add file system helpers that take kernel pointers for the init code v3

add file system helpers that take kernel pointers for the init code v3

[Christoph Hellwig]

Hi Al and Linus,

currently a lot of the file system calls in the early in code (and the
devtmpfs kthread) rely on the implicit set_fs(KERNEL_DS) during boot.
This is one of the few last remaining places we need to deal with to kill
off set_fs entirely, so this series adds new helpers that take kernel
pointers.  These helpers are in init/ and marked __init and thus will
be discarded after bootup.  A few also need to be duplicated in devtmpfs,
though unfortunately.

The series sits on top of my previous

  "decruft the early init / initrd / initramfs code v2"

series.


Git tree:

    git://git.infradead.org/users/hch/misc.git init_path

Gitweb:

    http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/init_path


Changes since v2:
 - move to fs/for-init.c
 - reuse the init routines in devtmpfs after refactoring devtmpfsd
   (and thus the broken error handling in the previous version)
 - actually use kern_path in a place where user_path_at sneaked back in

Changes since v1:
 - avoid most core VFS changes
 - renamed the functions and move them to init/ and devtmpfs
 - drop a bunch of cleanups that can be submitted independently now


Diffstat:
 drivers/base/devtmpfs.c       |   54 +++++----
 drivers/md/md-autodetect.c    |    3 
 fs/Makefile                   |    2 
 fs/for_init.c                 |  249 ++++++++++++++++++++++++++++++++++++++++++
 fs/internal.h                 |   19 +--
 fs/namei.c                    |   20 +--
 fs/namespace.c                |  107 ++++++++----------
 fs/open.c                     |   22 +--
 include/linux/init_syscalls.h |   18 +++
 include/linux/syscalls.h      |   66 -----------
 init/do_mounts.c              |   12 +-
 init/do_mounts.h              |    7 -
 init/do_mounts_initrd.c       |   26 ++--
 init/do_mounts_rd.c           |    2 
 init/initramfs.c              |   29 ++--
 init/main.c                   |   10 -
 init/noinitramfs.c            |    8 -
 17 files changed, 423 insertions(+), 231 deletions(-)

[PATCH 01/21] fs: refactor do_mount

[Christoph Hellwig]

Factor out a path_mount helper that takes a struct path * instead of the
actual file name.  This will allow to convert the init and devtmpfs code
to properly mount based on a kernel pointer instead of relying on the
implicit set_fs(KERNEL_DS) during early init.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/namespace.c | 67 ++++++++++++++++++++++++++------------------------
 1 file changed, 35 insertions(+), 32 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index f30ed401cc6d7a..6f8234f74bed90 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3115,12 +3115,11 @@ char *copy_mount_string(const void __user *data)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-long do_mount(const char *dev_name, const char __user *dir_name,
+static int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page)
 {
-	struct path path;
 	unsigned int mnt_flags = 0, sb_flags;
-	int retval = 0;
+	int ret;
 
 	/* Discard magic */
 	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
@@ -3133,19 +3132,13 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	if (flags & MS_NOUSER)
 		return -EINVAL;
 
-	/* ... and get the mountpoint */
-	retval = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path);
-	if (retval)
-		return retval;
-
-	retval = security_sb_mount(dev_name, &path,
-				   type_page, flags, data_page);
-	if (!retval && !may_mount())
-		retval = -EPERM;
-	if (!retval && (flags & SB_MANDLOCK) && !may_mandlock())
-		retval = -EPERM;
-	if (retval)
-		goto dput_out;
+	ret = security_sb_mount(dev_name, path, type_page, flags, data_page);
+	if (ret)
+		return ret;
+	if (!may_mount())
+		return -EPERM;
+	if ((flags & SB_MANDLOCK) && !may_mandlock())
+		return -EPERM;
 
 	/* Default to relatime unless overriden */
 	if (!(flags & MS_NOATIME))
@@ -3172,7 +3165,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	    ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
 		       MS_STRICTATIME)) == 0)) {
 		mnt_flags &= ~MNT_ATIME_MASK;
-		mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+		mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK;
 	}
 
 	sb_flags = flags & (SB_RDONLY |
@@ -3185,22 +3178,32 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 			    SB_I_VERSION);
 
 	if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND))
-		retval = do_reconfigure_mnt(&path, mnt_flags);
-	else if (flags & MS_REMOUNT)
-		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);
-	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
-		retval = do_change_type(&path, flags);
-	else if (flags & MS_MOVE)
-		retval = do_move_mount_old(&path, dev_name);
-	else
-		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
-				      dev_name, data_page);
-dput_out:
+		return do_reconfigure_mnt(path, mnt_flags);
+	if (flags & MS_REMOUNT)
+		return do_remount(path, flags, sb_flags, mnt_flags, data_page);
+	if (flags & MS_BIND)
+		return do_loopback(path, dev_name, flags & MS_REC);
+	if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
+		return do_change_type(path, flags);
+	if (flags & MS_MOVE)
+		return do_move_mount_old(path, dev_name);
+
+	return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name,
+			    data_page);
+}
+
+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;
+	int ret;
+
+	ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ret;
+	ret = path_mount(dev_name, &path, type_page, flags, data_page);
 	path_put(&path);
-	return retval;
+	return ret;
 }
 
 static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns)
-- 
2.27.0

[PATCH 02/21] fs: refactor ksys_umount

[Christoph Hellwig]

Factor out a path_umount helper that takes a struct path * instead of the
actual file name.  This will allow to convert the init and devtmpfs code
to properly mount based on a kernel pointer instead of relying on the
implicit set_fs(KERNEL_DS) during early init.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/namespace.c | 40 ++++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 22 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 6f8234f74bed90..43834b59eff6c3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1706,36 +1706,19 @@ static inline bool may_mandlock(void)
 }
 #endif
 
-/*
- * Now umount can handle mount points as well as block devices.
- * This is important for filesystems which use unnamed block devices.
- *
- * We now support a flag for forced unmount like the other 'big iron'
- * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
- */
-
-int ksys_umount(char __user *name, int flags)
+static int path_umount(struct path *path, int flags)
 {
-	struct path path;
 	struct mount *mnt;
 	int retval;
-	int lookup_flags = LOOKUP_MOUNTPOINT;
 
 	if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
 		return -EINVAL;
-
 	if (!may_mount())
 		return -EPERM;
 
-	if (!(flags & UMOUNT_NOFOLLOW))
-		lookup_flags |= LOOKUP_FOLLOW;
-
-	retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
-	if (retval)
-		goto out;
-	mnt = real_mount(path.mnt);
+	mnt = real_mount(path->mnt);
 	retval = -EINVAL;
-	if (path.dentry != path.mnt->mnt_root)
+	if (path->dentry != path->mnt->mnt_root)
 		goto dput_and_out;
 	if (!check_mnt(mnt))
 		goto dput_and_out;
@@ -1748,12 +1731,25 @@ int ksys_umount(char __user *name, int flags)
 	retval = do_umount(mnt, flags);
 dput_and_out:
 	/* we mustn't call path_put() as that would clear mnt_expiry_mark */
-	dput(path.dentry);
+	dput(path->dentry);
 	mntput_no_expire(mnt);
-out:
 	return retval;
 }
 
+int ksys_umount(char __user *name, int flags)
+{
+	int lookup_flags = LOOKUP_MOUNTPOINT;
+	struct path path;
+	int ret;
+
+	if (!(flags & UMOUNT_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
+	if (ret)
+		return ret;
+	return path_umount(&path, flags);
+}
+
 SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 {
 	return ksys_umount(name, flags);
-- 
2.27.0

[PATCH 03/21] fs: push the getname from do_rmdir into the callers

[Christoph Hellwig]

This mirrors do_unlinkat and will make life a little easier for
the init code to reuse the whole function with a kernel filename.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/internal.h            |  2 +-
 fs/namei.c               | 10 ++++------
 include/linux/syscalls.h |  4 ++--
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 9b863a7bd70892..e903d5aae139a2 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -65,7 +65,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev);
 long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-long do_rmdir(int dfd, const char __user *pathname);
+long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname);
diff --git a/fs/namei.c b/fs/namei.c
index 72d4219c93acb7..d75a6039ae3966 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3720,17 +3720,16 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 }
 EXPORT_SYMBOL(vfs_rmdir);
 
