linux/fs/proc/root.c

273 lines
5.7 KiB
C
Raw Normal View History

/*
* 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/user_namespace.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/parser.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)
{
int err = set_anon_super(sb, NULL);
if (!err) {
struct pid_namespace *ns = (struct pid_namespace *)data;
sb->s_fs_info = get_pid_ns(ns);
}
return err;
}
enum {
procfs: add hidepid= and gid= mount options Add support for mount options to restrict access to /proc/PID/ directories. The default backward-compatible "relaxed" behaviour is left untouched. The first mount option is called "hidepid" and its value defines how much info about processes we want to be available for non-owners: hidepid=0 (default) means the old behavior - anybody may read all world-readable /proc/PID/* files. hidepid=1 means users may not access any /proc/<pid>/ directories, but their own. Sensitive files like cmdline, sched*, status are now protected against other users. As permission checking done in proc_pid_permission() and files' permissions are left untouched, programs expecting specific files' modes are not confused. hidepid=2 means hidepid=1 plus all /proc/PID/ will be invisible to other users. It doesn't mean that it hides whether a process exists (it can be learned by other means, e.g. by kill -0 $PID), but it hides process' euid and egid. It compicates intruder's task of gathering info about running processes, whether some daemon runs with elevated privileges, whether another user runs some sensitive program, whether other users run any program at all, etc. gid=XXX defines a group that will be able to gather all processes' info (as in hidepid=0 mode). This group should be used instead of putting nonroot user in sudoers file or something. However, untrusted users (like daemons, etc.) which are not supposed to monitor the tasks in the whole system should not be added to the group. hidepid=1 or higher is designed to restrict access to procfs files, which might reveal some sensitive private information like precise keystrokes timings: http://www.openwall.com/lists/oss-security/2011/11/05/3 hidepid=1/2 doesn't break monitoring userspace tools. ps, top, pgrep, and conky gracefully handle EPERM/ENOENT and behave as if the current user is the only user running processes. pstree shows the process subtree which contains "pstree" process. Note: the patch doesn't deal with setuid/setgid issues of keeping preopened descriptors of procfs files (like https://lkml.org/lkml/2011/2/7/368). We rely on that the leaked information like the scheduling counters of setuid apps doesn't threaten anybody's privacy - only the user started the setuid program may read the counters. Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg KH <greg@kroah.com> Cc: Theodore Tso <tytso@MIT.EDU> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: James Morris <jmorris@namei.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:11:31 +08:00
Opt_gid, Opt_hidepid, Opt_err,
};
static const match_table_t tokens = {
procfs: add hidepid= and gid= mount options Add support for mount options to restrict access to /proc/PID/ directories. The default backward-compatible "relaxed" behaviour is left untouched. The first mount option is called "hidepid" and its value defines how much info about processes we want to be available for non-owners: hidepid=0 (default) means the old behavior - anybody may read all world-readable /proc/PID/* files. hidepid=1 means users may not access any /proc/<pid>/ directories, but their own. Sensitive files like cmdline, sched*, status are now protected against other users. As permission checking done in proc_pid_permission() and files' permissions are left untouched, programs expecting specific files' modes are not confused. hidepid=2 means hidepid=1 plus all /proc/PID/ will be invisible to other users. It doesn't mean that it hides whether a process exists (it can be learned by other means, e.g. by kill -0 $PID), but it hides process' euid and egid. It compicates intruder's task of gathering info about running processes, whether some daemon runs with elevated privileges, whether another user runs some sensitive program, whether other users run any program at all, etc. gid=XXX defines a group that will be able to gather all processes' info (as in hidepid=0 mode). This group should be used instead of putting nonroot user in sudoers file or something. However, untrusted users (like daemons, etc.) which are not supposed to monitor the tasks in the whole system should not be added to the group. hidepid=1 or higher is designed to restrict access to procfs files, which might reveal some sensitive private information like precise keystrokes timings: http://www.openwall.com/lists/oss-security/2011/11/05/3 hidepid=1/2 doesn't break monitoring userspace tools. ps, top, pgrep, and conky gracefully handle EPERM/ENOENT and behave as if the current user is the only user running processes. pstree shows the process subtree which contains "pstree" process. Note: the patch doesn't deal with setuid/setgid issues of keeping preopened descriptors of procfs files (like https://lkml.org/lkml/2011/2/7/368). We rely on that the leaked information like the scheduling counters of setuid apps doesn't threaten anybody's privacy - only the user started the setuid program may read the counters. Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg KH <greg@kroah.com> Cc: Theodore Tso <tytso@MIT.EDU> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: James Morris <jmorris@namei.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:11:31 +08:00
