/* * 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/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);} /* 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->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 Paul.Russell@rustcorp.com.au)			 * 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_tproc_file_read(struct file *file, char __user *buf, size_t nbytes,	       loff_t *ppos){	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);	ssize_t rv = -EIO; 	spin_lock(&pde->pde_unload_lock);	if (!pde->proc_fops) {		spin_unlock(&pde->pde_unload_lock);		return rv;	}	pde->pde_users++;	spin_unlock(&pde->pde_unload_lock); 	rv = __proc_file_read(file, buf, nbytes, ppos); 	pde_users_dec(pde);	return rv;} static ssize_tproc_file_write(struct file *file, const char __user *buffer,		size_t count, loff_t *ppos){	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);	ssize_t rv = -EIO; 	if (pde->write_proc) {		spin_lock(&pde->pde_unload_lock);		if (!pde->proc_fops) {			spin_unlock(&pde->pde_unload_lock);			return rv;		}		pde->pde_users++;		spin_unlock(&pde->pde_unload_lock); 		/* FIXME: does this routine need ppos?  probably... */		rv = pde->write_proc(file, buffer, count, pde->data);		pde_users_dec(pde);	}	return rv;}  static loff_tproc_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 const struct file_operations proc_file_operations = {	.llseek		= proc_file_lseek,	.read		= proc_file_read,	.write		= proc_file_write,}; 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; 	if ((iattr->ia_valid & ATTR_SIZE) &&	    iattr->ia_size != i_size_read(inode)) {		error = vmtruncate(inode, iattr->ia_size);		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. */static unsigned int get_inode_number(void){	unsigned int i;	int error; retry:	if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)		return 0; 	spin_lock(&proc_inum_lock);	error = ida_get_new(&proc_inum_ida, &i);	spin_unlock(&proc_inum_lock);	if (error == -EAGAIN)		goto retry;	else if (error)		return 0; 	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {		spin_lock(&proc_inum_lock);		ida_remove(&proc_inum_ida, i);		spin_unlock(&proc_inum_lock);		return 0;	}	return PROC_DYNAMIC_FIRST + i;} static void release_inode_number(unsigned int inum){	spin_lock(&proc_inum_lock);	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);	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(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 = NULL;	int error = -ENOENT; 	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);			error = -EINVAL;			inode = proc_get_inode(dir->i_sb, de);			goto out_unlock;		}	}	spin_unlock(&proc_subdir_lock);out_unlock: 	if (inode) {		d_set_d_op(dentry, &proc_dentry_operations);		d_add(dentry, inode);		return NULL;	}	if (de)		pde_put(de);	return ERR_PTR(error);} struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,		struct nameidata *nd){	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 = filp->f_path.dentry->d_inode;	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;

Lines 1–500 of 852. Load more