-long do_rmdir(int dfd, const char __user *pathname)
+long do_rmdir(int dfd, struct filename *name)
 {
 	int error = 0;
-	struct filename *name;
 	struct dentry *dentry;
 	struct path path;
 	struct qstr last;
 	int type;
 	unsigned int lookup_flags = 0;
 retry:
-	name = filename_parentat(dfd, getname(pathname), lookup_flags,
+	name = filename_parentat(dfd, name, lookup_flags,
 				&path, &last, &type);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
@@ -3781,7 +3780,7 @@ long do_rmdir(int dfd, const char __user *pathname)
 
 SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 {
-	return do_rmdir(AT_FDCWD, pathname);
+	return do_rmdir(AT_FDCWD, getname(pathname));
 }
 
 /**
@@ -3926,8 +3925,7 @@ SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
 		return -EINVAL;
 
 	if (flag & AT_REMOVEDIR)
-		return do_rmdir(dfd, pathname);
-
+		return do_rmdir(dfd, getname(pathname));
 	return do_unlinkat(dfd, getname(pathname));
 }
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5b0f1fca4cfb9d..e43816198e6001 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1281,11 +1281,11 @@ static inline long ksys_unlink(const char __user *pathname)
 	return do_unlinkat(AT_FDCWD, getname(pathname));
 }
 
-extern long do_rmdir(int dfd, const char __user *pathname);
+long do_rmdir(int dfd, struct filename *name);
 
 static inline long ksys_rmdir(const char __user *pathname)
 {
-	return do_rmdir(AT_FDCWD, pathname);
+	return do_rmdir(AT_FDCWD, getname(pathname));
 }
 
 extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-- 
2.27.0

[PATCH 04/21] devtmpfs: refactor devtmpfsd()

[Christoph Hellwig]

Split the main worker loop into a separate function.  This allows
devtmpfsd itself and devtmpfsd_setup to be marked __init, which will
allows us to call __init routines for the setup work.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c | 47 +++++++++++++++++++++++------------------
 1 file changed, 26 insertions(+), 21 deletions(-)

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index c9017e0584c003..a103ee7e229930 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -378,7 +378,30 @@ static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid,
 		return handle_remove(name, dev);
 }
 
-static int devtmpfs_setup(void *p)
+static void __noreturn devtmpfs_work_loop(void)
+{
+	while (1) {
+		spin_lock(&req_lock);
+		while (requests) {
+			struct req *req = requests;
+			requests = NULL;
+			spin_unlock(&req_lock);
+			while (req) {
+				struct req *next = req->next;
+				req->err = handle(req->name, req->mode,
+						  req->uid, req->gid, req->dev);
+				complete(&req->done);
+				req = next;
+			}
+			spin_lock(&req_lock);
+		}
+		__set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock(&req_lock);
+		schedule();
+	}
+}
+
+static int __init devtmpfs_setup(void *p)
 {
 	int err;
 
@@ -396,31 +419,13 @@ static int devtmpfs_setup(void *p)
 	return err;
 }
 
-static int devtmpfsd(void *p)
+static int __init devtmpfsd(void *p)
 {
 	int err = devtmpfs_setup(p);
 
 	if (err)
 		return err;
-	while (1) {
-		spin_lock(&req_lock);
-		while (requests) {
-			struct req *req = requests;
-			requests = NULL;
-			spin_unlock(&req_lock);
-			while (req) {
-				struct req *next = req->next;
-				req->err = handle(req->name, req->mode,
-						  req->uid, req->gid, req->dev);
-				complete(&req->done);
-				req = next;
-			}
-			spin_lock(&req_lock);
-		}
-		__set_current_state(TASK_INTERRUPTIBLE);
-		spin_unlock(&req_lock);
-		schedule();
-	}
+	devtmpfs_work_loop();
 	return 0;
 }
 
-- 
2.27.0

Re: [PATCH 04/21] devtmpfs: refactor devtmpfsd()

[Greg Kroah-Hartman]

On Sun, Jul 26, 2020 at 09:13:39AM +0200, Christoph Hellwig wrote:
> Split the main worker loop into a separate function.  This allows
> devtmpfsd itself and devtmpfsd_setup to be marked __init, which will
> allows us to call __init routines for the setup work.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  drivers/base/devtmpfs.c | 47 +++++++++++++++++++++++------------------
>  1 file changed, 26 insertions(+), 21 deletions(-)

Nice cleanup, thanks for doing this:

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Re: [PATCH 04/21] devtmpfs: refactor devtmpfsd()

[Christoph Hellwig]

On Sun, Jul 26, 2020 at 09:43:06AM +0200, Greg Kroah-Hartman wrote:
> On Sun, Jul 26, 2020 at 09:13:39AM +0200, Christoph Hellwig wrote:
> > Split the main worker loop into a separate function.  This allows
> > devtmpfsd itself and devtmpfsd_setup to be marked __init, which will
> > allows us to call __init routines for the setup work.
> > 
> > Signed-off-by: Christoph Hellwig <hch@lst.de>
> > ---
> >  drivers/base/devtmpfs.c | 47 +++++++++++++++++++++++------------------
> >  1 file changed, 26 insertions(+), 21 deletions(-)
> 
> Nice cleanup, thanks for doing this:

This was actualy Als idea, I should have probably mentioned that.

[PATCH 05/21] init: initialize ramdisk_execute_command at compile time

[Christoph Hellwig]

Set ramdisk_execute_command to "/init" at compile time.  The command
line can still override it, but this saves a few instructions and
removes a NULL check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 init/main.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/init/main.c b/init/main.c
index db0621dfbb0468..c2c9143db96795 100644
--- a/init/main.c
+++ b/init/main.c
@@ -154,7 +154,7 @@ static bool initargs_found;
 #endif
 
 static char *execute_command;
-static char *ramdisk_execute_command;
+static char *ramdisk_execute_command = "/init";
 
 /*
  * Used to generate warnings if static_key manipulation functions are used
@@ -1514,10 +1514,6 @@ static noinline void __init kernel_init_freeable(void)
 	 * check if there is an early userspace init.  If yes, let it do all
 	 * the work
 	 */
-
-	if (!ramdisk_execute_command)
-		ramdisk_execute_command = "/init";
-
 	if (ksys_access((const char __user *)
 			ramdisk_execute_command, 0) != 0) {
 		ramdisk_execute_command = NULL;
-- 
2.27.0

[PATCH 06/21] init: mark create_dev as __init

[Christoph Hellwig]

The helper is only used for the early init code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 init/do_mounts.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/do_mounts.h b/init/do_mounts.h
index c855b3f0e06d19..021e2f60223e25 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -13,7 +13,7 @@ void  mount_block_root(char *name, int flags);
 void  mount_root(void);
 extern int root_mountflags;
 
-static inline int create_dev(char *name, dev_t dev)
+static inline __init int create_dev(char *name, dev_t dev)
 {
 	ksys_unlink(name);
 	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
-- 
2.27.0

[PATCH 07/21] init: add an init_mount helper

[Christoph Hellwig]

Like do_mount, but takes a kernel pointer for the destination path.
Switch over the mounts in the init code and devtmpfs to it, which
just happen to work due to the implicit set_fs(KERNEL_DS) during early
init right now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  5 +++--
 fs/Makefile                   |  2 +-
 fs/for_init.c                 | 21 +++++++++++++++++++++
 fs/internal.h                 |  4 ++++
 fs/namespace.c                |  2 +-
 include/linux/init_syscalls.h |  4 ++++
 init/do_mounts.c              |  8 ++++----
 init/do_mounts.h              |  1 +
 init/do_mounts_initrd.c       |  6 +++---
 9 files changed, 42 insertions(+), 11 deletions(-)
 create mode 100644 fs/for_init.c
 create mode 100644 include/linux/init_syscalls.h

