[-V1,06/22] vfs: Add delete child and delete self permission flags
diff mbox

Message ID 1398615293-22931-7-git-send-email-aneesh.kumar@linux.vnet.ibm.com
State New, archived
Headers show

Commit Message

Aneesh Kumar K.V April 27, 2014, 4:14 p.m. UTC
From: Andreas Gruenbacher <agruen@kernel.org>

Normally, deleting a file requires write access to the parent directory.
Some permission models use a different permission on the parent
directory to indicate delete access.  In addition, a process can have
per-file delete access even without delete access on the parent
directory.

Introduce two new inode_permission() mask flags and use them in
may_delete()

Signed-off-by: Andreas Gruenbacher <agruen@kernel.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 fs/namei.c         | 45 ++++++++++++++++++++++++++++++++++-----------
 include/linux/fs.h |  2 ++
 2 files changed, 36 insertions(+), 11 deletions(-)

Comments

Dave Chinner April 29, 2014, 12:07 a.m. UTC | #1
On Sun, Apr 27, 2014 at 09:44:37PM +0530, Aneesh Kumar K.V wrote:
> From: Andreas Gruenbacher <agruen@kernel.org>
> 
> Normally, deleting a file requires write access to the parent directory.
> Some permission models use a different permission on the parent
> directory to indicate delete access.  In addition, a process can have
> per-file delete access even without delete access on the parent
> directory.
> 
> Introduce two new inode_permission() mask flags and use them in
> may_delete()
> 
> Signed-off-by: Andreas Gruenbacher <agruen@kernel.org>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> ---
>  fs/namei.c         | 45 ++++++++++++++++++++++++++++++++++-----------
>  include/linux/fs.h |  2 ++
>  2 files changed, 36 insertions(+), 11 deletions(-)
> 
> diff --git a/fs/namei.c b/fs/namei.c
> index 028bc8bcf77c..56ac7613fbca 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -446,7 +446,7 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
>   * changing the "normal" UIDs which are used for other things.
>   *
>   * When checking for MAY_APPEND, MAY_CREATE_FILE, MAY_CREATE_DIR,
> - * MAY_WRITE must also be set in @mask.
> + * MAY_DELETE_CHILD, MAY_DELETE_SELF, MAY_WRITE must also be set in @mask.
>   */
>  int inode_permission(struct inode *inode, int mask)
>  {
> @@ -2366,11 +2366,25 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path,
>  }
>  EXPORT_SYMBOL(kern_path_mountpoint);
>  
> +
> +/*
> + * We should have exec permission on directory and MAY_DELETE_SELF
> + * on the object being deleted.
> + */
> +static int richacl_may_selfdelete(struct inode *dir,
> +				  struct inode *inode, int replace_mask)
> +{
> +	return (IS_RICHACL(inode) &&
> +		(inode_permission(dir, MAY_EXEC | replace_mask) == 0) &&
> +		(inode_permission(inode, MAY_DELETE_SELF) == 0));
> +}

Can't say I like these "richacl" prefixes. Why not just "may_*"
like all the other permission checks?


> @@ -2414,13 +2431,19 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
>  	BUG_ON(victim->d_parent->d_inode != dir);
>  	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
>  
> -	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
> +	mask = MAY_WRITE | MAY_EXEC | MAY_DELETE_CHILD;
> +	if (replace)
> +		replace_mask = S_ISDIR(inode->i_mode) ?
> +				MAY_CREATE_DIR : MAY_CREATE_FILE;
> +	error = inode_permission(dir, mask | replace_mask);
> +	if (error && richacl_may_selfdelete(dir, inode, replace_mask))
> +		error = 0;
>  	if (error)
>  		return error;
>  	if (IS_APPEND(dir))
>  		return -EPERM;
>  
> -	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
> +	if (check_sticky(dir, inode, replace_mask) || IS_APPEND(inode) ||
>  	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
>  		return -EPERM;
>  	if (isdir) {
> @@ -3539,7 +3562,7 @@ EXPORT_SYMBOL(dentry_unhash);
>  
>  int vfs_rmdir(struct inode *dir, struct dentry *dentry)
>  {
> -	int error = may_delete(dir, dentry, 1);
> +	int error = may_delete(dir, dentry, 1, 0);
>  
>  	if (error)
>  		return error;
> @@ -3658,7 +3681,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
>  int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
>  {
>  	struct inode *target = dentry->d_inode;
> -	int error = may_delete(dir, dentry, 0);
> +	int error = may_delete(dir, dentry, 0, 0);
>  
>  	if (error)
>  		return error;
> @@ -4060,7 +4083,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
>  	if (source == target)
>  		return 0;
>  
> -	error = may_delete(old_dir, old_dentry, is_dir);
> +	error = may_delete(old_dir, old_dentry, is_dir, 0);
>  	if (error)
>  		return error;
>  
> @@ -4070,9 +4093,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
>  		new_is_dir = d_is_dir(new_dentry);
>  
>  		if (!(flags & RENAME_EXCHANGE))
> -			error = may_delete(new_dir, new_dentry, is_dir);
> +			error = may_delete(new_dir, new_dentry, is_dir, 1);
>  		else
> -			error = may_delete(new_dir, new_dentry, new_is_dir);
> +			error = may_delete(new_dir, new_dentry, new_is_dir, 1);

