path: root/fs/sysfs/dir.c

/*
 * fs/sysfs/dir.c - sysfs core and dir operation implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
 *
 * This file is released under the GPLv2.
 *
 * Please see Documentation/filesystems/sysfs.txt for more information.
 */

#undef DEBUG

#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/kobject.h>
#include <linux/namei.h>
#include <linux/idr.h>
#include <linux/completion.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/security.h>
#include "sysfs.h"

DEFINE_MUTEX(sysfs_mutex);
DEFINE_SPINLOCK(sysfs_assoc_lock);

static DEFINE_SPINLOCK(sysfs_ino_lock);
static DEFINE_IDA(sysfs_ino_ida);

/**
 *	sysfs_link_sibling - link sysfs_dirent into sibling list
 *	@sd: sysfs_dirent of interest
 *
 *	Link @sd into its sibling list which starts from
 *	sd->s_parent->s_dir.children.
 *
 *	Locking:
 *	mutex_lock(sysfs_mutex)
 */
static void sysfs_link_sibling(struct sysfs_dirent *sd)
{
	struct sysfs_dirent *parent_sd = sd->s_parent;
	struct sysfs_dirent **pos;

	BUG_ON(sd->s_sibling);

	/* Store directory entries in order by ino.  This allows
	 * readdir to properly restart without having to add a
	 * cursor into the s_dir.children list.
	 */
	for (pos = &parent_sd->s_dir.children; *pos; pos = &(*pos)->s_sibling) {
		if (sd->s_ino < (*pos)->s_ino)
			break;
	}
	sd->s_sibling = *pos;
	*pos = sd;
}

/**
 *	sysfs_unlink_sibling - unlink sysfs_dirent from sibling list
 *	@sd: sysfs_dirent of interest
 *
 *	Unlink @sd from its sibling list which starts from
 *	sd->s_parent->s_dir.children.
 *
 *	Locking:
 *	mutex_lock(sysfs_mutex)
 */
static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
{
	struct sysfs_dirent **pos;

	for (pos = &sd->s_parent->s_dir.children; *pos;
	     pos = &(*pos)->s_sibling) {
		if (*pos == sd) {
			*pos = sd->s_sibling;
			sd->s_sibling = NULL;
			break;
		}
	}
}

/**
 *	sysfs_get_active - get an active reference to sysfs_dirent
 *	@sd: sysfs_dirent to get an active reference to
 *
 *	Get an active reference of @sd.  This function is noop if @sd
 *	is NULL.
 *
 *	RETURNS:
 *	Pointer to @sd on success, NULL on failure.
 */
struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
{
	if (unlikely(!sd))
		return NULL;

	while (1) {
		int v, t;

		v = atomic_read(&sd->s_active);
		if (unlikely(v < 0))
			return NULL;

		t = atomic_cmpxchg(&sd->s_active, v, v + 1);
		if (likely(t == v)) {
			rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
			return sd;
		}
		if (t < 0)
			return NULL;

		cpu_relax();
	}
}

/**
 *	sysfs_put_active - put an active reference to sysfs_dirent
 *	@sd: sysfs_dirent to put an active reference to
 *
 *	Put an active reference to @sd.  This function is noop if @sd
 *	is NULL.
 */
void sysfs_put_active(struct sysfs_dirent *sd)
{
	struct completion *cmpl;
	int v;

	if (unlikely(!sd))
		return;

	rwsem_release(&sd->dep_map, 1, _RET_IP_);
	v = atomic_dec_return(&sd->s_active);
	if (likely(v != SD_DEACTIVATED_BIAS))
		return;

	/* atomic_dec_return() is a mb(), we'll always see the updated
	 * sd->s_sibling.
	 */
	cmpl = (void *)sd->s_sibling;
	complete(cmpl);
}

/**
 *	sysfs_deactivate - deactivate sysfs_dirent
 *	@sd: sysfs_dirent to deactivate
 *
 *	Deny new active references and drain existing ones.
 */
static void sysfs_deactivate(struct sysfs_dirent *sd)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	int v;

	BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED));

	if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF))
		return;

	sd->s_sibling = (void *)&wait;

	rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_);
	/* atomic_add_return() is a mb(), put_active() will always see
	 * the updated sd->s_sibling.
	 */
	v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);

	if (v != SD_DEACTIVATED_BIAS) {
		lock_contended(&sd->dep_map, _RET_IP_);
		wait_for_completion(&wait);
	}

	sd->s_sibling = NULL;

	lock_acquired(&sd->dep_map, _RET_IP_);
	rwsem_release(&sd->dep_map, 1, _RET_IP_);
}

static int sysfs_alloc_ino(ino_t *pino)
{
	int ino, rc;

 retry:
	spin_lock(&sysfs_ino_lock);
	rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino);
	spin_unlock(&sysfs_ino_lock);

	if (rc == -EAGAIN) {
		if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL))
			goto retry;
		rc = -ENOMEM;
	}

	*pino = ino;