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index a103ee7e229930..03051e8c12bdc9 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/init_syscalls.h>
 #include <uapi/linux/mount.h>
 #include "base.h"
 
@@ -359,7 +360,7 @@ int __init devtmpfs_mount(void)
 	if (!thread)
 		return 0;
 
-	err = do_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL);
+	err = init_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
 	else
@@ -408,7 +409,7 @@ static int __init devtmpfs_setup(void *p)
 	err = ksys_unshare(CLONE_NEWNS);
 	if (err)
 		goto out;
-	err = do_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
+	err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		goto out;
 	ksys_chdir("/.."); /* will traverse into overmounted root */
diff --git a/fs/Makefile b/fs/Makefile
index 2ce5112b02c867..837512ff387ccd 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -13,7 +13,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o fsopen.o
+		fs_types.o fs_context.o fs_parser.o fsopen.o for_init.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/for_init.c b/fs/for_init.c
new file mode 100644
index 00000000000000..6a04cc8d8557c4
--- /dev/null
+++ b/fs/for_init.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include <linux/init_syscalls.h>
+#include "internal.h"
+
+int __init init_mount(const char *dev_name, const char *dir_name,
+		const char *type_page, unsigned long flags, void *data_page)
+{
+	struct path path;
+	int ret;
+
+	ret = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ret;
+	ret = path_mount(dev_name, &path, type_page, flags, data_page);
+	path_put(&path);
+	return ret;
+}
diff --git a/fs/internal.h b/fs/internal.h
index e903d5aae139a2..72ea0b6f7435a4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -89,6 +89,10 @@ extern int __mnt_want_write_file(struct file *);
 extern void __mnt_drop_write_file(struct file *);
 
 extern void dissolve_on_fput(struct vfsmount *);
+
+int path_mount(const char *dev_name, struct path *path,
+		const char *type_page, unsigned long flags, void *data_page);
+
 /*
  * fs_struct.c
  */
diff --git a/fs/namespace.c b/fs/namespace.c
index 43834b59eff6c3..2c4d7592097485 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3111,7 +3111,7 @@ char *copy_mount_string(const void __user *data)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-static int path_mount(const char *dev_name, struct path *path,
+int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	unsigned int mnt_flags = 0, sb_flags;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
new file mode 100644
index 00000000000000..af9ea88a60e0bd
--- /dev/null
+++ b/include/linux/init_syscalls.h
@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+int __init init_mount(const char *dev_name, const char *dir_name,
+		const char *type_page, unsigned long flags, void *data_page);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 4f4ceb35805503..4812e21d149cab 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -395,16 +395,16 @@ static int __init do_mount_root(const char *name, const char *fs,
 	int ret;
 
 	if (data) {
-		/* do_mount() requires a full page as fifth argument */
+		/* init_mount() requires a full page as fifth argument */
 		p = alloc_page(GFP_KERNEL);
 		if (!p)
 			return -ENOMEM;
 		data_page = page_address(p);
-		/* zero-pad. do_mount() will make sure it's terminated */
+		/* zero-pad. init_mount() will make sure it's terminated */
 		strncpy(data_page, data, PAGE_SIZE);
 	}
 
-	ret = do_mount(name, "/root", fs, flags, data_page);
+	ret = init_mount(name, "/root", fs, flags, data_page);
 	if (ret)
 		goto out;
 
@@ -628,7 +628,7 @@ void __init prepare_namespace(void)
 	mount_root();
 out:
 	devtmpfs_mount();
-	do_mount(".", "/", NULL, MS_MOVE, NULL);
+	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 }
 
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 021e2f60223e25..20e7fec8cb499e 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -8,6 +8,7 @@
 #include <linux/mount.h>
 #include <linux/major.h>
 #include <linux/root_dev.h>
+#include <linux/init_syscalls.h>
 
 void  mount_block_root(char *name, int flags);
 void  mount_root(void);
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index e08669187d63be..1f9336209ad9cc 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -62,7 +62,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	console_on_rootfs();
 	/* move initrd over / and chdir/chroot in initrd root */
 	ksys_chdir("/root");
-	do_mount(".", "/", NULL, MS_MOVE, NULL);
+	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 	ksys_setsid();
 	return 0;
@@ -99,7 +99,7 @@ static void __init handle_initrd(void)
 	current->flags &= ~PF_FREEZER_SKIP;
 
 	/* move initrd to rootfs' /old */
-	do_mount("..", ".", NULL, MS_MOVE, NULL);
+	init_mount("..", ".", NULL, MS_MOVE, NULL);
 	/* switch root and cwd back to / of rootfs */
 	ksys_chroot("..");
 
@@ -113,7 +113,7 @@ static void __init handle_initrd(void)
 	mount_root();
 
 	printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
-	error = do_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
+	error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
 	if (!error)
 		printk("okay\n");
 	else {
-- 
2.27.0

[PATCH 08/21] init: add an init_umount helper

[Christoph Hellwig]

Like ksys_umount, but takes a kernel pointer for the destination path.
Switch over the umount in the init code, which just happen to work due to
the implicit set_fs(KERNEL_DS) during early init right now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 14 ++++++++++++++
 fs/internal.h                 |  1 +
 fs/namespace.c                |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  1 -
 init/do_mounts_initrd.c       |  2 +-
 6 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 6a04cc8d8557c4..7a039b6d107c92 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -19,3 +19,17 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 	path_put(&path);
 	return ret;
 }
+
+int __init init_umount(const char *name, int flags)
+{
+	int lookup_flags = LOOKUP_MOUNTPOINT;
+	struct path path;
+	int ret;
+
+	if (!(flags & UMOUNT_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	ret = kern_path(name, lookup_flags, &path);
+	if (ret)
+		return ret;
+	return path_umount(&path, flags);
+}
diff --git a/fs/internal.h b/fs/internal.h
index 72ea0b6f7435a4..491d1e63809b37 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -92,6 +92,7 @@ extern void dissolve_on_fput(struct vfsmount *);
 
 int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page);
+int path_umount(struct path *path, int flags);
 
 /*
  * fs_struct.c
diff --git a/fs/namespace.c b/fs/namespace.c
index 2c4d7592097485..a7301790abb211 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1706,7 +1706,7 @@ static inline bool may_mandlock(void)
 }
 #endif
 
-static int path_umount(struct path *path, int flags)
+int path_umount(struct path *path, int flags)
 {
 	struct mount *mnt;
 	int retval;
@@ -1736,7 +1736,7 @@ static int path_umount(struct path *path, int flags)
 	return retval;
 }
 
-int ksys_umount(char __user *name, int flags)
+static int ksys_umount(char __user *name, int flags)
 {
 	int lookup_flags = LOOKUP_MOUNTPOINT;
 	struct path path;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index af9ea88a60e0bd..a5a2e7f1991691 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -2,3 +2,4 @@
 
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
+int __init init_umount(const char *name, int flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e43816198e6001..1a4f5d8ee7044b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1236,7 +1236,6 @@ asmlinkage long sys_ni_syscall(void);
  * the ksys_xyzyyz() functions prototyped below.
  */
 
-int ksys_umount(char __user *name, int flags);
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 1f9336209ad9cc..6b020a06990251 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -122,7 +122,7 @@ static void __init handle_initrd(void)
 		else
 			printk("failed\n");
 		printk(KERN_NOTICE "Unmounting old root\n");
-		ksys_umount("/old", MNT_DETACH);
+		init_umount("/old", MNT_DETACH);
 	}
 }
 
-- 
2.27.0

[PATCH 09/21] init: add an init_unlink helper

[Christoph Hellwig]

