[v14,03/22] vfs: Add MAY_DELETE_SELF and MAY_DELETE_CHILD permission flags
diff mbox

Message ID 1446723580-3747-4-git-send-email-agruenba@redhat.com
State New
Headers show

Commit Message

Andreas Gruenbacher Nov. 5, 2015, 11:39 a.m. UTC
Normally, deleting a file requires MAY_WRITE access to the parent
directory.  With richacls, a file may be deleted with MAY_DELETE_CHILD access
to the parent directory or with MAY_DELETE_SELF access to the file.

To support that, pass the MAY_DELETE_CHILD mask flag to inode_permission()
when checking for delete access inside a directory, and MAY_DELETE_SELF
when checking for delete access to a file itelf.

The MAY_DELETE_SELF permission overrides the sticky directory check.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/namei.c         | 21 ++++++++++++---------
 include/linux/fs.h |  2 ++
 2 files changed, 14 insertions(+), 9 deletions(-)

Comments

Andreas Dilger Nov. 6, 2015, 9:26 p.m. UTC | #1
On Nov 5, 2015, at 4:39 AM, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> 
> Normally, deleting a file requires MAY_WRITE access to the parent
> directory.  With richacls, a file may be deleted with MAY_DELETE_CHILD access
> to the parent directory or with MAY_DELETE_SELF access to the file.
> 
> To support that, pass the MAY_DELETE_CHILD mask flag to inode_permission()
> when checking for delete access inside a directory, and MAY_DELETE_SELF
> when checking for delete access to a file itelf.
> 
> The MAY_DELETE_SELF permission overrides the sticky directory check.
> 
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
> Reviewed-by: J. Bruce Fields <bfields@redhat.com>
> ---
> fs/namei.c         | 21 ++++++++++++---------
> include/linux/fs.h |  2 ++
> 2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/namei.c b/fs/namei.c
> index 0259392..2eab19e 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -453,9 +453,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
>  * this, letting us set arbitrary permissions for filesystem access without
>  * changing the "normal" UIDs which are used for other things.
>  *
> - * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE, or
> - * MAY_CREATE_DIR are set.  That way, file systems that don't support these
> - * permissions will check for MAY_WRITE instead.
> + * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE,
> + * MAY_CREATE_DIR, or MAY_DELETE_CHILD are set.  That way, file systems that
> + * don't support these permissions will check for MAY_WRITE instead.
>  */
> int inode_permission(struct inode *inode, int mask)
> {
> @@ -2555,7 +2555,7 @@ static int may_delete(struct inode *dir, struct dentry *victim,
> 		      bool isdir, bool replace)
> {
> 	struct inode *inode = d_backing_inode(victim);
> -	int error, mask = MAY_WRITE | MAY_EXEC;
> +	int error, mask = MAY_EXEC;
> 
> 	if (d_is_negative(victim))
> 		return -ENOENT;
> @@ -2565,15 +2565,18 @@ static int may_delete(struct inode *dir, struct dentry *victim,
> 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
> 
> 	if (replace)
> -		mask |= isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE;
> -	error = inode_permission(dir, mask);
> +		mask |= MAY_WRITE | (isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE);
> +	error = inode_permission(dir, mask | MAY_WRITE | MAY_DELETE_CHILD);
> +	if (!error && check_sticky(dir, inode))
> +		error = -EPERM;
> +	if (error && IS_RICHACL(inode) &&
> +	    inode_permission(inode, MAY_DELETE_SELF) == 0)
> +		error = 0;

This looks like a serious bug, as it is overriding other errors returned
from inode_permission() such as -EROFS from sb_permission() or even from
generic_permission->acl_permission_check().  Clearing the error returned
by an earlier check doesn't seem safe, only new errors should be added.

The call to inode_permission(inode) is also duplicating the sb_permission()
check from inode_permission(dir), so at most should be __inode_permission().

