From ffa629fc6a83a6f0ec102a755b8cbfccc04c8fe8 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Thu, 2 Sep 2021 14:53:57 -0700
Subject: [PATCH] fs, mm: fix race in unlinking swapfile

References: git fixes (mm)
Patch-mainline: v5.15-rc1
Git-commit: 51cc3a6620a6ca934d468bda345678768493f5d8

We had a recurring situation in which admin procedures setting up
swapfiles would race with test preparation clearing away swapfiles; and
just occasionally that got stuck on a swapfile "(deleted)" which could
never be swapped off.  That is not supposed to be possible.

2.6.28 commit f9454548e17c ("don't unlink an active swapfile") admitted
that it was leaving a race window open: now close it.

may_delete() makes the IS_SWAPFILE check (amongst many others) before
inode_lock has been taken on target: now repeat just that simple check in
vfs_unlink() and vfs_rename(), after taking inode_lock.

Which goes most of the way to fixing the race, but swapon() must also
check after it acquires inode_lock, that the file just opened has not
already been unlinked.

Link: https://lkml.kernel.org/r/e17b91ad-a578-9a15-5e3-4989e0f999b5@google.com
Fixes: f9454548e17c ("don't unlink an active swapfile")
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/namei.c    | 8 +++++++-
 mm/swapfile.c | 6 ++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/fs/namei.c b/fs/namei.c
index bf6d8a738c59..ff866c07f4d2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4024,7 +4024,9 @@ int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir,
 		return -EPERM;
 
 	inode_lock(target);
-	if (is_local_mountpoint(dentry))
+	if (IS_SWAPFILE(target))
+		error = -EPERM;
+	else if (is_local_mountpoint(dentry))
 		error = -EBUSY;
 	else {
 		error = security_inode_unlink(dir, dentry);
@@ -4526,6 +4528,10 @@ int vfs_rename(struct renamedata *rd)
 	else if (target)
 		inode_lock(target);
 
+	error = -EPERM;
+	if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target)))
+		goto out;
+
 	error = -EBUSY;
 	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
 		goto out;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1e07d1c776f2..7527afd95284 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3130,6 +3130,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	struct filename *name;
 	struct file *swap_file = NULL;
 	struct address_space *mapping;
+	struct dentry *dentry;
 	int prio;
 	int error;
 	union swap_header *swap_header;
@@ -3173,6 +3174,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	p->swap_file = swap_file;
 	mapping = swap_file->f_mapping;
+	dentry = swap_file->f_path.dentry;
 	inode = mapping->host;
 
 	error = claim_swapfile(p, inode);
@@ -3180,6 +3182,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap;
 
 	inode_lock(inode);
+	if (d_unlinked(dentry) || cant_mount(dentry)) {
+		error = -ENOENT;
+		goto bad_swap_unlock_inode;
+	}
 	if (IS_SWAPFILE(inode)) {
 		error = -EBUSY;
 		goto bad_swap_unlock_inode;