Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 786 insertions, 0 deletions

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
new file mode 100644
index 000000000..361d69f75
--- /dev/null
+++ b/drivers/android/binderfs.c
@@ -0,0 +1,786 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/compiler_types.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/gfp.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/ipc_namespace.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/namei.h>
+#include <linux/magic.h>
+#include <linux/major.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mount.h>
+#include <linux/fs_parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/user_namespace.h>
+#include <linux/xarray.h>
+#include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
+
+#include "binder_internal.h"
+
+#define FIRST_INODE 1
+#define SECOND_INODE 2
+#define INODE_OFFSET 3
+#define BINDERFS_MAX_MINOR (1U << MINORBITS)
+/* Ensure that the initial ipc namespace always has devices available. */
+#define BINDERFS_MAX_MINOR_CAPPED (BINDERFS_MAX_MINOR - 4)
+
+static dev_t binderfs_dev;
+static DEFINE_MUTEX(binderfs_minors_mutex);
+static DEFINE_IDA(binderfs_minors);
+
+enum binderfs_param {
+	Opt_max,
+	Opt_stats_mode,
+};
+
+enum binderfs_stats_mode {
+	binderfs_stats_mode_unset,
+	binderfs_stats_mode_global,
+};
+
+struct binder_features {
+	bool oneway_spam_detection;
+	bool extended_error;
+	bool freeze_notification;
+	bool transaction_report;
+};
+
+static const struct constant_table binderfs_param_stats[] = {
+	{ "global", binderfs_stats_mode_global },
+	{}
+};
+
+static const struct fs_parameter_spec binderfs_fs_parameters[] = {
+	fsparam_u32("max",	Opt_max),
+	fsparam_enum("stats",	Opt_stats_mode, binderfs_param_stats),
+	{}
+};
+
+static struct binder_features binder_features = {
+	.oneway_spam_detection = true,
+	.extended_error = true,
+	.freeze_notification = true,
+	.transaction_report = true,
+};
+
+static inline struct binderfs_info *BINDERFS_SB(const struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+bool is_binderfs_device(const struct inode *inode)
+{
+	if (inode->i_sb->s_magic == BINDERFS_SUPER_MAGIC)
+		return true;
+
+	return false;
+}
+
+/**
+ * binderfs_binder_device_create - allocate inode from super block of a
+ *                                 binderfs mount
+ * @ref_inode: inode from which the super block will be taken
+ * @userp:     buffer to copy information about new device for userspace to
+ * @req:       struct binderfs_device as copied from userspace
+ *
+ * This function allocates a new binder_device and reserves a new minor
+ * number for it.
+ * Minor numbers are limited and tracked globally in binderfs_minors. The
+ * function will stash a struct binder_device for the specific binder
+ * device in i_private of the inode.
+ * It will go on to allocate a new inode from the super block of the
+ * filesystem mount, stash a struct binder_device in its i_private field
+ * and attach a dentry to that inode.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_device_create(struct inode *ref_inode,
+					 struct binderfs_device __user *userp,
+					 struct binderfs_device *req)
+{
+	int minor, ret;
+	struct dentry *dentry, *root;
+	struct binder_device *device;
+	char *name = NULL;
+	struct inode *inode = NULL;
+	struct super_block *sb = ref_inode->i_sb;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	/* Reserve new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	if (++info->device_count <= info->mount_opts.max)
+		minor = ida_alloc_max(&binderfs_minors,
+				      use_reserve ? BINDERFS_MAX_MINOR - 1 :
+						    BINDERFS_MAX_MINOR_CAPPED - 1,
+				      GFP_KERNEL);
+	else
+		minor = -ENOSPC;
+	if (minor < 0) {
+		--info->device_count;
+		mutex_unlock(&binderfs_minors_mutex);
+		return minor;
+	}
