dir.c

linux 内核源代码

/*
 * 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 <[e-mail]>
 *
 * 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 "sysfs.h"

DEFINE_MUTEX(sysfs_mutex);
DEFINE_MUTEX(sysfs_rename_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_dentry - get dentry for the given sysfs_dirent
 *	@sd: sysfs_dirent of interest
 *
 *	Get dentry for @sd.  Dentry is looked up if currently not
 *	present.  This function descends from the root looking up
 *	dentry for each step.
 *
 *	LOCKING:
 *	mutex_lock(sysfs_rename_mutex)
 *
 *	RETURNS:
 *	Pointer to found dentry on success, ERR_PTR() value on error.
 */
struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
{
	struct dentry *dentry = dget(sysfs_sb->s_root);

	while (dentry->d_fsdata != sd) {
		struct sysfs_dirent *cur;
		struct dentry *parent;

		/* find the first ancestor which hasn't been looked up */
		cur = sd;
		while (cur->s_parent != dentry->d_fsdata)
			cur = cur->s_parent;

		/* look it up */
		parent = dentry;
		mutex_lock(&parent->d_inode->i_mutex);
		dentry = lookup_one_noperm(cur->s_name, parent);
		mutex_unlock(&parent->d_inode->i_mutex);
		dput(parent);

		if (IS_ERR(dentry))
			break;
	}
	return dentry;
}

/**
 *	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.
 */
static 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))
			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.
 */
static void sysfs_put_active(struct sysfs_dirent *sd)
{
	struct completion *cmpl;
	int v;

	if (unlikely(!sd))
		return;

	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_get_active_two - get active references to sysfs_dirent and parent
 *	@sd: sysfs_dirent of interest
 *
 *	Get active reference to @sd and its parent.  Parent's active
 *	reference is grabbed first.  This function is noop if @sd is
 *	NULL.
 *
 *	RETURNS:
 *	Pointer to @sd on success, NULL on failure.
 */
struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd)
{
	if (sd) {
		if (sd->s_parent && unlikely(!sysfs_get_active(sd->s_parent)))
			return NULL;
		if (unlikely(!sysfs_get_active(sd))) {
			sysfs_put_active(sd->s_parent);
			return NULL;
		}
	}
	return sd;
}

/**
 *	sysfs_put_active_two - put active references to sysfs_dirent and parent
 *	@sd: sysfs_dirent of interest
 *
 *	Put active references to @sd and its parent.  This function is
 *	noop if @sd is NULL.
 */
void sysfs_put_active_two(struct sysfs_dirent *sd)
{
	if (sd) {
		sysfs_put_active(sd);
		sysfs_put_active(sd->s_parent);
	}
}

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

	/* 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)
		wait_for_completion(&wait);

	sd->s_sibling = NULL;
}

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;
	return rc;
}

static void sysfs_free_ino(ino_t ino)
{
	spin_lock(&sysfs_ino_lock);
	ida_remove(&sysfs_ino_ida, ino);
	spin_unlock(&sysfs_ino_lock);
}

void release_sysfs_dirent(struct sysfs_dirent * sd)
{
	struct sysfs_dirent *parent_sd;

 repeat:
	/* Moving/renaming is always done while holding reference.
	 * sd->s_parent won't change beneath us.
	 */
	parent_sd = sd->s_parent;

	if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
		sysfs_put(sd->s_symlink.target_sd);
	if (sysfs_type(sd) & SYSFS_COPY_NAME)
		kfree(sd->s_name);
	kfree(sd->s_iattr);
	sysfs_free_ino(sd->s_ino);
	kmem_cache_free(sysfs_dir_cachep, sd);

	sd = parent_sd;
	if (sd && atomic_dec_and_test(&sd->s_count))
		goto repeat;
}

static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
{
	struct sysfs_dirent * sd = dentry->d_fsdata;

	sysfs_put(sd);
	iput(inode);
}

static struct dentry_operations sysfs_dentry_ops = {
	.d_iput		= sysfs_d_iput,
};

struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
{
	char *dup_name = NULL;
	struct sysfs_dirent *sd;

	if (type & SYSFS_COPY_NAME) {
		name = dup_name = kstrdup(name, GFP_KERNEL);
		if (!name)
			return NULL;
	}

	sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL);
	if (!sd)
		goto err_out1;

	if (sysfs_alloc_ino(&sd->s_ino))
		goto err_out2;

	atomic_set(&sd->s_count, 1);
	atomic_set(&sd->s_active, 0);

	sd->s_name = name;
	sd->s_mode = mode;
	sd->s_flags = type;

	return sd;

 err_out2:
	kmem_cache_free(sysfs_dir_cachep, sd);
 err_out1:
	kfree(dup_name);
	return NULL;
}

static int sysfs_ilookup_test(struct inode *inode, void *arg)
{
	struct sysfs_dirent *sd = arg;
	return inode->i_ino == sd->s_ino;
}

