fs/proc/generic.c

/*
 * proc/fs/generic.c --- generic routines for the proc-fs
 *
 * This file contains generic proc-fs routines for handling
 * directories and files.
 * 
 * Copyright (C) 1991, 1992 Linus Torvalds.
 * Copyright (C) 1997 Theodore Ts'o
 */

#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/printk.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/idr.h>
#include <linux/namei.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <asm/uaccess.h>

#include "internal.h"

DEFINE_SPINLOCK(proc_subdir_lock);

static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
	if (de->namelen != len)
		return 0;
	return !memcmp(name, de->name, len);
}

static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = dentry->d_inode;
	struct proc_dir_entry *de = PDE(inode);
	int error;

	error = inode_change_ok(inode, iattr);
	if (error)
		return error;

	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);

	de->uid = inode->i_uid;
	de->gid = inode->i_gid;
	de->mode = inode->i_mode;
	return 0;
}

static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
			struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct proc_dir_entry *de = PROC_I(inode)->pde;
	if (de && de->nlink)
		set_nlink(inode, de->nlink);

	generic_fillattr(inode, stat);
	return 0;
}

static const struct inode_operations proc_file_inode_operations = {
	.setattr	= proc_notify_change,
};

/*
 * This function parses a name such as "tty/driver/serial", and
 * returns the struct proc_dir_entry for "/proc/tty/driver", and
 * returns "serial" in residual.
 */
static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
			     const char **residual)
{
	const char     		*cp = name, *next;
	struct proc_dir_entry	*de;
	unsigned int		len;

	de = *ret;
	if (!de)
		de = &proc_root;

	while (1) {
		next = strchr(cp, '/');
		if (!next)
			break;

		len = next - cp;
		for (de = de->subdir; de ; de = de->next) {
			if (proc_match(len, cp, de))
				break;
		}
		if (!de) {
			WARN(1, "name '%s'\n", name);
			return -ENOENT;
		}
		cp += len + 1;
	}
	*residual = cp;
	*ret = de;
	return 0;
}

static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
			   const char **residual)
{
	int rv;

	spin_lock(&proc_subdir_lock);
	rv = __xlate_proc_name(name, ret, residual);
	spin_unlock(&proc_subdir_lock);
	return rv;
}

static DEFINE_IDA(proc_inum_ida);
static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */

#define PROC_DYNAMIC_FIRST 0xF0000000U

/*
 * Return an inode number between PROC_DYNAMIC_FIRST and
 * 0xffffffff, or zero on failure.
 */
int proc_alloc_inum(unsigned int *inum)
{
	unsigned int i;
	int error;

retry:
	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
		return -ENOMEM;

	spin_lock_irq(&proc_inum_lock);
	error = ida_get_new(&proc_inum_ida, &i);
	spin_unlock_irq(&proc_inum_lock);
	if (error == -EAGAIN)
		goto retry;
	else if (error)
		return error;

	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
		spin_lock_irq(&proc_inum_lock);
		ida_remove(&proc_inum_ida, i);
		spin_unlock_irq(&proc_inum_lock);
		return -ENOSPC;
	}
	*inum = PROC_DYNAMIC_FIRST + i;
	return 0;
}

void proc_free_inum(unsigned int inum)
{
	unsigned long flags;
	spin_lock_irqsave(&proc_inum_lock, flags);
	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
	spin_unlock_irqrestore(&proc_inum_lock, flags);
}

static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	nd_set_link(nd, PDE_DATA(dentry->d_inode));
	return NULL;
}

static const struct inode_operations proc_link_inode_operations = {
	.readlink	= generic_readlink,
	.follow_link	= proc_follow_link,
};

/*
 * As some entries in /proc are volatile, we want to 
 * get rid of unused dentries.  This could be made 
 * smarter: we could keep a "volatile" flag in the 
 * inode to indicate which ones to keep.
 */
static int proc_delete_dentry(const struct dentry * dentry)
{
	return 1;
}

static const struct dentry_operations proc_dentry_operations =
{
	.d_delete	= proc_delete_dentry,
};

/*
 * Don't create negative dentries here, return -ENOENT by hand
 * instead.
 */
struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
		struct dentry *dentry)
{
	struct inode *inode;

	spin_lock(&proc_subdir_lock);
	for (de = de->subdir; de ; de = de->next) {
		if (de->namelen != dentry->d_name.len)
			continue;
		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
			pde_get(de);
			spin_unlock(&proc_subdir_lock);
			inode = proc_get_inode(dir->i_sb, de);
			if (!inode)
				return ERR_PTR(-ENOMEM);
			d_set_d_op(dentry, &proc_dentry_operations);
			d_add(dentry, inode);
			return NULL;
		}
	}
	spin_unlock(&proc_subdir_lock);
	return ERR_PTR(-ENOENT);
}

struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
		unsigned int flags)
{
	return proc_lookup_de(PDE(dir), dir, dentry);
}

/*
 * This returns non-zero if at EOF, so that the /proc
 * root directory can use this and check if it should
 * continue with the <pid> entries..
 *
 * Note that the VFS-layer doesn't care about the return
 * value of the readdir() call, as long as it's non-negative
 * for success..
 */
int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
		filldir_t filldir)
{
	unsigned int ino;
	int i;
	struct inode *inode = file_inode(filp);
	int ret = 0;

	ino = inode->i_ino;
	i = filp->f_pos;
	switch (i) {
		case 0:
			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
				goto out;
			i++;
			filp->f_pos++;
			/* fall through */
		case 1:
			if (filldir(dirent, "..", 2, i,
				    parent_ino(filp->f_path.dentry),
				    DT_DIR) < 0)
				goto out;
			i++;
			filp->f_pos++;
			/* fall through */
		default:
			spin_lock(&proc_subdir_lock);
			de = de->subdir;
			i -= 2;
			for (;;) {
				if (!de) {
					ret = 1;
					spin_unlock(&proc_subdir_lock);
					goto out;
				}
				if (!i)
					break;
				de = de->next;
				i--;
			}

			do {
				struct proc_dir_entry *next;

				/* filldir passes info to user space */
				pde_get(de);
				spin_unlock(&proc_subdir_lock);
				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
					    de->low_ino, de->mode >> 12) < 0) {
					pde_put(de);
					goto out;
				}
				spin_lock(&proc_subdir_lock);
				filp->f_pos++;
				next = de->next;
				pde_put(de);
				de = next;
			} while (de);
			spin_unlock(&proc_subdir_lock);
	}
	ret = 1;
out:
	return ret;	
}

int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
	struct inode *inode = file_inode(filp);

	return proc_readdir_de(PDE(inode), filp, dirent, filldir);
}

/*
 * These are the generic /proc directory operations. They
 * use the in-memory "struct proc_dir_entry" tree to parse
 * the /proc directory.
 */
static const struct file_operations proc_dir_operations = {
	.llseek			= generic_file_llseek,
	.read			= generic_read_dir,
	.readdir		= proc_readdir,
};

/*
 * proc directories can do almost nothing..
 */
static const struct inode_operations proc_dir_inode_operations = {
	.lookup		= proc_lookup,
	.getattr	= proc_getattr,
	.setattr	= proc_notify_change,
};

static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
{
	struct proc_dir_entry *tmp;
	int ret;
	
	ret = proc_alloc_inum(&dp->low_ino);
	if (ret)
		return ret;

	if (S_ISDIR(dp->mode)) {
		dp->proc_fops = &proc_dir_operations;
		dp->proc_iops = &proc_dir_inode_operations;
		dir->nlink++;
	} else if (S_ISLNK(dp->mode)) {
		dp->proc_iops = &proc_link_inode_operations;
	} else if (S_ISREG(dp->mode)) {
		BUG_ON(dp->proc_fops == NULL);
		dp->proc_iops = &proc_file_inode_operations;
	} else {
		WARN_ON(1);
		return -EINVAL;
	}

	spin_lock(&proc_subdir_lock);

	for (tmp = dir->subdir; tmp; tmp = tmp->next)
		if (strcmp(tmp->name, dp->name) == 0) {
			WARN(1, "proc_dir_entry '%s/%s' already registered\n",
				dir->name, dp->name);
			break;
		}

	dp->next = dir->subdir;
	dp->parent = dir;
	dir->subdir = dp;
	spin_unlock(&proc_subdir_lock);

	return 0;
}

static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
					  const char *name,
					  umode_t mode,
					  nlink_t nlink)
{
	struct proc_dir_entry *ent = NULL;
	const char *fn = name;
	unsigned int len;

	/* make sure name is valid */
	if (!name || !strlen(name))
		goto out;

	if (xlate_proc_name(name, parent, &fn) != 0)
		goto out;

	/* At this point there must not be any '/' characters beyond *fn */
	if (strchr(fn, '/'))
		goto out;

	len = strlen(fn);

	ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
	if (!ent)
		goto out;

	memcpy(ent->name, fn, len + 1);
	ent->namelen = len;
	ent->mode = mode;
	ent->nlink = nlink;
	atomic_set(&ent->count, 1);
	spin_lock_init(&ent->pde_unload_lock);
	INIT_LIST_HEAD(&ent->pde_openers);
out:
	return ent;
}

struct proc_dir_entry *proc_symlink(const char *name,
		struct proc_dir_entry *parent, const char *dest)
{
	struct proc_dir_entry *ent;

	ent = __proc_create(&parent, name,
			  (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);

	if (ent) {
		ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL);
		if (ent->data) {
			strcpy((char*)ent->data,dest);
			if (proc_register(parent, ent) < 0) {
				kfree(ent->data);
				kfree(ent);
				ent = NULL;
			}
		} else {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}
EXPORT_SYMBOL(proc_symlink);

struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
		struct proc_dir_entry *parent)
{
	struct proc_dir_entry *ent;

	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
	if (ent) {
		if (proc_register(parent, ent) < 0) {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}
EXPORT_SYMBOL(proc_mkdir_mode);

struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
		struct proc_dir_entry *parent)
{
	struct proc_dir_entry *ent;

	ent = __proc_create(&parent, name, S_IFDIR | S_IRUGO | S_IXUGO, 2);
	if (ent) {
		ent->data = net;
		if (proc_register(parent, ent) < 0) {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}
EXPORT_SYMBOL_GPL(proc_net_mkdir);

struct proc_dir_entry *proc_mkdir(const char *name,
		struct proc_dir_entry *parent)
{
	return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
}
EXPORT_SYMBOL(proc_mkdir);

struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
					struct proc_dir_entry *parent,
					const struct file_operations *proc_fops,
					void *data)
{
	struct proc_dir_entry *pde;
	if ((mode & S_IFMT) == 0)
		mode |= S_IFREG;

	if (!S_ISREG(mode)) {
		WARN_ON(1);	/* use proc_mkdir() */
		return NULL;
	}

	if ((mode & S_IALLUGO) == 0)
		mode |= S_IRUGO;
	pde = __proc_create(&parent, name, mode, 1);
	if (!pde)
		goto out;
	pde->proc_fops = proc_fops;
	pde->data = data;
	if (proc_register(parent, pde) < 0)
		goto out_free;
	return pde;
out_free:
	kfree(pde);
out:
	return NULL;
}
EXPORT_SYMBOL(proc_create_data);
 
void proc_set_size(struct proc_dir_entry *de, loff_t size)
{
	de->size = size;
}
EXPORT_SYMBOL(proc_set_size);

void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
{
	de->uid = uid;
	de->gid = gid;
}
EXPORT_SYMBOL(proc_set_user);

static void free_proc_entry(struct proc_dir_entry *de)
{
	proc_free_inum(de->low_ino);

	if (S_ISLNK(de->mode))
		kfree(de->data);
	kfree(de);
}

void pde_put(struct proc_dir_entry *pde)
{
	if (atomic_dec_and_test(&pde->count))
		free_proc_entry(pde);
}

/*
 * Remove a /proc entry and free it if it's not currently in use.
 */
void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
{
	struct proc_dir_entry **p;
	struct proc_dir_entry *de = NULL;
	const char *fn = name;
	unsigned int len;

	spin_lock(&proc_subdir_lock);
	if (__xlate_proc_name(name, &parent, &fn) != 0) {
		spin_unlock(&proc_subdir_lock);
		return;
	}
	len = strlen(fn);

	for (p = &parent->subdir; *p; p=&(*p)->next ) {
		if (proc_match(len, fn, *p)) {
			de = *p;
			*p = de->next;
			de->next = NULL;
			break;
		}
	}
	spin_unlock(&proc_subdir_lock);
	if (!de) {
		WARN(1, "name '%s'\n", name);
		return;
	}

	proc_entry_rundown(de);

	if (S_ISDIR(de->mode))
		parent->nlink--;
	de->nlink = 0;
	WARN(de->subdir, "%s: removing non-empty directory "
			 "'%s/%s', leaking at least '%s'\n", __func__,
			 de->parent->name, de->name, de->subdir->name);
	pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);

int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
{
	struct proc_dir_entry **p;
	struct proc_dir_entry *root = NULL, *de, *next;
	const char *fn = name;
	unsigned int len;

	spin_lock(&proc_subdir_lock);
	if (__xlate_proc_name(name, &parent, &fn) != 0) {
		spin_unlock(&proc_subdir_lock);
		return -ENOENT;
	}
	len = strlen(fn);

	for (p = &parent->subdir; *p; p=&(*p)->next ) {
		if (proc_match(len, fn, *p)) {
			root = *p;
			*p = root->next;
			root->next = NULL;
			break;
		}
	}
	if (!root) {
		spin_unlock(&proc_subdir_lock);
		return -ENOENT;
	}
	de = root;
	while (1) {
		next = de->subdir;
		if (next) {
			de->subdir = next->next;
			next->next = NULL;
			de = next;
			continue;
		}
		spin_unlock(&proc_subdir_lock);

		proc_entry_rundown(de);
		next = de->parent;
		if (S_ISDIR(de->mode))
			next->nlink--;
		de->nlink = 0;
		if (de == root)
			break;
		pde_put(de);

		spin_lock(&proc_subdir_lock);
		de = next;
	}
	pde_put(root);
	return 0;
}
EXPORT_SYMBOL(remove_proc_subtree);