diff mbox series

proc: Update inode upon changing task security attribute

Message ID 20231130003704.31928-1-kamatam@amazon.com
State New
Headers
Series proc: Update inode upon changing task security attribute |

Commit Message

Munehisa Kamata Nov. 30, 2023, 12:37 a.m. UTC 
  I'm not clear whether VFS is a better (or worse) place[1] to fix the
problem described below and would like to hear opinion.

If the /proc/[pid] directory is bind-mounted on a system with Smack
enabled, and if the task updates its current security attribute, the task
may lose access to files in its own /proc/[pid] through the mountpoint.

 $ sudo capsh --drop=cap_mac_override --
 # mkdir -p dir
 # mount --bind /proc/$$ dir
 # echo AAA > /proc/$$/task/current		# assuming built-in echo
 # cat /proc/$$/task/current			# revalidate
 AAA
 # echo BBB > dir/attr/current
 # cat dir/attr/current
 cat: dir/attr/current: Permission denied
 # ls dir/
 ls: cannot access dir/: Permission denied
 # cat /proc/$$/attr/current			# revalidate
 BBB
 # cat dir/attr/current
 BBB
 # echo CCC > /proc/$$/attr/current
 # cat dir/attr/current
 cat: dir/attr/current: Permission denied

This happens because path lookup doesn't revalidate the dentry of the
/proc/[pid] when traversing the filesystem boundary, so the inode security
blob of the /proc/[pid] doesn't get updated with the new task security
attribute. Then, this may lead security modules to deny an access to the
directory. Looking at the code[2] and the /proc/pid/attr/current entry in
proc man page, seems like the same could happen with SELinux. Though, I
didn't find relevant reports.

The steps above are quite artificial. I actually encountered such an
unexpected denial of access with an in-house application sandbox
framework; each app has its own dedicated filesystem tree where the
process's /proc/[pid] is bind-mounted to and the app enters into via
chroot.

With this patch, writing to /proc/[pid]/attr/current (and its per-security
module variant) updates the inode security blob of /proc/[pid] or
/proc/[pid]/task/[tid] (when pid != tid) with the new attribute.

[1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
---
 fs/proc/base.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

Comments

Casey Schaufler Nov. 30, 2023, 2:28 a.m. UTC | #1 
On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
> I'm not clear whether VFS is a better (or worse) place[1] to fix the
> problem described below and would like to hear opinion.

Please To: or at least Cc: me on all Smack related issues.

>
> If the /proc/[pid] directory is bind-mounted on a system with Smack
> enabled, and if the task updates its current security attribute, the task
> may lose access to files in its own /proc/[pid] through the mountpoint.
>
>  $ sudo capsh --drop=cap_mac_override --
>  # mkdir -p dir
>  # mount --bind /proc/$$ dir
>  # echo AAA > /proc/$$/task/current		# assuming built-in echo

I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?

>  # cat /proc/$$/task/current			# revalidate
>  AAA
>  # echo BBB > dir/attr/current
>  # cat dir/attr/current
>  cat: dir/attr/current: Permission denied
>  # ls dir/
>  ls: cannot access dir/: Permission denied
>  # cat /proc/$$/attr/current			# revalidate
>  BBB
>  # cat dir/attr/current
>  BBB
>  # echo CCC > /proc/$$/attr/current
>  # cat dir/attr/current
>  cat: dir/attr/current: Permission denied
>
> This happens because path lookup doesn't revalidate the dentry of the
> /proc/[pid] when traversing the filesystem boundary, so the inode security
> blob of the /proc/[pid] doesn't get updated with the new task security
> attribute. Then, this may lead security modules to deny an access to the
> directory. Looking at the code[2] and the /proc/pid/attr/current entry in
> proc man page, seems like the same could happen with SELinux. Though, I
> didn't find relevant reports.
>
> The steps above are quite artificial. I actually encountered such an
> unexpected denial of access with an in-house application sandbox
> framework; each app has its own dedicated filesystem tree where the
> process's /proc/[pid] is bind-mounted to and the app enters into via
> chroot.
>
> With this patch, writing to /proc/[pid]/attr/current (and its per-security
> module variant) updates the inode security blob of /proc/[pid] or
> /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
>
> [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
>
> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
> ---
>  fs/proc/base.c | 23 ++++++++++++++++++++---
>  1 file changed, 20 insertions(+), 3 deletions(-)
>
> diff --git a/fs/proc/base.c b/fs/proc/base.c
> index dd31e3b6bf77..bdb7bea53475 100644
> --- a/fs/proc/base.c
> +++ b/fs/proc/base.c
> @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>  {
>  	struct inode * inode = file_inode(file);
>  	struct task_struct *task;
> +	const char *name = file->f_path.dentry->d_name.name;
>  	void *page;
>  	int rv;
>  
> @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>  	if (rv < 0)
>  		goto out_free;
>  
> -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
> -				  file->f_path.dentry->d_name.name, page,
> -				  count);
> +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
>  	mutex_unlock(&current->signal->cred_guard_mutex);
> +
> +	/*
> +	 *  Update the inode security blob in advance if the task's security
> +	 *  attribute was updated
> +	 */
> +	if (rv > 0 && !strcmp(name, "current")) {
> +		struct pid *pid;
> +		struct proc_inode *cur, *ei;
> +
> +		rcu_read_lock();
> +		pid = get_task_pid(current, PIDTYPE_PID);
> +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
> +			ei = cur;
> +		put_pid(pid);
> +		pid_update_inode(current, &ei->vfs_inode);
> +		rcu_read_unlock();
> +	}
> +
>  out_free:
>  	kfree(page);
>  out:
Munehisa Kamata Nov. 30, 2023, 3:07 a.m. UTC | #2 
Hi Casey,

