1 files changed, 40 insertions, 24 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0789a762ce2f..2c33ff456ed5 100644
--- a/mm/swapfile.c
+++ b/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);
 	}
+
+	inode_lock(inode);
+	inode->i_flags &= ~S_SWAPFILE;
+	inode_unlock(inode);
 	filp_close(swap_file, NULL);
 
 	/*
@@ -2737,10 +2737,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
 	else
 		type = si->type + 1;
 
+	++(*pos);
 	for (; (si = swap_type_to_swap_info(type)); type++) {
 		if (!(si->flags & SWP_USED) || !si->swap_map)
 			continue;
-		++*pos;
 		return si;
 	}
 
@@ -2796,17 +2796,17 @@ static int swaps_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations proc_swaps_operations = {
-	.open		= swaps_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-	.poll		= swaps_poll,
+static const struct proc_ops swaps_proc_ops = {
+	.proc_open	= swaps_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
+	.proc_poll	= swaps_poll,
 };
 
 static int __init procswaps_init(void)
 {
-	proc_create("swaps", 0, NULL, &proc_swaps_operations);
+	proc_create("swaps", 0, NULL, &swaps_proc_ops);
 	return 0;
 }
 __initcall(procswaps_init);
@@ -2887,14 +2887,21 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		error = set_blocksize(p->bdev, PAGE_SIZE);
 		if (error < 0)
 			return error;
+		/*
+		 * Zoned block devices contain zones that have a sequential
+		 * write only restriction.  Hence zoned block devices are not
+		 * suitable for swapping.  Disallow them here.
+		 */
+		if (blk_queue_is_zoned(p->bdev->bd_queue))
+			return -EINVAL;
 		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;
+	}
+
+	inode_lock(inode);
+	if (IS_SWAPFILE(inode))
+		return -EBUSY;
 
 	return 0;
 }
@@ -3275,6 +3282,17 @@ 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 +3313,6 @@ 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 +3334,7 @@ bad_swap:
 	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 +3347,7 @@ out:
 	}
 	if (name)
 		putname(name);
-	if (inode && S_ISREG(inode->i_mode))
+	if (inode)
 		inode_unlock(inode);
 	if (!error)
 		enable_swap_slots_cache();