Fixed MTP to work with TWRP

fs/kernfs/Kconfig

@@ -0,0 +1,7 @@
+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+	bool
+	default n

fs/kernfs/Makefile

@@ -0,0 +1,5 @@
+#
+# Makefile for the kernfs pseudo filesystem
+#
+
+obj-y		:= mount.o inode.o dir.o file.o symlink.o

fs/kernfs/file.c

@@ -0,0 +1,952 @@
+/*
+ * fs/kernfs/file.c - kernfs file implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+#include <linux/fsnotify.h>
+
+#include "kernfs-internal.h"
+
+/*
+ * There's one kernfs_open_file for each open file and one kernfs_open_node
+ * for each kernfs_node with one or more open files.
+ *
+ * kernfs_node->attr.open points to kernfs_open_node.  attr.open is
+ * protected by kernfs_open_node_lock.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * kernfs_open_file.  kernfs_open_files are chained at
+ * kernfs_open_node->files, which is protected by kernfs_open_file_mutex.
+ */
+static DEFINE_SPINLOCK(kernfs_open_node_lock);
+static DEFINE_MUTEX(kernfs_open_file_mutex);
+
+struct kernfs_open_node {
+	atomic_t		refcnt;
+	atomic_t		event;
+	wait_queue_head_t	poll;
+	struct list_head	files; /* goes through kernfs_open_file.list */
+};
+
+/*
+ * kernfs_notify() may be called from any context and bounces notifications
+ * through a work item.  To minimize space overhead in kernfs_node, the
+ * pending queue is implemented as a singly linked list of kernfs_nodes.
+ * The list is terminated with the self pointer so that whether a
+ * kernfs_node is on the list or not can be determined by testing the next
+ * pointer for NULL.
+ */
+#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)
+
+static DEFINE_SPINLOCK(kernfs_notify_lock);
+static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;
+
+static struct kernfs_open_file *kernfs_of(struct file *file)
+{
+	return ((struct seq_file *)file->private_data)->private;
+}
+
+/*
+ * Determine the kernfs_ops for the given kernfs_node.  This function must
+ * be called while holding an active reference.
+ */
+static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
+{
+	if (kn->flags & KERNFS_LOCKDEP)
+		lockdep_assert_held(kn);
+	return kn->attr.ops;
+}
+
+/*
+ * As kernfs_seq_stop() is also called after kernfs_seq_start() or
+ * kernfs_seq_next() failure, it needs to distinguish whether it's stopping
+ * a seq_file iteration which is fully initialized with an active reference
+ * or an aborted kernfs_seq_start() due to get_active failure.  The
+ * position pointer is the only context for each seq_file iteration and
+ * thus the stop condition should be encoded in it.  As the return value is
+ * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
+ * choice to indicate get_active failure.
+ *
+ * Unfortunately, this is complicated due to the optional custom seq_file
+ * operations which may return ERR_PTR(-ENODEV) too.  kernfs_seq_stop()
+ * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
+ * custom seq_file operations and thus can't decide whether put_active
+ * should be performed or not only on ERR_PTR(-ENODEV).
+ *
+ * This is worked around by factoring out the custom seq_stop() and
+ * put_active part into kernfs_seq_stop_active(), skipping it from
+ * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
+ * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
+ * that kernfs_seq_stop_active() is skipped only after get_active failure.
+ */
+static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+	if (ops->seq_stop)
+		ops->seq_stop(sf, v);
+	kernfs_put_active(of->kn);
+}
+
+static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops;
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn))
+		return ERR_PTR(-ENODEV);
+
+	ops = kernfs_ops(of->kn);
+	if (ops->seq_start) {
+		void *next = ops->seq_start(sf, ppos);
+		/* see the comment above kernfs_seq_stop_active() */
+		if (next == ERR_PTR(-ENODEV))
+			kernfs_seq_stop_active(sf, next);
+		return next;
+	} else {
+		/*
+		 * The same behavior and code as single_open().  Returns
+		 * !NULL if pos is at the beginning; otherwise, NULL.
+		 */
+		return NULL + !*ppos;
+	}
+}
+
+static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+	if (ops->seq_next) {
+		void *next = ops->seq_next(sf, v, ppos);
+		/* see the comment above kernfs_seq_stop_active() */
+		if (next == ERR_PTR(-ENODEV))
+			kernfs_seq_stop_active(sf, next);
+		return next;
+	} else {
+		/*
+		 * The same behavior and code as single_open(), always
+		 * terminate after the initial read.
+		 */
+		++*ppos;
+		return NULL;
+	}
+}
+
+static void kernfs_seq_stop(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+
+	if (v != ERR_PTR(-ENODEV))
+		kernfs_seq_stop_active(sf, v);
+	mutex_unlock(&of->mutex);
+}
+
+static int kernfs_seq_show(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+
+	of->event = atomic_read(&of->kn->attr.open->event);
+
+	return of->kn->attr.ops->seq_show(sf, v);
+}
+
+static const struct seq_operations kernfs_seq_ops = {
+	.start = kernfs_seq_start,
+	.next = kernfs_seq_next,
+	.stop = kernfs_seq_stop,
+	.show = kernfs_seq_show,
+};
+
+/*
+ * As reading a bin file can have side-effects, the exact offset and bytes
+ * specified in read(2) call should be passed to the read callback making
+ * it difficult to use seq_file.  Implement simplistic custom buffering for
+ * bin files.