On Wed, 2023-11-29 18:28:55 -0800, Casey Schaufler wrote:
>
> On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
> > I'm not clear whether VFS is a better (or worse) place[1] to fix the
> > problem described below and would like to hear opinion.
> 
> Please To: or at least Cc: me on all Smack related issues.

Will do that next.

> >
> > If the /proc/[pid] directory is bind-mounted on a system with Smack
> > enabled, and if the task updates its current security attribute, the task
> > may lose access to files in its own /proc/[pid] through the mountpoint.
> >
> >  $ sudo capsh --drop=cap_mac_override --
> >  # mkdir -p dir
> >  # mount --bind /proc/$$ dir
> >  # echo AAA > /proc/$$/task/current		# assuming built-in echo
> 
> I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?

Ahh, yes, I meant /proc/$$/attr/current. Sorry about that...

> >  # cat /proc/$$/task/current			# revalidate
> >  AAA
> >  # echo BBB > dir/attr/current
> >  # cat dir/attr/current
> >  cat: dir/attr/current: Permission denied
> >  # ls dir/
> >  ls: cannot access dir/: Permission denied
> >  # cat /proc/$$/attr/current			# revalidate
> >  BBB
> >  # cat dir/attr/current
> >  BBB
> >  # echo CCC > /proc/$$/attr/current
> >  # cat dir/attr/current
> >  cat: dir/attr/current: Permission denied
> >
> > This happens because path lookup doesn't revalidate the dentry of the
> > /proc/[pid] when traversing the filesystem boundary, so the inode security
> > blob of the /proc/[pid] doesn't get updated with the new task security
> > attribute. Then, this may lead security modules to deny an access to the
> > directory. Looking at the code[2] and the /proc/pid/attr/current entry in
> > proc man page, seems like the same could happen with SELinux. Though, I
> > didn't find relevant reports.
> >
> > The steps above are quite artificial. I actually encountered such an
> > unexpected denial of access with an in-house application sandbox
> > framework; each app has its own dedicated filesystem tree where the
> > process's /proc/[pid] is bind-mounted to and the app enters into via
> > chroot.
> >
> > With this patch, writing to /proc/[pid]/attr/current (and its per-security
> > module variant) updates the inode security blob of /proc/[pid] or
> > /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
> >
> > [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
> > [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
> >
> > Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> > Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
> > ---
> >  fs/proc/base.c | 23 ++++++++++++++++++++---
> >  1 file changed, 20 insertions(+), 3 deletions(-)
> >
> > diff --git a/fs/proc/base.c b/fs/proc/base.c
> > index dd31e3b6bf77..bdb7bea53475 100644
> > --- a/fs/proc/base.c
> > +++ b/fs/proc/base.c
> > @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >  {
> >  	struct inode * inode = file_inode(file);
> >  	struct task_struct *task;
> > +	const char *name = file->f_path.dentry->d_name.name;
> >  	void *page;
> >  	int rv;
> >  
> > @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >  	if (rv < 0)
> >  		goto out_free;
> >  
> > -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
> > -				  file->f_path.dentry->d_name.name, page,
> > -				  count);
> > +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
> >  	mutex_unlock(&current->signal->cred_guard_mutex);
> > +
> > +	/*
> > +	 *  Update the inode security blob in advance if the task's security
> > +	 *  attribute was updated
> > +	 */
> > +	if (rv > 0 && !strcmp(name, "current")) {
> > +		struct pid *pid;
> > +		struct proc_inode *cur, *ei;
> > +
> > +		rcu_read_lock();
> > +		pid = get_task_pid(current, PIDTYPE_PID);
> > +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
> > +			ei = cur;
> > +		put_pid(pid);
> > +		pid_update_inode(current, &ei->vfs_inode);
> > +		rcu_read_unlock();
> > +	}
> > +
> >  out_free:
> >  	kfree(page);
> >  out:
>
Casey Schaufler Nov. 30, 2023, 6 p.m. UTC | #3 
On 11/29/2023 7:07 PM, Munehisa Kamata wrote:
> Hi Casey,
>
> On Wed, 2023-11-29 18:28:55 -0800, Casey Schaufler wrote:
>> On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
>>> I'm not clear whether VFS is a better (or worse) place[1] to fix the
>>> problem described below and would like to hear opinion.
>> Please To: or at least Cc: me on all Smack related issues.
> Will do that next.
>
>>> If the /proc/[pid] directory is bind-mounted on a system with Smack
>>> enabled, and if the task updates its current security attribute, the task
>>> may lose access to files in its own /proc/[pid] through the mountpoint.
>>>
>>>  $ sudo capsh --drop=cap_mac_override --
>>>  # mkdir -p dir
>>>  # mount --bind /proc/$$ dir
>>>  # echo AAA > /proc/$$/task/current		# assuming built-in echo
>> I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?
> Ahh, yes, I meant /proc/$$/attr/current. Sorry about that...
>
>>>  # cat /proc/$$/task/current			# revalidate
>>>  AAA
>>>  # echo BBB > dir/attr/current
>>>  # cat dir/attr/current
>>>  cat: dir/attr/current: Permission denied
>>>  # ls dir/
>>>  ls: cannot access dir/: Permission denied

I don't see this behavior. What kernel version are you using?
I have a 6.5 kernel.