Add a simple helper to unlink with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_unlink.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 5 +++++
 include/linux/init_syscalls.h | 1 +
 include/linux/syscalls.h      | 7 -------
 init/do_mounts.h              | 2 +-
 init/do_mounts_initrd.c       | 4 ++--
 init/do_mounts_rd.c           | 2 +-
 init/initramfs.c              | 3 ++-
 7 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 7a039b6d107c92..32472206d64136 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -33,3 +33,8 @@ int __init init_umount(const char *name, int flags)
 		return ret;
 	return path_umount(&path, flags);
 }
+
+int __init init_unlink(const char *pathname)
+{
+	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index a5a2e7f1991691..00d597249549ee 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -3,3 +3,4 @@
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
+int __init init_unlink(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1a4f5d8ee7044b..26f9738e5ab861 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_unlinkat(int dfd, struct filename *name);
-
-static inline long ksys_unlink(const char __user *pathname)
-{
-	return do_unlinkat(AT_FDCWD, getname(pathname));
-}
-
 long do_rmdir(int dfd, struct filename *name);
 
 static inline long ksys_rmdir(const char __user *pathname)
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 20e7fec8cb499e..104d8431725aeb 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -16,7 +16,7 @@ extern int root_mountflags;
 
 static inline __init int create_dev(char *name, dev_t dev)
 {
-	ksys_unlink(name);
+	init_unlink(name);
 	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
 }
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 6b020a06990251..8b44dd017842a8 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -137,11 +137,11 @@ bool __init initrd_load(void)
 		 * mounted in the normal path.
 		 */
 		if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) {
-			ksys_unlink("/initrd.image");
+			init_unlink("/initrd.image");
 			handle_initrd();
 			return true;
 		}
 	}
-	ksys_unlink("/initrd.image");
+	init_unlink("/initrd.image");
 	return false;
 }
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 7b64390c075043..b062f8b028ce7c 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -271,7 +271,7 @@ int __init rd_load_image(char *from)
 	fput(out_file);
 out:
 	kfree(buf);
-	ksys_unlink("/dev/ram");
+	init_unlink("/dev/ram");
 	return res;
 }
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 3823d15e5d2619..574ab3755203da 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -12,6 +12,7 @@
 #include <linux/file.h>
 #include <linux/memblock.h>
 #include <linux/namei.h>
+#include <linux/init_syscalls.h>
 
 static ssize_t __init xwrite(struct file *file, const char *p, size_t count)
 {
@@ -300,7 +301,7 @@ static void __init clean_path(char *path, umode_t fmode)
 		if (S_ISDIR(st.mode))
 			ksys_rmdir(path);
 		else
-			ksys_unlink(path);
+			init_unlink(path);
 	}
 }
 
-- 
2.27.0

[PATCH 10/21] init: add an init_rmdir helper

[Christoph Hellwig]

Add a simple helper to rmdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_rmdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 5 +++++
 include/linux/init_syscalls.h | 1 +
 include/linux/syscalls.h      | 7 -------
 init/initramfs.c              | 2 +-
 4 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 32472206d64136..1f10ebe78c1ba1 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -38,3 +38,8 @@ int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
 }
+
+int __init init_rmdir(const char *pathname)
+{
+	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 00d597249549ee..abf3af563c0b3a 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -4,3 +4,4 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
 int __init init_unlink(const char *pathname);
+int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 26f9738e5ab861..a7b14258d245e2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-long do_rmdir(int dfd, struct filename *name);
-
-static inline long ksys_rmdir(const char __user *pathname)
-{
-	return do_rmdir(AT_FDCWD, getname(pathname));
-}
-
 extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 
 static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
diff --git a/init/initramfs.c b/init/initramfs.c
index 574ab3755203da..1ceba88cfcc052 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -299,7 +299,7 @@ static void __init clean_path(char *path, umode_t fmode)
 
 	if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
-			ksys_rmdir(path);
+			init_rmdir(path);
 		else
 			init_unlink(path);
 	}
-- 
2.27.0

[PATCH 11/21] init: add an init_chdir helper

[Christoph Hellwig]

Add a simple helper to chdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_chdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  2 +-
 fs/for_init.c                 | 16 ++++++++++++++++
 fs/open.c                     |  7 +------
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  1 -
 init/do_mounts.c              |  2 +-
 init/do_mounts_initrd.c       |  8 ++++----
 7 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 03051e8c12bdc9..bc2cfe10018cd5 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -412,7 +412,7 @@ static int __init devtmpfs_setup(void *p)
 	err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		goto out;
-	ksys_chdir("/.."); /* will traverse into overmounted root */
+	init_chdir("/.."); /* will traverse into overmounted root */
 	ksys_chroot(".");
 out:
 	*(int *)p = err;
diff --git a/fs/for_init.c b/fs/for_init.c
index 1f10ebe78c1ba1..e5d907d4b98aac 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -3,6 +3,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/init_syscalls.h>
 #include "internal.h"
 
@@ -34,6 +35,21 @@ int __init init_umount(const char *name, int flags)
 	return path_umount(&path, flags);
 }
 
+int __init init_chdir(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (error)
+		return error;
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+	if (!error)
+		set_fs_pwd(current->fs, &path);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index b316dd6a86a8b9..723e0ac898935e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -482,7 +482,7 @@ SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
 	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
-int ksys_chdir(const char __user *filename)
+SYSCALL_DEFINE1(chdir, const char __user *, filename)
 {
 	struct path path;
 	int error;
@@ -508,11 +508,6 @@ int ksys_chdir(const char __user *filename)
 	return error;
 }
 
-SYSCALL_DEFINE1(chdir, const char __user *, filename)
-{
-	return ksys_chdir(filename);
-}
-
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
 	struct fd f = fdget_raw(fd);
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index abf3af563c0b3a..1e845910ae56e9 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -3,5 +3,6 @@
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
+int __init init_chdir(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a7b14258d245e2..31fa67fb9894b3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1238,7 +1238,6 @@ asmlinkage long sys_ni_syscall(void);
 
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
-int ksys_chdir(const char __user *filename);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
 void ksys_sync(void);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 4812e21d149cab..cc08ed7b44e764 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -408,7 +408,7 @@ static int __init do_mount_root(const char *name, const char *fs,
 	if (ret)
 		goto out;
 
-	ksys_chdir("/root");
+	init_chdir("/root");
 	s = current->fs->pwd.dentry->d_sb;
 	ROOT_DEV = s->s_dev;
 	printk(KERN_INFO
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 8b44dd017842a8..04627fd22a921f 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -61,7 +61,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	ksys_unshare(CLONE_FS | CLONE_FILES);
 	console_on_rootfs();
 	/* move initrd over / and chdir/chroot in initrd root */
-	ksys_chdir("/root");
+	init_chdir("/root");
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 	ksys_setsid();
@@ -82,7 +82,7 @@ static void __init handle_initrd(void)
 	/* mount initrd on rootfs' /root */
 	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
 	ksys_mkdir("/old", 0700);
-	ksys_chdir("/old");
+	init_chdir("/old");
 
 	/*
 	 * In case that a resume from disk is carried out by linuxrc or one of
@@ -104,11 +104,11 @@ static void __init handle_initrd(void)
 	ksys_chroot("..");
 
 	if (new_decode_dev(real_root_dev) == Root_RAM0) {
-		ksys_chdir("/old");
+		init_chdir("/old");
 		return;
 	}
 
-	ksys_chdir("/");
+	init_chdir("/");
 	ROOT_DEV = new_decode_dev(real_root_dev);
 	mount_root();
 
-- 
2.27.0

[PATCH 12/21] init: add an init_chroot helper

[Christoph Hellwig]

Add a simple helper to chroot with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_chroot.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  2 +-
 fs/for_init.c                 | 24 ++++++++++++++++++++++++
 fs/open.c                     |  7 +------
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  2 --
 init/do_mounts.c              |  2 +-
 init/do_mounts_initrd.c       |  4 ++--
 7 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index bc2cfe10018cd5..36e81b52368650 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -413,7 +413,7 @@ static int __init devtmpfs_setup(void *p)
 	if (err)
 		goto out;
 	init_chdir("/.."); /* will traverse into overmounted root */
-	ksys_chroot(".");
+	init_chroot(".");
 out:
 	*(int *)p = err;
 	complete(&setup_done);
diff --git a/fs/for_init.c b/fs/for_init.c
index e5d907d4b98aac..2d5428b7dc1420 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -5,6 +5,7 @@
 #include <linux/fs.h>
 #include <linux/fs_struct.h>
 #include <linux/init_syscalls.h>
+#include <linux/security.h>
 #include "internal.h"
 
 int __init init_mount(const char *dev_name, const char *dir_name,
@@ -50,6 +51,29 @@ int __init init_chdir(const char *filename)
 	return error;
 }
 