+ */
+static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
+				       char __user *user_buf, size_t count,
+				       loff_t *ppos)
+{
+	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+	const struct kernfs_ops *ops;
+	char *buf;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		len = -ENODEV;
+		mutex_unlock(&of->mutex);
+		goto out_free;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->read)
+		len = ops->read(of, buf, len, *ppos);
+	else
+		len = -EINVAL;
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+
+	if (len < 0)
+		goto out_free;
+
+	if (copy_to_user(user_buf, buf, len)) {
+		len = -EFAULT;
+		goto out_free;
+	}
+
+	*ppos += len;
+
+ out_free:
+	kfree(buf);
+	return len;
+}
+
+/**
+ * kernfs_fop_read - kernfs vfs read callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ */
+static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
+			       size_t count, loff_t *ppos)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+
+	if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
+		return seq_read(file, user_buf, count, ppos);
+	else
+		return kernfs_file_direct_read(of, user_buf, count, ppos);
+}
+
+/**
+ * kernfs_fop_write - kernfs vfs write callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ *
+ * Copy data in from userland and pass it to the matching kernfs write
+ * operation.
+ *
+ * There is no easy way for us to know if userspace is only doing a partial
+ * write, so we don't support them. We expect the entire buffer to come on
+ * the first write.  Hint: if you're writing a value, first read the file,
+ * modify only the the value you're changing, then write entire buffer
+ * back.
+ */
+static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
+				size_t count, loff_t *ppos)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	size_t len;
+	char *buf;
+
+	if (of->atomic_write_len) {
+		len = count;
+		if (len > of->atomic_write_len)
+			return -E2BIG;
+	} else {
+		len = min_t(size_t, count, PAGE_SIZE);
+	}
+
+	buf = kmalloc(len + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, user_buf, len)) {
+		len = -EFAULT;
+		goto out_free;
+	}
+	buf[len] = '\0';	/* guarantee string termination */
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		len = -ENODEV;
+		goto out_free;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->write)
+		len = ops->write(of, buf, len, *ppos);
+	else
+		len = -EINVAL;
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+
+	if (len > 0)
+		*ppos += len;
+out_free:
+	kfree(buf);
+	return len;
+}
+
+static void kernfs_vma_open(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+
+	if (!of->vm_ops)
+		return;
+
+	if (!kernfs_get_active(of->kn))
+		return;
+
+	if (of->vm_ops->open)
+		of->vm_ops->open(vma);
+
+	kernfs_put_active(of->kn);
+}
+
+static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return VM_FAULT_SIGBUS;
+
+	if (!kernfs_get_active(of->kn))
+		return VM_FAULT_SIGBUS;
+
+	ret = VM_FAULT_SIGBUS;
+	if (of->vm_ops->fault)
+		ret = of->vm_ops->fault(vma, vmf);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
+				   struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return VM_FAULT_SIGBUS;
+
+	if (!kernfs_get_active(of->kn))
+		return VM_FAULT_SIGBUS;
+
+	ret = 0;
+	if (of->vm_ops->page_mkwrite)
+		ret = of->vm_ops->page_mkwrite(vma, vmf);
+	else
+		file_update_time(file);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
+			     void *buf, int len, int write)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return -EINVAL;
+
+	if (!kernfs_get_active(of->kn))
+		return -EINVAL;
+
+	ret = -EINVAL;
+	if (of->vm_ops->access)
+		ret = of->vm_ops->access(vma, addr, buf, len, write);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+#ifdef CONFIG_NUMA
+static int kernfs_vma_set_policy(struct vm_area_struct *vma,
+				 struct mempolicy *new)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return 0;
+
+	if (!kernfs_get_active(of->kn))
+		return -EINVAL;
+
+	ret = 0;
+	if (of->vm_ops->set_policy)
+		ret = of->vm_ops->set_policy(vma, new);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
+					       unsigned long addr)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	struct mempolicy *pol;
+
+	if (!of->vm_ops)
+		return vma->vm_policy;
+
+	if (!kernfs_get_active(of->kn))
+		return vma->vm_policy;
+
+	pol = vma->vm_policy;
+	if (of->vm_ops->get_policy)
+		pol = of->vm_ops->get_policy(vma, addr);
+
+	kernfs_put_active(of->kn);
+	return pol;
+}
+
+static int kernfs_vma_migrate(struct vm_area_struct *vma,
+			      const nodemask_t *from, const nodemask_t *to,
+			      unsigned long flags)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return 0;
+
+	if (!kernfs_get_active(of->kn))
+		return 0;
+
+	ret = 0;
+	if (of->vm_ops->migrate)
+		ret = of->vm_ops->migrate(vma, from, to, flags);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+#endif
+
+static const struct vm_operations_struct kernfs_vm_ops = {
+	.open		= kernfs_vma_open,
+	.fault		= kernfs_vma_fault,
+	.page_mkwrite	= kernfs_vma_page_mkwrite,
+	.access		= kernfs_vma_access,
+#ifdef CONFIG_NUMA
+	.set_policy	= kernfs_vma_set_policy,
+	.get_policy	= kernfs_vma_get_policy,
+	.migrate	= kernfs_vma_migrate,
+#endif
+};
+
+static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	int rc;
+
+	/*
+	 * mmap path and of->mutex are prone to triggering spurious lockdep
+	 * warnings and we don't want to add spurious locking dependency
+	 * between the two.  Check whether mmap is actually implemented
+	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
+	 * comment in kernfs_file_open() for more details.
+	 */
+	if (!(of->kn->flags & KERNFS_HAS_MMAP))
+		return -ENODEV;
+
+	mutex_lock(&of->mutex);
+
+	rc = -ENODEV;
+	if (!kernfs_get_active(of->kn))
+		goto out_unlock;
+
+	ops = kernfs_ops(of->kn);
+	rc = ops->mmap(of, vma);
+	if (rc)
+		goto out_put;
+
+	/*
+	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
+	 * to satisfy versions of X which crash if the mmap fails: that
+	 * substitutes a new vm_file, and we don't then want bin_vm_ops.
