1 files changed, 201 insertions, 129 deletions

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 7413d065906b..194b44075ac7 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * devtmpfs - kernel-maintained tmpfs-based /dev
  *
@@ -12,11 +13,13 @@
  * overwrite the default setting if needed.
  */
 
+#define pr_fmt(fmt) "devtmpfs: " fmt
+
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/mount.h>
 #include <linux/device.h>
-#include <linux/genhd.h>
+#include <linux/blkdev.h>
 #include <linux/namei.h>
 #include <linux/fs.h>
 #include <linux/shmem_fs.h>
@@ -24,16 +27,20 @@
 #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"
 
-static struct task_struct *thread;
-
-#if defined CONFIG_DEVTMPFS_MOUNT
-static int mount_dev = 1;
+#ifdef CONFIG_DEVTMPFS_SAFE
+#define DEVTMPFS_MFLAGS       (MS_SILENT | MS_NOEXEC | MS_NOSUID)
 #else
-static int mount_dev;
+#define DEVTMPFS_MFLAGS       (MS_SILENT)
 #endif
 
+static struct task_struct *thread;
+
+static int __initdata mount_dev = IS_ENABLED(CONFIG_DEVTMPFS_MOUNT);
+
 static DEFINE_SPINLOCK(req_lock);
 
 static struct req {
@@ -54,30 +61,70 @@ static int __init mount_param(char *str)
 }
 __setup("devtmpfs.mount=", mount_param);
 
-static struct dentry *dev_mount(struct file_system_type *fs_type, int flags,
-		      const char *dev_name, void *data)
+static struct vfsmount *mnt;
+
+static struct file_system_type internal_fs_type = {
+	.name = "devtmpfs",
+#ifdef CONFIG_TMPFS
+	.init_fs_context = shmem_init_fs_context,
+#else
+	.init_fs_context = ramfs_init_fs_context,
+#endif
+	.kill_sb = kill_anon_super,
+};
+
+/* Simply take a ref on the existing mount */
+static int devtmpfs_get_tree(struct fs_context *fc)
 {
+	struct super_block *sb = mnt->mnt_sb;
+
+	atomic_inc(&sb->s_active);
+	down_write(&sb->s_umount);
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+/* Ops are filled in during init depending on underlying shmem or ramfs type */
+struct fs_context_operations devtmpfs_context_ops = {};
+
+/* Call the underlying initialization and set to our ops */
+static int devtmpfs_init_fs_context(struct fs_context *fc)
+{
+	int ret;
 #ifdef CONFIG_TMPFS
-	return mount_single(fs_type, flags, data, shmem_fill_super);
+	ret = shmem_init_fs_context(fc);
 #else
-	return mount_single(fs_type, flags, data, ramfs_fill_super);
+	ret = ramfs_init_fs_context(fc);
 #endif
+	if (ret < 0)
+		return ret;
+
+	fc->ops = &devtmpfs_context_ops;
+
+	return 0;
 }
 
 static struct file_system_type dev_fs_type = {
 	.name = "devtmpfs",
-	.mount = dev_mount,
-	.kill_sb = kill_litter_super,
+	.init_fs_context = devtmpfs_init_fs_context,
 };
 
-#ifdef CONFIG_BLOCK
-static inline int is_blockdev(struct device *dev)
+static int devtmpfs_submit_req(struct req *req, const char *tmp)
 {
-	return dev->class == &block_class;
+	init_completion(&req->done);
+
+	spin_lock(&req_lock);
+	req->next = requests;
+	requests = req;
+	spin_unlock(&req_lock);
+
+	wake_up_process(thread);
+	wait_for_completion(&req->done);
+
+	kfree(tmp);
+
+	return req->err;
 }
-#else
-static inline int is_blockdev(struct device *dev) { return 0; }
-#endif
 
 int devtmpfs_create_node(struct device *dev)
 {
@@ -103,19 +150,7 @@ int devtmpfs_create_node(struct device *dev)
 
 	req.dev = dev;
 