It looks like this would be correct if you check MAY_DELETE_SELF together
with check_sticky():

	if (!error && check_sticky(dir, inode) &&
	    !__inode_permission(inode, MAY_DELETE_SELF))
		error = -EPERM;

I ommitted the IS_RICHACL() check here, since that should probably be in
__inode_permission() when MAY_DELETE_SELF is passed?

Cheers, Andreas

> 	if (error)
> 		return error;
> 	if (IS_APPEND(dir))
> 		return -EPERM;

> -
> -	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
> -	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
> +	if (IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
> 		return -EPERM;

> 	if (isdir) {
> 		if (!d_is_dir(victim))
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index d6e2330..402acd7 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -84,6 +84,8 @@ typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
> #define MAY_NOT_BLOCK		0x00000080
> #define MAY_CREATE_FILE		0x00000100
> #define MAY_CREATE_DIR		0x00000200
> +#define MAY_DELETE_CHILD	0x00000400
> +#define MAY_DELETE_SELF		0x00000800
> 
> /*
>  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
> --
> 2.5.0
> 


Cheers, Andreas
Andreas Dilger Nov. 6, 2015, 9:26 p.m. UTC | #2
On Nov 5, 2015, at 4:39 AM, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> 
> Normally, deleting a file requires MAY_WRITE access to the parent
> directory.  With richacls, a file may be deleted with MAY_DELETE_CHILD access
> to the parent directory or with MAY_DELETE_SELF access to the file.
> 
> To support that, pass the MAY_DELETE_CHILD mask flag to inode_permission()
> when checking for delete access inside a directory, and MAY_DELETE_SELF
> when checking for delete access to a file itelf.
> 
> The MAY_DELETE_SELF permission overrides the sticky directory check.
> 
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
> Reviewed-by: J. Bruce Fields <bfields@redhat.com>
> ---
> fs/namei.c         | 21 ++++++++++++---------
> include/linux/fs.h |  2 ++
> 2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/namei.c b/fs/namei.c
> index 0259392..2eab19e 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -453,9 +453,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
>  * this, letting us set arbitrary permissions for filesystem access without
>  * changing the "normal" UIDs which are used for other things.
>  *
> - * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE, or
> - * MAY_CREATE_DIR are set.  That way, file systems that don't support these
> - * permissions will check for MAY_WRITE instead.
> + * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE,
> + * MAY_CREATE_DIR, or MAY_DELETE_CHILD are set.  That way, file systems that
> + * don't support these permissions will check for MAY_WRITE instead.
>  */
> int inode_permission(struct inode *inode, int mask)
> {
> @@ -2555,7 +2555,7 @@ static int may_delete(struct inode *dir, struct dentry *victim,
> 		      bool isdir, bool replace)
> {
> 	struct inode *inode = d_backing_inode(victim);
> -	int error, mask = MAY_WRITE | MAY_EXEC;
> +	int error, mask = MAY_EXEC;
> 
> 	if (d_is_negative(victim))
> 		return -ENOENT;
> @@ -2565,15 +2565,18 @@ static int may_delete(struct inode *dir, struct dentry *victim,
> 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
> 
> 	if (replace)
> -		mask |= isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE;
> -	error = inode_permission(dir, mask);
> +		mask |= MAY_WRITE | (isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE);
> +	error = inode_permission(dir, mask | MAY_WRITE | MAY_DELETE_CHILD);
> +	if (!error && check_sticky(dir, inode))
> +		error = -EPERM;
> +	if (error && IS_RICHACL(inode) &&
> +	    inode_permission(inode, MAY_DELETE_SELF) == 0)
> +		error = 0;

This looks like a serious bug, as it is overriding other errors returned
from inode_permission() such as -EROFS from sb_permission() or even from
generic_permission->acl_permission_check().  Clearing the error returned
by an earlier check doesn't seem safe, only new errors should be added.

The call to inode_permission(inode) is also duplicating the sb_permission()
check from inode_permission(dir), so at most should be __inode_permission().