+	 */
+	if (vma->vm_file != file)
+		goto out_put;
+
+	rc = -EINVAL;
+	if (of->mmapped && of->vm_ops != vma->vm_ops)
+		goto out_put;
+
+	/*
+	 * It is not possible to successfully wrap close.
+	 * So error if someone is trying to use close.
+	 */
+	rc = -EINVAL;
+	if (vma->vm_ops && vma->vm_ops->close)
+		goto out_put;
+
+	rc = 0;
+	of->mmapped = 1;
+	of->vm_ops = vma->vm_ops;
+	vma->vm_ops = &kernfs_vm_ops;
+out_put:
+	kernfs_put_active(of->kn);
+out_unlock:
+	mutex_unlock(&of->mutex);
+
+	return rc;
+}
+
+/**
+ *	kernfs_get_open_node - get or create kernfs_open_node
+ *	@kn: target kernfs_node
+ *	@of: kernfs_open_file for this instance of open
+ *
+ *	If @kn->attr.open exists, increment its reference count; otherwise,
+ *	create one.  @of is chained to the files list.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno on failure.
+ */
+static int kernfs_get_open_node(struct kernfs_node *kn,
+				struct kernfs_open_file *of)
+{
+	struct kernfs_open_node *on, *new_on = NULL;
+
+ retry:
+	mutex_lock(&kernfs_open_file_mutex);
+	spin_lock_irq(&kernfs_open_node_lock);
+
+	if (!kn->attr.open && new_on) {
+		kn->attr.open = new_on;
+		new_on = NULL;
+	}
+
+	on = kn->attr.open;
+	if (on) {
+		atomic_inc(&on->refcnt);
+		list_add_tail(&of->list, &on->files);
+	}
+
+	spin_unlock_irq(&kernfs_open_node_lock);
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	if (on) {
+		kfree(new_on);
+		return 0;
+	}
+
+	/* not there, initialize a new one and retry */
+	new_on = kmalloc(sizeof(*new_on), GFP_KERNEL);
+	if (!new_on)
+		return -ENOMEM;
+
+	atomic_set(&new_on->refcnt, 0);
+	atomic_set(&new_on->event, 1);
+	init_waitqueue_head(&new_on->poll);
+	INIT_LIST_HEAD(&new_on->files);
+	goto retry;
+}
+
+/**
+ *	kernfs_put_open_node - put kernfs_open_node
+ *	@kn: target kernfs_nodet
+ *	@of: associated kernfs_open_file
+ *
+ *	Put @kn->attr.open and unlink @of from the files list.  If
+ *	reference count reaches zero, disassociate and free it.
+ *
+ *	LOCKING:
+ *	None.
+ */
+static void kernfs_put_open_node(struct kernfs_node *kn,
+				 struct kernfs_open_file *of)
+{
+	struct kernfs_open_node *on = kn->attr.open;
+	unsigned long flags;
+
+	mutex_lock(&kernfs_open_file_mutex);
+	spin_lock_irqsave(&kernfs_open_node_lock, flags);
+
+	if (of)
+		list_del(&of->list);
+
+	if (atomic_dec_and_test(&on->refcnt))
+		kn->attr.open = NULL;
+	else
+		on = NULL;
+
+	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	kfree(on);
+}
+
+static int kernfs_fop_open(struct inode *inode, struct file *file)
+{
+	struct kernfs_node *kn = file->f_path.dentry->d_fsdata;
+	struct kernfs_root *root = kernfs_root(kn);
+	const struct kernfs_ops *ops;
+	struct kernfs_open_file *of;
+	bool has_read, has_write, has_mmap;
+	int error = -EACCES;
+
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	ops = kernfs_ops(kn);
+
+	has_read = ops->seq_show || ops->read || ops->mmap;
+	has_write = ops->write || ops->mmap;
+	has_mmap = ops->mmap;
+
+	/* see the flag definition for details */
+	if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) {
+		if ((file->f_mode & FMODE_WRITE) &&
+		    (!(inode->i_mode & S_IWUGO) || !has_write))
+			goto err_out;
+
+		if ((file->f_mode & FMODE_READ) &&
+		    (!(inode->i_mode & S_IRUGO) || !has_read))
+			goto err_out;
+	}
+
+	/* allocate a kernfs_open_file for the file */
+	error = -ENOMEM;
+	of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL);
+	if (!of)
+		goto err_out;
+
+	/*
+	 * The following is done to give a different lockdep key to
+	 * @of->mutex for files which implement mmap.  This is a rather
+	 * crude way to avoid false positive lockdep warning around
+	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
+	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
+	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
+	 * open file has a separate mutex, it's okay as long as those don't
+	 * happen on the same file.  At this point, we can't easily give
+	 * each file a separate locking class.  Let's differentiate on
+	 * whether the file has mmap or not for now.
+	 *
+	 * Both paths of the branch look the same.  They're supposed to
+	 * look that way and give @of->mutex different static lockdep keys.
+	 */
+	if (has_mmap)
+		mutex_init(&of->mutex);
+	else
+		mutex_init(&of->mutex);
+
+	of->kn = kn;
+	of->file = file;
+
+	/*
+	 * Write path needs to atomic_write_len outside active reference.
+	 * Cache it in open_file.  See kernfs_fop_write() for details.
+	 */
+	of->atomic_write_len = ops->atomic_write_len;
+
+	/*
+	 * Always instantiate seq_file even if read access doesn't use
+	 * seq_file or is not requested.  This unifies private data access
+	 * and readable regular files are the vast majority anyway.