{Opt_hidepid, "hidepid=%u"},
{Opt_gid, "gid=%u"},
{Opt_err, NULL},
};
static int proc_parse_options(char *options, struct pid_namespace *pid)
{
char *p;
substring_t args[MAX_OPT_ARGS];
procfs: add hidepid= and gid= mount options Add support for mount options to restrict access to /proc/PID/ directories. The default backward-compatible "relaxed" behaviour is left untouched. The first mount option is called "hidepid" and its value defines how much info about processes we want to be available for non-owners: hidepid=0 (default) means the old behavior - anybody may read all world-readable /proc/PID/* files. hidepid=1 means users may not access any /proc/<pid>/ directories, but their own. Sensitive files like cmdline, sched*, status are now protected against other users. As permission checking done in proc_pid_permission() and files' permissions are left untouched, programs expecting specific files' modes are not confused. hidepid=2 means hidepid=1 plus all /proc/PID/ will be invisible to other users. It doesn't mean that it hides whether a process exists (it can be learned by other means, e.g. by kill -0 $PID), but it hides process' euid and egid. It compicates intruder's task of gathering info about running processes, whether some daemon runs with elevated privileges, whether another user runs some sensitive program, whether other users run any program at all, etc. gid=XXX defines a group that will be able to gather all processes' info (as in hidepid=0 mode). This group should be used instead of putting nonroot user in sudoers file or something. However, untrusted users (like daemons, etc.) which are not supposed to monitor the tasks in the whole system should not be added to the group. hidepid=1 or higher is designed to restrict access to procfs files, which might reveal some sensitive private information like precise keystrokes timings: http://www.openwall.com/lists/oss-security/2011/11/05/3 hidepid=1/2 doesn't break monitoring userspace tools. ps, top, pgrep, and conky gracefully handle EPERM/ENOENT and behave as if the current user is the only user running processes. pstree shows the process subtree which contains "pstree" process. Note: the patch doesn't deal with setuid/setgid issues of keeping preopened descriptors of procfs files (like https://lkml.org/lkml/2011/2/7/368). We rely on that the leaked information like the scheduling counters of setuid apps doesn't threaten anybody's privacy - only the user started the setuid program may read the counters. Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg KH <greg@kroah.com> Cc: Theodore Tso <tytso@MIT.EDU> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: James Morris <jmorris@namei.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:11:31 +08:00
int option;
if (!options)
return 1;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
switch (token) {
procfs: add hidepid= and gid= mount options Add support for mount options to restrict access to /proc/PID/ directories. The default backward-compatible "relaxed" behaviour is left untouched. The first mount option is called "hidepid" and its value defines how much info about processes we want to be available for non-owners: hidepid=0 (default) means the old behavior - anybody may read all world-readable /proc/PID/* files. hidepid=1 means users may not access any /proc/<pid>/ directories, but their own. Sensitive files like cmdline, sched*, status are now protected against other users. As permission checking done in proc_pid_permission() and files' permissions are left untouched, programs expecting specific files' modes are not confused. hidepid=2 means hidepid=1 plus all /proc/PID/ will be invisible to other users. It doesn't mean that it hides whether a process exists (it can be learned by other means, e.g. by kill -0 $PID), but it hides process' euid and egid. It compicates intruder's task of gathering info about running processes, whether some daemon runs with elevated privileges, whether another user runs some sensitive program, whether other users run any program at all, etc. gid=XXX defines a group that will be able to gather all processes' info (as in hidepid=0 mode). This group should be used instead of putting nonroot user in sudoers file or something. However, untrusted users (like daemons, etc.) which are not supposed to monitor the tasks in the whole system should not be added to the group. hidepid=1 or higher is designed to restrict access to procfs files, which might reveal some sensitive private information like precise keystrokes timings: http://www.openwall.com/lists/oss-security/2011/11/05/3 hidepid=1/2 doesn't break monitoring userspace tools. ps, top, pgrep, and conky gracefully handle EPERM/ENOENT and behave as if the current user is the only user running processes. pstree shows the process subtree which contains "pstree" process. Note: the patch doesn't deal with setuid/setgid issues of keeping preopened descriptors of procfs files (like https://lkml.org/lkml/2011/2/7/368). We rely on that the leaked information like the scheduling counters of setuid apps doesn't threaten anybody's privacy - only the user started the setuid program may read the counters. Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg KH <greg@kroah.com> Cc: Theodore Tso <tytso@MIT.EDU> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: James Morris <jmorris@namei.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:11:31 +08:00