+	mutex_unlock(&binderfs_minors_mutex);
+
+	ret = -ENOMEM;
+	device = kzalloc_obj(*device);
+	if (!device)
+		goto err;
+
+	inode = new_inode(sb);
+	if (!inode)
+		goto err;
+
+	inode->i_ino = minor + INODE_OFFSET;
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &binder_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */
+	name = kstrdup(req->name, GFP_KERNEL);
+	if (!name)
+		goto err;
+
+	refcount_set(&device->ref, 1);
+	device->binderfs_inode = inode;
+	device->context.binder_context_mgr_uid = INVALID_UID;
+	device->context.name = name;
+	device->miscdev.name = name;
+	device->miscdev.minor = minor;
+	mutex_init(&device->context.context_mgr_node_lock);
+
+	req->major = MAJOR(binderfs_dev);
+	req->minor = minor;
+
+	if (userp && copy_to_user(userp, req, sizeof(*req))) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	root = sb->s_root;
+	dentry = simple_start_creating(root, name);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+	inode->i_private = device;
+	d_make_persistent(dentry, inode);
+	fsnotify_create(root->d_inode, dentry);
+	simple_done_creating(dentry);
+
+	binder_add_device(device);
+
+	return 0;
+
+err:
+	kfree(name);
+	kfree(device);
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, minor);
+	mutex_unlock(&binderfs_minors_mutex);
+	iput(inode);
+
+	return ret;
+}
+
+/**
+ * binder_ctl_ioctl - handle binder device node allocation requests
+ * @file: The file pointer for the binder-control device node.
+ * @cmd: The ioctl command.
+ * @arg: The ioctl argument.
+ *
+ * The request handler for the binder-control device. All requests operate on
+ * the binderfs mount the binder-control device resides in:
+ * - BINDER_CTL_ADD
+ *   Allocate a new binder device.
+ *
+ * Return: %0 on success, negative errno on failure.
+ */
+static long binder_ctl_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	int ret = -EINVAL;
+	struct inode *inode = file_inode(file);
+	struct binderfs_device __user *device = (struct binderfs_device __user *)arg;
+	struct binderfs_device device_req;
+
+	switch (cmd) {
+	case BINDER_CTL_ADD:
+		ret = copy_from_user(&device_req, device, sizeof(device_req));
+		if (ret) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret = binderfs_binder_device_create(inode, device, &device_req);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void binderfs_evict_inode(struct inode *inode)
+{
+	struct binder_device *device = inode->i_private;
+	struct binderfs_info *info = BINDERFS_SB(inode->i_sb);
+
+	clear_inode(inode);
+
+	if (!S_ISCHR(inode->i_mode) || !device)
+		return;
+
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, device->miscdev.minor);
+	mutex_unlock(&binderfs_minors_mutex);
+
+	if (refcount_dec_and_test(&device->ref)) {
+		binder_remove_device(device);
+		kfree(device->context.name);
+		kfree(device);
+	}
+}
+
+static int binderfs_fs_context_parse_param(struct fs_context *fc,
+					   struct fs_parameter *param)
+{
+	int opt;
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct fs_parse_result result;
+
+	opt = fs_parse(fc, binderfs_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_max:
+		if (result.uint_32 > BINDERFS_MAX_MINOR)
+			return invalfc(fc, "Bad value for '%s'", param->key);
+
+		ctx->max = result.uint_32;
+		break;
+	case Opt_stats_mode:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		ctx->stats_mode = result.uint_32;
+		break;
+	default:
+		return invalfc(fc, "Unsupported parameter '%s'", param->key);
+	}
+
+	return 0;
+}
+
+static int binderfs_fs_context_reconfigure(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct binderfs_info *info = BINDERFS_SB(fc->root->d_sb);
+
+	if (info->mount_opts.stats_mode != ctx->stats_mode)
+		return invalfc(fc, "Binderfs stats mode cannot be changed during a remount");
+
+	info->mount_opts.stats_mode = ctx->stats_mode;
+	info->mount_opts.max = ctx->max;
