Re: kobject: provide kobject_put_wait to fix module unload race

[Linus Torvalds]

This looks completely broken to me. You do a "kobject_put()" and then
after you've dropped that last use, you wait for the completion of
something that may already have been free'd.

Wtf? Am I missing something?

               Linus

On Tue, Jan 7, 2014 at 12:01 PM, Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote:
>
>
> On Mon, 6 Jan 2014, Mike Snitzer wrote:
>
>> On Mon, Jan 06 2014 at  1:55pm -0500,
>> Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote:
>>
>> >
>> >
>> > On Sun, 5 Jan 2014, Greg Kroah-Hartman wrote:
>> >
>> > > On Sun, Jan 05, 2014 at 05:43:56PM +0100, Bart Van Assche wrote:
>> > > > On 01/04/14 19:06, Mikulas Patocka wrote:
>> > > > > -     if (t && !t->release)
>> > > > > -             pr_debug("kobject: '%s' (%p): does not have a release() "
>> > > > > -                      "function, it is broken and must be fixed.\n",
>> > > > > -                      kobject_name(kobj), kobj);
>> > > > > -
>> > > >
>> > > > Has it been considered to issue a warning if no release function has
>> > > > been defined and free_completion == NULL instead of removing the above
>> > > > debug message entirely ? I think even with this patch applied it is
>> > > > still wrong to invoke kobject_put() on an object without defining a
>> > > > release function.
>> > >
>> > > This patch isn't going to be applied, and I've reverted the original
>> > > commit, so there shouldn't be any issues anymore with this code.
>> >
>> > Why? This patch does the same thing as
>> > eee031649707db3c9920d9498f8d03819b74fc23, but it's smaller. So why did you
>> > accept eee031649707db3c9920d9498f8d03819b74fc23 and not this?
>> >
>> > The code to wait for kobject destruction using completion already exists
>> > in cpufreq_sysfs_release, cpuidle_sysfs_release,
>> > cpuidle_state_sysfs_release, cpuidle_driver_sysfs_release,
>> > ext4_sb_release, ext4_feat_release, f2fs_sb_release (these are the only
>> > kobject users that are correct w.r.t. module unloading), so if you accept
>> > this patch, you can simplify them to use kobject_put_wait.
>>
>> Hi Mikulas,
>>
>> Please just submit a DM-only patch that follows the same racey pattern
>> of firing a completion from the kobj_type .release method in dm_mod.
>> I'll get it queued up for 3.14.
>>
>> If/when we gets reports of a crash due to dm_mod unload racing with
>> kobject_put we can revisit this.
>>
>> Thanks,
>> Mike
>
> Here I'm sending dm-only patch.
>
>
>
> dm: wait until kobject is destroyed
>
> There may be other parts of the kernel taking reference to the dm kobject.
> We must wait until they drop the references before deallocating the md
> structure.
>
> Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
>
> ---
>  drivers/md/dm-sysfs.c |   10 +++++++++-
>  drivers/md/dm.c       |   11 +++++++++++
>  drivers/md/dm.h       |    2 ++
>  3 files changed, 22 insertions(+), 1 deletion(-)
>
> Index: linux-3.13-rc7/drivers/md/dm-sysfs.c
> ===================================================================
> --- linux-3.13-rc7.orig/drivers/md/dm-sysfs.c   2014-01-07 02:06:08.000000000 +0100
> +++ linux-3.13-rc7/drivers/md/dm-sysfs.c        2014-01-07 02:07:09.000000000 +0100
> @@ -79,6 +79,11 @@ static const struct sysfs_ops dm_sysfs_o
>         .show   = dm_attr_show,
>  };
>
> +static void dm_kobject_release(struct kobject *kobj)
> +{
> +       complete(dm_get_completion_from_kobject(kobj));
> +}
> +
>  /*
>   * dm kobject is embedded in mapped_device structure
>   * no need to define release function here
> @@ -86,6 +91,7 @@ static const struct sysfs_ops dm_sysfs_o
>  static struct kobj_type dm_ktype = {
>         .sysfs_ops      = &dm_sysfs_ops,
>         .default_attrs  = dm_attrs,
> +       .release        = dm_kobject_release,
>  };
>
>  /*
> @@ -104,5 +110,7 @@ int dm_sysfs_init(struct mapped_device *
>   */
>  void dm_sysfs_exit(struct mapped_device *md)
>  {
> -       kobject_put(dm_kobject(md));
> +       struct kobject *kobj = dm_kobject(md);
> +       kobject_put(kobj);
> +       wait_for_completion(dm_get_completion_from_kobject(kobj));
>  }
> Index: linux-3.13-rc7/drivers/md/dm.c
> ===================================================================
> --- linux-3.13-rc7.orig/drivers/md/dm.c 2014-01-07 02:07:09.000000000 +0100
> +++ linux-3.13-rc7/drivers/md/dm.c      2014-01-07 04:58:37.000000000 +0100
> @@ -203,6 +203,9 @@ struct mapped_device {
>         /* sysfs handle */
>         struct kobject kobj;
>
> +       /* wait until the kobject is released */
> +       struct completion kobj_completion;
> +
>         /* zero-length flush that will be cloned and submitted to targets */
>         struct bio flush_bio;
>
> @@ -2049,6 +2052,7 @@ static struct mapped_device *alloc_dev(i
>         init_waitqueue_head(&md->wait);
>         INIT_WORK(&md->work, dm_wq_work);
>         init_waitqueue_head(&md->eventq);
> +       init_completion(&md->kobj_completion);
>
>         md->disk->major = _major;
>         md->disk->first_minor = minor;
> @@ -2931,6 +2935,13 @@ struct mapped_device *dm_get_from_kobjec
>         return md;
>  }
>
> +struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
> +{
> +       struct mapped_device *md = container_of(kobj, struct mapped_device, kobj);
> +
> +       return &md->kobj_completion;
> +}
> +
>  int dm_suspended_md(struct mapped_device *md)
>  {
>         return test_bit(DMF_SUSPENDED, &md->flags);
> Index: linux-3.13-rc7/drivers/md/dm.h
> ===================================================================
> --- linux-3.13-rc7.orig/drivers/md/dm.h 2014-01-07 02:06:08.000000000 +0100
> +++ linux-3.13-rc7/drivers/md/dm.h      2014-01-07 02:07:09.000000000 +0100
> @@ -15,6 +15,7 @@
>  #include <linux/list.h>
>  #include <linux/blkdev.h>
>  #include <linux/hdreg.h>
> +#include <linux/completion.h>
>
>  #include "dm-stats.h"
>
> @@ -152,6 +153,7 @@ int dm_sysfs_init(struct mapped_device *
>  void dm_sysfs_exit(struct mapped_device *md);
>  struct kobject *dm_kobject(struct mapped_device *md);
>  struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
> +struct completion *dm_get_completion_from_kobject(struct kobject *kobj);
>
>  /*
>   * Targets for linear and striped mappings
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/