diff mbox series

[v4,2/2] ceph: add ceph specific member support for file_lock

Message ID 20221213121103.213631-3-xiubli@redhat.com
State Superseded
Headers show
Series ceph: fix the use-after-free bug for file_lock | expand

Commit Message

Xiubo Li Dec. 13, 2022, 12:11 p.m. UTC
From: Xiubo Li <xiubli@redhat.com>

When ceph releasing the file_lock it will try to get the inode pointer
from the fl->fl_file, which the memory could already be released by
another thread in filp_close(). Because in VFS layer the fl->fl_file
doesn't increase the file's reference counter.

Will switch to use ceph dedicate lock info to track the inode.

And in ceph_fl_release_lock() we should skip all the operations if
the fl->fl_u.ceph_fl.fl_inode is not set, which should come from
the request file_lock. And we will set fl->fl_u.ceph_fl.fl_inode when
inserting it to the inode lock list, which is when copying the lock.

Cc: stable@vger.kernel.org
Cc: Jeff Layton <jlayton@kernel.org>
URL: https://tracker.ceph.com/issues/57986
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/locks.c    | 20 ++++++++++++++++++--
 include/linux/fs.h |  3 +++
 2 files changed, 21 insertions(+), 2 deletions(-)

Comments

Ilya Dryomov Dec. 13, 2022, 6:05 p.m. UTC | #1
On Tue, Dec 13, 2022 at 1:11 PM <xiubli@redhat.com> wrote:
>
> From: Xiubo Li <xiubli@redhat.com>
>
> When ceph releasing the file_lock it will try to get the inode pointer
> from the fl->fl_file, which the memory could already be released by
> another thread in filp_close(). Because in VFS layer the fl->fl_file
> doesn't increase the file's reference counter.
>
> Will switch to use ceph dedicate lock info to track the inode.
>
> And in ceph_fl_release_lock() we should skip all the operations if
> the fl->fl_u.ceph_fl.fl_inode is not set, which should come from
> the request file_lock. And we will set fl->fl_u.ceph_fl.fl_inode when
> inserting it to the inode lock list, which is when copying the lock.
>
> Cc: stable@vger.kernel.org
> Cc: Jeff Layton <jlayton@kernel.org>
> URL: https://tracker.ceph.com/issues/57986
> Signed-off-by: Xiubo Li <xiubli@redhat.com>
> ---
>  fs/ceph/locks.c    | 20 ++++++++++++++++++--
>  include/linux/fs.h |  3 +++
>  2 files changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
> index b191426bf880..cf78608a3f9a 100644
> --- a/fs/ceph/locks.c
> +++ b/fs/ceph/locks.c
> @@ -34,18 +34,34 @@ static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
>  {
>         struct inode *inode = file_inode(dst->fl_file);
>         atomic_inc(&ceph_inode(inode)->i_filelock_ref);
> +       dst->fl_u.ceph.fl_inode = igrab(inode);
>  }
>
> +/*
> + * Do not use the 'fl->fl_file' in release function, which
> + * is possibly already released by another thread.
> + */
>  static void ceph_fl_release_lock(struct file_lock *fl)
>  {
> -       struct inode *inode = file_inode(fl->fl_file);
> -       struct ceph_inode_info *ci = ceph_inode(inode);
> +       struct inode *inode = fl->fl_u.ceph.fl_inode;
> +       struct ceph_inode_info *ci;
> +
> +       /*
> +        * If inode is NULL it should be a request file_lock,
> +        * nothing we can do.
> +        */
> +       if (!inode)
> +               return;
> +
> +       ci = ceph_inode(inode);
>         if (atomic_dec_and_test(&ci->i_filelock_ref)) {
>                 /* clear error when all locks are released */
>                 spin_lock(&ci->i_ceph_lock);
>                 ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
>                 spin_unlock(&ci->i_ceph_lock);
>         }
> +       fl->fl_u.ceph.fl_inode = NULL;
> +       iput(inode);
>  }
>
>  static const struct file_lock_operations ceph_fl_lock_ops = {
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 7b52fdfb6da0..6106374f5257 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1119,6 +1119,9 @@ struct file_lock {
>                         int state;              /* state of grant or error if -ve */
>                         unsigned int    debug_id;
>                 } afs;
> +               struct {
> +                       struct inode *fl_inode;

Hi Xiubo,

Nit: I think it could be just "inode", without the prefix which is
already present in the union field name.