+	 */
+	if (ops->seq_show)
+		error = seq_open(file, &kernfs_seq_ops);
+	else
+		error = seq_open(file, NULL);
+	if (error)
+		goto err_free;
+
+	((struct seq_file *)file->private_data)->private = of;
+
+	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
+	if (file->f_mode & FMODE_WRITE)
+		file->f_mode |= FMODE_PWRITE;
+
+	/* make sure we have open node struct */
+	error = kernfs_get_open_node(kn, of);
+	if (error)
+		goto err_close;
+
+	/* open succeeded, put active references */
+	kernfs_put_active(kn);
+	return 0;
+
+err_close:
+	seq_release(inode, file);
+err_free:
+	kfree(of);
+err_out:
+	kernfs_put_active(kn);
+	return error;
+}
+
+static int kernfs_fop_release(struct inode *inode, struct file *filp)
+{
+	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+	struct kernfs_open_file *of = kernfs_of(filp);
+
+	kernfs_put_open_node(kn, of);
+	seq_release(inode, filp);
+	kfree(of);
+
+	return 0;
+}
+
+void kernfs_unmap_bin_file(struct kernfs_node *kn)
+{
+	struct kernfs_open_node *on;
+	struct kernfs_open_file *of;
+
+	if (!(kn->flags & KERNFS_HAS_MMAP))
+		return;
+
+	spin_lock_irq(&kernfs_open_node_lock);
+	on = kn->attr.open;
+	if (on)
+		atomic_inc(&on->refcnt);
+	spin_unlock_irq(&kernfs_open_node_lock);
+	if (!on)
+		return;
+
+	mutex_lock(&kernfs_open_file_mutex);
+	list_for_each_entry(of, &on->files, list) {
+		struct inode *inode = file_inode(of->file);
+		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+	}
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	kernfs_put_open_node(kn, NULL);
+}
+
+/*
+ * Kernfs attribute files are pollable.  The idea is that you read
+ * the content and then you use 'poll' or 'select' to wait for
+ * the content to change.  When the content changes (assuming the
+ * manager for the kobject supports notification), poll will
+ * return POLLERR|POLLPRI, and select will return the fd whether
+ * it is waiting for read, write, or exceptions.
+ * Once poll/select indicates that the value has changed, you
+ * need to close and re-open the file, or seek to 0 and read again.
+ * Reminder: this only works for attributes which actively support
+ * it, and it is not possible to test an attribute from userspace
+ * to see if it supports poll (Neither 'poll' nor 'select' return
+ * an appropriate error code).  When in doubt, set a suitable timeout value.
+ */
+static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
+{
+	struct kernfs_open_file *of = kernfs_of(filp);
+	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+	struct kernfs_open_node *on = kn->attr.open;
+
+	/* need parent for the kobj, grab both */
+	if (!kernfs_get_active(kn))
+		goto trigger;
+
+	poll_wait(filp, &on->poll, wait);
+
+	kernfs_put_active(kn);
+
+	if (of->event != atomic_read(&on->event))
+		goto trigger;
+
+	return DEFAULT_POLLMASK;
+
+ trigger:
+	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
+}
+
+static void kernfs_notify_workfn(struct work_struct *work)
+{
+	struct kernfs_node *kn;
+	struct kernfs_open_node *on;
+	struct kernfs_super_info *info;
+repeat:
+	/* pop one off the notify_list */
+	spin_lock_irq(&kernfs_notify_lock);
+	kn = kernfs_notify_list;
+	if (kn == KERNFS_NOTIFY_EOL) {
+		spin_unlock_irq(&kernfs_notify_lock);
+		return;
+	}
+	kernfs_notify_list = kn->attr.notify_next;
+	kn->attr.notify_next = NULL;
+	spin_unlock_irq(&kernfs_notify_lock);
+
+	/* kick poll */
+	spin_lock_irq(&kernfs_open_node_lock);
+
+	on = kn->attr.open;
+	if (on) {
+		atomic_inc(&on->event);
+		wake_up_interruptible(&on->poll);
+	}
+
+	spin_unlock_irq(&kernfs_open_node_lock);
+
+	/* kick fsnotify */
+	mutex_lock(&kernfs_mutex);
+
+	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
+		struct inode *inode;
+		struct dentry *dentry;
+
+		inode = ilookup(info->sb, kn->ino);
+		if (!inode)
+			continue;
+
+		dentry = d_find_any_alias(inode);
+		if (dentry) {
+			fsnotify_parent(NULL, dentry, FS_MODIFY);
+			fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+				 NULL, 0);
+			dput(dentry);
+		}
+
+		iput(inode);
+	}
+
+	mutex_unlock(&kernfs_mutex);
+	kernfs_put(kn);
+	goto repeat;
+}
+
+/**
+ * kernfs_notify - notify a kernfs file
+ * @kn: file to notify
+ *
+ * Notify @kn such that poll(2) on @kn wakes up.  Maybe be called from any
+ * context.
+ */
+void kernfs_notify(struct kernfs_node *kn)
+{
+	static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
+	unsigned long flags;
+
+	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+		return;
+
+	spin_lock_irqsave(&kernfs_notify_lock, flags);
+	if (!kn->attr.notify_next) {
+		kernfs_get(kn);
+		kn->attr.notify_next = kernfs_notify_list;
+		kernfs_notify_list = kn;
+		schedule_work(&kernfs_notify_work);
+	}
+	spin_unlock_irqrestore(&kernfs_notify_lock, flags);
+}
+EXPORT_SYMBOL_GPL(kernfs_notify);
+
+const struct file_operations kernfs_file_fops = {
+	.read		= kernfs_fop_read,
+	.write		= kernfs_fop_write,
+	.llseek		= generic_file_llseek,
+	.mmap		= kernfs_fop_mmap,
+	.open		= kernfs_fop_open,
+	.release	= kernfs_fop_release,
+	.poll		= kernfs_fop_poll,
+};
+
+/**
+ * __kernfs_create_file - kernfs internal function to create a file
+ * @parent: directory to create the file in
+ * @name: name of the file
+ * @mode: mode of the file
+ * @size: size of the file
+ * @ops: kernfs operations for the file
+ * @priv: private data for the file
+ * @ns: optional namespace tag of the file
+ * @name_is_static: don't copy file name
+ * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
+ *
+ * Returns the created node on success, ERR_PTR() value on error.