>>>  # cat /proc/$$/attr/current			# revalidate
>>>  BBB
>>>  # cat dir/attr/current
>>>  BBB
>>>  # echo CCC > /proc/$$/attr/current
>>>  # cat dir/attr/current
>>>  cat: dir/attr/current: Permission denied
>>>
>>> This happens because path lookup doesn't revalidate the dentry of the
>>> /proc/[pid] when traversing the filesystem boundary, so the inode security
>>> blob of the /proc/[pid] doesn't get updated with the new task security
>>> attribute. Then, this may lead security modules to deny an access to the
>>> directory. Looking at the code[2] and the /proc/pid/attr/current entry in
>>> proc man page, seems like the same could happen with SELinux. Though, I
>>> didn't find relevant reports.
>>>
>>> The steps above are quite artificial. I actually encountered such an
>>> unexpected denial of access with an in-house application sandbox
>>> framework; each app has its own dedicated filesystem tree where the
>>> process's /proc/[pid] is bind-mounted to and the app enters into via
>>> chroot.
>>>
>>> With this patch, writing to /proc/[pid]/attr/current (and its per-security
>>> module variant) updates the inode security blob of /proc/[pid] or
>>> /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
>>>
>>> [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
>>> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
>>>
>>> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
>>> Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
>>> ---
>>>  fs/proc/base.c | 23 ++++++++++++++++++++---
>>>  1 file changed, 20 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/fs/proc/base.c b/fs/proc/base.c
>>> index dd31e3b6bf77..bdb7bea53475 100644
>>> --- a/fs/proc/base.c
>>> +++ b/fs/proc/base.c
>>> @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>>>  {
>>>  	struct inode * inode = file_inode(file);
>>>  	struct task_struct *task;
>>> +	const char *name = file->f_path.dentry->d_name.name;
>>>  	void *page;
>>>  	int rv;
>>>  
>>> @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>>>  	if (rv < 0)
>>>  		goto out_free;
>>>  
>>> -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
>>> -				  file->f_path.dentry->d_name.name, page,
>>> -				  count);
>>> +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
>>>  	mutex_unlock(&current->signal->cred_guard_mutex);
>>> +
>>> +	/*
>>> +	 *  Update the inode security blob in advance if the task's security
>>> +	 *  attribute was updated
>>> +	 */
>>> +	if (rv > 0 && !strcmp(name, "current")) {
>>> +		struct pid *pid;
>>> +		struct proc_inode *cur, *ei;
>>> +
>>> +		rcu_read_lock();
>>> +		pid = get_task_pid(current, PIDTYPE_PID);
>>> +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
>>> +			ei = cur;
>>> +		put_pid(pid);
>>> +		pid_update_inode(current, &ei->vfs_inode);
>>> +		rcu_read_unlock();
>>> +	}
>>> +
>>>  out_free:
>>>  	kfree(page);
>>>  out:
Munehisa Kamata Nov. 30, 2023, 8:35 p.m. UTC | #4 
On Thu, 2023-11-30 18:00:13 +0000, Casey Schaufler wrote:
>
> On 11/29/2023 7:07 PM, Munehisa Kamata wrote:
> > Hi Casey,
> >
> > On Wed, 2023-11-29 18:28:55 -0800, Casey Schaufler wrote:
> >> On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
> >>> I'm not clear whether VFS is a better (or worse) place[1] to fix the
> >>> problem described below and would like to hear opinion.
> >> Please To: or at least Cc: me on all Smack related issues.
> > Will do that next.
> >
> >>> If the /proc/[pid] directory is bind-mounted on a system with Smack
> >>> enabled, and if the task updates its current security attribute, the task
> >>> may lose access to files in its own /proc/[pid] through the mountpoint.
> >>>
> >>>  $ sudo capsh --drop=cap_mac_override --
> >>>  # mkdir -p dir
> >>>  # mount --bind /proc/$$ dir
> >>>  # echo AAA > /proc/$$/task/current		# assuming built-in echo
> >> I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?
> > Ahh, yes, I meant /proc/$$/attr/current. Sorry about that...
> >
> >>>  # cat /proc/$$/task/current			# revalidate
> >>>  AAA
> >>>  # echo BBB > dir/attr/current
> >>>  # cat dir/attr/current
> >>>  cat: dir/attr/current: Permission denied
> >>>  # ls dir/
> >>>  ls: cannot access dir/: Permission denied
> 
> I don't see this behavior. What kernel version are you using?
> I have a 6.5 kernel.

I verified the behavior with 6.7-rc3. 

Here is more "raw" log from my machine:

 [ec2-user@ip-10-0-32-198 ~]$ uname -r
 6.7.0-rc3-proc-fix+
 [ec2-user@ip-10-0-32-198 ~]$ sudo capsh --drop=cap_mac_override --
 [root@ip-10-0-32-198 ec2-user]# mount --bind /proc/$$ dir
 [root@ip-10-0-32-198 ec2-user]# echo AAA > /proc/$$/attr/current
 [root@ip-10-0-32-198 ec2-user]# cat /proc/$$/attr/current; echo
 AAA
 [root@ip-10-0-32-198 ec2-user]# echo BBB > dir/attr/current
 [root@ip-10-0-32-198 ec2-user]# cat dir/attr/current
 cat: dir/attr/current: Permission denied

If something frequently scans /proc, such as ps, top or whatever, on your
machine, the inode may get updated quickly (i.e. revalidated during path
lookup) and then you may only have a short window to observe the behavior. 

