mddev->pers = NULL;
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent(mddev->sysfs_state);
@@ -4578,9 +4577,6 @@ out:
}
mddev->bitmap_info.offset = 0;
- /* make sure all md_delayed_delete calls have finished */
- flush_scheduled_work();
-
export_array(mddev);
mddev->array_sectors = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b5629c3e14f..ceb24afdc14 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5136,9 +5136,8 @@ static int stop(mddev_t *mddev)
mddev->thread = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
- sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
free_conf(conf);
- mddev->private = NULL;
+ mddev->private = &raid5_attrs_group;
return 0;
}