+ */
+struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
+					 const char *name,
+					 umode_t mode, loff_t size,
+					 const struct kernfs_ops *ops,
+					 void *priv, const void *ns,
+					 bool name_is_static,
+					 struct lock_class_key *key)
+{
+	struct kernfs_node *kn;
+	unsigned flags;
+	int rc;
+
+	flags = KERNFS_FILE;
+	if (name_is_static)
+		flags |= KERNFS_STATIC_NAME;
+
+	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	kn->attr.ops = ops;
+	kn->attr.size = size;
+	kn->ns = ns;
+	kn->priv = priv;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (key) {
+		lockdep_init_map(&kn->dep_map, "s_active", key, 0);
+		kn->flags |= KERNFS_LOCKDEP;
+	}
+#endif
+
+	/*
+	 * kn->attr.ops is accesible only while holding active ref.  We
+	 * need to know whether some ops are implemented outside active
+	 * ref.  Cache their existence in flags.
+	 */
+	if (ops->seq_show)
+		kn->flags |= KERNFS_HAS_SEQ_SHOW;
+	if (ops->mmap)
+		kn->flags |= KERNFS_HAS_MMAP;
+
+	rc = kernfs_add_one(kn);
+	if (rc) {
+		kernfs_put(kn);
+		return ERR_PTR(rc);
+	}
+	return kn;
+}

fs/kernfs/inode.c

@@ -0,0 +1,383 @@
+/*
+ * fs/kernfs/inode.c - kernfs inode implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "kernfs-internal.h"
+
+static const struct address_space_operations kernfs_aops = {
+	.readpage	= simple_readpage,
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
+};
+
+static struct backing_dev_info kernfs_bdi = {
+	.name		= "kernfs",
+	.ra_pages	= 0,	/* No readahead */
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+
+static const struct inode_operations kernfs_iops = {
+	.permission	= kernfs_iop_permission,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.setxattr	= kernfs_iop_setxattr,
+	.removexattr	= kernfs_iop_removexattr,
+	.getxattr	= kernfs_iop_getxattr,
+	.listxattr	= kernfs_iop_listxattr,
+};
+
+void __init kernfs_inode_init(void)
+{
+	if (bdi_init(&kernfs_bdi))
+		panic("failed to init kernfs_bdi");
+}
+
+static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
+{
+	static DEFINE_MUTEX(iattr_mutex);
+	struct kernfs_iattrs *ret;
+	struct iattr *iattrs;
+
+	mutex_lock(&iattr_mutex);
+
+	if (kn->iattr)
+		goto out_unlock;
+
+	kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL);
+	if (!kn->iattr)
+		goto out_unlock;
+	iattrs = &kn->iattr->ia_iattr;
+
+	/* assign default attributes */
+	iattrs->ia_mode = kn->mode;
+	iattrs->ia_uid = GLOBAL_ROOT_UID;
+	iattrs->ia_gid = GLOBAL_ROOT_GID;
+	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
+
+	simple_xattrs_init(&kn->iattr->xattrs);
+out_unlock:
+	ret = kn->iattr;
+	mutex_unlock(&iattr_mutex);
+	return ret;
+}
+
+static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	struct kernfs_iattrs *attrs;
+	struct iattr *iattrs;
+	unsigned int ia_valid = iattr->ia_valid;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	iattrs = &attrs->ia_iattr;
+
+	if (ia_valid & ATTR_UID)
+		iattrs->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		iattrs->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		iattrs->ia_atime = iattr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		iattrs->ia_mtime = iattr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		iattrs->ia_ctime = iattr->ia_ctime;
+	if (ia_valid & ATTR_MODE) {
+		umode_t mode = iattr->ia_mode;
+		iattrs->ia_mode = kn->mode = mode;
+	}
+	return 0;
+}
+
+/**
+ * kernfs_setattr - set iattr on a node
+ * @kn: target node
+ * @iattr: iattr to set
+ *
+ * Returns 0 on success, -errno on failure.
+ */
+int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	int ret;
+
+	mutex_lock(&kernfs_mutex);
+	ret = __kernfs_setattr(kn, iattr);
+	mutex_unlock(&kernfs_mutex);
+	return ret;
+}
+
+int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct kernfs_node *kn = dentry->d_fsdata;
+	int error;
+
+	if (!kn)
+		return -EINVAL;
+
+	mutex_lock(&kernfs_mutex);
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		goto out;
+
+	error = __kernfs_setattr(kn, iattr);
+	if (error)
+		goto out;
+
+	/* this ignores size changes */
+	setattr_copy(inode, iattr);
+
+out:
+	mutex_unlock(&kernfs_mutex);
+	return error;
+}
+
+static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata,
+				  u32 *secdata_len)
+{
+	struct kernfs_iattrs *attrs;
+	void *old_secdata;
+	size_t old_secdata_len;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	old_secdata = attrs->ia_secdata;
+	old_secdata_len = attrs->ia_secdata_len;
+
+	attrs->ia_secdata = *secdata;
+	attrs->ia_secdata_len = *secdata_len;
+
+	*secdata = old_secdata;
+	*secdata_len = old_secdata_len;
+	return 0;
+}
+
+int kernfs_iop_setxattr(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+	void *secdata;
+	int error;
+	u32 secdata_len = 0;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
+		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+		error = security_inode_setsecurity(dentry->d_inode, suffix,
+						value, size, flags);
+		if (error)
+			return error;
+		error = security_inode_getsecctx(dentry->d_inode,
+						&secdata, &secdata_len);
+		if (error)
+			return error;
+
+		mutex_lock(&kernfs_mutex);
+		error = kernfs_node_setsecdata(kn, &secdata, &secdata_len);
+		mutex_unlock(&kernfs_mutex);
+
+		if (secdata)
+			security_release_secctx(secdata, secdata_len);
+		return error;
+	} else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
+		return simple_xattr_set(&attrs->xattrs, name, value, size,
+					flags);
+	}
+
+	return -EINVAL;
+}
+
+int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_remove(&attrs->xattrs, name);
+}
+
+ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
+			    size_t size)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_get(&attrs->xattrs, name, buf, size);
+}
+
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_list(&attrs->xattrs, buf, size);
+}
+
+static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
+{
+	inode->i_mode = mode;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+}
+
+static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
+{
+	inode->i_uid = iattr->ia_uid;
+	inode->i_gid = iattr->ia_gid;
+	inode->i_atime = iattr->ia_atime;
+	inode->i_mtime = iattr->ia_mtime;
+	inode->i_ctime = iattr->ia_ctime;
+}
+
+static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	struct kernfs_iattrs *attrs = kn->iattr;
+
+	inode->i_mode = kn->mode;
+	if (attrs) {
+		/*
+		 * kernfs_node has non-default attributes get them from
+		 * persistent copy in kernfs_node.