+	return 0;
+}
+
+static int binderfs_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct binderfs_info *info = BINDERFS_SB(root->d_sb);
+
+	if (info->mount_opts.max <= BINDERFS_MAX_MINOR)
+		seq_printf(seq, ",max=%d", info->mount_opts.max);
+
+	switch (info->mount_opts.stats_mode) {
+	case binderfs_stats_mode_unset:
+		break;
+	case binderfs_stats_mode_global:
+		seq_printf(seq, ",stats=global");
+		break;
+	}
+
+	return 0;
+}
+
+static const struct super_operations binderfs_super_ops = {
+	.evict_inode    = binderfs_evict_inode,
+	.show_options	= binderfs_show_options,
+	.statfs         = simple_statfs,
+};
+
+static inline bool is_binderfs_control_device(const struct dentry *dentry)
+{
+	struct binderfs_info *info = dentry->d_sb->s_fs_info;
+
+	return info->control_dentry == dentry;
+}
+
+static int binderfs_rename(struct mnt_idmap *idmap,
+			   struct inode *old_dir, struct dentry *old_dentry,
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
+{
+	if (is_binderfs_control_device(old_dentry) ||
+	    is_binderfs_control_device(new_dentry))
+		return -EPERM;
+
+	return simple_rename(idmap, old_dir, old_dentry, new_dir,
+			     new_dentry, flags);
+}
+
+static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	if (is_binderfs_control_device(dentry))
+		return -EPERM;
+
+	return simple_unlink(dir, dentry);
+}
+
+static const struct file_operations binder_ctl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nonseekable_open,
+	.unlocked_ioctl	= binder_ctl_ioctl,
+	.compat_ioctl	= binder_ctl_ioctl,
+	.llseek		= noop_llseek,
+};
+
+/**
+ * binderfs_binder_ctl_create - create a new binder-control device
+ * @sb: super block of the binderfs mount
+ *
+ * This function creates a new binder-control device node in the binderfs mount
+ * referred to by @sb.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_ctl_create(struct super_block *sb)
+{
+	int minor, ret;
+	struct dentry *dentry;
+	struct binder_device *device;
+	struct inode *inode = NULL;
+	struct dentry *root = sb->s_root;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	device = kzalloc_obj(*device);
+	if (!device)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	inode = new_inode(sb);
+	if (!inode)
+		goto out;
+
+	/* Reserve a new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	minor = ida_alloc_max(&binderfs_minors,
+			      use_reserve ? BINDERFS_MAX_MINOR - 1 :
+					    BINDERFS_MAX_MINOR_CAPPED - 1,
+			      GFP_KERNEL);
+	mutex_unlock(&binderfs_minors_mutex);
+	if (minor < 0) {
+		ret = minor;
+		goto out;
+	}
+
+	inode->i_ino = SECOND_INODE;
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &binder_ctl_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	refcount_set(&device->ref, 1);
+	device->binderfs_inode = inode;
+	device->miscdev.minor = minor;
+
+	dentry = d_alloc_name(root, "binder-control");
+	if (!dentry)
+		goto out;
+
+	inode->i_private = device;
+	info->control_dentry = dentry;
+	d_make_persistent(dentry, inode);
+	dput(dentry);
+
+	return 0;
+
+out:
+	kfree(device);
+	iput(inode);
+
+	return ret;
+}
+
+static const struct inode_operations binderfs_dir_inode_operations = {
+	.lookup = simple_lookup,
+	.rename = binderfs_rename,
+	.unlink = binderfs_unlink,
+};
+
+static struct inode *binderfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret;
+
+	ret = new_inode(sb);
+	if (ret) {
+		ret->i_ino = iunique(sb, BINDERFS_MAX_MINOR + INODE_OFFSET);
+		ret->i_mode = mode;
+		simple_inode_init_ts(ret);
+	}
+	return ret;
+}
+
+struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
+				    const struct file_operations *fops,
+				    void *data)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry))
+		return dentry;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFREG | 0444);
+	if (!new_inode) {
