[5/5] vfs: don't allow writes to swap files
diff mbox series

Message ID 156151641177.2283603.7806026378321236401.stgit@magnolia
State New
Headers show
Series
  • vfs: make immutable files actually immutable
Related show

Commit Message

Darrick J. Wong June 26, 2019, 2:33 a.m. UTC
From: Darrick J. Wong <darrick.wong@oracle.com>

Don't let userspace write to an active swap file because the kernel
effectively has a long term lease on the storage and things could get
seriously corrupted if we let this happen.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/attr.c     |    3 +++
 mm/filemap.c  |    3 +++
 mm/memory.c   |    4 +++-
 mm/mmap.c     |    2 ++
 mm/swapfile.c |   15 +++++++++++++--
 5 files changed, 24 insertions(+), 3 deletions(-)

Comments

Al Viro June 26, 2019, 3:51 a.m. UTC | #1
On Tue, Jun 25, 2019 at 07:33:31PM -0700, Darrick J. Wong wrote:
> --- a/fs/attr.c
> +++ b/fs/attr.c
> @@ -236,6 +236,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
>  	if (IS_IMMUTABLE(inode))
>  		return -EPERM;
>  
> +	if (IS_SWAPFILE(inode))
> +		return -ETXTBSY;
> +
>  	if ((ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) &&
>  	    IS_APPEND(inode))
>  		return -EPERM;

Er...  So why exactly is e.g. chmod(2) forbidden for swapfiles?  Or touch(1),
for that matter...

> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 596ac98051c5..1ca4ee8c2d60 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -3165,6 +3165,19 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>  	if (error)
>  		goto bad_swap;
>  
> +	/*
> +	 * Flush any pending IO and dirty mappings before we start using this
> +	 * swap file.
> +	 */
> +	if (S_ISREG(inode->i_mode)) {
> +		inode->i_flags |= S_SWAPFILE;
> +		error = inode_drain_writes(inode);
> +		if (error) {
> +			inode->i_flags &= ~S_SWAPFILE;
> +			goto bad_swap;
> +		}
> +	}

Why are swap partitions any less worthy of protection?
Darrick J. Wong June 26, 2019, 4:28 p.m. UTC | #2
On Wed, Jun 26, 2019 at 04:51:51AM +0100, Al Viro wrote:
> On Tue, Jun 25, 2019 at 07:33:31PM -0700, Darrick J. Wong wrote:
> > --- a/fs/attr.c
> > +++ b/fs/attr.c
> > @@ -236,6 +236,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
> >  	if (IS_IMMUTABLE(inode))
> >  		return -EPERM;
> >  
> > +	if (IS_SWAPFILE(inode))
> > +		return -ETXTBSY;
> > +
> >  	if ((ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) &&
> >  	    IS_APPEND(inode))
> >  		return -EPERM;
> 
> Er...  So why exactly is e.g. chmod(2) forbidden for swapfiles?  Or touch(1),
> for that matter...

Oops, that check is overly broad; I think the only attribute change we
need to filter here is ATTR_SIZE.... which we could do unconditionally
in inode_newsize_ok.

What's the use case for allowing userspace to increase the size of an
active swapfile?  I don't see any; the kernel has a permanent lease on
the file space mapping (at least until swapoff)...

> > diff --git a/mm/swapfile.c b/mm/swapfile.c
> > index 596ac98051c5..1ca4ee8c2d60 100644
> > --- a/mm/swapfile.c
> > +++ b/mm/swapfile.c
> > @@ -3165,6 +3165,19 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
> >  	if (error)
> >  		goto bad_swap;
> >  
> > +	/*
> > +	 * Flush any pending IO and dirty mappings before we start using this
> > +	 * swap file.
> > +	 */
> > +	if (S_ISREG(inode->i_mode)) {
> > +		inode->i_flags |= S_SWAPFILE;
> > +		error = inode_drain_writes(inode);
> > +		if (error) {
> > +			inode->i_flags &= ~S_SWAPFILE;
> > +			goto bad_swap;
> > +		}
> > +	}
> 
> Why are swap partitions any less worthy of protection?

Hmm, yeah, S_SWAPFILE should apply to block devices too.  I figured that
the mantra of "sane tools will open block devices with O_EXCL" should
have sufficed, but there's really no reason to allow that either.

--D

Patch
diff mbox series

diff --git a/fs/attr.c b/fs/attr.c
index 1fcfdcc5b367..42f4d4fb0631 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -236,6 +236,9 @@  int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
 	if (IS_IMMUTABLE(inode))
 		return -EPERM;
 
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
 	if ((ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) &&
 	    IS_APPEND(inode))
 		return -EPERM;
diff --git a/mm/filemap.c b/mm/filemap.c
index dad85e10f5f8..fd80bc20e30a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2938,6 +2938,9 @@  inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	if (IS_IMMUTABLE(inode))
 		return -EPERM;
 
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
 	if (!iov_iter_count(from))
 		return 0;
 
diff --git a/mm/memory.c b/mm/memory.c
index 4311cfdade90..c04c6a689995 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2235,7 +2235,9 @@  static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
 
 	vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 
-	if (vmf->vma->vm_file && IS_IMMUTABLE(file_inode(vmf->vma->vm_file)))
+	if (vmf->vma->vm_file &&
+	    (IS_IMMUTABLE(file_inode(vmf->vma->vm_file)) ||
+	     IS_SWAPFILE(file_inode(vmf->vma->vm_file))))
 		return VM_FAULT_SIGBUS;
 
 	ret = vmf->vma->vm_ops->page_mkwrite(vmf);
diff --git a/mm/mmap.c b/mm/mmap.c
index ac1e32205237..031807339869 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1488,6 +1488,8 @@  unsigned long do_mmap(struct file *file, unsigned long addr,
 					return -EACCES;
 				if (IS_IMMUTABLE(file_inode(file)))
 					return -EPERM;
+				if (IS_SWAPFILE(file_inode(file)))
+					return -ETXTBSY;
 			}
 
 			/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 596ac98051c5..1ca4ee8c2d60 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3165,6 +3165,19 @@  SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (error)
 		goto bad_swap;
 
+	/*
+	 * Flush any pending IO and dirty mappings before we start using this
+	 * swap file.
+	 */
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_flags |= S_SWAPFILE;
+		error = inode_drain_writes(inode);
+		if (error) {
+			inode->i_flags &= ~S_SWAPFILE;
+			goto bad_swap;
+		}
+	}
+
 	mutex_lock(&swapon_mutex);
 	prio = -1;
 	if (swap_flags & SWAP_FLAG_PREFER)
@@ -3185,8 +3198,6 @@  SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	atomic_inc(&proc_poll_event);
 	wake_up_interruptible(&proc_poll_wait);
 
-	if (S_ISREG(inode->i_mode))
-		inode->i_flags |= S_SWAPFILE;
 	error = 0;
 	goto out;
 bad_swap: