linux-sg2042/fs/proc/generic.c

864 lines
20 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/mm.h>
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#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>
2007-07-16 14:39:00 +08:00
#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_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_t
proc_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_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)
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)
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;
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.
*/
[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>
2008-03-08 03:08:40 +08:00
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;
pde_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)
pde_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>
2008-03-08 03:08:40 +08:00
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>
2008-03-08 03:08:40 +08:00
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;
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;
}
[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>
2008-03-08 03:08:40 +08:00
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 = {
.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;
}
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 20:18:37 +08:00
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 15:45:28 +08:00
atomic_set(&ent->count, 1);
2007-07-16 14:39:00 +08:00
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 20:18:37 +08:00
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;
}
EXPORT_SYMBOL(proc_symlink);
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 20:18:37 +08:00
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);
}
EXPORT_SYMBOL(proc_mkdir);
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 20:18:37 +08:00
ent = __proc_create(&parent, name, mode, nlink);
if (ent) {
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
}
}
return ent;
}
EXPORT_SYMBOL(create_proc_entry);
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 16:02:00 +08:00
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 20:18:37 +08:00
{
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 16:02:00 +08:00
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 20:18:37 +08:00
if (proc_register(parent, pde) < 0)
goto out_free;
return pde;
out_free:
kfree(pde);
out:
return NULL;
}
EXPORT_SYMBOL(proc_create_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 20:18:37 +08:00
static 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);
}
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;
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;
}
2007-07-16 14:39:00 +08:00
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 14:39:00 +08:00
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 14:39:00 +08:00
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);
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);