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 <kay.sievers@vrfy.org>
Signed-off-by: Jan Blunck <jblunck@suse.de>
Tested-By: Harald Hoyer <harald@redhat.com>
Tested-By: Scott James Remnant <scott@ubuntu.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

11 files changed, 422 insertions, 7 deletions

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 8f006f96ff53..ee377270beb9 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -8,6 +8,31 @@ config UEVENT_HELPER_PATH
           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
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 1b2640ce74f0..c12c7f2f2a6f 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,6 +4,7 @@ obj-y			:= core.o sys.o bus.o dd.o \
                            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
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 503d59c57501..2ca7f5b7b824 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -139,3 +139,9 @@ static inline void module_add_driver(struct module *mod,
                                      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
diff --git a/drivers/base/core.c b/drivers/base/core.c
index a992985d1fab..390e664ec1c7 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -929,6 +929,8 @@ int device_add(struct device *dev)
                 error = device_create_sys_dev_entry(dev);
                 if (error)
                         goto devtattrError;
+
+                devtmpfs_create_node(dev);
         }
 
         error = device_add_class_symlinks(dev);
@@ -1075,6 +1077,7 @@ void device_del(struct device *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);
         }
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
new file mode 100644
index 000000000000..fd488ad4263a
--- /dev/null
+++ b/drivers/base/devtmpfs.c
@@ -0,0 +1,367 @@
+/*
+ * devtmpfs - kernel-maintained tmpfs-based /dev
+ *
+ * Copyright (C) 2009, Kay Sievers <kay.sievers@vrfy.org>
+ *
+ * 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)
+