| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1061031060051.5046@suse.de>
Date: Tue, 31 Oct 2006 17:00:51 +1100
From: NeilBrown <neilb@...e.de>
To: Andrew Morton <akpm@...l.org>
Cc: gregkh@...e.de
Subject: [PATCH 002 of 6] md: Change lifetime rules for 'md' devices.
Currently md devices are created when first opened and remain in existence
until the module is unloaded.
This isn't a major problem, but it somewhat ugly.
This patch changes the lifetime rules so that an md device will
disappear on the last close if it has no state.
Locking rules depend on bd_mutex being held in do_open and
__blkdev_put, and on setting bd_disk->private_data to 'mddev'.
There is room for a race because md_probe is called early in do_open
(get_gendisk) to create the mddev. As this isn't protected by
bd_mutex, a concurrent call to md_close can destroy that mddev before
do_open calls md_open to get a reference on it.
md_open and md_close are serialised by md_mutex so the worst that
can happen is that md_open finds that the mddev structure doesn't
exist after all. In this case bd_disk->private_data will be NULL,
and md_open chooses to exit with -EBUSY in this case, which is
arguable and appropriate result.
The new 'dead' field in mddev is used to track whether it is time
to destroy the mddev (if a last-close happens). It is cleared when
any state is create (set_array_info) and set when the array is stopped
(do_md_stop).
mddev_put becomes simpler. It just destroys the mddev when the
refcount hits zero. This will normally be the reference held in
bd_disk->private_data.
cc: gregkh@...e.de
Signed-off-by: Neil Brown <neilb@...e.de>
### Diffstat output
./drivers/md/md.c | 35 +++++++++++++++++++++++++----------
./include/linux/raid/md_k.h | 3 +++
2 files changed, 28 insertions(+), 10 deletions(-)
diff .prev/drivers/md/md.c ./drivers/md/md.c
--- .prev/drivers/md/md.c 2006-10-31 16:41:02.000000000 +1100
+++ ./drivers/md/md.c 2006-10-31 16:41:14.000000000 +1100
@@ -226,13 +226,14 @@ static void mddev_put(mddev_t *mddev)
{
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
- if (!mddev->raid_disks && list_empty(&mddev->disks)) {
- list_del(&mddev->all_mddevs);
- spin_unlock(&all_mddevs_lock);
- blk_cleanup_queue(mddev->queue);
- kobject_unregister(&mddev->kobj);
- } else
- spin_unlock(&all_mddevs_lock);
+ list_del(&mddev->all_mddevs);
+ spin_unlock(&all_mddevs_lock);
+
+ blk_cleanup_queue(mddev->queue);
+ mddev->queue = NULL;
+ del_gendisk(mddev->gendisk);
+ mddev->gendisk = NULL;
+ kobject_unregister(&mddev->kobj);
}
static mddev_t * mddev_find(dev_t unit)
@@ -273,6 +274,7 @@ static mddev_t * mddev_find(dev_t unit)
atomic_set(&new->active, 1);
spin_lock_init(&new->write_lock);
init_waitqueue_head(&new->sb_wait);
+ new->dead = 1;
new->queue = blk_alloc_queue(GFP_KERNEL);
if (!new->queue) {
@@ -3362,6 +3364,8 @@ static int do_md_stop(mddev_t * mddev, i
disk = mddev->gendisk;
if (disk)
set_capacity(disk, 0);
+ mddev->dead = 1;
+
mddev->changed = 1;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
@@ -4293,7 +4297,8 @@ static int md_ioctl(struct inode *inode,
printk(KERN_WARNING "md: couldn't set"
" array info. %d\n", err);
goto abort_unlock;
- }
+ } else
+ mddev->dead = 0;
}
goto done_unlock;
@@ -4377,6 +4382,8 @@ static int md_ioctl(struct inode *inode,
err = -EFAULT;
else
err = add_new_disk(mddev, &info);
+ if (!err)
+ mddev->dead = 0;
goto done_unlock;
}
@@ -4423,8 +4430,12 @@ static int md_open(struct inode *inode,
* Succeed if we can lock the mddev, which confirms that
* it isn't being stopped right now.
*/
- mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
- int err;
+ mddev_t *mddev;
+ int err = -EBUSY;
+
+ mddev = inode->i_bdev->bd_disk->private_data;
+ if (!mddev)
+ goto out;
if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
goto out;
@@ -4443,6 +4454,10 @@ static int md_release(struct inode *inod
mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
BUG_ON(!mddev);
+ if (inode->i_bdev->bd_openers == 0 && mddev->dead) {
+ inode->i_bdev->bd_disk->private_data = NULL;
+ mddev_put(mddev);
+ }
mddev_put(mddev);
return 0;
diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
--- .prev/include/linux/raid/md_k.h 2006-10-31 16:40:51.000000000 +1100
+++ ./include/linux/raid/md_k.h 2006-10-31 16:41:14.000000000 +1100
@@ -119,6 +119,9 @@ struct mddev_s
#define MD_CHANGE_PENDING 2 /* superblock update in progress */
int ro;
+ int dead; /* array should be discarded on
+ * last close
+ */
struct gendisk *gendisk;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists