vfs: add fileattr ops

There's a substantial amount of boilerplate in filesystems handling
FS_IOC_[GS]ETFLAGS/ FS_IOC_FS[GS]ETXATTR ioctls.

Also due to userspace buffers being involved in the ioctl API this is
difficult to stack, as shown by overlayfs issues related to these ioctls.

Introduce a new internal API named "fileattr" (fsxattr can be confused with
xattr, xflags is inappropriate, since this is more than just flags).

There's significant overlap between flags and xflags and this API handles
the conversions automatically, so filesystems may choose which one to use.

In ->fileattr_get() a hint is provided to the filesystem whether flags or
xattr are being requested by userspace, but in this series this hint is
ignored by all filesystems, since generating all the attributes is cheap.

If a filesystem doesn't implemement the fileattr API, just fall back to
f_op->ioctl().  When all filesystems are converted, the fallback can be
removed.

32bit compat ioctls are now handled by the generic code as well.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

1 files changed, 325 insertions, 0 deletions

diff --git a/fs/ioctl.c b/fs/ioctl.c
index 4e6cc0a7d69c..1e2204fa9963 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -19,6 +19,9 @@
 #include <linux/falloc.h>
 #include <linux/sched/signal.h>
 #include <linux/fiemap.h>
+#include <linux/mount.h>
+#include <linux/fscrypt.h>
+#include <linux/fileattr.h>
 
 #include "internal.h"
 