+int __init init_chroot(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (error)
+		return error;
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+	if (error)
+		goto dput_and_out;
+	error = -EPERM;
+	if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
+		goto dput_and_out;
+	error = security_path_chroot(&path);
+	if (error)
+		goto dput_and_out;
+	set_fs_root(current->fs, &path);
+dput_and_out:
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index 723e0ac898935e..f62f4752bb436d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -530,7 +530,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 	return error;
 }
 
-int ksys_chroot(const char __user *filename)
+SYSCALL_DEFINE1(chroot, const char __user *, filename)
 {
 	struct path path;
 	int error;
@@ -563,11 +563,6 @@ int ksys_chroot(const char __user *filename)
 	return error;
 }
 
-SYSCALL_DEFINE1(chroot, const char __user *, filename)
-{
-	return ksys_chroot(filename);
-}
-
 static int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 1e845910ae56e9..e07099a14b91db 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -4,5 +4,6 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
+int __init init_chroot(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 31fa67fb9894b3..e89d62e944dc0e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1235,8 +1235,6 @@ asmlinkage long sys_ni_syscall(void);
  * Instead, use one of the functions which work equivalently, such as
  * the ksys_xyzyyz() functions prototyped below.
  */
-
-int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index cc08ed7b44e764..c8ccdc80ffcdd5 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -629,7 +629,7 @@ void __init prepare_namespace(void)
 out:
 	devtmpfs_mount();
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
-	ksys_chroot(".");
+	init_chroot(".");
 }
 
 static bool is_tmpfs;
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 04627fd22a921f..a6b447b191dbc8 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -63,7 +63,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	/* move initrd over / and chdir/chroot in initrd root */
 	init_chdir("/root");
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
-	ksys_chroot(".");
+	init_chroot(".");
 	ksys_setsid();
 	return 0;
 }
@@ -101,7 +101,7 @@ static void __init handle_initrd(void)
 	/* move initrd to rootfs' /old */
 	init_mount("..", ".", NULL, MS_MOVE, NULL);
 	/* switch root and cwd back to / of rootfs */
-	ksys_chroot("..");
+	init_chroot("..");
 
 	if (new_decode_dev(real_root_dev) == Root_RAM0) {
 		init_chdir("/old");
-- 
2.27.0

[PATCH 13/21] init: add an init_chown helper

[Christoph Hellwig]

Add a simple helper to chown with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 18 ++++++++++++++++++
 fs/internal.h                 |  2 +-
 fs/open.c                     |  2 +-
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  6 +++---
 5 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 2d5428b7dc1420..0541851d86f42e 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -74,6 +74,24 @@ int __init init_chroot(const char *filename)
 	return error;
 }
 
+int __init init_chown(const char *filename, uid_t user, gid_t group, int flags)
+{
+	int lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	error = kern_path(filename, lookup_flags, &path);
+	if (error)
+		return error;
+	error = mnt_want_write(path.mnt);
+	if (!error) {
+		error = chown_common(&path, user, group);
+		mnt_drop_write(path.mnt);
+	}
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 491d1e63809b37..e81b9e23c3ea3f 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -134,7 +134,7 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
-
+int chown_common(const struct path *path, uid_t user, gid_t group);
 extern int vfs_open(const struct path *, struct file *);
 
 /*
diff --git a/fs/open.c b/fs/open.c
index f62f4752bb436d..49960a1248f14b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -639,7 +639,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 	return do_fchmodat(AT_FDCWD, filename, mode);
 }
 
-static int chown_common(const struct path *path, uid_t user, gid_t group)
+int chown_common(const struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct inode *delegated_inode = NULL;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index e07099a14b91db..0da59d76133e17 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -5,5 +5,6 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
+int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/init/initramfs.c b/init/initramfs.c
index 1ceba88cfcc052..919b40fb07bada 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -346,14 +346,14 @@ static int __init do_name(void)
 		}
 	} else if (S_ISDIR(mode)) {
 		ksys_mkdir(collected, mode);
-		ksys_chown(collected, uid, gid);
+		init_chown(collected, uid, gid, 0);
 		ksys_chmod(collected, mode);
 		dir_add(collected, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
 			ksys_mknod(collected, mode, rdev);
-			ksys_chown(collected, uid, gid);
+			init_chown(collected, uid, gid, 0);
 			ksys_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
@@ -391,7 +391,7 @@ static int __init do_symlink(void)
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
 	ksys_symlink(collected + N_ALIGN(name_len), collected);
-	ksys_lchown(collected, uid, gid);
+	init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW);
 	do_utime(collected, mtime);
 	state = SkipIt;
 	next_state = Reset;
-- 
2.27.0

[PATCH 14/21] init: add an init_chmod helper

[Christoph Hellwig]

Add a simple helper to chmod with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 13 +++++++++++++
 fs/internal.h                 |  2 +-
 fs/open.c                     |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/initramfs.c              |  4 ++--
 6 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 0541851d86f42e..098e9b69c32ef6 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -92,6 +92,19 @@ int __init init_chown(const char *filename, uid_t user, gid_t group, int flags)
 	return error;
 }
 
+int __init init_chmod(const char *filename, umode_t mode)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW, &path);
+	if (error)
+		return error;
+	error = chmod_common(&path, mode);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index e81b9e23c3ea3f..6d82681c7d8372 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -131,7 +131,7 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
-int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
+int chmod_common(const struct path *path, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 int chown_common(const struct path *path, uid_t user, gid_t group);
diff --git a/fs/open.c b/fs/open.c
index 49960a1248f14b..7ba89eae46c560 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -563,7 +563,7 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 	return error;
 }
 
-static int chmod_common(const struct path *path, umode_t mode)
+int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct inode *delegated_inode = NULL;
@@ -610,7 +610,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 	return err;
 }
 
-int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
+static int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
 {
 	struct path path;
 	int error;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 0da59d76133e17..2b1b4dc586825f 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -6,5 +6,6 @@ int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
+int __init init_chmod(const char *filename, umode_t mode);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e89d62e944dc0e..8b71fa321ca20c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname,
 	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-extern int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
-
-static inline int ksys_chmod(const char __user *filename, umode_t mode)
-{
-	return do_fchmodat(AT_FDCWD, filename, mode);
-}
-
 long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
 
 static inline long ksys_access(const char __user *filename, int mode)
diff --git a/init/initramfs.c b/init/initramfs.c
index 919b40fb07bada..f2ec2f024f9e67 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -347,14 +347,14 @@ static int __init do_name(void)
 	} else if (S_ISDIR(mode)) {
 		ksys_mkdir(collected, mode);
 		init_chown(collected, uid, gid, 0);
-		ksys_chmod(collected, mode);
+		init_chmod(collected, mode);
 		dir_add(collected, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
 			ksys_mknod(collected, mode, rdev);
 			init_chown(collected, uid, gid, 0);
-			ksys_chmod(collected, mode);
+			init_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
 	}
-- 
2.27.0

[PATCH 15/21] init: add an init_eaccess helper

[Christoph Hellwig]

Add a simple helper to check if a file exists based on kernel space file
name and switch the early init code over to it.  Note that this
theoretically changes behavior as it always is based on the effective
permissions.  But during early init that doesn't make a difference.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 13 +++++++++++++
 fs/open.c                     |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/main.c                   |  4 ++--
 5 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 098e9b69c32ef6..abc152f41e648b 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -105,6 +105,19 @@ int __init init_chmod(const char *filename, umode_t mode)
 	return error;
 }
 
+int __init init_eaccess(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW, &path);
+	if (error)
+		return error;
+	error = inode_permission(d_inode(path.dentry), MAY_ACCESS);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index 7ba89eae46c560..aafecd1f7ba1a5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -394,7 +394,7 @@ static const struct cred *access_override_creds(void)
 	return old_cred;
 }
 
