linux/fs/proc/generic.c

812 lines
18 KiB
C
Raw Normal View History

/*
* 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>
2007-07-16 06:39:00 +00:00
#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.
*/
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-07 19:08:40 +00:00
struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = NULL;
int error = -ENOENT;
lock_kernel();
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:
unlock_kernel();
if (inode) {
dentry->d_op = &proc_dentry_operations;
d_add(dentry, inode);
return NULL;
}
if (de)
de_put(de);
return ERR_PTR(error);
}
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-07 19:08:40 +00:00
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..
*/
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-07 19:08:40 +00:00
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;
lock_kernel();
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: unlock_kernel();
return ret;
}
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-07 19:08:40 +00:00
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 = {
.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;
}
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
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;
proc: fix proc_dir_entry refcounting Creating PDEs with refcount 0 and "deleted" flag has problems (see below). Switch to usual scheme: * PDE is created with refcount 1 * every de_get does +1 * every de_put() and remove_proc_entry() do -1 * once refcount reaches 0, PDE is freed. This elegantly fixes at least two following races (both observed) without introducing new locks, without abusing old locks, without spreading lock_kernel(): 1) PDE leak remove_proc_entry de_put ----------------- ------ [refcnt = 1] if (atomic_read(&de->count) == 0) if (atomic_dec_and_test(&de->count)) if (de->deleted) /* also not taken! */ free_proc_entry(de); else de->deleted = 1; [refcount=0, deleted=1] 2) use after free remove_proc_entry de_put ----------------- ------ [refcnt = 1] if (atomic_dec_and_test(&de->count)) if (atomic_read(&de->count) == 0) free_proc_entry(de); /* boom! */ if (de->deleted) free_proc_entry(de); BUG: unable to handle kernel paging request at virtual address 6b6b6b6b printing eip: c10acdda *pdpt = 00000000338f8001 *pde = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 23161, comm: cat Not tainted (2.6.24-rc2-8c0863403f109a43d7000b4646da4818220d501f #4) EIP: 0060:[<c10acdda>] EFLAGS: 00210097 CPU: 1 EIP is at strnlen+0x6/0x18 EAX: 6b6b6b6b EBX: 6b6b6b6b ECX: 6b6b6b6b EDX: fffffffe ESI: c128fa3b EDI: f380bf34 EBP: ffffffff ESP: f380be44 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 23161, ti=f380b000 task=f38f2570 task.ti=f380b000) Stack: c10ac4f0 00000278 c12ce000 f43cd2a8 00000163 00000000 7da86067 00000400 c128fa20 00896b18 f38325a8 c128fe20 ffffffff 00000000 c11f291e 00000400 f75be300 c128fa20 f769c9a0 c10ac779 f380bf34 f7bfee70 c1018e6b f380bf34 Call Trace: [<c10ac4f0>] vsnprintf+0x2ad/0x49b [<c10ac779>] vscnprintf+0x14/0x1f [<c1018e6b>] vprintk+0xc5/0x2f9 [<c10379f1>] handle_fasteoi_irq+0x0/0xab [<c1004f44>] do_IRQ+0x9f/0xb7 [<c117db3b>] preempt_schedule_irq+0x3f/0x5b [<c100264e>] need_resched+0x1f/0x21 [<c10190ba>] printk+0x1b/0x1f [<c107c8ad>] de_put+0x3d/0x50 [<c107c8f8>] proc_delete_inode+0x38/0x41 [<c107c8c0>] proc_delete_inode+0x0/0x41 [<c1066298>] generic_delete_inode+0x5e/0xc6 [<c1065aa9>] iput+0x60/0x62 [<c1063c8e>] d_kill+0x2d/0x46 [<c1063fa9>] dput+0xdc/0xe4 [<c10571a1>] __fput+0xb0/0xcd [<c1054e49>] filp_close+0x48/0x4f [<c1055ee9>] sys_close+0x67/0xa5 [<c10026b6>] sysenter_past_esp+0x5f/0x85 ======================= Code: c9 74 0c f2 ae 74 05 bf 01 00 00 00 4f 89 fa 5f 89 d0 c3 85 c9 57 89 c7 89 d0 74 05 f2 ae 75 01 4f 89 f8 5f c3 89 c1 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 c3 90 90 90 57 83 c9 EIP: [<c10acdda>] strnlen+0x6/0x18 SS:ESP 0068:f380be44 Also, remove broken usage of ->deleted from reiserfs: if sget() succeeds, module is already pinned and remove_proc_entry() can't happen => nobody can mark PDE deleted. Dummy proc root in netns code is not marked with refcount 1. AFAICS, we never get it, it's just for proper /proc/net removal. I double checked CLONE_NETNS continues to work. Patch survives many hours of modprobe/rmmod/cat loops without new bugs which can be attributed to refcounting. Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-12-05 07:45:28 +00:00
atomic_set(&ent->count, 1);
2007-07-16 06:39:00 +00:00
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;
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
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;