> >>>  # cat /proc/$$/attr/current			# revalidate
> >>>  BBB
> >>>  # cat dir/attr/current
> >>>  BBB
> >>>  # echo CCC > /proc/$$/attr/current
> >>>  # cat dir/attr/current
> >>>  cat: dir/attr/current: Permission denied
> >>>
> >>> This happens because path lookup doesn't revalidate the dentry of the
> >>> /proc/[pid] when traversing the filesystem boundary, so the inode security
> >>> blob of the /proc/[pid] doesn't get updated with the new task security
> >>> attribute. Then, this may lead security modules to deny an access to the
> >>> directory. Looking at the code[2] and the /proc/pid/attr/current entry in
> >>> proc man page, seems like the same could happen with SELinux. Though, I
> >>> didn't find relevant reports.
> >>>
> >>> The steps above are quite artificial. I actually encountered such an
> >>> unexpected denial of access with an in-house application sandbox
> >>> framework; each app has its own dedicated filesystem tree where the
> >>> process's /proc/[pid] is bind-mounted to and the app enters into via
> >>> chroot.
> >>>
> >>> With this patch, writing to /proc/[pid]/attr/current (and its per-security
> >>> module variant) updates the inode security blob of /proc/[pid] or
> >>> /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
> >>>
> >>> [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
> >>> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
> >>>
> >>> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> >>> Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
> >>> ---
> >>>  fs/proc/base.c | 23 ++++++++++++++++++++---
> >>>  1 file changed, 20 insertions(+), 3 deletions(-)
> >>>
> >>> diff --git a/fs/proc/base.c b/fs/proc/base.c
> >>> index dd31e3b6bf77..bdb7bea53475 100644
> >>> --- a/fs/proc/base.c
> >>> +++ b/fs/proc/base.c
> >>> @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >>>  {
> >>>  	struct inode * inode = file_inode(file);
> >>>  	struct task_struct *task;
> >>> +	const char *name = file->f_path.dentry->d_name.name;
> >>>  	void *page;
> >>>  	int rv;
> >>>  
> >>> @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >>>  	if (rv < 0)
> >>>  		goto out_free;
> >>>  
> >>> -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
> >>> -				  file->f_path.dentry->d_name.name, page,
> >>> -				  count);
> >>> +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
> >>>  	mutex_unlock(&current->signal->cred_guard_mutex);
> >>> +
> >>> +	/*
> >>> +	 *  Update the inode security blob in advance if the task's security
> >>> +	 *  attribute was updated
> >>> +	 */
> >>> +	if (rv > 0 && !strcmp(name, "current")) {
> >>> +		struct pid *pid;
