summaryrefslogtreecommitdiff
path: root/fs/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/super.c')
-rw-r--r--fs/super.c77
1 files changed, 56 insertions, 21 deletions
diff --git a/fs/super.c b/fs/super.c
index d6efeba0d0ce..5a7db4a556e3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -274,6 +274,7 @@ static void destroy_super_work(struct work_struct *work)
{
struct super_block *s = container_of(work, struct super_block,
destroy_work);
+ fsnotify_sb_free(s);
security_sb_free(s);
put_user_ns(s->s_user_ns);
kfree(s->s_subtype);
@@ -620,7 +621,7 @@ void generic_shutdown_super(struct super_block *sb)
sync_filesystem(sb);
sb->s_flags &= ~SB_ACTIVE;
- cgroup_writeback_umount();
+ cgroup_writeback_umount(sb);
/* Evict all inodes with zero refcount. */
evict_inodes(sb);
@@ -646,7 +647,7 @@ void generic_shutdown_super(struct super_block *sb)
*/
fscrypt_destroy_keyring(sb);
- if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes),
+ if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL,
"VFS: Busy inodes after unmount of %s (%s)",
sb->s_id, sb->s_type->name)) {
/*
@@ -735,6 +736,17 @@ struct super_block *sget_fc(struct fs_context *fc,
struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns;
int err;
+ /*
+ * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is
+ * not set, as the filesystem is likely unprepared to handle it.
+ * This can happen when fsconfig() is called from init_user_ns with
+ * an fs_fd opened in another user namespace.
+ */
+ if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) {
+ errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed");
+ return ERR_PTR(-EPERM);
+ }
+
retry:
spin_lock(&sb_lock);
if (test) {
@@ -1501,8 +1513,17 @@ static int fs_bdev_thaw(struct block_device *bdev)
lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+ /*
+ * The block device may have been frozen before it was claimed by a
+ * filesystem. Concurrently another process might try to mount that
+ * frozen block device and has temporarily claimed the block device for
+ * that purpose causing a concurrent fs_bdev_thaw() to end up here. The
+ * mounter is already about to abort mounting because they still saw an
+ * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
+ * NULL in that case.
+ */
sb = get_bdev_super(bdev);
- if (WARN_ON_ONCE(!sb))
+ if (!sb)
return -EINVAL;
if (sb->s_op->thaw_super)
@@ -1527,16 +1548,16 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
struct fs_context *fc)
{
blk_mode_t mode = sb_open_mode(sb_flags);
- struct bdev_handle *bdev_handle;
+ struct file *bdev_file;
struct block_device *bdev;
- bdev_handle = bdev_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
- if (IS_ERR(bdev_handle)) {
+ bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
+ if (IS_ERR(bdev_file)) {
if (fc)
errorf(fc, "%s: Can't open blockdev", fc->source);
- return PTR_ERR(bdev_handle);
+ return PTR_ERR(bdev_file);
}
- bdev = bdev_handle->bdev;
+ bdev = file_bdev(bdev_file);
/*
* This really should be in blkdev_get_by_dev, but right now can't due
@@ -1544,7 +1565,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
* writable from userspace even for a read-only block device.
*/
if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
- bdev_release(bdev_handle);
+ bdev_fput(bdev_file);
return -EACCES;
}
@@ -1555,11 +1576,11 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
if (fc)
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
- bdev_release(bdev_handle);
+ bdev_fput(bdev_file);
return -EBUSY;
}
spin_lock(&sb_lock);
- sb->s_bdev_handle = bdev_handle;
+ sb->s_bdev_file = bdev_file;
sb->s_bdev = bdev;
sb->s_bdi = bdi_get(bdev->bd_disk->bdi);
if (bdev_stable_writes(bdev))
@@ -1575,13 +1596,14 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
EXPORT_SYMBOL_GPL(setup_bdev_super);
/**
- * get_tree_bdev - Get a superblock based on a single block device
+ * get_tree_bdev_flags - Get a superblock based on a single block device
* @fc: The filesystem context holding the parameters
* @fill_super: Helper to initialise a new superblock
+ * @flags: GET_TREE_BDEV_* flags
*/
-int get_tree_bdev(struct fs_context *fc,
- int (*fill_super)(struct super_block *,
- struct fs_context *))
+int get_tree_bdev_flags(struct fs_context *fc,
+ int (*fill_super)(struct super_block *sb,
+ struct fs_context *fc), unsigned int flags)
{
struct super_block *s;
int error = 0;
@@ -1592,10 +1614,10 @@ int get_tree_bdev(struct fs_context *fc,
error = lookup_bdev(fc->source, &dev);
if (error) {
- errorf(fc, "%s: Can't lookup blockdev", fc->source);
+ if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP))
+ errorf(fc, "%s: Can't lookup blockdev", fc->source);
return error;
}
-
fc->sb_flags |= SB_NOSEC;
s = sget_dev(fc, dev);
if (IS_ERR(s))
@@ -1623,6 +1645,19 @@ int get_tree_bdev(struct fs_context *fc,
fc->root = dget(s->s_root);
return 0;
}
+EXPORT_SYMBOL_GPL(get_tree_bdev_flags);
+
+/**
+ * get_tree_bdev - Get a superblock based on a single block device
+ * @fc: The filesystem context holding the parameters
+ * @fill_super: Helper to initialise a new superblock
+ */
+int get_tree_bdev(struct fs_context *fc,
+ int (*fill_super)(struct super_block *,
+ struct fs_context *))
+{
+ return get_tree_bdev_flags(fc, fill_super, 0);
+}
EXPORT_SYMBOL(get_tree_bdev);
static int test_bdev_super(struct super_block *s, void *data)
@@ -1675,7 +1710,7 @@ void kill_block_super(struct super_block *sb)
generic_shutdown_super(sb);
if (bdev) {
sync_blockdev(bdev);
- bdev_release(sb->s_bdev_handle);
+ bdev_fput(sb->s_bdev_file);
}
}
@@ -1781,8 +1816,8 @@ int vfs_get_tree(struct fs_context *fc)
return error;
if (!fc->root) {
- pr_err("Filesystem %s get_tree() didn't set fc->root\n",
- fc->fs_type->name);
+ pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n",
+ fc->fs_type->name, error);
/* We don't know what the locking state of the superblock is -
* if there is a superblock.
*/
@@ -1884,7 +1919,7 @@ static void lockdep_sb_freeze_release(struct super_block *sb)
int level;
for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
- percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
+ percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_);
}
/*
generated by cgit (git 2.34.1) at 2025-07-25 18:10:19 +0000