linux-sg2042/fs/proc/generic.c

808 lines
18 KiB
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/module.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(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_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 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)
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;
de = *ret;
if (!de)
de = &proc_root;
spin_lock(&proc_subdir_lock);
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_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(struct dentry * dentry)
{
return 1;
}
static 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)) {
unsigned int ino;
ino = de->low_ino;
de_get(de);
spin_unlock(&proc_subdir_lock);
error = -EINVAL;
inode = proc_get_inode(dir->i_sb, ino, de);
goto out_unlock;
}
}
spin_unlock(&proc_subdir_lock);
out_unlock:
if (inode) {
dentry->d_op = &proc_dentry_operations;
d_add(dentry, inode);
return NULL;
}
if (de)
de_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;
i--;
}
do {
struct proc_dir_entry *next;
/* filldir passes info to user space */
de_get(de);
spin_unlock(&proc_subdir_lock);
if (filldir(dirent, de->name, de->namelen, filp->f_pos,
de->low_ino, de->mode >> 12) < 0) {
de_put(de);
goto out;
}
spin_lock(&proc_subdir_lock);
filp->f_pos++;
next = de->next;
de_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 = filp->f_path.dentry->d_inode;
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)
{
unsigned int i;
struct proc_dir_entry *tmp;
i = get_inode_number();
if (i == 0)
return -EAGAIN;
dp->low_ino = i;
if (S_ISDIR(dp->mode)) {
if (dp->proc_iops == NULL) {
dp->proc_fops = &proc_dir_operations;
dp->proc_iops = &proc_dir_inode_operations;
}
dir->nlink++;
} else if (S_ISLNK(dp->mode)) {
if (dp->proc_iops == NULL)
dp->proc_iops = &proc_link_inode_operations;
} else if (S_ISREG(dp->mode)) {
if (dp->proc_fops == NULL)
dp->proc_fops = &proc_file_operations;
if (dp->proc_iops == NULL)
dp->proc_iops = &proc_file_inode_operations;
}
spin_lock(&proc_subdir_lock);
for (tmp = dir->subdir; tmp; tmp = tmp->next)
if (strcmp(tmp->name, dp->name) == 0) {
WARN(1, KERN_WARNING "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,
mode_t mode,
nlink_t nlink)
{
struct proc_dir_entry *ent = NULL;
const char *fn = name;
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 = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
if (!ent) goto out;
memset(ent, 0, sizeof(struct proc_dir_entry));
memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1);
ent->name = ((char *) ent) + sizeof(*ent);
ent->namelen = len;
ent->mode = mode;
ent->nlink = nlink;
atomic_set(&ent->count, 1);
ent->pde_users = 0;
spin_lock_init(&ent->pde_unload_lock);
ent->pde_unload_completion = NULL;
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;
}
struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_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;
}
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);
}
struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
struct proc_dir_entry *parent)
{
struct proc_dir_entry *ent;
nlink_t nlink;
if (S_ISDIR(mode)) {
if ((mode & S_IALLUGO) == 0)
mode |= S_IRUGO | S_IXUGO;
nlink = 2;
} else {
if ((mode & S_IFMT) == 0)
mode |= S_IFREG;
if ((mode & S_IALLUGO) == 0)
mode |= S_IRUGO;
nlink = 1;
}
ent = __proc_create(&parent, name, mode, nlink);
if (ent) {
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
}
}
return ent;
}
struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
struct proc_dir_entry *parent,
const struct file_operations *proc_fops,
void *data)
{
struct proc_dir_entry *pde;
nlink_t nlink;
if (S_ISDIR(mode)) {
if ((mode & S_IALLUGO) == 0)
mode |= S_IRUGO | S_IXUGO;
nlink = 2;
} else {
if ((mode & S_IFMT) == 0)
mode |= S_IFREG;
if ((mode & S_IALLUGO) == 0)
mode |= S_IRUGO;
nlink = 1;
}
pde = __proc_create(&parent, name, mode, nlink);
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;
}
void free_proc_entry(struct proc_dir_entry *de)
{
unsigned int ino = de->low_ino;
if (ino < PROC_DYNAMIC_FIRST)
return;
release_inode_number(ino);
if (S_ISLNK(de->mode))
kfree(de->data);
kfree(de);
}
/*
* 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;
int len;
if (xlate_proc_name(name, &parent, &fn) != 0)
return;
len = strlen(fn);
spin_lock(&proc_subdir_lock);
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)
return;
spin_lock(&de->pde_unload_lock);
/*
* Stop accepting new callers into module. If you're
* dynamically allocating ->proc_fops, save a pointer somewhere.
*/
de->proc_fops = NULL;
/* Wait until all existing callers into module are done. */
if (de->pde_users > 0) {
DECLARE_COMPLETION_ONSTACK(c);
if (!de->pde_unload_completion)
de->pde_unload_completion = &c;
spin_unlock(&de->pde_unload_lock);
wait_for_completion(de->pde_unload_completion);
goto continue_removing;
}
spin_unlock(&de->pde_unload_lock);
continue_removing:
spin_lock(&de->pde_unload_lock);
while (!list_empty(&de->pde_openers)) {
struct pde_opener *pdeo;
pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
list_del(&pdeo->lh);
spin_unlock(&de->pde_unload_lock);
pdeo->release(pdeo->inode, pdeo->file);
kfree(pdeo);
spin_lock(&de->pde_unload_lock);
}
spin_unlock(&de->pde_unload_lock);
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
"'%s/%s', leaking at least '%s'\n", __func__,
de->parent->name, de->name, de->subdir->name);
if (atomic_dec_and_test(&de->count))
free_proc_entry(de);
}