> >>> +		struct proc_inode *cur, *ei;
> >>> +
> >>> +		rcu_read_lock();
> >>> +		pid = get_task_pid(current, PIDTYPE_PID);
> >>> +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
> >>> +			ei = cur;
> >>> +		put_pid(pid);
> >>> +		pid_update_inode(current, &ei->vfs_inode);
> >>> +		rcu_read_unlock();
> >>> +	}
> >>> +
> >>>  out_free:
> >>>  	kfree(page);
> >>>  out:
>
Casey Schaufler Dec. 1, 2023, 12:31 a.m. UTC | #5 
On 11/30/2023 12:35 PM, Munehisa Kamata wrote:
> On Thu, 2023-11-30 18:00:13 +0000, Casey Schaufler wrote:
>> On 11/29/2023 7:07 PM, Munehisa Kamata wrote:
>>> Hi Casey,
>>>
>>> On Wed, 2023-11-29 18:28:55 -0800, Casey Schaufler wrote:
>>>> On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
>>>>> I'm not clear whether VFS is a better (or worse) place[1] to fix the
>>>>> problem described below and would like to hear opinion.
>>>> Please To: or at least Cc: me on all Smack related issues.
>>> Will do that next.
>>>
>>>>> If the /proc/[pid] directory is bind-mounted on a system with Smack
>>>>> enabled, and if the task updates its current security attribute, the task
>>>>> may lose access to files in its own /proc/[pid] through the mountpoint.
>>>>>
>>>>>  $ sudo capsh --drop=cap_mac_override --
>>>>>  # mkdir -p dir
>>>>>  # mount --bind /proc/$$ dir
>>>>>  # echo AAA > /proc/$$/task/current		# assuming built-in echo
>>>> I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?
>>> Ahh, yes, I meant /proc/$$/attr/current. Sorry about that...
>>>
>>>>>  # cat /proc/$$/task/current			# revalidate
>>>>>  AAA
>>>>>  # echo BBB > dir/attr/current
>>>>>  # cat dir/attr/current
>>>>>  cat: dir/attr/current: Permission denied
>>>>>  # ls dir/
>>>>>  ls: cannot access dir/: Permission denied
>> I don't see this behavior. What kernel version are you using?
>> I have a 6.5 kernel.
> I verified the behavior with 6.7-rc3. 
>
> Here is more "raw" log from my machine:
>
>  [ec2-user@ip-10-0-32-198 ~]$ uname -r
>  6.7.0-rc3-proc-fix+
>  [ec2-user@ip-10-0-32-198 ~]$ sudo capsh --drop=cap_mac_override --
>  [root@ip-10-0-32-198 ec2-user]# mount --bind /proc/$$ dir
>  [root@ip-10-0-32-198 ec2-user]# echo AAA > /proc/$$/attr/current
>  [root@ip-10-0-32-198 ec2-user]# cat /proc/$$/attr/current; echo
>  AAA
>  [root@ip-10-0-32-198 ec2-user]# echo BBB > dir/attr/current
>  [root@ip-10-0-32-198 ec2-user]# cat dir/attr/current
>  cat: dir/attr/current: Permission denied
>
> If something frequently scans /proc, such as ps, top or whatever, on your
> machine, the inode may get updated quickly (i.e. revalidated during path
> lookup) and then you may only have a short window to observe the behavior. 

