summaryrefslogtreecommitdiffstats
path: root/fs/namespace.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/namespace.c')
-rw-r--r--fs/namespace.c126
1 files changed, 95 insertions, 31 deletions
diff --git a/fs/namespace.c b/fs/namespace.c
index ce82a5b2da12..54059b142d6b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -275,7 +275,7 @@ int __mnt_is_readonly(struct vfsmount *mnt)
{
if (mnt->mnt_flags & MNT_READONLY)
return 1;
- if (mnt->mnt_sb->s_flags & MS_RDONLY)
+ if (sb_rdonly(mnt->mnt_sb))
return 1;
return 0;
}
@@ -431,13 +431,18 @@ int __mnt_want_write_file(struct file *file)
}
/**
- * mnt_want_write_file - get write access to a file's mount
+ * mnt_want_write_file_path - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
* This is like mnt_want_write, but it takes a file and can
* do some optimisations if the file is open for write already
+ *
+ * Called by the vfs for cases when we have an open file at hand, but will do an
+ * inode operation on it (important distinction for files opened on overlayfs,
+ * since the file operations will come from the real underlying file, while
+ * inode operations come from the overlay).
*/
-int mnt_want_write_file(struct file *file)
+int mnt_want_write_file_path(struct file *file)
{
int ret;
@@ -447,6 +452,53 @@ int mnt_want_write_file(struct file *file)
sb_end_write(file->f_path.mnt->mnt_sb);
return ret;
}
+
+static inline int may_write_real(struct file *file)
+{
+ struct dentry *dentry = file->f_path.dentry;
+ struct dentry *upperdentry;
+
+ /* Writable file? */
+ if (file->f_mode & FMODE_WRITER)
+ return 0;
+
+ /* Not overlayfs? */
+ if (likely(!(dentry->d_flags & DCACHE_OP_REAL)))
+ return 0;
+
+ /* File refers to upper, writable layer? */
+ upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER);
+ if (upperdentry && file_inode(file) == d_inode(upperdentry))
+ return 0;
+
+ /* Lower layer: can't write to real file, sorry... */
+ return -EPERM;
+}
+
+/**
+ * mnt_want_write_file - get write access to a file's mount
+ * @file: the file who's mount on which to take a write
+ *
+ * This is like mnt_want_write, but it takes a file and can
+ * do some optimisations if the file is open for write already
+ *
+ * Mostly called by filesystems from their ioctl operation before performing
+ * modification. On overlayfs this needs to check if the file is on a read-only
+ * lower layer and deny access in that case.
+ */
+int mnt_want_write_file(struct file *file)
+{
+ int ret;
+
+ ret = may_write_real(file);
+ if (!ret) {
+ sb_start_write(file_inode(file)->i_sb);
+ ret = __mnt_want_write_file(file);
+ if (ret)
+ sb_end_write(file_inode(file)->i_sb);
+ }
+ return ret;
+}
EXPORT_SYMBOL_GPL(mnt_want_write_file);
/**
@@ -484,10 +536,16 @@ void __mnt_drop_write_file(struct file *file)
__mnt_drop_write(file->f_path.mnt);
}
-void mnt_drop_write_file(struct file *file)
+void mnt_drop_write_file_path(struct file *file)
{
mnt_drop_write(file->f_path.mnt);
}
+
+void mnt_drop_write_file(struct file *file)
+{
+ __mnt_drop_write(file->f_path.mnt);
+ sb_end_write(file_inode(file)->i_sb);
+}
EXPORT_SYMBOL(mnt_drop_write_file);
static int mnt_make_readonly(struct mount *mnt)
@@ -971,7 +1029,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
if (!mnt)
return ERR_PTR(-ENOMEM);
- if (flags & MS_KERNMOUNT)
+ if (flags & SB_KERNMOUNT)
mnt->mnt.mnt_flags = MNT_INTERNAL;
root = mount_fs(type, flags, name, data);
@@ -1003,7 +1061,7 @@ vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
if (mountpoint->d_sb->s_user_ns != &init_user_ns)
return ERR_PTR(-EPERM);
- return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+ return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
}
EXPORT_SYMBOL_GPL(vfs_submount);
@@ -1532,8 +1590,8 @@ static int do_umount(struct mount *mnt, int flags)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
down_write(&sb->s_umount);
- if (!(sb->s_flags & MS_RDONLY))
- retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
+ if (!sb_rdonly(sb))
+ retval = do_remount_sb(sb, SB_RDONLY, NULL, 0);
up_write(&sb->s_umount);
return retval;
}
@@ -2057,7 +2115,7 @@ static void unlock_mount(struct mountpoint *where)
static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
{
- if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER)
+ if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER)
return -EINVAL;
if (d_is_dir(mp->m_dentry) !=
@@ -2071,9 +2129,9 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
* Sanity check the flags to change_mnt_propagation.
*/
-static int flags_to_propagation_type(int flags)
+static int flags_to_propagation_type(int ms_flags)
{
- int type = flags & ~(MS_REC | MS_SILENT);
+ int type = ms_flags & ~(MS_REC | MS_SILENT);
/* Fail if any non-propagation flags are set */
if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
@@ -2087,18 +2145,18 @@ static int flags_to_propagation_type(int flags)
/*
* recursively change the type of the mountpoint.