-	init_completion(&req.done);
-
-	spin_lock(&req_lock);
-	req.next = requests;
-	requests = &req;
-	spin_unlock(&req_lock);
-
-	wake_up_process(thread);
-	wait_for_completion(&req.done);
-
-	kfree(tmp);
-
-	return req.err;
+	return devtmpfs_submit_req(&req, tmp);
 }
 
 int devtmpfs_delete_node(struct device *dev)
@@ -133,36 +168,24 @@ int devtmpfs_delete_node(struct device *dev)
 	req.mode = 0;
 	req.dev = dev;
 
-	init_completion(&req.done);
-
-	spin_lock(&req_lock);
-	req.next = requests;
-	requests = &req;
-	spin_unlock(&req_lock);
-
-	wake_up_process(thread);
-	wait_for_completion(&req.done);
-
-	kfree(tmp);
-	return req.err;
+	return devtmpfs_submit_req(&req, tmp);
 }
 
 static int dev_mkdir(const char *name, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
-	int err;
 
-	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
+	dentry = start_creating_path(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	err = vfs_mkdir(path.dentry->d_inode, dentry, mode);
-	if (!err)
+	dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode, NULL);
+	if (!IS_ERR(dentry))
 		/* mark as kernel-created inode */
-		dentry->d_inode->i_private = &thread;
-	done_path_create(&path, dentry);
-	return err;
+		d_inode(dentry)->i_private = &thread;
+	end_creating_path(&path, dentry);
+	return PTR_ERR_OR_ZERO(dentry);
 }
 
 static int create_path(const char *nodepath)
@@ -199,15 +222,16 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 	struct path path;
 	int err;
 
-	dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
+	dentry = start_creating_path(AT_FDCWD, nodename, &path, 0);
 	if (dentry == ERR_PTR(-ENOENT)) {
 		create_path(nodename);
-		dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
+		dentry = start_creating_path(AT_FDCWD, nodename, &path, 0);
 	}
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	err = vfs_mknod(path.dentry->d_inode, dentry, mode, dev->devt);
+	err = vfs_mknod(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode,
+			dev->devt, NULL);
 	if (!err) {
 		struct iattr newattrs;
 
@@ -215,14 +239,14 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		newattrs.ia_uid = uid;
 		newattrs.ia_gid = gid;
 		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
-		mutex_lock(&dentry->d_inode->i_mutex);
-		notify_change(dentry, &newattrs);
-		mutex_unlock(&dentry->d_inode->i_mutex);
+		inode_lock(d_inode(dentry));
+		notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
+		inode_unlock(d_inode(dentry));
 
 		/* mark as kernel-created inode */
-		dentry->d_inode->i_private = &thread;
+		d_inode(dentry)->i_private = &thread;
 	}
-	done_path_create(&path, dentry);
+	end_creating_path(&path, dentry);
 	return err;
 }
 
@@ -232,26 +256,22 @@ static int dev_rmdir(const char *name)
 	struct dentry *dentry;
 	int err;
 
-	dentry = kern_path_locked(name, &parent);
+	dentry = start_removing_path(name, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
-	if (dentry->d_inode) {
-		if (dentry->d_inode->i_private == &thread)
-			err = vfs_rmdir(parent.dentry->d_inode, dentry);
-		else
-			err = -EPERM;
-	} else {
-		err = -ENOENT;
-	}
-	dput(dentry);
-	mutex_unlock(&parent.dentry->d_inode->i_mutex);
-	path_put(&parent);
+	if (d_inode(dentry)->i_private == &thread)
+		err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry),
+				dentry, NULL);
+	else
+		err = -EPERM;
+
+	end_removing_path(&parent, dentry);
 	return err;
 }
 
 static int delete_path(const char *nodepath)
 {
-	const char *path;
+	char *path;
 	int err = 0;
 
 	path = kstrdup(nodepath, GFP_KERNEL);
@@ -274,7 +294,7 @@ static int delete_path(const char *nodepath)
 	return err;
 }
 
-static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+static int dev_mynode(struct device *dev, struct inode *inode)
 {
 	/* did we create it */
 	if (inode->i_private != &thread)
@@ -282,13 +302,13 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta
 