I was able to reproduce the issue with a 6.5 kernel. The window seems
to be really short.

Would it be completely unreasonable for your sandboxing application to
call syncfs(2) after writing to current?

>
>>>>>  # cat /proc/$$/attr/current			# revalidate
>>>>>  BBB
>>>>>  # cat dir/attr/current
>>>>>  BBB
>>>>>  # echo CCC > /proc/$$/attr/current
>>>>>  # cat dir/attr/current
>>>>>  cat: dir/attr/current: Permission denied
>>>>>
>>>>> This happens because path lookup doesn't revalidate the dentry of the
>>>>> /proc/[pid] when traversing the filesystem boundary, so the inode security
>>>>> blob of the /proc/[pid] doesn't get updated with the new task security
>>>>> attribute. Then, this may lead security modules to deny an access to the
>>>>> directory. Looking at the code[2] and the /proc/pid/attr/current entry in
>>>>> proc man page, seems like the same could happen with SELinux. Though, I
>>>>> didn't find relevant reports.
>>>>>
>>>>> The steps above are quite artificial. I actually encountered such an
>>>>> unexpected denial of access with an in-house application sandbox
>>>>> framework; each app has its own dedicated filesystem tree where the
>>>>> process's /proc/[pid] is bind-mounted to and the app enters into via
>>>>> chroot.
>>>>>
>>>>> With this patch, writing to /proc/[pid]/attr/current (and its per-security
>>>>> module variant) updates the inode security blob of /proc/[pid] or
>>>>> /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
>>>>>
>>>>> [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
>>>>> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
>>>>>
>>>>> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
>>>>> Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
>>>>> ---
>>>>>  fs/proc/base.c | 23 ++++++++++++++++++++---
>>>>>  1 file changed, 20 insertions(+), 3 deletions(-)
>>>>>
>>>>> diff --git a/fs/proc/base.c b/fs/proc/base.c
>>>>> index dd31e3b6bf77..bdb7bea53475 100644
>>>>> --- a/fs/proc/base.c
>>>>> +++ b/fs/proc/base.c
>>>>> @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>>>>>  {
>>>>>  	struct inode * inode = file_inode(file);
>>>>>  	struct task_struct *task;
>>>>> +	const char *name = file->f_path.dentry->d_name.name;
>>>>>  	void *page;
>>>>>  	int rv;
>>>>>  
>>>>> @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
>>>>>  	if (rv < 0)
>>>>>  		goto out_free;
>>>>>  
>>>>> -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
>>>>> -				  file->f_path.dentry->d_name.name, page,
>>>>> -				  count);
>>>>> +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
>>>>>  	mutex_unlock(&current->signal->cred_guard_mutex);
>>>>> +
>>>>> +	/*
>>>>> +	 *  Update the inode security blob in advance if the task's security
>>>>> +	 *  attribute was updated
>>>>> +	 */
>>>>> +	if (rv > 0 && !strcmp(name, "current")) {
>>>>> +		struct pid *pid;
>>>>> +		struct proc_inode *cur, *ei;