+		simple_done_creating(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	new_inode->i_fop = fops;
+	new_inode->i_private = data;
+	d_make_persistent(dentry, new_inode);
+	fsnotify_create(parent_inode, dentry);
+	simple_done_creating(dentry);
+	return dentry; // borrowed
+}
+
+static struct dentry *binderfs_create_dir(struct dentry *parent,
+					  const char *name)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry))
+		return dentry;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFDIR | 0755);
+	if (!new_inode) {
+		simple_done_creating(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	new_inode->i_fop = &simple_dir_operations;
+	new_inode->i_op = &simple_dir_inode_operations;
+
+	set_nlink(new_inode, 2);
+	d_make_persistent(dentry, new_inode);
+	inc_nlink(parent_inode);
+	fsnotify_mkdir(parent_inode, dentry);
+	simple_done_creating(dentry);
+	return dentry;
+}
+
+static int binder_features_show(struct seq_file *m, void *unused)
+{
+	bool *feature = m->private;
+
+	seq_printf(m, "%d\n", *feature);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(binder_features);
+
+static int init_binder_features(struct super_block *sb)
+{
+	struct dentry *dentry, *dir;
+
+	dir = binderfs_create_dir(sb->s_root, "features");
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	dentry = binderfs_create_file(dir, "oneway_spam_detection",
+				      &binder_features_fops,
+				      &binder_features.oneway_spam_detection);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = binderfs_create_file(dir, "extended_error",
+				      &binder_features_fops,
+				      &binder_features.extended_error);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = binderfs_create_file(dir, "freeze_notification",
+				      &binder_features_fops,
+				      &binder_features.freeze_notification);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = binderfs_create_file(dir, "transaction_report",
+				      &binder_features_fops,
+				      &binder_features.transaction_report);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return 0;
+}
+
+static int init_binder_logs(struct super_block *sb)
+{
+	struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir;
+	const struct binder_debugfs_entry *db_entry;
+	struct binderfs_info *info;
+	int ret = 0;
+
+	binder_logs_root_dir = binderfs_create_dir(sb->s_root,
+						   "binder_logs");
+	if (IS_ERR(binder_logs_root_dir)) {
+		ret = PTR_ERR(binder_logs_root_dir);
+		goto out;
+	}
+
+	binder_for_each_debugfs_entry(db_entry) {
+		dentry = binderfs_create_file(binder_logs_root_dir,
+					      db_entry->name,
+					      db_entry->fops,
+					      db_entry->data);
+		if (IS_ERR(dentry)) {
+			ret = PTR_ERR(dentry);
+			goto out;
+		}
+	}
+
+	proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc");
+	if (IS_ERR(proc_log_dir)) {
+		ret = PTR_ERR(proc_log_dir);
+		goto out;
+	}
+	info = sb->s_fs_info;
+	info->proc_log_dir = proc_log_dir;
+
+out:
+	return ret;
+}
+
+static int binderfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	int ret;
+	struct binderfs_info *info;
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+	struct inode *inode = NULL;
+	struct binderfs_device device_info = {};
+	const char *name;
+	size_t len;
+
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+
+	/*
+	 * The binderfs filesystem can be mounted by userns root in a
+	 * non-initial userns. By default such mounts have the SB_I_NODEV flag
+	 * set in s_iflags to prevent security issues where userns root can
+	 * just create random device nodes via mknod() since it owns the
+	 * filesystem mount. But binderfs does not allow to create any files
+	 * including devices nodes. The only way to create binder devices nodes
+	 * is through the binder-control device which userns root is explicitly
+	 * allowed to do. So removing the SB_I_NODEV flag from s_iflags is both
+	 * necessary and safe.