 	/* does the dev_t match */
 	if (is_blockdev(dev)) {
-		if (!S_ISBLK(stat->mode))
+		if (!S_ISBLK(inode->i_mode))
 			return 0;
 	} else {
-		if (!S_ISCHR(stat->mode))
+		if (!S_ISCHR(inode->i_mode))
 			return 0;
 	}
-	if (stat->rdev != dev->devt)
+	if (inode->i_rdev != dev->devt)
 		return 0;
 
 	/* ours */
@@ -299,42 +319,36 @@ static int handle_remove(const char *nodename, struct device *dev)
 {
 	struct path parent;
 	struct dentry *dentry;
-	int deleted = 1;
-	int err;
+	struct inode *inode;
+	int deleted = 0;
+	int err = 0;
 
-	dentry = kern_path_locked(nodename, &parent);
+	dentry = start_removing_path(nodename, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (dentry->d_inode) {
-		struct kstat stat;
-		struct path p = {.mnt = parent.mnt, .dentry = dentry};
-		err = vfs_getattr(&p, &stat);
-		if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
-			struct iattr newattrs;
-			/*
-			 * before unlinking this node, reset permissions
-			 * of possible references like hardlinks
-			 */
-			newattrs.ia_uid = GLOBAL_ROOT_UID;
-			newattrs.ia_gid = GLOBAL_ROOT_GID;
-			newattrs.ia_mode = stat.mode & ~0777;
-			newattrs.ia_valid =
-				ATTR_UID|ATTR_GID|ATTR_MODE;
-			mutex_lock(&dentry->d_inode->i_mutex);
-			notify_change(dentry, &newattrs);
-			mutex_unlock(&dentry->d_inode->i_mutex);
-			err = vfs_unlink(parent.dentry->d_inode, dentry);
-			if (!err || err == -ENOENT)
-				deleted = 1;
-		}
-	} else {
-		err = -ENOENT;
+	inode = d_inode(dentry);
+	if (dev_mynode(dev, inode)) {
+		struct iattr newattrs;
+		/*
+		 * before unlinking this node, reset permissions
+		 * of possible references like hardlinks
+		 */
+		newattrs.ia_uid = GLOBAL_ROOT_UID;
+		newattrs.ia_gid = GLOBAL_ROOT_GID;
+		newattrs.ia_mode = inode->i_mode & ~0777;
+		newattrs.ia_valid =
+			ATTR_UID|ATTR_GID|ATTR_MODE;
+		inode_lock(d_inode(dentry));
+		notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
+		inode_unlock(d_inode(dentry));
+		err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry),
+				 dentry, NULL);
+		if (!err || err == -ENOENT)
+			deleted = 1;
 	}
-	dput(dentry);
-	mutex_unlock(&parent.dentry->d_inode->i_mutex);
+	end_removing_path(&parent, dentry);
 
-	path_put(&parent);
 	if (deleted && strchr(nodename, '/'))
 		delete_path(nodename);
 	return err;
@@ -344,7 +358,7 @@ static int handle_remove(const char *nodename, struct device *dev)
  * If configured, or requested by the commandline, devtmpfs will be
  * auto-mounted after the kernel mounted the root filesystem.
  */
-int devtmpfs_mount(const char *mntdir)
+int __init devtmpfs_mount(void)
 {
 	int err;
 
@@ -354,15 +368,15 @@ int devtmpfs_mount(const char *mntdir)
 	if (!thread)
 		return 0;
 
-	err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, NULL);
+	err = init_mount("devtmpfs", "dev", "devtmpfs", DEVTMPFS_MFLAGS, NULL);
 	if (err)
-		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
+		pr_info("error mounting %d\n", err);
 	else
-		printk(KERN_INFO "devtmpfs: mounted\n");
+		pr_info("mounted\n");
 	return err;
 }
 
-static DECLARE_COMPLETION(setup_done);
+static __initdata DECLARE_COMPLETION(setup_done);
 
 static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid,
 		  struct device *dev)
@@ -373,19 +387,8 @@ static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid,
 		return handle_remove(name, dev);
 }
 