>>>>> +
>>>>> +		rcu_read_lock();
>>>>> +		pid = get_task_pid(current, PIDTYPE_PID);
>>>>> +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
>>>>> +			ei = cur;
>>>>> +		put_pid(pid);
>>>>> +		pid_update_inode(current, &ei->vfs_inode);
>>>>> +		rcu_read_unlock();
>>>>> +	}
>>>>> +
>>>>>  out_free:
>>>>>  	kfree(page);
>>>>>  out:
Munehisa Kamata Dec. 1, 2023, 6:10 a.m. UTC | #6 
On Thu, 2023-11-30 16:31:11 -0800, Casey Schaufler wrote:
>
> On 11/30/2023 12:35 PM, Munehisa Kamata wrote:
> > On Thu, 2023-11-30 18:00:13 +0000, Casey Schaufler wrote:
> >> On 11/29/2023 7:07 PM, Munehisa Kamata wrote:
> >>> Hi Casey,
> >>>
> >>> On Wed, 2023-11-29 18:28:55 -0800, Casey Schaufler wrote:
> >>>> On 11/29/2023 4:37 PM, Munehisa Kamata wrote:
> >>>>> I'm not clear whether VFS is a better (or worse) place[1] to fix the
> >>>>> problem described below and would like to hear opinion.
> >>>> Please To: or at least Cc: me on all Smack related issues.
> >>> Will do that next.
> >>>
> >>>>> If the /proc/[pid] directory is bind-mounted on a system with Smack
> >>>>> enabled, and if the task updates its current security attribute, the task
> >>>>> may lose access to files in its own /proc/[pid] through the mountpoint.
> >>>>>
> >>>>>  $ sudo capsh --drop=cap_mac_override --
> >>>>>  # mkdir -p dir
> >>>>>  # mount --bind /proc/$$ dir
> >>>>>  # echo AAA > /proc/$$/task/current		# assuming built-in echo
> >>>> I don't see "current" in /proc/$$/task. Did you mean /proc/$$/attr?
> >>> Ahh, yes, I meant /proc/$$/attr/current. Sorry about that...
> >>>
> >>>>>  # cat /proc/$$/task/current			# revalidate
> >>>>>  AAA
> >>>>>  # echo BBB > dir/attr/current
> >>>>>  # cat dir/attr/current
> >>>>>  cat: dir/attr/current: Permission denied
> >>>>>  # ls dir/
> >>>>>  ls: cannot access dir/: Permission denied
> >> I don't see this behavior. What kernel version are you using?
> >> I have a 6.5 kernel.
> > I verified the behavior with 6.7-rc3. 
> >
> > Here is more "raw" log from my machine:
> >
> >  [ec2-user@ip-10-0-32-198 ~]$ uname -r
> >  6.7.0-rc3-proc-fix+
> >  [ec2-user@ip-10-0-32-198 ~]$ sudo capsh --drop=cap_mac_override --
> >  [root@ip-10-0-32-198 ec2-user]# mount --bind /proc/$$ dir
> >  [root@ip-10-0-32-198 ec2-user]# echo AAA > /proc/$$/attr/current
> >  [root@ip-10-0-32-198 ec2-user]# cat /proc/$$/attr/current; echo
> >  AAA
> >  [root@ip-10-0-32-198 ec2-user]# echo BBB > dir/attr/current
> >  [root@ip-10-0-32-198 ec2-user]# cat dir/attr/current
> >  cat: dir/attr/current: Permission denied
> >
> > If something frequently scans /proc, such as ps, top or whatever, on your
> > machine, the inode may get updated quickly (i.e. revalidated during path
> > lookup) and then you may only have a short window to observe the behavior. 
> 
> I was able to reproduce the issue with a 6.5 kernel. The window seems
> to be really short.