@@ -657,6 +660,307 @@ out:
 	return ret;
 }
 
+/**
+ * fileattr_fill_xflags - initialize fileattr with xflags
+ * @fa:		fileattr pointer
+ * @xflags:	FS_XFLAG_* flags
+ *
+ * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags).  All
+ * other fields are zeroed.
+ */
+void fileattr_fill_xflags(struct fileattr *fa, u32 xflags)
+{
+	memset(fa, 0, sizeof(*fa));
+	fa->fsx_valid = true;
+	fa->fsx_xflags = xflags;
+	if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE)
+		fa->flags |= FS_IMMUTABLE_FL;
+	if (fa->fsx_xflags & FS_XFLAG_APPEND)
+		fa->flags |= FS_APPEND_FL;
+	if (fa->fsx_xflags & FS_XFLAG_SYNC)
+		fa->flags |= FS_SYNC_FL;
+	if (fa->fsx_xflags & FS_XFLAG_NOATIME)
+		fa->flags |= FS_NOATIME_FL;
+	if (fa->fsx_xflags & FS_XFLAG_NODUMP)
+		fa->flags |= FS_NODUMP_FL;
+	if (fa->fsx_xflags & FS_XFLAG_DAX)
+		fa->flags |= FS_DAX_FL;
+	if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
+		fa->flags |= FS_PROJINHERIT_FL;
+}
+EXPORT_SYMBOL(fileattr_fill_xflags);
+
+/**
+ * fileattr_fill_flags - initialize fileattr with flags
+ * @fa:		fileattr pointer
+ * @flags:	FS_*_FL flags
+ *
+ * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags).
+ * All other fields are zeroed.
+ */
+void fileattr_fill_flags(struct fileattr *fa, u32 flags)
+{
+	memset(fa, 0, sizeof(*fa));
+	fa->flags_valid = true;
+	fa->flags = flags;
+	if (fa->flags & FS_SYNC_FL)
+		fa->fsx_xflags |= FS_XFLAG_SYNC;
+	if (fa->flags & FS_IMMUTABLE_FL)
+		fa->fsx_xflags |= FS_XFLAG_IMMUTABLE;
+	if (fa->flags & FS_APPEND_FL)
+		fa->fsx_xflags |= FS_XFLAG_APPEND;
+	if (fa->flags & FS_NODUMP_FL)
+		fa->fsx_xflags |= FS_XFLAG_NODUMP;
+	if (fa->flags & FS_NOATIME_FL)
+		fa->fsx_xflags |= FS_XFLAG_NOATIME;
+	if (fa->flags & FS_DAX_FL)
+		fa->fsx_xflags |= FS_XFLAG_DAX;
+	if (fa->flags & FS_PROJINHERIT_FL)
+		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+}
+EXPORT_SYMBOL(fileattr_fill_flags);
+
+/**
+ * vfs_fileattr_get - retrieve miscellaneous file attributes
+ * @dentry:	the object to retrieve from
+ * @fa:		fileattr pointer
+ *
+ * Call i_op->fileattr_get() callback, if exists.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (!inode->i_op->fileattr_get)
+		return -ENOIOCTLCMD;
+
+	return inode->i_op->fileattr_get(dentry, fa);
+}
+EXPORT_SYMBOL(vfs_fileattr_get);
+
+/**
+ * copy_fsxattr_to_user - copy fsxattr to userspace.
+ * @fa:		fileattr pointer
+ * @ufa:	fsxattr user pointer
+ *
+ * Return: 0 on success, or -EFAULT on failure.
+ */
+int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
+{
+	struct fsxattr xfa;
+
+	memset(&xfa, 0, sizeof(xfa));
+	xfa.fsx_xflags = fa->fsx_xflags;
+	xfa.fsx_extsize = fa->fsx_extsize;
+	xfa.fsx_nextents = fa->fsx_nextents;
+	xfa.fsx_projid = fa->fsx_projid;
+	xfa.fsx_cowextsize = fa->fsx_cowextsize;
+
+	if (copy_to_user(ufa, &xfa, sizeof(xfa)))
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fsxattr_to_user);
+
+static int copy_fsxattr_from_user(struct fileattr *fa,
+				  struct fsxattr __user *ufa)
+{
+	struct fsxattr xfa;
+
+	if (copy_from_user(&xfa, ufa, sizeof(xfa)))
+		return -EFAULT;
+
+	fileattr_fill_xflags(fa, xfa.fsx_xflags);
+	fa->fsx_extsize = xfa.fsx_extsize;
+	fa->fsx_nextents = xfa.fsx_nextents;
+	fa->fsx_projid = xfa.fsx_projid;
+	fa->fsx_cowextsize = xfa.fsx_cowextsize;
+
+	return 0;
+}
+
+/*
+ * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject
+ * any invalid configurations.
+ *
+ * Note: must be called with inode lock held.
+ */
+static int fileattr_set_prepare(struct inode *inode,
+			      const struct fileattr *old_ma,
+			      struct fileattr *fa)
+{
+	int err;
+
+	/*
+	 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+	 * the relevant capability.
+	 */
+	if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags);
+	if (err)
+		return err;
+
+	/*
+	 * Project Quota ID state is only allowed to change from within the init
+	 * namespace. Enforce that restriction only if we are trying to change
+	 * the quota ID state. Everything else is allowed in user namespaces.
+	 */
+	if (current_user_ns() != &init_user_ns) {
+		if (old_ma->fsx_projid != fa->fsx_projid)
+			return -EINVAL;
+		if ((old_ma->fsx_xflags ^ fa->fsx_xflags) &
+				FS_XFLAG_PROJINHERIT)
+			return -EINVAL;
+	}
+
+	/* Check extent size hints. */
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
+			!S_ISDIR(inode->i_mode))
+		return -EINVAL;
+
+	if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) &&
+	    !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+		return -EINVAL;
+
+	/*
