Driver Core: devtmpfs - kernel-maintained tmpfs-based /dev

Devtmpfs lets the kernel create a tmpfs instance called devtmpfs
very early at kernel initialization, before any driver-core device
is registered. Every device with a major/minor will provide a
device node in devtmpfs.

Devtmpfs can be changed and altered by userspace at any time,
and in any way needed - just like today's udev-mounted tmpfs.
Unmodified udev versions will run just fine on top of it, and will
recognize an already existing kernel-created device node and use it.
The default node permissions are root:root 0600. Proper permissions
and user/group ownership, meaningful symlinks, all other policy still
needs to be applied by userspace.

If a node is created by devtmps, devtmpfs will remove the device node
when the device goes away. If the device node was created by
userspace, or the devtmpfs created node was replaced by userspace, it
will no longer be removed by devtmpfs.

If it is requested to auto-mount it, it makes init=/bin/sh work
without any further userspace support. /dev will be fully populated
and dynamic, and always reflect the current device state of the kernel.
With the commonly used dynamic device numbers, it solves the problem
where static devices nodes may point to the wrong devices.

It is intended to make the initial bootup logic simpler and more robust,
by de-coupling the creation of the inital environment, to reliably run
userspace processes, from a complex userspace bootstrap logic to provide
a working /dev.

Signed-off-by: Kay Sievers <[e-mail]>
Signed-off-by: Jan Blunck <[e-mail]>
Tested-By: Harald Hoyer <[e-mail]>
Tested-By: Scott James Remnant <[e-mail]>
Signed-off-by: Greg Kroah-Hartman <[e-mail]>

drivers/base/Kconfig

···
 	  Path to uevent helper program forked by the kernel for
 	  every uevent.
 
+config DEVTMPFS
+	bool "Create a kernel maintained /dev tmpfs (EXPERIMENTAL)"
+	depends on HOTPLUG && SHMEM && TMPFS
+	help
+	  This creates a tmpfs filesystem, and mounts it at bootup
+	  and mounts it at /dev. The kernel driver core creates device
+	  nodes for all registered devices in that filesystem. All device
+	  nodes are owned by root and have the default mode of 0600.
+	  Userspace can add and delete the nodes as needed. This is
+	  intended to simplify bootup, and make it possible to delay
+	  the initial coldplug at bootup done by udev in userspace.
+	  It should also provide a simpler way for rescue systems
+	  to bring up a kernel with dynamic major/minor numbers.
+	  Meaningful symlinks, permissions and device ownership must
+	  still be handled by userspace.
+	  If unsure, say N here.
+
+config DEVTMPFS_MOUNT
+	bool "Automount devtmpfs at /dev"
+	depends on DEVTMPFS
+	help
+	  This will mount devtmpfs at /dev if the kernel mounts the root
+	  filesystem. It will not affect initramfs based mounting.
+	  If unsure, say N here.
+
 config STANDALONE
 	bool "Select only drivers that don't need compile-time external firmware" if EXPERIMENTAL
 	default y

drivers/base/Makefile

···
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o
+obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o

drivers/base/base.h

···
 				     struct device_driver *drv) { }
 static inline void module_remove_driver(struct device_driver *drv) { }
 #endif
+
+#ifdef CONFIG_DEVTMPFS
+extern int devtmpfs_init(void);
+#else
+static inline int devtmpfs_init(void) { return 0; }
+#endif

drivers/base/core.c

···
 		error = device_create_sys_dev_entry(dev);
 		if (error)
 			goto devtattrError;
+
+		devtmpfs_create_node(dev);
 	}
 
 	error = device_add_class_symlinks(dev);
···
 	if (parent)
 		klist_del(&dev->p->knode_parent);
 	if (MAJOR(dev->devt)) {
+		devtmpfs_delete_node(dev);
 		device_remove_sys_dev_entry(dev);
 		device_remove_file(dev, &devt_attr);
 	}