Creating a PID namespace before the bind-mount may make the window lasts
longer (or forever).

 $ sudo unshare -pf --mount-proc
 
> Would it be completely unreasonable for your sandboxing application to
> call syncfs(2) after writing to current?

It doesn't help. It won't revalidate dentries.

> >
> >>>>>  # cat /proc/$$/attr/current			# revalidate
> >>>>>  BBB
> >>>>>  # cat dir/attr/current
> >>>>>  BBB
> >>>>>  # echo CCC > /proc/$$/attr/current
> >>>>>  # cat dir/attr/current
> >>>>>  cat: dir/attr/current: Permission denied
> >>>>>
> >>>>> This happens because path lookup doesn't revalidate the dentry of the
> >>>>> /proc/[pid] when traversing the filesystem boundary, so the inode security
> >>>>> blob of the /proc/[pid] doesn't get updated with the new task security
> >>>>> attribute. Then, this may lead security modules to deny an access to the
> >>>>> directory. Looking at the code[2] and the /proc/pid/attr/current entry in
> >>>>> proc man page, seems like the same could happen with SELinux. Though, I
> >>>>> didn't find relevant reports.
> >>>>>
> >>>>> The steps above are quite artificial. I actually encountered such an
> >>>>> unexpected denial of access with an in-house application sandbox
> >>>>> framework; each app has its own dedicated filesystem tree where the
> >>>>> process's /proc/[pid] is bind-mounted to and the app enters into via
> >>>>> chroot.
> >>>>>
> >>>>> With this patch, writing to /proc/[pid]/attr/current (and its per-security
> >>>>> module variant) updates the inode security blob of /proc/[pid] or
> >>>>> /proc/[pid]/task/[tid] (when pid != tid) with the new attribute.
> >>>>>
> >>>>> [1] https://lkml.kernel.org/linux-fsdevel/4A2D15AF.8090000@sun.com/
> >>>>> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/security/selinux/hooks.c#n4220
> >>>>>
> >>>>> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> >>>>> Signed-off-by: Munehisa Kamata <kamatam@amazon.com>
> >>>>> ---
> >>>>>  fs/proc/base.c | 23 ++++++++++++++++++++---
> >>>>>  1 file changed, 20 insertions(+), 3 deletions(-)
> >>>>>
> >>>>> diff --git a/fs/proc/base.c b/fs/proc/base.c
> >>>>> index dd31e3b6bf77..bdb7bea53475 100644
> >>>>> --- a/fs/proc/base.c
> >>>>> +++ b/fs/proc/base.c
> >>>>> @@ -2741,6 +2741,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >>>>>  {
> >>>>>  	struct inode * inode = file_inode(file);
> >>>>>  	struct task_struct *task;
> >>>>> +	const char *name = file->f_path.dentry->d_name.name;
> >>>>>  	void *page;
> >>>>>  	int rv;
> >>>>>  
> >>>>> @@ -2784,10 +2785,26 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
> >>>>>  	if (rv < 0)
> >>>>>  		goto out_free;
> >>>>>  
> >>>>> -	rv = security_setprocattr(PROC_I(inode)->op.lsm,
> >>>>> -				  file->f_path.dentry->d_name.name, page,
> >>>>> -				  count);
> >>>>> +	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
> >>>>>  	mutex_unlock(&current->signal->cred_guard_mutex);
> >>>>> +
> >>>>> +	/*
> >>>>> +	 *  Update the inode security blob in advance if the task's security
> >>>>> +	 *  attribute was updated
> >>>>> +	 */
> >>>>> +	if (rv > 0 && !strcmp(name, "current")) {
> >>>>> +		struct pid *pid;
> >>>>> +		struct proc_inode *cur, *ei;
> >>>>> +
> >>>>> +		rcu_read_lock();
> >>>>> +		pid = get_task_pid(current, PIDTYPE_PID);
> >>>>> +		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
> >>>>> +			ei = cur;
> >>>>> +		put_pid(pid);
> >>>>> +		pid_update_inode(current, &ei->vfs_inode);
> >>>>> +		rcu_read_unlock();
> >>>>> +	}
> >>>>> +
> >>>>>  out_free:
> >>>>>  	kfree(page);
> >>>>>  out:
>
diff mbox series

Patch

diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd31e3b6bf77..bdb7bea53475 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2741,6 +2741,7 @@  static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 {
 	struct inode * inode = file_inode(file);
 	struct task_struct *task;
+	const char *name = file->f_path.dentry->d_name.name;
 	void *page;
 	int rv;
 
@@ -2784,10 +2785,26 @@  static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	if (rv < 0)
 		goto out_free;
 
-	rv = security_setprocattr(PROC_I(inode)->op.lsm,
-				  file->f_path.dentry->d_name.name, page,
-				  count);
+	rv = security_setprocattr(PROC_I(inode)->op.lsm, name, page, count);
 	mutex_unlock(&current->signal->cred_guard_mutex);
+
+	/*
+	 *  Update the inode security blob in advance if the task's security
+	 *  attribute was updated
+	 */
+	if (rv > 0 && !strcmp(name, "current")) {
+		struct pid *pid;
+		struct proc_inode *cur, *ei;
+
+		rcu_read_lock();
+		pid = get_task_pid(current, PIDTYPE_PID);
+		hlist_for_each_entry(cur, &pid->inodes, sibling_inodes)
+			ei = cur;
+		put_pid(pid);
+		pid_update_inode(current, &ei->vfs_inode);
+		rcu_read_unlock();
+	}
+
 out_free:
 	kfree(page);
 out: