generic.c

linux 内核源代码

/*
 * 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/module.h>
#include <linux/mount.h>
#include <linux/smp_lock.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"

static ssize_t proc_file_read(struct file *file, char __user *buf,
			      size_t nbytes, loff_t *ppos);
static ssize_t proc_file_write(struct file *file, const char __user *buffer,
			       size_t count, loff_t *ppos);
static loff_t proc_file_lseek(struct file *, loff_t, int);

DEFINE_SPINLOCK(proc_subdir_lock);

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

static const struct file_operations proc_file_operations = {
	.llseek		= proc_file_lseek,
	.read		= proc_file_read,
	.write		= proc_file_write,
};

/* buffer size is one page but our output routines use some slack for overruns */
#define PROC_BLOCK_SIZE	(PAGE_SIZE - 1024)

static ssize_t
proc_file_read(struct file *file, char __user *buf, size_t nbytes,
	       loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	char 	*page;
	ssize_t	retval=0;
	int	eof=0;
	ssize_t	n, count;
	char	*start;
	struct proc_dir_entry * dp;
	unsigned long long pos;

	/*
	 * Gaah, please just use "seq_file" instead. The legacy /proc
	 * interfaces cut loff_t down to off_t for reads, and ignore
	 * the offset entirely for writes..
	 */
	pos = *ppos;
	if (pos > MAX_NON_LFS)
		return 0;
	if (nbytes > MAX_NON_LFS - pos)
		nbytes = MAX_NON_LFS - pos;

	dp = PDE(inode);
	if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
		return -ENOMEM;

	while ((nbytes > 0) && !eof) {
		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);

		start = NULL;
		if (dp->get_info) {
			/* Handle old net routines */
			n = dp->get_info(page, &start, *ppos, count);
			if (n < count)
				eof = 1;
		} else if (dp->read_proc) {
			/*
			 * How to be a proc read function
			 * ------------------------------
			 * Prototype:
			 *    int f(char *buffer, char **start, off_t offset,
			 *          int count, int *peof, void *dat)
			 *
			 * Assume that the buffer is "count" bytes in size.
			 *
			 * If you know you have supplied all the data you
			 * have, set *peof.
			 *
			 * You have three ways to return data:
			 * 0) Leave *start = NULL.  (This is the default.)
			 *    Put the data of the requested offset at that
			 *    offset within the buffer.  Return the number (n)
			 *    of bytes there are from the beginning of the
			 *    buffer up to the last byte of data.  If the
			 *    number of supplied bytes (= n - offset) is 
			 *    greater than zero and you didn't signal eof
			 *    and the reader is prepared to take more data
			 *    you will be called again with the requested
			 *    offset advanced by the number of bytes 
			 *    absorbed.  This interface is useful for files
			 *    no larger than the buffer.
			 * 1) Set *start = an unsigned long value less than
			 *    the buffer address but greater than zero.
			 *    Put the data of the requested offset at the
			 *    beginning of the buffer.  Return the number of
			 *    bytes of data placed there.  If this number is
			 *    greater than zero and you didn't signal eof
			 *    and the reader is prepared to take more data
			 *    you will be called again with the requested
			 *    offset advanced by *start.  This interface is
			 *    useful when you have a large file consisting
			 *    of a series of blocks which you want to count
			 *    and return as wholes.
			 *    (Hack by [e-mail])
			 * 2) Set *start = an address within the buffer.
			 *    Put the data of the requested offset at *start.
			 *    Return the number of bytes of data placed there.
			 *    If this number is greater than zero and you
			 *    didn't signal eof and the reader is prepared to
			 *    take more data you will be called again with the
			 *    requested offset advanced by the number of bytes
			 *    absorbed.
			 */
			n = dp->read_proc(page, &start, *ppos,
					  count, &eof, dp->data);
		} else
			break;

		if (n == 0)   /* end of file */
			break;
		if (n < 0) {  /* error */
			if (retval == 0)
				retval = n;
			break;
		}

		if (start == NULL) {
			if (n > PAGE_SIZE) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE;
			}
			n -= *ppos;
			if (n <= 0)
				break;
			if (n > count)
				n = count;
			start = page + *ppos;
		} else if (start < page) {
			if (n > PAGE_SIZE) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE;
			}
			if (n > count) {
				/*
				 * Don't reduce n because doing so might
				 * cut off part of a data block.
				 */
				printk(KERN_WARNING
				       "proc_file_read: Read count exceeded\n");
			}
		} else /* start >= page */ {
			unsigned long startoff = (unsigned long)(start - page);
			if (n > (PAGE_SIZE - startoff)) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE - startoff;
			}
			if (n > count)
				n = count;
		}
		
 		n -= copy_to_user(buf, start < page ? page : start, n);
		if (n == 0) {
			if (retval == 0)
				retval = -EFAULT;
			break;
		}

		*ppos += start < page ? (unsigned long)start : n;
		nbytes -= n;
		buf += n;
		retval += n;
	}
	free_page((unsigned long) page);
	return retval;
}

static ssize_t
proc_file_write(struct file *file, const char __user *buffer,
		size_t count, loff_t *ppos)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct proc_dir_entry * dp;
	
	dp = PDE(inode);

	if (!dp->write_proc)
		return -EIO;

	/* FIXME: does this routine need ppos?  probably... */
	return dp->write_proc(file, buffer, count, dp->data);
}


static loff_t
proc_file_lseek(struct file *file, loff_t offset, int orig)
{
	loff_t retval = -EINVAL;
	switch (orig) {
	case 1:
		offset += file->f_pos;
	/* fallthrough */
	case 0:
		if (offset < 0 || offset > MAX_NON_LFS)
			break;
		file->f_pos = retval = offset;
	}
	return retval;
}

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)
		goto out;

	error = inode_setattr(inode, iattr);
	if (error)
		goto out;
	
	de->uid = inode->i_uid;
	de->gid = inode->i_gid;
	de->mode = inode->i_mode;
out:
	return error;
}

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)
		inode->i_nlink = 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;
	int			len;
	int 			rtn = 0;

	spin_lock(&proc_subdir_lock);
	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) {
			rtn = -ENOENT;
			goto out;
		}
		cp += len + 1;
	}
	*residual = cp;
	*ret = de;
out:
	spin_unlock(&proc_subdir_lock);
	return rtn;
}

static DEFINE_IDR(proc_inum_idr);
static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */

#define PROC_DYNAMIC_FIRST 0xF0000000UL

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

retry:
	if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
		return 0;

	spin_lock(&proc_inum_lock);
	error = idr_get_new(&proc_inum_idr, NULL, &i);
	spin_unlock(&proc_inum_lock);
	if (error == -EAGAIN)
		goto retry;
	else if (error)
		return 0;

	inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;

	/* inum will never be more than 0xf0ffffff, so no check
	 * for overflow.
	 */

	return inum;
}

static void release_inode_number(unsigned int inum)
{
	int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;

	spin_lock(&proc_inum_lock);
	idr_remove(&proc_inum_idr, id);
	spin_unlock(&proc_inum_lock);
}

static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	nd_set_link(nd, PDE(dentry->d_inode)->data);
	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(struct dentry * dentry)
{