case Opt_gid:
if (match_int(&args[0], &option))
return 0;
pid->pid_gid = make_kgid(current_user_ns(), option);
procfs: add hidepid= and gid= mount options Add support for mount options to restrict access to /proc/PID/ directories. The default backward-compatible "relaxed" behaviour is left untouched. The first mount option is called "hidepid" and its value defines how much info about processes we want to be available for non-owners: hidepid=0 (default) means the old behavior - anybody may read all world-readable /proc/PID/* files. hidepid=1 means users may not access any /proc/<pid>/ directories, but their own. Sensitive files like cmdline, sched*, status are now protected against other users. As permission checking done in proc_pid_permission() and files' permissions are left untouched, programs expecting specific files' modes are not confused. hidepid=2 means hidepid=1 plus all /proc/PID/ will be invisible to other users. It doesn't mean that it hides whether a process exists (it can be learned by other means, e.g. by kill -0 $PID), but it hides process' euid and egid. It compicates intruder's task of gathering info about running processes, whether some daemon runs with elevated privileges, whether another user runs some sensitive program, whether other users run any program at all, etc. gid=XXX defines a group that will be able to gather all processes' info (as in hidepid=0 mode). This group should be used instead of putting nonroot user in sudoers file or something. However, untrusted users (like daemons, etc.) which are not supposed to monitor the tasks in the whole system should not be added to the group. hidepid=1 or higher is designed to restrict access to procfs files, which might reveal some sensitive private information like precise keystrokes timings: http://www.openwall.com/lists/oss-security/2011/11/05/3 hidepid=1/2 doesn't break monitoring userspace tools. ps, top, pgrep, and conky gracefully handle EPERM/ENOENT and behave as if the current user is the only user running processes. pstree shows the process subtree which contains "pstree" process. Note: the patch doesn't deal with setuid/setgid issues of keeping preopened descriptors of procfs files (like https://lkml.org/lkml/2011/2/7/368). We rely on that the leaked information like the scheduling counters of setuid apps doesn't threaten anybody's privacy - only the user started the setuid program may read the counters. Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg KH <greg@kroah.com> Cc: Theodore Tso <tytso@MIT.EDU> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: James Morris <jmorris@namei.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:11:31 +08:00
break;
case Opt_hidepid:
if (match_int(&args[0], &option))
return 0;
if (option < 0 || option > 2) {
pr_err("proc: hidepid value must be between 0 and 2.\n");
return 0;
}
pid->hide_pid = option;
break;
default:
pr_err("proc: unrecognized mount option \"%s\" "
"or missing value\n", p);
return 0;
}
}
return 1;
}
int proc_remount(struct super_block *sb, int *flags, char *data)
{
struct pid_namespace *pid = sb->s_fs_info;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
return !proc_parse_options(data, pid);
}
static struct dentry *proc_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
int err;
struct super_block *sb;
struct pid_namespace *ns;
char *options;
if (flags & MS_KERNMOUNT) {
ns = (struct pid_namespace *)data;
options = NULL;
} else {
ns = task_active_pid_ns(current);
options = data;
/* Does the mounter have privilege over the pid namespace? */
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
}
sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!proc_parse_options(options, ns)) {
deactivate_locked_super(sb);
return ERR_PTR(-EINVAL);
}
if (!sb->s_root) {
err = proc_fill_super(sb);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
vfs: Commit to never having exectuables on proc and sysfs. Today proc and sysfs do not contain any executable files. Several applications today mount proc or sysfs without noexec and nosuid and then depend on there being no exectuables files on proc or sysfs. Having any executable files show on proc or sysfs would cause a user space visible regression, and most likely security problems. Therefore commit to never allowing executables on proc and sysfs by adding a new flag to mark them as filesystems without executables and enforce that flag. Test the flag where MNT_NOEXEC is tested today, so that the only user visible effect will be that exectuables will be treated as if the execute bit is cleared. The filesystems proc and sysfs do not currently incoporate any executable files so this does not result in any user visible effects. This makes it unnecessary to vet changes to proc and sysfs tightly for adding exectuable files or changes to chattr that would modify existing files, as no matter what the individual file say they will not be treated as exectuable files by the vfs. Not having to vet changes to closely is important as without this we are only one proc_create call (or another goof up in the implementation of notify_change) from having problematic executables on proc. Those mistakes are all too easy to make and would create a situation where there are security issues or the assumptions of some program having to be broken (and cause userspace regressions). Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2015-06-30 03:42:03 +08:00