-static int devtmpfsd(void *p)
+static void __noreturn devtmpfs_work_loop(void)
 {
-	char options[] = "mode=0755";
-	int *err = p;
-	*err = sys_unshare(CLONE_NEWNS);
-	if (*err)
-		goto out;
-	*err = sys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options);
-	if (*err)
-		goto out;
-	sys_chdir("/.."); /* will traverse into overmounted root */
-	sys_chroot(".");
-	complete(&setup_done);
 	while (1) {
 		spin_lock(&req_lock);
 		while (requests) {
@@ -405,10 +408,64 @@ static int devtmpfsd(void *p)
 		spin_unlock(&req_lock);
 		schedule();
 	}
-	return 0;
+}
+
+static noinline int __init devtmpfs_setup(void *p)
+{
+	int err;
+
+	err = ksys_unshare(CLONE_NEWNS);
+	if (err)
+		goto out;
+	err = init_mount("devtmpfs", "/", "devtmpfs", DEVTMPFS_MFLAGS, NULL);
+	if (err)
+		goto out;
+	init_chdir("/.."); /* will traverse into overmounted root */
+	init_chroot(".");
 out:
+	*(int *)p = err;
+	return err;
+}
+
+/*
+ * The __ref is because devtmpfs_setup needs to be __init for the routines it
+ * calls.  That call is done while devtmpfs_init, which is marked __init,
+ * synchronously waits for it to complete.
+ */
+static int __ref devtmpfsd(void *p)
+{
+	int err = devtmpfs_setup(p);
+
 	complete(&setup_done);
-	return *err;
+	if (err)
+		return err;
+	devtmpfs_work_loop();
+	return 0;
+}
+
+/*
+ * Get the underlying (shmem/ramfs) context ops to build ours
+ */
+static int devtmpfs_configure_context(void)
+{
+	struct fs_context *fc;
+
+	fc = fs_context_for_reconfigure(mnt->mnt_root, mnt->mnt_sb->s_flags,
+					MS_RMT_MASK);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	/* Set up devtmpfs_context_ops based on underlying type */
+	devtmpfs_context_ops.free	      = fc->ops->free;
+	devtmpfs_context_ops.dup	      = fc->ops->dup;
+	devtmpfs_context_ops.parse_param      = fc->ops->parse_param;
+	devtmpfs_context_ops.parse_monolithic = fc->ops->parse_monolithic;
+	devtmpfs_context_ops.get_tree	      = &devtmpfs_get_tree;
+	devtmpfs_context_ops.reconfigure      = fc->ops->reconfigure;
+
+	put_fs_context(fc);
+
+	return 0;
 }
 
 /*
@@ -417,10 +474,24 @@ out:
  */
 int __init devtmpfs_init(void)
 {
-	int err = register_filesystem(&dev_fs_type);
+	char opts[] = "mode=0755";
+	int err;
+
+	mnt = vfs_kern_mount(&internal_fs_type, 0, "devtmpfs", opts);
+	if (IS_ERR(mnt)) {
+		pr_err("unable to create devtmpfs %ld\n", PTR_ERR(mnt));
+		return PTR_ERR(mnt);
+	}
+
+	err = devtmpfs_configure_context();
+	if (err) {
+		pr_err("unable to configure devtmpfs type %d\n", err);
+		return err;
+	}
+
+	err = register_filesystem(&dev_fs_type);
 	if (err) {
-		printk(KERN_ERR "devtmpfs: unable to register devtmpfs "
-		       "type %i\n", err);
+		pr_err("unable to register devtmpfs type %d\n", err);
 		return err;
 	}
 
@@ -433,11 +504,12 @@ int __init devtmpfs_init(void)
 	}
 
 	if (err) {
-		printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
+		pr_err("unable to create devtmpfs %d\n", err);
 		unregister_filesystem(&dev_fs_type);
+		thread = NULL;
 		return err;
 	}
 
-	printk(KERN_INFO "devtmpfs: initialized\n");
+	pr_info("initialized\n");
 	return 0;
 }