mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 18:00:53 +07:00
59b7435149
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 2d3a4e3666
:
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>
235 lines
5.0 KiB
C
235 lines
5.0 KiB
C
/*
|
|
* linux/fs/proc/root.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* proc root directory handling functions
|
|
*/
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/time.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/stat.h>
|
|
#include <linux/init.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/pid_namespace.h>
|
|
|
|
#include "internal.h"
|
|
|
|
static int proc_test_super(struct super_block *sb, void *data)
|
|
{
|
|
return sb->s_fs_info == data;
|
|
}
|
|
|
|
static int proc_set_super(struct super_block *sb, void *data)
|
|
{
|
|
struct pid_namespace *ns;
|
|
|
|
ns = (struct pid_namespace *)data;
|
|
sb->s_fs_info = get_pid_ns(ns);
|
|
return set_anon_super(sb, NULL);
|
|
}
|
|
|
|
static int proc_get_sb(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
|
|
{
|
|
int err;
|
|
struct super_block *sb;
|
|
struct pid_namespace *ns;
|
|
struct proc_inode *ei;
|
|
|
|
if (proc_mnt) {
|
|
/* Seed the root directory with a pid so it doesn't need
|
|
* to be special in base.c. I would do this earlier but
|
|
* the only task alive when /proc is mounted the first time
|
|
* is the init_task and it doesn't have any pids.
|
|
*/
|
|
ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
|
|
if (!ei->pid)
|
|
ei->pid = find_get_pid(1);
|
|
}
|
|
|
|
if (flags & MS_KERNMOUNT)
|
|
ns = (struct pid_namespace *)data;
|
|
else
|
|
ns = current->nsproxy->pid_ns;
|
|
|
|
sb = sget(fs_type, proc_test_super, proc_set_super, ns);
|
|
if (IS_ERR(sb))
|
|
return PTR_ERR(sb);
|
|
|
|
if (!sb->s_root) {
|
|
sb->s_flags = flags;
|
|
err = proc_fill_super(sb);
|
|
if (err) {
|
|
up_write(&sb->s_umount);
|
|
deactivate_super(sb);
|
|
return err;
|
|
}
|
|
|
|
ei = PROC_I(sb->s_root->d_inode);
|
|
if (!ei->pid) {
|
|
rcu_read_lock();
|
|
ei->pid = get_pid(find_pid_ns(1, ns));
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
sb->s_flags |= MS_ACTIVE;
|
|
ns->proc_mnt = mnt;
|
|
}
|
|
|
|
return simple_set_mnt(mnt, sb);
|
|
}
|
|
|
|
static void proc_kill_sb(struct super_block *sb)
|
|
{
|
|
struct pid_namespace *ns;
|
|
|
|
ns = (struct pid_namespace *)sb->s_fs_info;
|
|
kill_anon_super(sb);
|
|
put_pid_ns(ns);
|
|
}
|
|
|
|
static struct file_system_type proc_fs_type = {
|
|
.name = "proc",
|
|
.get_sb = proc_get_sb,
|
|
.kill_sb = proc_kill_sb,
|
|
};
|
|
|
|
void __init proc_root_init(void)
|
|
{
|
|
int err = proc_init_inodecache();
|
|
if (err)
|
|
return;
|
|
err = register_filesystem(&proc_fs_type);
|
|
if (err)
|
|
return;
|
|
proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
|
|
err = PTR_ERR(proc_mnt);
|
|
if (IS_ERR(proc_mnt)) {
|
|
unregister_filesystem(&proc_fs_type);
|
|
return;
|
|
}
|
|
|
|
proc_misc_init();
|
|
|
|
proc_net_init();
|
|
|
|
#ifdef CONFIG_SYSVIPC
|
|
proc_mkdir("sysvipc", NULL);
|
|
#endif
|
|
proc_mkdir("fs", NULL);
|
|
proc_mkdir("driver", NULL);
|
|
proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
|
|
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
|
|
/* just give it a mountpoint */
|
|
proc_mkdir("openprom", NULL);
|
|
#endif
|
|
proc_tty_init();
|
|
#ifdef CONFIG_PROC_DEVICETREE
|
|
proc_device_tree_init();
|
|
#endif
|
|
proc_mkdir("bus", NULL);
|
|
proc_sys_init();
|
|
}
|
|
|
|
static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
|
|
)
|
|
{
|
|
generic_fillattr(dentry->d_inode, stat);
|
|
stat->nlink = proc_root.nlink + nr_processes();
|
|
return 0;
|
|
}
|
|
|
|
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
|
|
{
|
|
if (!proc_lookup(dir, dentry, nd)) {
|
|
return NULL;
|
|
}
|
|
|
|
return proc_pid_lookup(dir, dentry, nd);
|
|
}
|
|
|
|
static int proc_root_readdir(struct file * filp,
|
|
void * dirent, filldir_t filldir)
|
|
{
|
|
unsigned int nr = filp->f_pos;
|
|
int ret;
|
|
|
|
lock_kernel();
|
|
|
|
if (nr < FIRST_PROCESS_ENTRY) {
|
|
int error = proc_readdir(filp, dirent, filldir);
|
|
if (error <= 0) {
|
|
unlock_kernel();
|
|
return error;
|
|
}
|
|
filp->f_pos = FIRST_PROCESS_ENTRY;
|
|
}
|
|
unlock_kernel();
|
|
|
|
ret = proc_pid_readdir(filp, dirent, filldir);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* The root /proc directory is special, as it has the
|
|
* <pid> directories. Thus we don't use the generic
|
|
* directory handling functions for that..
|
|
*/
|
|
static const struct file_operations proc_root_operations = {
|
|
.read = generic_read_dir,
|
|
.readdir = proc_root_readdir,
|
|
};
|
|
|
|
/*
|
|
* proc root can do almost nothing..
|
|
*/
|
|
static const struct inode_operations proc_root_inode_operations = {
|
|
.lookup = proc_root_lookup,
|
|
.getattr = proc_root_getattr,
|
|
};
|
|
|
|
/*
|
|
* This is the root "inode" in the /proc tree..
|
|
*/
|
|
struct proc_dir_entry proc_root = {
|
|
.low_ino = PROC_ROOT_INO,
|
|
.namelen = 5,
|
|
.name = "/proc",
|
|
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
|
|
.nlink = 2,
|
|
.count = ATOMIC_INIT(1),
|
|
.proc_iops = &proc_root_inode_operations,
|
|
.proc_fops = &proc_root_operations,
|
|
.parent = &proc_root,
|
|
};
|
|
|
|
int pid_ns_prepare_proc(struct pid_namespace *ns)
|
|
{
|
|
struct vfsmount *mnt;
|
|
|
|
mnt = kern_mount_data(&proc_fs_type, ns);
|
|
if (IS_ERR(mnt))
|
|
return PTR_ERR(mnt);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void pid_ns_release_proc(struct pid_namespace *ns)
|
|
{
|
|
mntput(ns->proc_mnt);
|
|
}
|
|
|
|
EXPORT_SYMBOL(proc_symlink);
|
|
EXPORT_SYMBOL(proc_mkdir);
|
|
EXPORT_SYMBOL(create_proc_entry);
|
|
EXPORT_SYMBOL(proc_create_data);
|
|
EXPORT_SYMBOL(remove_proc_entry);
|