+		 */
+		set_inode_attr(inode, &attrs->ia_iattr);
+		security_inode_notifysecctx(inode, attrs->ia_secdata,
+					    attrs->ia_secdata_len);
+	}
+
+	if (kernfs_type(kn) == KERNFS_DIR)
+		set_nlink(inode, kn->dir.subdirs + 2);
+}
+
+int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		   struct kstat *stat)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct inode *inode = dentry->d_inode;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_refresh_inode(kn, inode);
+	mutex_unlock(&kernfs_mutex);
+
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	kernfs_get(kn);
+	inode->i_private = kn;
+	inode->i_mapping->a_ops = &kernfs_aops;
+	inode->i_mapping->backing_dev_info = &kernfs_bdi;
+	inode->i_op = &kernfs_iops;
+
+	set_default_inode_attr(inode, kn->mode);
+	kernfs_refresh_inode(kn, inode);
+
+	/* initialize inode according to type */
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		inode->i_op = &kernfs_dir_iops;
+		inode->i_fop = &kernfs_dir_fops;
+		break;
+	case KERNFS_FILE:
+		inode->i_size = kn->attr.size;
+		inode->i_fop = &kernfs_file_fops;
+		break;
+	case KERNFS_LINK:
+		inode->i_op = &kernfs_symlink_iops;
+		break;
+	default:
+		BUG();
+	}
+
+	unlock_new_inode(inode);
+}
+
+/**
+ *	kernfs_get_inode - get inode for kernfs_node
+ *	@sb: super block
+ *	@kn: kernfs_node to allocate inode for
+ *
+ *	Get inode for @kn.  If such inode doesn't exist, a new inode is
+ *	allocated and basics are initialized.  New inode is returned
+ *	locked.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	Pointer to allocated inode on success, NULL on failure.
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
+{
+	struct inode *inode;
+
+	inode = iget_locked(sb, kn->ino);
+	if (inode && (inode->i_state & I_NEW))
+		kernfs_init_inode(kn, inode);
+
+	return inode;
+}
+
+/*
+ * The kernfs_node serves as both an inode and a directory entry for
+ * kernfs.  To prevent the kernfs inode numbers from being freed
+ * prematurely we take a reference to kernfs_node from the kernfs inode.  A
+ * super_operations.evict_inode() implementation is needed to drop that
+ * reference upon inode destruction.
+ */
+void kernfs_evict_inode(struct inode *inode)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kernfs_put(kn);
+}
+
+int kernfs_iop_permission(struct inode *inode, int mask)
+{
+	struct kernfs_node *kn;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	kn = inode->i_private;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_refresh_inode(kn, inode);
+	mutex_unlock(&kernfs_mutex);
+
+	return generic_permission(inode, mask);
+}

fs/kernfs/kernfs-internal.h

@@ -0,0 +1,120 @@
+/*
+ * fs/kernfs/kernfs-internal.h - kernfs internal header file
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef __KERNFS_INTERNAL_H
+#define __KERNFS_INTERNAL_H
+
+#include <linux/lockdep.h>
+#include <linux/fs.h>
+#include <linux/mutex.h>
+#include <linux/xattr.h>
+
+#include <linux/kernfs.h>
+
+struct kernfs_iattrs {
+	struct iattr		ia_iattr;
+	void			*ia_secdata;
+	u32			ia_secdata_len;
+
+	struct simple_xattrs	xattrs;
+};
+
+/* +1 to avoid triggering overflow warning when negating it */
+#define KN_DEACTIVATED_BIAS		(INT_MIN + 1)
+
+/* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
+
+/**
+ * kernfs_root - find out the kernfs_root a kernfs_node belongs to
+ * @kn: kernfs_node of interest
+ *
+ * Return the kernfs_root @kn belongs to.
+ */
+static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
+{
+	/* if parent exists, it's always a dir; otherwise, @sd is a dir */
+	if (kn->parent)
+		kn = kn->parent;
+	return kn->dir.root;
+}
+
+/*
+ * mount.c
+ */
+struct kernfs_super_info {
+	struct super_block	*sb;
+
+	/*
+	 * The root associated with this super_block.  Each super_block is
+	 * identified by the root and ns it's associated with.
+	 */
+	struct kernfs_root	*root;
+
+	/*
+	 * Each sb is associated with one namespace tag, currently the
+	 * network namespace of the task which mounted this kernfs
+	 * instance.  If multiple tags become necessary, make the following
+	 * an array and compare kernfs_node tag against every entry.