-long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
+static long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
 {
 	struct path path;
 	struct inode *inode;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 2b1b4dc586825f..7031c0934bee9f 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -7,5 +7,6 @@ int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
+int __init init_eaccess(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8b71fa321ca20c..a2779638e41445 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname,
 	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
-
-static inline long ksys_access(const char __user *filename, int mode)
-{
-	return do_faccessat(AT_FDCWD, filename, mode, 0);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/main.c b/init/main.c
index c2c9143db96795..6e2a4a078b78c4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -96,6 +96,7 @@
 #include <linux/jump_label.h>
 #include <linux/mem_encrypt.h>
 #include <linux/kcsan.h>
+#include <linux/init_syscalls.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -1514,8 +1515,7 @@ static noinline void __init kernel_init_freeable(void)
 	 * check if there is an early userspace init.  If yes, let it do all
 	 * the work
 	 */
-	if (ksys_access((const char __user *)
-			ramdisk_execute_command, 0) != 0) {
+	if (init_eaccess(ramdisk_execute_command) != 0) {
 		ramdisk_execute_command = NULL;
 		prepare_namespace();
 	}
-- 
2.27.0

[PATCH 16/21] init: add an init_link helper

[Christoph Hellwig]

Add a simple helper to link with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_link.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 33 +++++++++++++++++++++++++++++++++
 fs/internal.h                 |  3 +--
 fs/namei.c                    |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/initramfs.c              |  2 +-
 6 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index abc152f41e648b..339ac1a52ca150 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -118,6 +118,39 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_link(const char *oldname, const char *newname)
+{
+	struct dentry *new_dentry;
+	struct path old_path, new_path;
+	int error;
+
+	error = kern_path(oldname, 0, &old_path);
+	if (error)
+		return error;
+
+	new_dentry = kern_path_create(AT_FDCWD, newname, &new_path, 0);
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry))
+		goto out;
+
+	error = -EXDEV;
+	if (old_path.mnt != new_path.mnt)
+		goto out_dput;
+	error = may_linkat(&old_path);
+	if (unlikely(error))
+		goto out_dput;
+	error = security_path_link(old_path.dentry, &new_path, new_dentry);
+	if (error)
+		goto out_dput;
+	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry,
+			 NULL);
+out_dput:
+	done_path_create(&new_path, new_dentry);
+out:
+	path_put(&old_path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 6d82681c7d8372..58451b033d2698 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -69,8 +69,7 @@ long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname);
-int do_linkat(int olddfd, const char __user *oldname, int newdfd,
-	      const char __user *newname, int flags);
+int may_linkat(struct path *link);
 
 /*
  * namespace.c
diff --git a/fs/namei.c b/fs/namei.c
index d75a6039ae3966..13de64c6be7640 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1024,7 +1024,7 @@ static bool safe_hardlink_source(struct inode *inode)
  *
  * Returns 0 if successful, -ve on error.
  */
-static int may_linkat(struct path *link)
+int may_linkat(struct path *link)
 {
 	struct inode *inode = link->dentry->d_inode;
 
@@ -4086,7 +4086,7 @@ EXPORT_SYMBOL(vfs_link);
  * with linux 2.0, and to avoid hard-linking to directories
  * and other special files.  --ADM
  */
-int do_linkat(int olddfd, const char __user *oldname, int newdfd,
+static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
 	      const char __user *newname, int flags)
 {
 	struct dentry *new_dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 7031c0934bee9f..5ca15a5b55b7d7 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,5 +8,6 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_link(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a2779638e41445..4b18b91ce46573 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1295,15 +1295,6 @@ static inline long ksys_mknod(const char __user *filename, umode_t mode,
 	return do_mknodat(AT_FDCWD, filename, mode, dev);
 }
 
-extern int do_linkat(int olddfd, const char __user *oldname, int newdfd,
-		     const char __user *newname, int flags);
-
-static inline long ksys_link(const char __user *oldname,
-			     const char __user *newname)
-{
-	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/initramfs.c b/init/initramfs.c
index f2ec2f024f9e67..48c137142fed7f 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -311,7 +311,7 @@ static int __init maybe_link(void)
 		char *old = find_link(major, minor, ino, mode, collected);
 		if (old) {
 			clean_path(collected, 0);
-			return (ksys_link(old, collected) < 0) ? -1 : 1;
+			return (init_link(old, collected) < 0) ? -1 : 1;
 		}
 	}
 	return 0;
-- 
2.27.0

[PATCH 17/21] init: add an init_symlink helper

[Christoph Hellwig]

Add a simple helper to symlink with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_symlink.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 16 ++++++++++++++++
 fs/internal.h                 |  2 --
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/initramfs.c              |  2 +-
 6 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 339ac1a52ca150..082ff1004f06b3 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -151,6 +151,22 @@ int __init init_link(const char *oldname, const char *newname)
 	return error;
 }
 
+int __init init_symlink(const char *oldname, const char *newname)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	dentry = kern_path_create(AT_FDCWD, newname, &path, 0);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	error = security_path_symlink(&path, dentry, oldname);
+	if (!error)
+		error = vfs_symlink(path.dentry->d_inode, dentry, oldname);
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 58451b033d2698..40b50a222d7a22 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -67,8 +67,6 @@ long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
-long do_symlinkat(const char __user *oldname, int newdfd,
-		  const char __user *newname);
 int may_linkat(struct path *link);
 
 /*
diff --git a/fs/namei.c b/fs/namei.c
index 13de64c6be7640..2f6fa53eb3da28 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3955,7 +3955,7 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-long do_symlinkat(const char __user *oldname, int newdfd,
+static long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname)
 {
 	int error;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 5ca15a5b55b7d7..125f55ae3f80b8 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -9,5 +9,6 @@ int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
 int __init init_link(const char *oldname, const char *newname);
+int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 4b18b91ce46573..7cdc0d749a049f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1277,15 +1277,6 @@ static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
 	return do_mkdirat(AT_FDCWD, pathname, mode);
 }
 
-extern long do_symlinkat(const char __user *oldname, int newdfd,
-			 const char __user *newname);
-
-static inline long ksys_symlink(const char __user *oldname,
-				const char __user *newname)
-{
-	return do_symlinkat(oldname, AT_FDCWD, newname);
-}
-
 extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		       unsigned int dev);
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 48c137142fed7f..889c470b0c2aba 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -390,7 +390,7 @@ static int __init do_symlink(void)
 {
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
-	ksys_symlink(collected + N_ALIGN(name_len), collected);
+	init_symlink(collected + N_ALIGN(name_len), collected);
 	init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW);
 	do_utime(collected, mtime);
 	state = SkipIt;
-- 
2.27.0

[PATCH 18/21] init: add an init_mkdir helper

[Christoph Hellwig]

Add a simple helper to mkdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_mkdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 18 ++++++++++++++++++
 fs/internal.h                 |  1 -
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/do_mounts_initrd.c       |  2 +-
 init/initramfs.c              |  2 +-
 init/noinitramfs.c            |  5 +++--
 8 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 082ff1004f06b3..6ae3305bece1eb 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -172,6 +172,24 @@ int __init init_unlink(const char *pathname)
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
 }
 
+int __init init_mkdir(const char *pathname, umode_t mode)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	dentry = kern_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mkdir(&path, dentry, mode);
+	if (!error)
+		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_rmdir(const char *pathname)
 {
 	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 40b50a222d7a22..4741e591e923bf 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -64,7 +64,6 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
 long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev);
-long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct path *link);
diff --git a/fs/namei.c b/fs/namei.c
index 2f6fa53eb3da28..d6b25dd32f4d50 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3645,7 +3645,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
-long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
+static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 125f55ae3f80b8..d808985231f8f8 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -11,4 +11,5 @@ int __init init_eaccess(const char *filename);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
+int __init init_mkdir(const char *pathname, umode_t mode);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7cdc0d749a049f..5ef77a91382aa5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1270,13 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-
-static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
-{
-	return do_mkdirat(AT_FDCWD, pathname, mode);
-}
-
 extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		       unsigned int dev);
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index a6b447b191dbc8..3f5ac81913dde4 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -81,7 +81,7 @@ static void __init handle_initrd(void)
 	create_dev("/dev/root.old", Root_RAM0);
 	/* mount initrd on rootfs' /root */
 	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
-	ksys_mkdir("/old", 0700);
+	init_mkdir("/old", 0700);
 	init_chdir("/old");
 