Another boolean parameter that means nothing at the call site.  This
should really be passing a flags field, not a bunch of booleans that
are simply evaluated into flags...

Cheers,

Dave.
Aneesh Kumar K.V May 1, 2014, 3:18 p.m. UTC | #2
Dave Chinner <david@fromorbit.com> writes:

> On Sun, Apr 27, 2014 at 09:44:37PM +0530, Aneesh Kumar K.V wrote:
>> From: Andreas Gruenbacher <agruen@kernel.org>
>> 
>> Normally, deleting a file requires write access to the parent directory.
>> Some permission models use a different permission on the parent
>> directory to indicate delete access.  In addition, a process can have
>> per-file delete access even without delete access on the parent
>> directory.
>> 
>> Introduce two new inode_permission() mask flags and use them in
>> may_delete()
>> 
>> Signed-off-by: Andreas Gruenbacher <agruen@kernel.org>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>> ---
>>  fs/namei.c         | 45 ++++++++++++++++++++++++++++++++++-----------
>>  include/linux/fs.h |  2 ++
>>  2 files changed, 36 insertions(+), 11 deletions(-)
>> 
>> diff --git a/fs/namei.c b/fs/namei.c
>> index 028bc8bcf77c..56ac7613fbca 100644
>> --- a/fs/namei.c
>> +++ b/fs/namei.c
>> @@ -446,7 +446,7 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
>>   * changing the "normal" UIDs which are used for other things.
>>   *
>>   * When checking for MAY_APPEND, MAY_CREATE_FILE, MAY_CREATE_DIR,
>> - * MAY_WRITE must also be set in @mask.
>> + * MAY_DELETE_CHILD, MAY_DELETE_SELF, MAY_WRITE must also be set in @mask.
>>   */
>>  int inode_permission(struct inode *inode, int mask)
>>  {
>> @@ -2366,11 +2366,25 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path,
>>  }
>>  EXPORT_SYMBOL(kern_path_mountpoint);
>>  
>> +
>> +/*
>> + * We should have exec permission on directory and MAY_DELETE_SELF
>> + * on the object being deleted.
>> + */
>> +static int richacl_may_selfdelete(struct inode *dir,
>> +				  struct inode *inode, int replace_mask)
>> +{
>> +	return (IS_RICHACL(inode) &&
>> +		(inode_permission(dir, MAY_EXEC | replace_mask) == 0) &&
>> +		(inode_permission(inode, MAY_DELETE_SELF) == 0));
>> +}
>
> Can't say I like these "richacl" prefixes. Why not just "may_*"
> like all the other permission checks?

Will update.

>
>
>> @@ -2414,13 +2431,19 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
>>  	BUG_ON(victim->d_parent->d_inode != dir);
>>  	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
>>  
>> -	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
>> +	mask = MAY_WRITE | MAY_EXEC | MAY_DELETE_CHILD;
>> +	if (replace)
>> +		replace_mask = S_ISDIR(inode->i_mode) ?
>> +				MAY_CREATE_DIR : MAY_CREATE_FILE;
>> +	error = inode_permission(dir, mask | replace_mask);
>> +	if (error && richacl_may_selfdelete(dir, inode, replace_mask))
>> +		error = 0;

....