/* User space would break if executables appear on proc */
sb->s_iflags |= SB_I_NOEXEC;
}
return dget(sb->s_root);
}
static void proc_kill_sb(struct super_block *sb)
{
struct pid_namespace *ns;
ns = (struct pid_namespace *)sb->s_fs_info;
if (ns->proc_self)
dput(ns->proc_self);
if (ns->proc_thread_self)
dput(ns->proc_thread_self);
kill_anon_super(sb);
put_pid_ns(ns);
}
proc: fix NULL ->i_fop oops proc_kill_inodes() can clear ->i_fop in the middle of vfs_readdir resulting in NULL dereference during "file->f_op->readdir(file, buf, filler)". The solution is to remove proc_kill_inodes() completely: a) we don't have tricky modules implementing their tricky readdir hooks which could keeping this revoke from hell. b) In a situation when module is gone but PDE still alive, standard readdir will return only "." and "..", because pde->next was cleared by remove_proc_entry(). c) the race proc_kill_inode() destined to prevent is not completely fixed, just race window made smaller, because vfs_readdir() is run without sb_lock held and without file_list_lock held. Effectively, ->i_fop is cleared at random moment, which can't fix properly anything. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000018 printing eip: c1061205 *pdpt = 0000000005b22001 *pde = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw sr_mod k8temp cdrom hwmon amd_rng Pid: 2033, comm: find Not tainted (2.6.24-rc1-b1d08ac064268d0ae2281e98bf5e82627e0f0c56 #2) EIP: 0060:[<c1061205>] EFLAGS: 00010246 CPU: 0 EIP is at vfs_readdir+0x47/0x74 EAX: c6b6a780 EBX: 00000000 ECX: c1061040 EDX: c5decf94 ESI: c6b6a780 EDI: fffffffe EBP: c9797c54 ESP: c5decf78 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process find (pid: 2033, ti=c5dec000 task=c64bba90 task.ti=c5dec000) Stack: c5decf94 c1061040 fffffff7 0805ffbc 00000000 c6b6a780 c1061295 0805ffbc 00000000 00000400 00000000 00000004 0805ffbc 4588eff4 c5dec000 c10026ba 00000004 0805ffbc 00000400 0805ffbc 4588eff4 bfdc6c70 000000dc 0000007b Call Trace: [<c1061040>] filldir64+0x0/0xc5 [<c1061295>] sys_getdents64+0x63/0xa5 [<c10026ba>] sysenter_past_esp+0x5f/0x85 ======================= Code: 49 83 78 18 00 74 43 8d 6b 74 bf fe ff ff ff 89 e8 e8 b8 c0 12 00 f6 83 2c 01 00 00 10 75 22 8b 5e 10 8b 4c 24 04 89 f0 8b 14 24 <ff> 53 18 f6 46 1a 04 89 c7 75 0b 8b 56 0c 8b 46 08 e8 c8 66 00 EIP: [<c1061205>] vfs_readdir+0x47/0x74 SS:ESP 0068:c5decf78 hch: "Nice, getting rid of this is a very good step formwards. Unfortunately we have another copy of this junk in security/selinux/selinuxfs.c:sel_remove_entries() which would need the same treatment." Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Acked-by: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> 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>
2007-11-29 08:21:23 +08:00
static struct file_system_type proc_fs_type = {
.name = "proc",
.mount = proc_mount,
.kill_sb = proc_kill_sb,
.fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
};
void __init proc_root_init(void)
{
int err;
proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
proc_self_init();
proc_thread_self_init();
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
#ifdef CONFIG_SYSVIPC
proc_mkdir("sysvipc", NULL);
#endif
proc_mkdir("fs", NULL);
proc_mkdir("driver", NULL);
proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
/* just give it a mountpoint */
proc_create_mount_point("openprom");
#endif
proc_tty_init();
proc_mkdir("bus", NULL);
proc_sys_init();
}
static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
)
{
generic_fillattr(d_inode(dentry), stat);
stat->nlink = proc_root.nlink + nr_processes();
return 0;
}
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
if (!proc_pid_lookup(dir, dentry, flags))
return NULL;
return proc_lookup(dir, dentry, flags);
}
static int proc_root_readdir(struct file *file, struct dir_context *ctx)
{
if (ctx->pos < FIRST_PROCESS_ENTRY) {
int error = proc_readdir(file, ctx);
if (unlikely(error <= 0))
return error;
ctx->pos = FIRST_PROCESS_ENTRY;
}
return proc_pid_readdir(file, ctx);
}
/*
* 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,
.iterate = proc_root_readdir,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.llseek = default_llseek,
};
/*
* 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,
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
.nlink = 2,
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
.count = ATOMIC_INIT(1),
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
.subdir = RB_ROOT,
.name = "/proc",
};
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);
ns->proc_mnt = mnt;
return 0;
}
void pid_ns_release_proc(struct pid_namespace *ns)
{
kern_unmount(ns->proc_mnt);
}