 	/*
diff --git a/init/initramfs.c b/init/initramfs.c
index 889c470b0c2aba..076e66f11bda8d 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -345,7 +345,7 @@ static int __init do_name(void)
 			state = CopyFile;
 		}
 	} else if (S_ISDIR(mode)) {
-		ksys_mkdir(collected, mode);
+		init_mkdir(collected, mode);
 		init_chown(collected, uid, gid, 0);
 		init_chmod(collected, mode);
 		dir_add(collected, mtime);
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index fa9cdfa7101d3c..94cc4df74b11f2 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -9,6 +9,7 @@
 #include <linux/stat.h>
 #include <linux/kdev_t.h>
 #include <linux/syscalls.h>
+#include <linux/init_syscalls.h>
 
 /*
  * Create a simple rootfs that is similar to the default initramfs
@@ -17,7 +18,7 @@ static int __init default_rootfs(void)
 {
 	int err;
 
-	err = ksys_mkdir((const char __user __force *) "/dev", 0755);
+	err = init_mkdir("/dev", 0755);
 	if (err < 0)
 		goto out;
 
@@ -27,7 +28,7 @@ static int __init default_rootfs(void)
 	if (err < 0)
 		goto out;
 
-	err = ksys_mkdir((const char __user __force *) "/root", 0700);
+	err = init_mkdir("/root", 0700);
 	if (err < 0)
 		goto out;
 
-- 
2.27.0

[PATCH 19/21] init: add an init_mknod helper

[Christoph Hellwig]

Add a simple helper to mknod with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_mknod.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 25 +++++++++++++++++++++++++
 fs/internal.h                 |  2 --
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/do_mounts.h              |  2 +-
 init/initramfs.c              |  2 +-
 init/noinitramfs.c            |  3 +--
 8 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 6ae3305bece1eb..50813d2913b57b 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -118,6 +118,31 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	if (S_ISFIFO(mode) || S_ISSOCK(mode))
+		dev = 0;
+	else if (!(S_ISBLK(mode) || S_ISCHR(mode)))
+		return -EINVAL;
+
+	dentry = kern_path_create(AT_FDCWD, filename, &path, 0);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mknod(&path, dentry, mode, dev);
+	if (!error)
+		error = vfs_mknod(path.dentry->d_inode, dentry, mode,
+				  new_decode_dev(dev));
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_link(const char *oldname, const char *newname)
 {
 	struct dentry *new_dentry;
diff --git a/fs/internal.h b/fs/internal.h
index 4741e591e923bf..07e145b2f88c4a 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -62,8 +62,6 @@ extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
 			   struct path *path, struct path *root);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
-long do_mknodat(int dfd, const char __user *filename, umode_t mode,
-		unsigned int dev);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct path *link);
diff --git a/fs/namei.c b/fs/namei.c
index d6b25dd32f4d50..fde8fe086c090d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3564,7 +3564,7 @@ static int may_mknod(umode_t mode)
 	}
 }
 
-long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev)
 {
 	struct dentry *dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index d808985231f8f8..fa1fe7a877795f 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,6 +8,7 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_mknod(const char *filename, umode_t mode, unsigned int dev);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5ef77a91382aa5..63046c5e9fc5d4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1270,15 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
-		       unsigned int dev);
-
-static inline long ksys_mknod(const char __user *filename, umode_t mode,
-			      unsigned int dev)
-{
-	return do_mknodat(AT_FDCWD, filename, mode, dev);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 104d8431725aeb..7a29ac3e427bab 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -17,7 +17,7 @@ extern int root_mountflags;
 static inline __init int create_dev(char *name, dev_t dev)
 {
 	init_unlink(name);
-	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
+	return init_mknod(name, S_IFBLK | 0600, new_encode_dev(dev));
 }
 
 #ifdef CONFIG_BLK_DEV_RAM
diff --git a/init/initramfs.c b/init/initramfs.c
index 076e66f11bda8d..9b2d93a2eb5e4b 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -352,7 +352,7 @@ static int __init do_name(void)
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
-			ksys_mknod(collected, mode, rdev);
+			init_mknod(collected, mode, rdev);
 			init_chown(collected, uid, gid, 0);
 			init_chmod(collected, mode);
 			do_utime(collected, mtime);
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 94cc4df74b11f2..3d62b07f3bb9c3 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -22,8 +22,7 @@ static int __init default_rootfs(void)
 	if (err < 0)
 		goto out;
 
-	err = ksys_mknod((const char __user __force *) "/dev/console",
-			S_IFCHR | S_IRUSR | S_IWUSR,
+	err = init_mknod("/dev/console", S_IFCHR | S_IRUSR | S_IWUSR,
 			new_encode_dev(MKDEV(5, 1)));
 	if (err < 0)
 		goto out;
-- 
2.27.0

[PATCH 20/21] init: add an init_stat helper

[Christoph Hellwig]

Add a simple helper to stat with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/md/md-autodetect.c    |  3 ++-
 fs/for_init.c                 | 15 +++++++++++++++
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  3 ++-
 4 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 14b6e86814c061..6bbec89976a748 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -5,6 +5,7 @@
 #include <linux/mount.h>
 #include <linux/major.h>
 #include <linux/delay.h>
+#include <linux/init_syscalls.h>
 #include <linux/raid/detect.h>
 #include <linux/raid/md_u.h>
 #include <linux/raid/md_p.h>
@@ -151,7 +152,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 		if (strncmp(devname, "/dev/", 5) == 0)
 			devname += 5;
 		snprintf(comp_name, 63, "/dev/%s", devname);
-		if (vfs_stat(comp_name, &stat) == 0 && S_ISBLK(stat.mode))
+		if (init_stat(comp_name, &stat, 0) == 0 && S_ISBLK(stat.mode))
 			dev = new_decode_dev(stat.rdev);
 		if (!dev) {
 			pr_warn("md: Unknown device name: %s\n", devname);
diff --git a/fs/for_init.c b/fs/for_init.c
index 50813d2913b57b..919a50130a5919 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -118,6 +118,21 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_stat(const char *filename, struct kstat *stat, int flags)
+{
+	int lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	error = kern_path(filename, lookup_flags, &path);
+	if (error)
+		return error;
+	error = vfs_getattr(&path, stat, STATX_BASIC_STATS,
+			    flags | AT_NO_AUTOMOUNT);
+	path_put(&path);
+	return error;
+}
+
 int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
 {
 	struct dentry *dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index fa1fe7a877795f..b2fda50daca6c5 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,6 +8,7 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_stat(const char *filename, struct kstat *stat, int flags);
 int __init init_mknod(const char *filename, umode_t mode, unsigned int dev);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
diff --git a/init/initramfs.c b/init/initramfs.c
index 9b2d93a2eb5e4b..b1be3ada3ce4b3 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -297,7 +297,8 @@ static void __init clean_path(char *path, umode_t fmode)
 {
 	struct kstat st;
 
-	if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) {
+	if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
+	    (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
 			init_rmdir(path);
 		else
-- 
2.27.0

[PATCH 21/21] init: add an init_utimes helper

[Christoph Hellwig]