It looks like this would be correct if you check MAY_DELETE_SELF together
with check_sticky():

	if (!error && check_sticky(dir, inode) &&
	    !__inode_permission(inode, MAY_DELETE_SELF))
		error = -EPERM;

I ommitted the IS_RICHACL() check here, since that should probably be in
__inode_permission() when MAY_DELETE_SELF is passed?

Cheers, Andreas

> 	if (error)
> 		return error;
> 	if (IS_APPEND(dir))
> 		return -EPERM;

> -
> -	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
> -	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
> +	if (IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
> 		return -EPERM;

> 	if (isdir) {
> 		if (!d_is_dir(victim))
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index d6e2330..402acd7 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -84,6 +84,8 @@ typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
> #define MAY_NOT_BLOCK		0x00000080
> #define MAY_CREATE_FILE		0x00000100
> #define MAY_CREATE_DIR		0x00000200
> +#define MAY_DELETE_CHILD	0x00000400
> +#define MAY_DELETE_SELF		0x00000800
> 
> /*
>  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
> --
> 2.5.0
> 


Cheers, Andreas
Andreas Gruenbacher Nov. 7, 2015, 8:47 p.m. UTC | #3
On Fri, Nov 6, 2015 at 10:26 PM, Andreas Dilger <adilger@dilger.ca> wrote:
> On Nov 5, 2015, at 4:39 AM, Andreas Gruenbacher <agruenba@redhat.com> wrote:
>>
>> Normally, deleting a file requires MAY_WRITE access to the parent
>> directory.  With richacls, a file may be deleted with MAY_DELETE_CHILD access
>> to the parent directory or with MAY_DELETE_SELF access to the file.
>>
>> To support that, pass the MAY_DELETE_CHILD mask flag to inode_permission()
>> when checking for delete access inside a directory, and MAY_DELETE_SELF
>> when checking for delete access to a file itelf.
>>
>> The MAY_DELETE_SELF permission overrides the sticky directory check.
>>
>> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
>> Reviewed-by: J. Bruce Fields <bfields@redhat.com>
>> ---
>> fs/namei.c         | 21 ++++++++++++---------
>> include/linux/fs.h |  2 ++
>> 2 files changed, 14 insertions(+), 9 deletions(-)
>>
>> diff --git a/fs/namei.c b/fs/namei.c
>> index 0259392..2eab19e 100644
>> --- a/fs/namei.c
>> +++ b/fs/namei.c
>> @@ -453,9 +453,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
>>  * this, letting us set arbitrary permissions for filesystem access without
>>  * changing the "normal" UIDs which are used for other things.
>>  *
>> - * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE, or
>> - * MAY_CREATE_DIR are set.  That way, file systems that don't support these
>> - * permissions will check for MAY_WRITE instead.
>> + * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE,
>> + * MAY_CREATE_DIR, or MAY_DELETE_CHILD are set.  That way, file systems that
>> + * don't support these permissions will check for MAY_WRITE instead.
>>  */
>> int inode_permission(struct inode *inode, int mask)
>> {
>> @@ -2555,7 +2555,7 @@ static int may_delete(struct inode *dir, struct dentry *victim,
>>                     bool isdir, bool replace)
>> {
>>       struct inode *inode = d_backing_inode(victim);
>> -     int error, mask = MAY_WRITE | MAY_EXEC;
>> +     int error, mask = MAY_EXEC;
>>
>>       if (d_is_negative(victim))
>>               return -ENOENT;
>> @@ -2565,15 +2565,18 @@ static int may_delete(struct inode *dir, struct dentry *victim,
>>       audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
>>
>>       if (replace)
>> -             mask |= isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE;
>> -     error = inode_permission(dir, mask);
>> +             mask |= MAY_WRITE | (isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE);
>> +     error = inode_permission(dir, mask | MAY_WRITE | MAY_DELETE_CHILD);
>> +     if (!error && check_sticky(dir, inode))
>> +             error = -EPERM;
>> +     if (error && IS_RICHACL(inode) &&
>> +         inode_permission(inode, MAY_DELETE_SELF) == 0)
>> +             error = 0;
>
> This looks like a serious bug, as it is overriding other errors returned
> from inode_permission() such as -EROFS from sb_permission() or even from
> generic_permission->acl_permission_check().  Clearing the error returned
> by an earlier check doesn't seem safe, only new errors should be added.