drivers/base/devtmpfs.c

···
+/*
+ * devtmpfs - kernel-maintained tmpfs-based /dev
+ *
+ * Copyright (C) 2009, Kay Sievers <[e-mail]>
+ *
+ * During bootup, before any driver core device is registered,
+ * devtmpfs, a tmpfs-based filesystem is created. Every driver-core
+ * device which requests a device node, will add a node in this
+ * filesystem. The node is named after the the name of the device,
+ * or the susbsytem can provide a custom name. All devices are
+ * owned by root and have a mode of 0600.
+ */
+
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/mount.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
+#include <linux/cred.h>
+#include <linux/init_task.h>
+
+static struct vfsmount *dev_mnt;
+
+#if defined CONFIG_DEVTMPFS_MOUNT
+static int dev_mount = 1;
+#else
+static int dev_mount;
+#endif
+
+static int __init mount_param(char *str)
+{
+	dev_mount = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("devtmpfs.mount=", mount_param);
+
+static int dev_get_sb(struct file_system_type *fs_type, int flags,
+		      const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	return get_sb_single(fs_type, flags, data, shmem_fill_super, mnt);
+}
+
+static struct file_system_type dev_fs_type = {
+	.name = "devtmpfs",
+	.get_sb = dev_get_sb,
+	.kill_sb = kill_litter_super,
+};
+
+#ifdef CONFIG_BLOCK
+static inline int is_blockdev(struct device *dev)
+{
+	return dev->class == &block_class;
+}
+#else
+static inline int is_blockdev(struct device *dev) { return 0; }
+#endif
+
+static int dev_mkdir(const char *name, mode_t mode)
+{
+	struct nameidata nd;
+	struct dentry *dentry;
+	int err;
+
+	err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+			      name, LOOKUP_PARENT, &nd);
+	if (err)
+		return err;
+
+	dentry = lookup_create(&nd, 1);
+	if (!IS_ERR(dentry)) {
+		err = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
+		dput(dentry);
+	} else {
+		err = PTR_ERR(dentry);
+	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+
+	path_put(&nd.path);
+	return err;
+}
+
+static int create_path(const char *nodepath)
+{
+	char *path;
+	struct nameidata nd;
+	int err = 0;
+
+	path = kstrdup(nodepath, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+			      path, LOOKUP_PARENT, &nd);
+	if (err == 0) {
+		struct dentry *dentry;
+
+		/* create directory right away */
+		dentry = lookup_create(&nd, 1);
+		if (!IS_ERR(dentry)) {
+			err = vfs_mkdir(nd.path.dentry->d_inode,
+					dentry, 0755);
+			dput(dentry);
+		}
+		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+
+		path_put(&nd.path);
+	} else if (err == -ENOENT) {
+		char *s;
+
+		/* parent directories do not exist, create them */
+		s = path;
+		while (1) {
+			s = strchr(s, '/');
+			if (!s)
+				break;
+			s[0] = '\0';
+			err = dev_mkdir(path, 0755);
+			if (err && err != -EEXIST)
+				break;
+			s[0] = '/';
+			s++;
+		}
+	}
+
+	kfree(path);
+	return err;
+}
+
+int devtmpfs_create_node(struct device *dev)
+{
+	const char *tmp = NULL;
+	const char *nodename;
+	const struct cred *curr_cred;
+	mode_t mode;
+	struct nameidata nd;
+	struct dentry *dentry;
+	int err;
+
+	if (!dev_mnt)
+		return 0;
+
+	nodename = device_get_nodename(dev, &tmp);
+	if (!nodename)
+		return -ENOMEM;
+
+	if (is_blockdev(dev))
+		mode = S_IFBLK|0600;
+	else
+		mode = S_IFCHR|0600;
+
+	curr_cred = override_creds(&init_cred);
+	err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+			      nodename, LOOKUP_PARENT, &nd);
+	if (err == -ENOENT) {
+		/* create missing parent directories */
+		create_path(nodename);
+		err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+				      nodename, LOOKUP_PARENT, &nd);
+		if (err)
+			goto out;
+	}
+
+	dentry = lookup_create(&nd, 0);
+	if (!IS_ERR(dentry)) {
+		err = vfs_mknod(nd.path.dentry->d_inode,
+				dentry, mode, dev->devt);
+		/* mark as kernel created inode */
+		if (!err)
+			dentry->d_inode->i_private = &dev_mnt;
+		dput(dentry);
+	} else {
+		err = PTR_ERR(dentry);
+	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+
+	path_put(&nd.path);
+out:
+	kfree(tmp);
+	revert_creds(curr_cred);
+	return err;
+}
+
+static int dev_rmdir(const char *name)
+{
+	struct nameidata nd;
+	struct dentry *dentry;
+	int err;
+
+	err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+			      name, LOOKUP_PARENT, &nd);
+	if (err)
+		return err;
+
+	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+	if (!IS_ERR(dentry)) {
+		if (dentry->d_inode)
+			err = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+		else
+			err = -ENOENT;
+		dput(dentry);
+	} else {
+		err = PTR_ERR(dentry);
+	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+
+	path_put(&nd.path);
+	return err;
+}
+
+static int delete_path(const char *nodepath)
+{
+	const char *path;
+	int err = 0;
+
+	path = kstrdup(nodepath, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	while (1) {
+		char *base;
+
+		base = strrchr(path, '/');
+		if (!base)
+			break;
+		base[0] = '\0';
+		err = dev_rmdir(path);
+		if (err)
+			break;
+	}
+
+	kfree(path);
+	return err;
+}
+
+static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+{
+	/* did we create it */
+	if (inode->i_private != &dev_mnt)
+		return 0;
+
+	/* does the dev_t match */
+	if (is_blockdev(dev)) {
+		if (!S_ISBLK(stat->mode))
+			return 0;
+	} else {
+		if (!S_ISCHR(stat->mode))
+			return 0;
+	}
+	if (stat->rdev != dev->devt)
+		return 0;
+
+	/* ours */
+	return 1;
+}
+
+int devtmpfs_delete_node(struct device *dev)
+{
+	const char *tmp = NULL;
+	const char *nodename;
+	const struct cred *curr_cred;
+	struct nameidata nd;
+	struct dentry *dentry;
+	struct kstat stat;
+	int deleted = 1;
+	int err;
+
+	if (!dev_mnt)
+		return 0;
+
+	nodename = device_get_nodename(dev, &tmp);
+	if (!nodename)
+		return -ENOMEM;
+
+	curr_cred = override_creds(&init_cred);
+	err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
+			      nodename, LOOKUP_PARENT, &nd);
+	if (err)
+		goto out;
+
+	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+	if (!IS_ERR(dentry)) {
+		if (dentry->d_inode) {
+			err = vfs_getattr(nd.path.mnt, dentry, &stat);
+			if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
+				err = vfs_unlink(nd.path.dentry->d_inode,
+						 dentry);
+				if (!err || err == -ENOENT)
+					deleted = 1;
+			}
+		} else {
+			err = -ENOENT;
+		}
+		dput(dentry);
+	} else {
+		err = PTR_ERR(dentry);
+	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+
+	path_put(&nd.path);
+	if (deleted && strchr(nodename, '/'))
+		delete_path(nodename);
+out:
+	kfree(tmp);
+	revert_creds(curr_cred);
+	return err;
+}
+
+/*
+ * If configured, or requested by the commandline, devtmpfs will be
+ * auto-mounted after the kernel mounted the root filesystem.
+ */
+int devtmpfs_mount(const char *mountpoint)
+{
+	struct path path;
+	int err;
+
+	if (!dev_mount)
+		return 0;
+
+	if (!dev_mnt)
+		return 0;
+
+	err = kern_path(mountpoint, LOOKUP_FOLLOW, &path);
+	if (err)
+		return err;
+	err = do_add_mount(dev_mnt, &path, 0, NULL);
+	if (err)
+		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
+	else
+		printk(KERN_INFO "devtmpfs: mounted\n");
+	path_put(&path);
+	return err;
+}
+
+/*
+ * Create devtmpfs instance, driver-core devices will add their device
+ * nodes here.
+ */
+int __init devtmpfs_init(void)
+{
+	int err;
+	struct vfsmount *mnt;
+
+	err = register_filesystem(&dev_fs_type);
+	if (err) {
+		printk(KERN_ERR "devtmpfs: unable to register devtmpfs "
+		       "type %i\n", err);
+		return err;
+	}
+
+	mnt = kern_mount(&dev_fs_type);
+	if (IS_ERR(mnt)) {
+		err = PTR_ERR(mnt);
+		printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
+		unregister_filesystem(&dev_fs_type);
+		return err;
+	}
+	dev_mnt = mnt;
+
+	printk(KERN_INFO "devtmpfs: initialized\n");
+	return 0;
+}