*/
-static int do_change_type(struct path *path, int flag)
+static int do_change_type(struct path *path, int ms_flags)
{
struct mount *m;
struct mount *mnt = real_mount(path->mnt);
- int recurse = flag & MS_REC;
+ int recurse = ms_flags & MS_REC;
int type;
int err = 0;
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
- type = flags_to_propagation_type(flag);
+ type = flags_to_propagation_type(ms_flags);
if (!type)
return -EINVAL;
@@ -2220,8 +2278,8 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
* If you've mounted a non-root directory somewhere and want to do remount
* on it - tough luck.
*/
-static int do_remount(struct path *path, int flags, int mnt_flags,
- void *data)
+static int do_remount(struct path *path, int ms_flags, int sb_flags,
+ int mnt_flags, void *data)
{
int err;
struct super_block *sb = path->mnt->mnt_sb;
@@ -2265,12 +2323,12 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
return err;
down_write(&sb->s_umount);
- if (flags & MS_BIND)
- err = change_mount_flags(path->mnt, flags);
+ if (ms_flags & MS_BIND)
+ err = change_mount_flags(path->mnt, ms_flags);
else if (!capable(CAP_SYS_ADMIN))
err = -EPERM;
else
- err = do_remount_sb(sb, flags, data, 0);
+ err = do_remount_sb(sb, sb_flags, data, 0);
if (!err) {
lock_mount_hash();
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
@@ -2435,7 +2493,7 @@ static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);
* create a new mount for userspace and request it to be added into the
* namespace's tree
*/
-static int do_new_mount(struct path *path, const char *fstype, int flags,
+static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
int mnt_flags, const char *name, void *data)
{
struct file_system_type *type;
@@ -2449,7 +2507,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
if (!type)
return -ENODEV;
- mnt = vfs_kern_mount(type, flags, name, data);
+ mnt = vfs_kern_mount(type, sb_flags, name, data);
if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
!mnt->mnt_sb->s_subtype)
mnt = fs_set_subtype(mnt, fstype);
@@ -2704,8 +2762,8 @@ long do_mount(const char *dev_name, const char __user *dir_name,
const char *type_page, unsigned long flags, void *data_page)
{
struct path path;
+ unsigned int mnt_flags = 0, sb_flags;
int retval = 0;
- int mnt_flags = 0;
/* Discard magic */
if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
@@ -2715,6 +2773,9 @@ long do_mount(const char *dev_name, const char __user *dir_name,
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
+ if (flags & MS_NOUSER)
+ return -EINVAL;
+
/* ... and get the mountpoint */
retval = user_path(dir_name, &path);
if (retval)
@@ -2724,7 +2785,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
type_page, flags, data_page);
if (!retval && !may_mount())
retval = -EPERM;
- if (!retval && (flags & MS_MANDLOCK) && !may_mandlock())
+ if (!retval && (flags & SB_MANDLOCK) && !may_mandlock())
retval = -EPERM;
if (retval)
goto dput_out;
@@ -2746,7 +2807,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
mnt_flags |= MNT_NODIRATIME;
if (flags & MS_STRICTATIME)
mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
- if (flags & MS_RDONLY)
+ if (flags & SB_RDONLY)
mnt_flags |= MNT_READONLY;
/* The default atime for remount is preservation */
@@ -2757,12 +2818,15 @@ long do_mount(const char *dev_name, const char __user *dir_name,
mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
}
- flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
- MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
- MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
+ sb_flags = flags & (SB_RDONLY |
+ SB_SYNCHRONOUS |
+ SB_MANDLOCK |
+ SB_DIRSYNC |
+ SB_SILENT |
+ SB_POSIXACL);
if (flags & MS_REMOUNT)
- retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
+ retval = do_remount(&path, flags, sb_flags, mnt_flags,
data_page);
else if (flags & MS_BIND)
retval = do_loopback(&path, dev_name, flags & MS_REC);
@@ -2771,7 +2835,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
else if (flags & MS_MOVE)
retval = do_move_mount(&path, dev_name);
else
- retval = do_new_mount(&path, type_page, flags, mnt_flags,
+ retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
dev_name, data_page);
dput_out:
path_put(&path);
@@ -3221,7 +3285,7 @@ void put_mnt_ns(struct mnt_namespace *ns)
struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
{
struct vfsmount *mnt;
- mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
+ mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, data);
if (!IS_ERR(mnt)) {
/*
* it is a longterm mount, don't release mnt until
@@ -3298,7 +3362,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns, struct vfsmount *new,
mnt_flags = mnt->mnt.mnt_flags;
/* Don't miss readonly hidden in the superblock flags */
- if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY)
+ if (sb_rdonly(mnt->mnt.mnt_sb))
mnt_flags |= MNT_LOCK_READONLY;
/* Verify the mount flags are equal to or more permissive
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 16:14:21 +0100