See further below ...

> The call to inode_permission(inode) is also duplicating the sb_permission()
> check from inode_permission(dir), so at most should be __inode_permission().

This could be optimized, but that would make the code harder to read.
I don't think it really matters: this only affects file with the
MAY_DELETE_SELF permission, and sb_permissions is really cheap anyway.

> It looks like this would be correct if you check MAY_DELETE_SELF together
> with check_sticky():
>
>         if (!error && check_sticky(dir, inode) &&
>             !__inode_permission(inode, MAY_DELETE_SELF))
>                 error = -EPERM;

Nope, this version would deny users with MAY_DELETE_SELF access to a
file and MAY_EXEC access to the directory the right to delete the file
because @error would already be set then.

You are right that the check for MAY_DELETE_SELF overrides too much
here though; we need an additional inode_permission(dir, ...) check in
there.

I've pushed a fixed version here that I will do some more testing on
before reposting:

  git://git.kernel.org/pub/scm/linux/kernel/git/agruen/linux-richacl.git
richacl-wip

> I ommitted the IS_RICHACL() check here, since that should probably be in
> __inode_permission() when MAY_DELETE_SELF is passed?

The IS_RICHACL() check is indeed done in inode_permission ->
__inode_permission -> do_inode_permission -> generic_permission ->
acl_permission_check. I've duplicated that check here to avoid slowing
down may_delete in the common case where the filesystem doesn't
support richacls.

Thanks,
Andreas
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch
diff mbox

diff --git a/fs/namei.c b/fs/namei.c
index 0259392..2eab19e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -453,9 +453,9 @@  static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
  * this, letting us set arbitrary permissions for filesystem access without
  * changing the "normal" UIDs which are used for other things.
  *
- * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE, or
- * MAY_CREATE_DIR are set.  That way, file systems that don't support these
- * permissions will check for MAY_WRITE instead.
+ * MAY_WRITE must be set in @mask whenever MAY_APPEND, MAY_CREATE_FILE,
+ * MAY_CREATE_DIR, or MAY_DELETE_CHILD are set.  That way, file systems that
+ * don't support these permissions will check for MAY_WRITE instead.
  */
 int inode_permission(struct inode *inode, int mask)
 {
@@ -2555,7 +2555,7 @@  static int may_delete(struct inode *dir, struct dentry *victim,
 		      bool isdir, bool replace)
 {
 	struct inode *inode = d_backing_inode(victim);
-	int error, mask = MAY_WRITE | MAY_EXEC;
+	int error, mask = MAY_EXEC;
 
 	if (d_is_negative(victim))
 		return -ENOENT;
@@ -2565,15 +2565,18 @@  static int may_delete(struct inode *dir, struct dentry *victim,
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	if (replace)
-		mask |= isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE;
-	error = inode_permission(dir, mask);
+		mask |= MAY_WRITE | (isdir ? MAY_CREATE_DIR : MAY_CREATE_FILE);
+	error = inode_permission(dir, mask | MAY_WRITE | MAY_DELETE_CHILD);
+	if (!error && check_sticky(dir, inode))
+		error = -EPERM;
+	if (error && IS_RICHACL(inode) &&
+	    inode_permission(inode, MAY_DELETE_SELF) == 0)
+		error = 0;
 	if (error)
 		return error;
 	if (IS_APPEND(dir))
 		return -EPERM;
-
-	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
-	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
 		if (!d_is_dir(victim))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d6e2330..402acd7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -84,6 +84,8 @@  typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
 #define MAY_NOT_BLOCK		0x00000080
 #define MAY_CREATE_FILE		0x00000100
 #define MAY_CREATE_DIR		0x00000200
+#define MAY_DELETE_CHILD	0x00000400
+#define MAY_DELETE_SELF		0x00000800
 
 /*
  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond