Changes for 5.4:

- Prohibit writing to active swap files and swap partitions.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAl1cDHQACgkQ+H93GTRK
 tOs1qw//aqXAQ7bpLDl7jx9CSuAighzKir0mHYFm9HUsnuRT6gLqIOVSeugoi8hY
 tYhPNzcKHL39YDa1QfKo1RKW6uCwsECHT/5TebLxBkTL3vGGAenPchAcjj89SV54
 lQ/h8O6hkDU+KCKC0kmDem7ma7DD5YZmWXDxW/HvnygjCnZ9BFaOeLQt/TPBmOmN
 lozPHcdrxhIuCuSTMjIZRq27Zl6uzj5tr+FkT+FWiYDrGhgWT7is6o397SEm7yYT
 3JqUQ+ZUOY4IwLlrWiVKqi0IqjvWqhaLzmjZaKF+YC8Ni0sdpaDdsE/uPSCyQ7k7
 28qbfypnu7bswakjcekdSX2Dj/SZivFb8AzlqaSIMVlw4STFzjMMYMLib8/OlPES
 z1pAjXHypLjNO3dNBYp/mRll+/BQ2NM6oCtnVVQGKVnlcx3oLo+n6JSRK8t74DTf
 BkYu93aybBpfE49Fb3VQum+9okg9BdShRxvUp023/WTUaa8aUyIbizn3iTrke/sx
 0bC+Vvdr33JZnoO8WKVzSd7COTHOTQ920NodTKAJ9bkF3WKyLM135ctavHrtdAg3
 FHBXpN7AjbOaLovLpiy3eb//ghKJwgyhqbN6VCGTudC/nkaXq7y7M3DPbXxQYxom
 yCA0qMByMg+cL4BtzS52QEda7xK1iiuQ/3jbdQ4lFuBHhwekVKs=
 =Ag/B
 -----END PGP SIGNATURE-----

Merge tag 'vfs-5.4-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull swap access updates from Darrick Wong:
 "Prohibit writing to active swap files and swap partitions.

  There's no non-malicious use case for allowing userspace to scribble
  on storage that the kernel thinks it owns"

* tag 'vfs-5.4-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  vfs: don't allow writes to swap files
  mm: set S_SWAPFILE on blockdev swap devices

fs/block_dev.c

@@ -1972,6 +1972,9 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (bdev_read_only(I_BDEV(bd_inode)))
 		return -EPERM;
 
+	if (IS_SWAPFILE(bd_inode))
+		return -ETXTBSY;
+
 	if (!iov_iter_count(from))
 		return 0;
 

include/linux/fs.h

@@ -3565,4 +3565,15 @@ static inline void simple_fill_fsxattr(struct fsxattr *fa, __u32 xflags)
 	fa->fsx_xflags = xflags;
 }
 
+/*
+ * Flush file data before changing attributes.  Caller must hold any locks
+ * required to prevent further writes to this file until we're done setting
+ * flags.
+ */
+static inline int inode_drain_writes(struct inode *inode)
+{
+	inode_dio_wait(inode);
+	return filemap_write_and_wait(inode->i_mapping);
+}
+
 #endif /* _LINUX_FS_H */

mm/filemap.c

@@ -2988,6 +2988,9 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	loff_t count;
 	int ret;
 
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
 	if (!iov_iter_count(from))
 		return 0;
 

mm/memory.c

@@ -2196,6 +2196,10 @@ 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_SWAPFILE(vmf->vma->vm_file->f_mapping->host))
+		return VM_FAULT_SIGBUS;
+
 	ret = vmf->vma->vm_ops->page_mkwrite(vmf);
 	/* Restore original flags so that caller is not surprised */
 	vmf->flags = old_flags;

mm/mmap.c

@@ -1483,8 +1483,12 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		case MAP_SHARED_VALIDATE:
 			if (flags & ~flags_mask)
 				return -EOPNOTSUPP;
-			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
+			if (prot & PROT_WRITE) {
+				if (!(file->f_mode & FMODE_WRITE))
 					return -EACCES;
+				if (IS_SWAPFILE(file->f_mapping->host))
+					return -ETXTBSY;
+			}
 
 			/*
 			 * Make sure we don't allow writing to an append-only

mm/swapfile.c

@@ -2368,9 +2368,8 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
  * requirements, they are simply tossed out - we will never use those blocks
  * for swapping.
  *
- * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This
- * prevents root from shooting her foot off by ftruncating an in-use swapfile,
- * which will scribble on the fs.
+ * For all swap devices we set S_SWAPFILE across the life of the swapon.  This
+ * prevents users from writing to the swap device, which will corrupt memory.
  *
  * The amount of disk space which a single swap extent represents varies.
  * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
@@ -2661,13 +2660,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
+
 		set_blocksize(bdev, old_block_size);
 		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
-	} else {
+	}
+
 	inode_lock(inode);
 	inode->i_flags &= ~S_SWAPFILE;
 	inode_unlock(inode);
-	}
 	filp_close(swap_file, NULL);
 
 	/*
@@ -2890,11 +2890,11 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		p->flags |= SWP_BLKDEV;
 	} else if (S_ISREG(inode->i_mode)) {
 		p->bdev = inode->i_sb->s_bdev;
+	}
+
 	inode_lock(inode);
 	if (IS_SWAPFILE(inode))
 		return -EBUSY;
-	} else
-		return -EINVAL;
 
 	return 0;
 }
@@ -3275,6 +3275,17 @@ 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 device.
+	 */
+	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)
@@ -3295,8 +3306,6 @@ 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:
@@ -3318,7 +3327,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (inced_nr_rotate_swap)
 		atomic_dec(&nr_rotate_swap);
 	if (swap_file) {
-		if (inode && S_ISREG(inode->i_mode)) {
+		if (inode) {
 			inode_unlock(inode);
 			inode = NULL;
 		}
@@ -3331,7 +3340,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 	if (name)
 		putname(name);
-	if (inode && S_ISREG(inode->i_mode))
+	if (inode)
 		inode_unlock(inode);
 	if (!error)
 		enable_swap_slots_cache();