+	 * It is only valid to set the DAX flag on regular files and
+	 * directories on filesystems.
+	 */
+	if ((fa->fsx_xflags & FS_XFLAG_DAX) &&
+	    !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+		return -EINVAL;
+
+	/* Extent size hints of zero turn off the flags. */
+	if (fa->fsx_extsize == 0)
+		fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
+	if (fa->fsx_cowextsize == 0)
+		fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
+
+	return 0;
+}
+
+/**
+ * vfs_fileattr_set - change miscellaneous file attributes
+ * @mnt_userns:	user namespace of the mount
+ * @dentry:	the object to change
+ * @fa:		fileattr pointer
+ *
+ * After verifying permissions, call i_op->fileattr_set() callback, if
+ * exists.
+ *
+ * Verifying attributes involves retrieving current attributes with
+ * i_op->fileattr_get(), this also allows initializing attributes that have
+ * not been set by the caller to current values.  Inode lock is held
+ * thoughout to prevent racing with another instance.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry,
+		     struct fileattr *fa)
+{
+	struct inode *inode = d_inode(dentry);
+	struct fileattr old_ma = {};
+	int err;
+
+	if (!inode->i_op->fileattr_set)
+		return -ENOIOCTLCMD;
+
+	if (!inode_owner_or_capable(mnt_userns, inode))
+		return -EPERM;
+
+	inode_lock(inode);
+	err = vfs_fileattr_get(dentry, &old_ma);
+	if (!err) {
+		/* initialize missing bits from old_ma */
+		if (fa->flags_valid) {
+			fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON;
+			fa->fsx_extsize = old_ma.fsx_extsize;
+			fa->fsx_nextents = old_ma.fsx_nextents;
+			fa->fsx_projid = old_ma.fsx_projid;
+			fa->fsx_cowextsize = old_ma.fsx_cowextsize;
+		} else {
+			fa->flags |= old_ma.flags & ~FS_COMMON_FL;
+		}
+		err = fileattr_set_prepare(inode, &old_ma, fa);
+		if (!err)
+			err = inode->i_op->fileattr_set(mnt_userns, dentry, fa);
+	}
+	inode_unlock(inode);
+
+	return err;
+}
+EXPORT_SYMBOL(vfs_fileattr_set);
+
+static int ioctl_getflags(struct file *file, unsigned int __user *argp)
+{
+	struct fileattr fa = { .flags_valid = true }; /* hint only */
+	int err;
+
+	err = vfs_fileattr_get(file->f_path.dentry, &fa);
+	if (!err)
+		err = put_user(fa.flags, argp);
+	return err;
+}
+
+static int ioctl_setflags(struct file *file, unsigned int __user *argp)
+{
+	struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+	struct dentry *dentry = file->f_path.dentry;
+	struct fileattr fa;
+	unsigned int flags;
+	int err;
+
+	err = get_user(flags, argp);
+	if (!err) {
+		err = mnt_want_write_file(file);
+		if (!err) {
+			fileattr_fill_flags(&fa, flags);
+			err = vfs_fileattr_set(mnt_userns, dentry, &fa);
+			mnt_drop_write_file(file);
+		}
+	}
+	return err;
+}
+
+static int ioctl_fsgetxattr(struct file *file, void __user *argp)
+{
+	struct fileattr fa = { .fsx_valid = true }; /* hint only */
+	int err;
+
+	err = vfs_fileattr_get(file->f_path.dentry, &fa);
+	if (!err)
+		err = copy_fsxattr_to_user(&fa, argp);
+
+	return err;
+}
+
+static int ioctl_fssetxattr(struct file *file, void __user *argp)
+{
+	struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+	struct dentry *dentry = file->f_path.dentry;
+	struct fileattr fa;
+	int err;
+
+	err = copy_fsxattr_from_user(&fa, argp);
+	if (!err) {
+		err = mnt_want_write_file(file);
+		if (!err) {
+			err = vfs_fileattr_set(mnt_userns, dentry, &fa);
+			mnt_drop_write_file(file);
+		}
+	}
+	return err;
+}
+
 /*
  * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
  * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
@@ -727,6 +1031,18 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
 		return put_user(i_size_read(inode) - filp->f_pos,
 				(int __user *)argp);
 
+	case FS_IOC_GETFLAGS:
+		return ioctl_getflags(filp, argp);
+
+	case FS_IOC_SETFLAGS:
+		return ioctl_setflags(filp, argp);
+
+	case FS_IOC_FSGETXATTR:
+		return ioctl_fsgetxattr(filp, argp);
+
+	case FS_IOC_FSSETXATTR:
+		return ioctl_fssetxattr(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			return file_ioctl(filp, cmd, argp);
@@ -828,6 +1144,15 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 #endif
 
 	/*
+	 * These access 32-bit values anyway so no further handling is
+	 * necessary.
+	 */
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+		cmd = (cmd == FS_IOC32_GETFLAGS) ?
+			FS_IOC_GETFLAGS : FS_IOC_SETFLAGS;
+		fallthrough;
+	/*
 	 * everything else in do_vfs_ioctl() takes either a compatible
 	 * pointer argument or no argument -- call it with a modified
 	 * argument.