+	 */
+	sb->s_iflags &= ~SB_I_NODEV;
+	sb->s_iflags |= SB_I_NOEXEC;
+	sb->s_magic = BINDERFS_SUPER_MAGIC;
+	sb->s_op = &binderfs_super_ops;
+	sb->s_time_gran = 1;
+
+	sb->s_fs_info = kzalloc_obj(struct binderfs_info);
+	if (!sb->s_fs_info)
+		return -ENOMEM;
+	info = sb->s_fs_info;
+
+	info->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
+
+	info->root_gid = make_kgid(sb->s_user_ns, 0);
+	if (!gid_valid(info->root_gid))
+		info->root_gid = GLOBAL_ROOT_GID;
+	info->root_uid = make_kuid(sb->s_user_ns, 0);
+	if (!uid_valid(info->root_uid))
+		info->root_uid = GLOBAL_ROOT_UID;
+	info->mount_opts.max = ctx->max;
+	info->mount_opts.stats_mode = ctx->stats_mode;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return -ENOMEM;
+
+	inode->i_ino = FIRST_INODE;
+	inode->i_fop = &simple_dir_operations;
+	inode->i_mode = S_IFDIR | 0755;
+	simple_inode_init_ts(inode);
+	inode->i_op = &binderfs_dir_inode_operations;
+	set_nlink(inode, 2);
+
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root)
+		return -ENOMEM;
+
+	ret = binderfs_binder_ctl_create(sb);
+	if (ret)
+		return ret;
+
+	name = binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		strscpy(device_info.name, name, len + 1);
+		ret = binderfs_binder_device_create(inode, NULL, &device_info);
+		if (ret)
+			return ret;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	ret = init_binder_features(sb);
+	if (ret)
+		return ret;
+
+	if (info->mount_opts.stats_mode == binderfs_stats_mode_global)
+		return init_binder_logs(sb);
+
+	return 0;
+}
+
+static int binderfs_fs_context_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, binderfs_fill_super);
+}
+
+static void binderfs_fs_context_free(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx = fc->fs_private;
+
+	kfree(ctx);
+}
+
+static const struct fs_context_operations binderfs_fs_context_ops = {
+	.free		= binderfs_fs_context_free,
+	.get_tree	= binderfs_fs_context_get_tree,
+	.parse_param	= binderfs_fs_context_parse_param,
+	.reconfigure	= binderfs_fs_context_reconfigure,
+};
+
+static int binderfs_init_fs_context(struct fs_context *fc)
+{
+	struct binderfs_mount_opts *ctx;
+
+	ctx = kzalloc_obj(struct binderfs_mount_opts);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->max = BINDERFS_MAX_MINOR;
+	ctx->stats_mode = binderfs_stats_mode_unset;
+
+	fc->fs_private = ctx;
+	fc->ops = &binderfs_fs_context_ops;
+
+	return 0;
+}
+
+static void binderfs_kill_super(struct super_block *sb)
+{
+	struct binderfs_info *info = sb->s_fs_info;
+
+	/*
+	 * During inode eviction struct binderfs_info is needed.
+	 * So first wipe the super_block then free struct binderfs_info.
+	 */
+	kill_anon_super(sb);
+
+	if (info && info->ipc_ns)
+		put_ipc_ns(info->ipc_ns);
+
+	kfree(info);
+}
+
+static struct file_system_type binder_fs_type = {
+	.name			= "binder",
+	.init_fs_context	= binderfs_init_fs_context,
+	.parameters		= binderfs_fs_parameters,
+	.kill_sb		= binderfs_kill_super,
+	.fs_flags		= FS_USERNS_MOUNT,
+};
+
+int __init init_binderfs(void)
+{
+	int ret;
+	const char *name;
+	size_t len;
+
+	/* Verify that the default binderfs device names are valid. */
+	name = binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		if (len > BINDERFS_MAX_NAME)
+			return -E2BIG;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	/* Allocate new major number for binderfs. */
+	ret = alloc_chrdev_region(&binderfs_dev, 0, BINDERFS_MAX_MINOR,
+				  "binder");
+	if (ret)
+		return ret;
+
+	ret = register_filesystem(&binder_fs_type);
+	if (ret) {
+		unregister_chrdev_region(binderfs_dev, BINDERFS_MAX_MINOR);
+		return ret;
+	}
+
+	return ret;
+}