+	 */
+	const void		*ns;
+
+	/* anchored at kernfs_root->supers, protected by kernfs_mutex */
+	struct list_head	node;
+};
+#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
+
+extern const struct super_operations kernfs_sops;
+extern struct kmem_cache *kernfs_node_cache;
+
+/*
+ * inode.c
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn);
+void kernfs_evict_inode(struct inode *inode);
+int kernfs_iop_permission(struct inode *inode, int mask);
+int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
+int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		       struct kstat *stat);
+int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value,
+			size_t size, int flags);
+int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
+ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
+			    size_t size);
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
+void kernfs_inode_init(void);
+
+/*
+ * dir.c
+ */
+extern struct mutex kernfs_mutex;
+extern const struct dentry_operations kernfs_dops;
+extern const struct file_operations kernfs_dir_fops;
+extern const struct inode_operations kernfs_dir_iops;
+
+struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
+void kernfs_put_active(struct kernfs_node *kn);
+int kernfs_add_one(struct kernfs_node *kn);
+struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
+				    const char *name, umode_t mode,
+				    unsigned flags);
+
+/*
+ * file.c
+ */
+extern const struct file_operations kernfs_file_fops;
+
+void kernfs_unmap_bin_file(struct kernfs_node *kn);
+
+/*
+ * symlink.c
+ */
+extern const struct inode_operations kernfs_symlink_iops;
+
+#endif	/* __KERNFS_INTERNAL_H */

fs/kernfs/mount.c

@@ -0,0 +1,250 @@
+/*
+ * fs/kernfs/mount.c - kernfs mount implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+
+#include "kernfs-internal.h"
+
+struct kmem_cache *kernfs_node_cache;
+
+static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct kernfs_root *root = kernfs_info(sb)->root;
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->remount_fs)
+		return scops->remount_fs(root, flags, data);
+	return 0;
+}
+
+static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
+{
+	struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->show_options)
+		return scops->show_options(sf, root);
+	return 0;
+}
+
+const struct super_operations kernfs_sops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= kernfs_evict_inode,
+
+	.remount_fs	= kernfs_sop_remount_fs,
+	.show_options	= kernfs_sop_show_options,
+};
+
+/**
+ * kernfs_root_from_sb - determine kernfs_root associated with a super_block
+ * @sb: the super_block in question
+ *
+ * Return the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * %NULL is returned.
+ */
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{
+	if (sb->s_op == &kernfs_sops)
+		return kernfs_info(sb)->root;
+	return NULL;
+}
+
+static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct inode *inode;
+	struct dentry *root;
+
+	info->sb = sb;
+	sb->s_blocksize = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_magic = magic;
+	sb->s_op = &kernfs_sops;
+	sb->s_time_gran = 1;
+
+	/* get root inode, initialize and unlock it */
+	mutex_lock(&kernfs_mutex);
+	inode = kernfs_get_inode(sb, info->root->kn);
+	mutex_unlock(&kernfs_mutex);
+	if (!inode) {
+		pr_debug("kernfs: could not get root inode\n");
+		return -ENOMEM;
+	}
+
+	/* instantiate and link root dentry */
+	root = d_make_root(inode);
+	if (!root) {
+		pr_debug("%s: could not get root dentry!\n", __func__);
+		return -ENOMEM;
+	}
+	kernfs_get(info->root->kn);
+	root->d_fsdata = info->root->kn;
+	sb->s_root = root;
+	sb->s_d_op = &kernfs_dops;
+	return 0;
+}
+
+static int kernfs_test_super(struct super_block *sb, void *data)
+{
+	struct kernfs_super_info *sb_info = kernfs_info(sb);
+	struct kernfs_super_info *info = data;
+
+	return sb_info->root == info->root && sb_info->ns == info->ns;
+}
+
+static int kernfs_set_super(struct super_block *sb, void *data)
+{
+	int error;
+	error = set_anon_super(sb, data);
+	if (!error)
+		sb->s_fs_info = data;
+	return error;
+}
+
+/**
+ * kernfs_super_ns - determine the namespace tag of a kernfs super_block
+ * @sb: super_block of interest
+ *
+ * Return the namespace tag associated with kernfs super_block @sb.
+ */
+const void *kernfs_super_ns(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+
+	return info->ns;
+}
+
+/**
+ * kernfs_mount_ns - kernfs mount helper
+ * @fs_type: file_system_type of the fs being mounted
+ * @flags: mount flags specified for the mount
+ * @root: kernfs_root of the hierarchy being mounted
+ * @magic: file system specific magic number
+ * @new_sb_created: tell the caller if we allocated a new superblock
+ * @ns: optional namespace tag of the mount
+ *
+ * This is to be called from each kernfs user's file_system_type->mount()
+ * implementation, which should pass through the specified @fs_type and
+ * @flags, and specify the hierarchy and namespace tag to mount via @root
+ * and @ns, respectively.
+ *
+ * The return value can be passed to the vfs layer verbatim.
+ */
+struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
+				struct kernfs_root *root, unsigned long magic,
+				bool *new_sb_created, const void *ns)
+{
+	struct super_block *sb;
+	struct kernfs_super_info *info;
+	int error;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->root = root;
+	info->ns = ns;
+
+	sb = sget(fs_type, kernfs_test_super, kernfs_set_super, flags, info);
+	if (IS_ERR(sb) || sb->s_fs_info != info)
+		kfree(info);
+	if (IS_ERR(sb))
+		return ERR_CAST(sb);
+
+	if (new_sb_created)
+		*new_sb_created = !sb->s_root;
+
+	if (!sb->s_root) {
+		struct kernfs_super_info *info = kernfs_info(sb);
+
+		error = kernfs_fill_super(sb, magic);
+		if (error) {
+			deactivate_locked_super(sb);
+			return ERR_PTR(error);
+		}
+		sb->s_flags |= MS_ACTIVE;
+
+		mutex_lock(&kernfs_mutex);
+		list_add(&info->node, &root->supers);
+		mutex_unlock(&kernfs_mutex);
+	}
+
+	return dget(sb->s_root);
+}
+
+/**
+ * kernfs_kill_sb - kill_sb for kernfs
+ * @sb: super_block being killed
+ *
+ * This can be used directly for file_system_type->kill_sb().  If a kernfs
+ * user needs extra cleanup, it can implement its own kill_sb() and call
+ * this function at the end.