drivers/base/init.c

···
 void __init driver_init(void)
 {
 	/* These are the core pieces */
+	devtmpfs_init();
 	devices_init();
 	buses_init();
 	classes_init();

include/linux/device.h

···
 
 extern void wait_for_device_probe(void);
 
+#ifdef CONFIG_DEVTMPFS
+extern int devtmpfs_create_node(struct device *dev);
+extern int devtmpfs_delete_node(struct device *dev);
+extern int devtmpfs_mount(const char *mountpoint);
+#else
+static inline int devtmpfs_create_node(struct device *dev) { return 0; }
+static inline int devtmpfs_delete_node(struct device *dev) { return 0; }
+static inline int devtmpfs_mount(const char *mountpoint) { return 0; }
+#endif
+
 /* drivers/base/power/shutdown.c */
 extern void device_shutdown(void);
 

include/linux/shmem_fs.h

···
 	return container_of(inode, struct shmem_inode_info, vfs_inode);
 }
 
+extern int init_tmpfs(void);
+extern int shmem_fill_super(struct super_block *sb, void *data, int silent);
+
 #ifdef CONFIG_TMPFS_POSIX_ACL
 int shmem_check_acl(struct inode *, int);
 int shmem_acl_init(struct inode *, struct inode *);

init/do_mounts.c

···
 
 	mount_root();
 out:
+	devtmpfs_mount("dev");
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
 	sys_chroot(".");
 }
-

init/main.c

···
 #include <linux/async.h>
 #include <linux/kmemcheck.h>
 #include <linux/kmemtrace.h>
+#include <linux/shmem_fs.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
···
 	init_workqueues();
 	cpuset_init_smp();
 	usermodehelper_init();
+	init_tmpfs();
 	driver_init();
 	init_irq_proc();
 	do_ctors();

mm/shmem.c

···
 	sb->s_fs_info = NULL;
 }
 
-static int shmem_fill_super(struct super_block *sb,
-			    void *data, int silent)
+int shmem_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
 	struct dentry *root;
···
 	.kill_sb	= kill_litter_super,
 };
 
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
 {
 	int error;
 
···
 	.kill_sb	= kill_litter_super,
 };
 
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
 {
 	BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
 
···
 	vma->vm_ops = &shmem_vm_ops;
 	return 0;
 }
-
-module_init(init_tmpfs)