Add a simple helper to set timestamps with a kernel space file name and
switch the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/for_init.c                 | 13 +++++++++++++
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  3 +--
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/fs/for_init.c b/fs/for_init.c
index 919a50130a5919..4eee11ad63ffce 100644
--- a/fs/for_init.c
+++ b/fs/for_init.c
@@ -234,3 +234,16 @@ int __init init_rmdir(const char *pathname)
 {
 	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
 }
+
+int __init init_utimes(char *filename, struct timespec64 *ts)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, 0, &path);
+	if (error)
+		return error;
+	error = vfs_utimes(&path, ts);
+	path_put(&path);
+	return error;
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index b2fda50daca6c5..3654b525ac0b17 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -15,3 +15,4 @@ int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_mkdir(const char *pathname, umode_t mode);
 int __init init_rmdir(const char *pathname);
+int __init init_utimes(char *filename, struct timespec64 *ts);
diff --git a/init/initramfs.c b/init/initramfs.c
index b1be3ada3ce4b3..b9dfc941a4c3e4 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -110,8 +110,7 @@ static long __init do_utime(char *filename, time64_t mtime)
 	t[0].tv_nsec = 0;
 	t[1].tv_sec = mtime;
 	t[1].tv_nsec = 0;
-
-	return do_utimes(AT_FDCWD, filename, t, AT_SYMLINK_NOFOLLOW);
+	return init_utimes(filename, t);
 }
 
 static __initdata LIST_HEAD(dir_list);
-- 
2.27.0

Re: add file system helpers that take kernel pointers for the init code v3

[Linus Torvalds]

On Sun, Jul 26, 2020 at 12:14 AM Christoph Hellwig <hch@lst.de> wrote:
>
> Hi Al and Linus,
>
> currently a lot of the file system calls in the early in code (and the
> devtmpfs kthread) rely on the implicit set_fs(KERNEL_DS) during boot.
> This is one of the few last remaining places we need to deal with to kill
> off set_fs entirely, so this series adds new helpers that take kernel
> pointers.  These helpers are in init/ and marked __init and thus will
> be discarded after bootup.  A few also need to be duplicated in devtmpfs,
> though unfortunately.

I see nothing objectionable here.

The only bikeshed comment I have is that I think the "for_init.c" name
is ugly and pointless - I think you could just call it "fs/init.c" and
it's both simpler and more straightforward. It _is_ init code, it's
not "for" init.

Other than that it all looked straightforward to me.

                Linus

Re: add file system helpers that take kernel pointers for the init code v3

[Christoph Hellwig]

On Sun, Jul 26, 2020 at 08:49:28AM -0700, Linus Torvalds wrote:
> On Sun, Jul 26, 2020 at 12:14 AM Christoph Hellwig <hch@lst.de> wrote:
> >
> > Hi Al and Linus,
> >
> > currently a lot of the file system calls in the early in code (and the
> > devtmpfs kthread) rely on the implicit set_fs(KERNEL_DS) during boot.
> > This is one of the few last remaining places we need to deal with to kill
> > off set_fs entirely, so this series adds new helpers that take kernel
> > pointers.  These helpers are in init/ and marked __init and thus will
> > be discarded after bootup.  A few also need to be duplicated in devtmpfs,
> > though unfortunately.
> 
> I see nothing objectionable here.
> 
> The only bikeshed comment I have is that I think the "for_init.c" name
> is ugly and pointless - I think you could just call it "fs/init.c" and
> it's both simpler and more straightforward. It _is_ init code, it's
> not "for" init.

That was Al's suggestion.  I personally don't care, so if between the
two of you, you can come up with a preferred choice I'll switch to it.

Re: add file system helpers that take kernel pointers for the init code v3

[Al Viro]

On Sun, Jul 26, 2020 at 05:52:04PM +0200, Christoph Hellwig wrote:
> On Sun, Jul 26, 2020 at 08:49:28AM -0700, Linus Torvalds wrote:
> > On Sun, Jul 26, 2020 at 12:14 AM Christoph Hellwig <hch@lst.de> wrote:
> > >
> > > Hi Al and Linus,
> > >
> > > currently a lot of the file system calls in the early in code (and the
> > > devtmpfs kthread) rely on the implicit set_fs(KERNEL_DS) during boot.
> > > This is one of the few last remaining places we need to deal with to kill
> > > off set_fs entirely, so this series adds new helpers that take kernel
> > > pointers.  These helpers are in init/ and marked __init and thus will
> > > be discarded after bootup.  A few also need to be duplicated in devtmpfs,
> > > though unfortunately.
> > 
> > I see nothing objectionable here.
> > 
> > The only bikeshed comment I have is that I think the "for_init.c" name
> > is ugly and pointless - I think you could just call it "fs/init.c" and
> > it's both simpler and more straightforward. It _is_ init code, it's
> > not "for" init.
> 
> That was Al's suggestion.  I personally don't care, so if between the
> two of you, you can come up with a preferred choice I'll switch to it.

I can live with either variant; the only problem with fs/init.c is that
such name would imply the init code _of_ VFS, rather than VFS helpers for
init.

Anyway, the series looks generally sane; if no other objections are raised,
I'm adding it to vfs.git#for-next

Re: add file system helpers that take kernel pointers for the init code v3

[Christoph Hellwig]

On Sun, Jul 26, 2020 at 05:21:13PM +0100, Al Viro wrote:
> On Sun, Jul 26, 2020 at 05:52:04PM +0200, Christoph Hellwig wrote:
> > On Sun, Jul 26, 2020 at 08:49:28AM -0700, Linus Torvalds wrote:
> > > On Sun, Jul 26, 2020 at 12:14 AM Christoph Hellwig <hch@lst.de> wrote:
> > > >
> > > > Hi Al and Linus,
> > > >
> > > > currently a lot of the file system calls in the early in code (and the
> > > > devtmpfs kthread) rely on the implicit set_fs(KERNEL_DS) during boot.
> > > > This is one of the few last remaining places we need to deal with to kill
> > > > off set_fs entirely, so this series adds new helpers that take kernel
> > > > pointers.  These helpers are in init/ and marked __init and thus will
> > > > be discarded after bootup.  A few also need to be duplicated in devtmpfs,
> > > > though unfortunately.
> > > 
> > > I see nothing objectionable here.
> > > 
> > > The only bikeshed comment I have is that I think the "for_init.c" name
> > > is ugly and pointless - I think you could just call it "fs/init.c" and
> > > it's both simpler and more straightforward. It _is_ init code, it's
> > > not "for" init.
> > 
> > That was Al's suggestion.  I personally don't care, so if between the
> > two of you, you can come up with a preferred choice I'll switch to it.
> 
> I can live with either variant; the only problem with fs/init.c is that
> such name would imply the init code _of_ VFS, rather than VFS helpers for
> init.
> 
> Anyway, the series looks generally sane; if no other objections are raised,
> I'm adding it to vfs.git#for-next

Thanks!

Note that this is based on top of my init-user-pointers branch, so you'll
need to pull that in as.

Btw, care to take a look at 

http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/kernel_readwrite

it has been in linux-next for 2 1/2 weeks, and the only interesting
thing found was that btrfs didn't wire up iter_splice_write, which has
already been fixed in mainline.

Re: add file system helpers that take kernel pointers for the init code v3

[Christoph Hellwig]

On Sun, Jul 26, 2020 at 06:24:26PM +0200, Christoph Hellwig wrote:
> Btw, care to take a look at 
> 
> http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/kernel_readwrite
> 
> it has been in linux-next for 2 1/2 weeks, and the only interesting
> thing found was that btrfs didn't wire up iter_splice_write, which has
> already been fixed in mainline.

Actually, the above is a stale old branch sorry.  The real one that has
been in linux-next is:

http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/set_fs-rw

Re: add file system helpers that take kernel pointers for the init code v3

[Al Viro]

On Sun, Jul 26, 2020 at 06:26:27PM +0200, Christoph Hellwig wrote:
> On Sun, Jul 26, 2020 at 06:24:26PM +0200, Christoph Hellwig wrote:
> > Btw, care to take a look at 
> > 
> > http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/kernel_readwrite
> > 
> > it has been in linux-next for 2 1/2 weeks, and the only interesting
> > thing found was that btrfs didn't wire up iter_splice_write, which has
> > already been fixed in mainline.
> 
> Actually, the above is a stale old branch sorry.  The real one that has
> been in linux-next is:
> 
> http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/set_fs-rw

Will check... still crawling through the accumulated VFS-related threads
from the last weeks ;-/