/**
 *	sysfs_addrm_start - prepare for sysfs_dirent add/remove
 *	@acxt: pointer to sysfs_addrm_cxt to be used
 *	@parent_sd: parent sysfs_dirent
 *
 *	This function is called when the caller is about to add or
 *	remove sysfs_dirent under @parent_sd.  This function acquires
 *	sysfs_mutex, grabs inode for @parent_sd if available and lock
 *	i_mutex of it.  @acxt is used to keep and pass context to
 *	other addrm functions.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).  sysfs_mutex is locked on
 *	return.  i_mutex of parent inode is locked on return if
 *	available.
 */
void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
		       struct sysfs_dirent *parent_sd)
{
	struct inode *inode;

	memset(acxt, 0, sizeof(*acxt));
	acxt->parent_sd = parent_sd;

	/* Lookup parent inode.  inode initialization and I_NEW
	 * clearing are protected by sysfs_mutex.  By grabbing it and
	 * looking up with _nowait variant, inode state can be
	 * determined reliably.
	 */
	mutex_lock(&sysfs_mutex);

	inode = ilookup5_nowait(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
				parent_sd);

	if (inode && !(inode->i_state & I_NEW)) {
		/* parent inode available */
		acxt->parent_inode = inode;

		/* sysfs_mutex is below i_mutex in lock hierarchy.
		 * First, trylock i_mutex.  If fails, unlock
		 * sysfs_mutex and lock them in order.
		 */
		if (!mutex_trylock(&inode->i_mutex)) {
			mutex_unlock(&sysfs_mutex);
			mutex_lock(&inode->i_mutex);
			mutex_lock(&sysfs_mutex);
		}
	} else
		iput(inode);
}

/**
 *	sysfs_add_one - add sysfs_dirent to parent
 *	@acxt: addrm context to use
 *	@sd: sysfs_dirent to be added
 *
 *	Get @acxt->parent_sd and set sd->s_parent to it and increment
 *	nlink of parent inode if @sd is a directory and link into the
 *	children list of the parent.
 *
 *	This function should be called between calls to
 *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
 *	passed the same @acxt as passed to sysfs_addrm_start().
 *
 *	LOCKING:
 *	Determined by sysfs_addrm_start().
 *
 *	RETURNS:
 *	0 on success, -EEXIST if entry with the given name already
 *	exists.
 */
int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
	if (sysfs_find_dirent(acxt->parent_sd, sd->s_name)) {
		printk(KERN_WARNING "sysfs: duplicate filename '%s' "
		       "can not be created\n", sd->s_name);
		WARN_ON(1);
		return -EEXIST;
	}

	sd->s_parent = sysfs_get(acxt->parent_sd);

	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
		inc_nlink(acxt->parent_inode);

	acxt->cnt++;

	sysfs_link_sibling(sd);

	return 0;
}

/**
 *	sysfs_remove_one - remove sysfs_dirent from parent
 *	@acxt: addrm context to use
 *	@sd: sysfs_dirent to be added
 *
 *	Mark @sd removed and drop nlink of parent inode if @sd is a
 *	directory.  @sd is unlinked from the children list.
 *
 *	This function should be called between calls to
 *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
 *	passed the same @acxt as passed to sysfs_addrm_start().
 *
 *	LOCKING:
 *	Determined by sysfs_addrm_start().
 */
void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
	BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);

	sysfs_unlink_sibling(sd);

	sd->s_flags |= SYSFS_FLAG_REMOVED;
	sd->s_sibling = acxt->removed;
	acxt->removed = sd;

	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
		drop_nlink(acxt->parent_inode);

	acxt->cnt++;
}

/**
 *	sysfs_drop_dentry - drop dentry for the specified sysfs_dirent
 *	@sd: target sysfs_dirent
 *
 *	Drop dentry for @sd.  @sd must have been unlinked from its
 *	parent on entry to this function such that it can't be looked
 *	up anymore.
 */
static void sysfs_drop_dentry(struct sysfs_dirent *sd)
{
	struct inode *inode;
	struct dentry *dentry;