>>  
>>  		if (!(flags & RENAME_EXCHANGE))
>> -			error = may_delete(new_dir, new_dentry, is_dir);
>> +			error = may_delete(new_dir, new_dentry, is_dir, 1);
>>  		else
>> -			error = may_delete(new_dir, new_dentry, new_is_dir);
>> +			error = may_delete(new_dir, new_dentry, new_is_dir, 1);
>
> Another boolean parameter that means nothing at the call site.  This
> should really be passing a flags field, not a bunch of booleans that
> are simply evaluated into flags...
>

Will update

Thanks
-aneesh

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" 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 028bc8bcf77c..56ac7613fbca 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -446,7 +446,7 @@  static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
  * changing the "normal" UIDs which are used for other things.
  *
  * When checking for MAY_APPEND, MAY_CREATE_FILE, MAY_CREATE_DIR,
- * MAY_WRITE must also be set in @mask.
+ * MAY_DELETE_CHILD, MAY_DELETE_SELF, MAY_WRITE must also be set in @mask.
  */
 int inode_permission(struct inode *inode, int mask)
 {
@@ -2366,11 +2366,25 @@  kern_path_mountpoint(int dfd, const char *name, struct path *path,
 }
 EXPORT_SYMBOL(kern_path_mountpoint);
 
+
+/*
+ * We should have exec permission on directory and MAY_DELETE_SELF
+ * on the object being deleted.
+ */
+static int richacl_may_selfdelete(struct inode *dir,
+				  struct inode *inode, int replace_mask)
+{
+	return (IS_RICHACL(inode) &&
+		(inode_permission(dir, MAY_EXEC | replace_mask) == 0) &&
+		(inode_permission(inode, MAY_DELETE_SELF) == 0));
+}
+
 /*
  * It's inline, so penalty for filesystems that don't use sticky bit is
  * minimal.
  */
-static inline int check_sticky(struct inode *dir, struct inode *inode)
+static inline int check_sticky(struct inode *dir,
+			       struct inode *inode, int replace_mask)
 {
 	kuid_t fsuid = current_fsuid();
 
@@ -2380,6 +2394,8 @@  static inline int check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
+	if (richacl_may_selfdelete(dir, inode, replace_mask))
+		return 0;
 	return !inode_capable(inode, CAP_FOWNER);
 }
 
@@ -2402,10 +2418,11 @@  static inline int check_sticky(struct inode *dir, struct inode *inode)
  * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
  *     nfs_async_unlink().
  */
-static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
+static int may_delete(struct inode *dir, struct dentry *victim,
+		      bool isdir, bool replace)
 {
 	struct inode *inode = victim->d_inode;
-	int error;
+	int error, mask, replace_mask = 0;
 
 	if (d_is_negative(victim))
 		return -ENOENT;
@@ -2414,13 +2431,19 @@  static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 	BUG_ON(victim->d_parent->d_inode != dir);
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	mask = MAY_WRITE | MAY_EXEC | MAY_DELETE_CHILD;
+	if (replace)
+		replace_mask = S_ISDIR(inode->i_mode) ?
+				MAY_CREATE_DIR : MAY_CREATE_FILE;
+	error = inode_permission(dir, mask | replace_mask);
+	if (error && richacl_may_selfdelete(dir, inode, replace_mask))
+		error = 0;
 	if (error)
 		return error;
 	if (IS_APPEND(dir))
 		return -EPERM;
 
-	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
+	if (check_sticky(dir, inode, replace_mask) || IS_APPEND(inode) ||
 	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
@@ -3539,7 +3562,7 @@  EXPORT_SYMBOL(dentry_unhash);
 
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	int error = may_delete(dir, dentry, 1);
+	int error = may_delete(dir, dentry, 1, 0);
 
 	if (error)
 		return error;
@@ -3658,7 +3681,7 @@  SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
 {
 	struct inode *target = dentry->d_inode;
-	int error = may_delete(dir, dentry, 0);
+	int error = may_delete(dir, dentry, 0, 0);
 
 	if (error)
 		return error;
@@ -4060,7 +4083,7 @@  int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (source == target)
 		return 0;
 
-	error = may_delete(old_dir, old_dentry, is_dir);
+	error = may_delete(old_dir, old_dentry, is_dir, 0);
 	if (error)
 		return error;
 
@@ -4070,9 +4093,9 @@  int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_is_dir = d_is_dir(new_dentry);
 
 		if (!(flags & RENAME_EXCHANGE))
-			error = may_delete(new_dir, new_dentry, is_dir);
+			error = may_delete(new_dir, new_dentry, is_dir, 1);
 		else
-			error = may_delete(new_dir, new_dentry, new_is_dir);
+			error = may_delete(new_dir, new_dentry, new_is_dir, 1);
 	}
 	if (error)
 		return error;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index da5521de04ab..3f0ad0f2bce8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -79,6 +79,8 @@  typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #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