Thanks,

                Ilya
Xiubo Li Dec. 14, 2022, 2:03 a.m. UTC | #2
On 14/12/2022 02:05, Ilya Dryomov wrote:
> On Tue, Dec 13, 2022 at 1:11 PM <xiubli@redhat.com> wrote:
>> From: Xiubo Li <xiubli@redhat.com>
>>
>> When ceph releasing the file_lock it will try to get the inode pointer
>> from the fl->fl_file, which the memory could already be released by
>> another thread in filp_close(). Because in VFS layer the fl->fl_file
>> doesn't increase the file's reference counter.
>>
>> Will switch to use ceph dedicate lock info to track the inode.
>>
>> And in ceph_fl_release_lock() we should skip all the operations if
>> the fl->fl_u.ceph_fl.fl_inode is not set, which should come from
>> the request file_lock. And we will set fl->fl_u.ceph_fl.fl_inode when
>> inserting it to the inode lock list, which is when copying the lock.
>>
>> Cc: stable@vger.kernel.org
>> Cc: Jeff Layton <jlayton@kernel.org>
>> URL: https://tracker.ceph.com/issues/57986
>> Signed-off-by: Xiubo Li <xiubli@redhat.com>
>> ---
>>   fs/ceph/locks.c    | 20 ++++++++++++++++++--
>>   include/linux/fs.h |  3 +++
>>   2 files changed, 21 insertions(+), 2 deletions(-)
>>
>> diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
>> index b191426bf880..cf78608a3f9a 100644
>> --- a/fs/ceph/locks.c
>> +++ b/fs/ceph/locks.c
>> @@ -34,18 +34,34 @@ static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
>>   {
>>          struct inode *inode = file_inode(dst->fl_file);
>>          atomic_inc(&ceph_inode(inode)->i_filelock_ref);
>> +       dst->fl_u.ceph.fl_inode = igrab(inode);
>>   }
>>
>> +/*
>> + * Do not use the 'fl->fl_file' in release function, which
>> + * is possibly already released by another thread.
>> + */
>>   static void ceph_fl_release_lock(struct file_lock *fl)
>>   {
>> -       struct inode *inode = file_inode(fl->fl_file);
>> -       struct ceph_inode_info *ci = ceph_inode(inode);
>> +       struct inode *inode = fl->fl_u.ceph.fl_inode;
>> +       struct ceph_inode_info *ci;
>> +
>> +       /*
>> +        * If inode is NULL it should be a request file_lock,
>> +        * nothing we can do.
>> +        */
>> +       if (!inode)
>> +               return;
>> +
>> +       ci = ceph_inode(inode);
>>          if (atomic_dec_and_test(&ci->i_filelock_ref)) {
>>                  /* clear error when all locks are released */
>>                  spin_lock(&ci->i_ceph_lock);
>>                  ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
>>                  spin_unlock(&ci->i_ceph_lock);
>>          }
>> +       fl->fl_u.ceph.fl_inode = NULL;
>> +       iput(inode);
>>   }
>>
>>   static const struct file_lock_operations ceph_fl_lock_ops = {
>> diff --git a/include/linux/fs.h b/include/linux/fs.h
>> index 7b52fdfb6da0..6106374f5257 100644
>> --- a/include/linux/fs.h
>> +++ b/include/linux/fs.h
>> @@ -1119,6 +1119,9 @@ struct file_lock {
>>                          int state;              /* state of grant or error if -ve */
>>                          unsigned int    debug_id;
>>                  } afs;
>> +               struct {
>> +                       struct inode *fl_inode;
> Hi Xiubo,
>
> Nit: I think it could be just "inode", without the prefix which is
> already present in the union field name.

Okay, I can fix this in the next version.

Thanks.

- Xiubo


> Thanks,
>
>                  Ilya
>
diff mbox series

Patch

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index b191426bf880..cf78608a3f9a 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -34,18 +34,34 @@  static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
 {
 	struct inode *inode = file_inode(dst->fl_file);
 	atomic_inc(&ceph_inode(inode)->i_filelock_ref);
+	dst->fl_u.ceph.fl_inode = igrab(inode);
 }
 
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
 static void ceph_fl_release_lock(struct file_lock *fl)
 {
-	struct inode *inode = file_inode(fl->fl_file);
-	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct inode *inode = fl->fl_u.ceph.fl_inode;
+	struct ceph_inode_info *ci;
+
+	/*
+	 * If inode is NULL it should be a request file_lock,
+	 * nothing we can do.
+	 */
+	if (!inode)
+		return;
+
+	ci = ceph_inode(inode);
 	if (atomic_dec_and_test(&ci->i_filelock_ref)) {
 		/* clear error when all locks are released */
 		spin_lock(&ci->i_ceph_lock);
 		ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
 		spin_unlock(&ci->i_ceph_lock);
 	}
+	fl->fl_u.ceph.fl_inode = NULL;
+	iput(inode);
 }
 
 static const struct file_lock_operations ceph_fl_lock_ops = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7b52fdfb6da0..6106374f5257 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1119,6 +1119,9 @@  struct file_lock {
 			int state;		/* state of grant or error if -ve */
 			unsigned int	debug_id;
 		} afs;
+		struct {
+			struct inode *fl_inode;
+		} ceph;
 	} fl_u;
 } __randomize_layout;