+ */
+void kernfs_kill_sb(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_node *root_kn = sb->s_root->d_fsdata;
+
+	mutex_lock(&kernfs_mutex);
+	list_del(&info->node);
+	mutex_unlock(&kernfs_mutex);
+
+	/*
+	 * Remove the superblock from fs_supers/s_instances
+	 * so we can't find it, before freeing kernfs_super_info.
+	 */
+	kill_anon_super(sb);
+	kfree(info);
+	kernfs_put(root_kn);
+}
+
+/**
+ * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
+ * @kernfs_root: the kernfs_root in question
+ * @ns: the namespace tag
+ *
+ * Pin the superblock so the superblock won't be destroyed in subsequent
+ * operations.  This can be used to block ->kill_sb() which may be useful
+ * for kernfs users which dynamically manage superblocks.
+ *
+ * Returns NULL if there's no superblock associated to this kernfs_root, or
+ * -EINVAL if the superblock is being freed.
+ */
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
+{
+	struct kernfs_super_info *info;
+	struct super_block *sb = NULL;
+
+	mutex_lock(&kernfs_mutex);
+	list_for_each_entry(info, &root->supers, node) {
+		if (info->ns == ns) {
+			sb = info->sb;
+			if (!atomic_inc_not_zero(&info->sb->s_active))
+				sb = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	mutex_unlock(&kernfs_mutex);
+	return sb;
+}
+
+void __init kernfs_init(void)
+{
+	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
+					      sizeof(struct kernfs_node),
+					      0, SLAB_PANIC, NULL);
+	kernfs_inode_init();
+}

fs/kernfs/symlink.c

@@ -0,0 +1,147 @@
+/*
+ * fs/kernfs/symlink.c - kernfs symlink implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/namei.h>
+
+#include "kernfs-internal.h"
+
+/**
+ * kernfs_create_link - create a symlink
+ * @parent: directory to create the symlink in
+ * @name: name of the symlink
+ * @target: target node for the symlink to point to
+ *
+ * Returns the created node on success, ERR_PTR() value on error.
+ */
+struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
+				       const char *name,
+				       struct kernfs_node *target)
+{
+	struct kernfs_node *kn;
+	int error;
+
+	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	if (kernfs_ns_enabled(parent))
+		kn->ns = target->ns;
+	kn->symlink.target_kn = target;
+	kernfs_get(target);	/* ref owned by symlink */
+
+	error = kernfs_add_one(kn);
+	if (!error)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(error);
+}
+
+static int kernfs_get_target_path(struct kernfs_node *parent,
+				  struct kernfs_node *target, char *path)
+{
+	struct kernfs_node *base, *kn;
+	char *s = path;
+	int len = 0;
+
+	/* go up to the root, stop at the base */
+	base = parent;
+	while (base->parent) {
+		kn = target->parent;
+		while (kn->parent && base != kn)
+			kn = kn->parent;
+
+		if (base == kn)
+			break;
+
+		strcpy(s, "../");
+		s += 3;
+		base = base->parent;
+	}
+
+	/* determine end of target string for reverse fillup */
+	kn = target;
+	while (kn->parent && kn != base) {
+		len += strlen(kn->name) + 1;
+		kn = kn->parent;
+	}
+
+	/* check limits */
+	if (len < 2)
+		return -EINVAL;
+	len--;
+	if ((s - path) + len > PATH_MAX)
+		return -ENAMETOOLONG;
+
+	/* reverse fillup of target string from target to base */
+	kn = target;
+	while (kn->parent && kn != base) {
+		int slen = strlen(kn->name);
+
+		len -= slen;
+		strncpy(s + len, kn->name, slen);
+		if (len)
+			s[--len] = '/';
+
+		kn = kn->parent;
+	}
+
+	return 0;
+}
+
+static int kernfs_getlink(struct dentry *dentry, char *path)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_node *parent = kn->parent;
+	struct kernfs_node *target = kn->symlink.target_kn;
+	int error;
+
+	mutex_lock(&kernfs_mutex);
+	error = kernfs_get_target_path(parent, target, path);
+	mutex_unlock(&kernfs_mutex);
+
+	return error;
+}
+
+static void *kernfs_iop_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	int error = -ENOMEM;
+	unsigned long page = get_zeroed_page(GFP_KERNEL);
+	if (page) {
+		error = kernfs_getlink(dentry, (char *) page);
+		if (error < 0)
+			free_page((unsigned long)page);
+	}
+	nd_set_link(nd, error ? ERR_PTR(error) : (char *)page);
+	return NULL;
+}
+
+static void kernfs_iop_put_link(struct dentry *dentry, struct nameidata *nd,
+				void *cookie)
+{
+	char *page = nd_get_link(nd);
+	if (!IS_ERR(page))
+		free_page((unsigned long)page);
+}
+
+const struct inode_operations kernfs_symlink_iops = {
+	.setxattr	= kernfs_iop_setxattr,
+	.removexattr	= kernfs_iop_removexattr,
+	.getxattr	= kernfs_iop_getxattr,
+	.listxattr	= kernfs_iop_listxattr,
+	.readlink	= generic_readlink,
+	.follow_link	= kernfs_iop_follow_link,
+	.put_link	= kernfs_iop_put_link,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.permission	= kernfs_iop_permission,
+};