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
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;
}
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
ent = __proc_create(&parent, name, mode, nlink);
if (ent) {
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
}
}
return ent;
}
proc: introduce proc_create_data to setup de->data This set of patches fixes an proc ->open'less usage due to ->proc_fops flip in the most part of the kernel code. The original OOPS is described in the commit 2d3a4e3666325a9709cc8ea2e88151394e8f20fc: Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. In addition to this, proc_create_data is introduced to fix reading from proc without PDE->data. The race is basically the same as above. create_proc_entries is replaced in the entire kernel code as new method is also simply better. This patch: The problem is the same as for de->proc_fops. Right now PDE becomes visible without data set. So, the entry could be looked up without data. This, in most cases, will simply OOPS. proc_create_data call is created to address this issue. proc_create now becomes a wrapper around it. Signed-off-by: Denis V. Lunev <den@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Alessandro Zummo <a.zummo@towertech.it> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bjorn Helgaas <bjorn.helgaas@hp.com> Cc: Chris Mason <chris.mason@oracle.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Dmitry Torokhov <dtor@mail.ru> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: Greg Kroah-Hartman <gregkh@suse.de> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Jaroslav Kysela <perex@suse.cz> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Karsten Keil <kkeil@suse.de> Cc: Kyle McMartin <kyle@parisc-linux.org> Cc: Len Brown <lenb@kernel.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Nadia Derbey <Nadia.Derbey@bull.net> Cc: Neil Brown <neilb@suse.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Osterlund <petero2@telia.com> Cc: Pierre Peiffer <peifferp@gmail.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Takashi Iwai <tiwai@suse.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:02:00 +00:00
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)
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
{
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;
proc: introduce proc_create_data to setup de->data This set of patches fixes an proc ->open'less usage due to ->proc_fops flip in the most part of the kernel code. The original OOPS is described in the commit 2d3a4e3666325a9709cc8ea2e88151394e8f20fc: Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. In addition to this, proc_create_data is introduced to fix reading from proc without PDE->data. The race is basically the same as above. create_proc_entries is replaced in the entire kernel code as new method is also simply better. This patch: The problem is the same as for de->proc_fops. Right now PDE becomes visible without data set. So, the entry could be looked up without data. This, in most cases, will simply OOPS. proc_create_data call is created to address this issue. proc_create now becomes a wrapper around it. Signed-off-by: Denis V. Lunev <den@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Alessandro Zummo <a.zummo@towertech.it> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bjorn Helgaas <bjorn.helgaas@hp.com> Cc: Chris Mason <chris.mason@oracle.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Dmitry Torokhov <dtor@mail.ru> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: Greg Kroah-Hartman <gregkh@suse.de> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Jaroslav Kysela <perex@suse.cz> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Karsten Keil <kkeil@suse.de> Cc: Kyle McMartin <kyle@parisc-linux.org> Cc: Len Brown <lenb@kernel.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Nadia Derbey <Nadia.Derbey@bull.net> Cc: Neil Brown <neilb@suse.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Osterlund <petero2@telia.com> Cc: Pierre Peiffer <peifferp@gmail.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Takashi Iwai <tiwai@suse.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:02:00 +00:00
pde->data = data;
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:37 +00:00
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;
2007-07-16 06:39:00 +00:00
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;
2007-07-16 06:39:00 +00:00
spin_unlock(&de->pde_unload_lock);
wait_for_completion(de->pde_unload_completion);
goto continue_removing;
}
spin_unlock(&de->pde_unload_lock);
2007-07-16 06:39:00 +00:00
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);
}