1
0
Fork 0
remarkable-linux/fs/proc/root.c

231 lines
4.9 KiB
C
Raw Normal View History

/*
* linux/fs/proc/root.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* proc root directory handling functions
*/
#include <linux/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"
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>
2012-01-10 16:11:31 -07:00
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>
2012-01-10 16:11:31 -07:00
{Opt_hidepid, "hidepid=%u"},
{Opt_gid, "gid=%u"},
{Opt_err, NULL},
};
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>
2012-01-10 16:11:31 -07:00
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>
2012-01-10 16:11:31 -07:00
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>
2012-01-10 16:11:31 -07:00
break;
case Opt_hidepid:
if (match_int(&args[0], &option))
return 0;
if (option < HIDEPID_OFF ||
option > HIDEPID_INVISIBLE) {
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>
2012-01-10 16:11:31 -07:00
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 08:14:33 -06:00
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)
{
struct pid_namespace *ns;
if (flags & MS_KERNMOUNT) {
ns = data;
data = NULL;
} else {
ns = task_active_pid_ns(current);
}
return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
}
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>
2007-11-28 17:21:23 -07:00
static struct file_system_type proc_fs_type = {
.name = "proc",
.mount = proc_mount,
.kill_sb = proc_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
void __init proc_root_init(void)
{
int err;
proc_init_inodecache();
set_proc_pid_nlink();
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();
}
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 09:46:22 -07:00
static int proc_root_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 09:46:22 -07:00
generic_fillattr(d_inode(path->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_shared = proc_root_readdir,
.llseek = generic_file_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 00:45:28 -07:00
.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);
}