linux_dsm_epyc7002/fs/proc/namespaces.c
Kirill Tkhai eaa0d190bf pidns: expose task pid_ns_for_children to userspace
pid_ns_for_children set by a task is known only to the task itself, and
it's impossible to identify it from outside.

It's a big problem for checkpoint/restore software like CRIU, because it
can't correctly handle tasks, that do setns(CLONE_NEWPID) in proccess of
their work.

This patch solves the problem, and it exposes pid_ns_for_children to ns
directory in standard way with the name "pid_for_children":

  ~# ls /proc/5531/ns -l | grep pid
  lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid -> pid:[4026531836]
  lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid_for_children -> pid:[4026532286]

Link: http://lkml.kernel.org/r/149201123914.6007.2187327078064239572.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Andrei Vagin <avagin@virtuozzo.com>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 17:15:12 -07:00

181 lines
4.2 KiB
C

#include <linux/proc_fs.h>
#include <linux/nsproxy.h>
#include <linux/ptrace.h>
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <net/net_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include "internal.h"
static const struct proc_ns_operations *ns_entries[] = {
#ifdef CONFIG_NET_NS
&netns_operations,
#endif
#ifdef CONFIG_UTS_NS
&utsns_operations,
#endif
#ifdef CONFIG_IPC_NS
&ipcns_operations,
#endif
#ifdef CONFIG_PID_NS
&pidns_operations,
&pidns_for_children_operations,
#endif
#ifdef CONFIG_USER_NS
&userns_operations,
#endif
&mntns_operations,
#ifdef CONFIG_CGROUPS
&cgroupns_operations,
#endif
};
static const char *proc_ns_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
struct task_struct *task;
struct path ns_path;
void *error = ERR_PTR(-EACCES);
if (!dentry)
return ERR_PTR(-ECHILD);
task = get_proc_task(inode);
if (!task)
return error;
if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
nd_jump_link(&ns_path);
}
put_task_struct(task);
return error;
}
static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
struct task_struct *task;
char name[50];
int res = -EACCES;
task = get_proc_task(inode);
if (!task)
return res;
if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
res = readlink_copy(buffer, buflen, name);
}
put_task_struct(task);
return res;
}
static const struct inode_operations proc_ns_link_inode_operations = {
.readlink = proc_ns_readlink,
.get_link = proc_ns_get_link,
.setattr = proc_setattr,
};
static int proc_ns_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
const struct proc_ns_operations *ns_ops = ptr;
struct inode *inode;
struct proc_inode *ei;
inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK | S_IRWXUGO);
if (!inode)
goto out;
ei = PROC_I(inode);
inode->i_op = &proc_ns_link_inode_operations;
ei->ns_ops = ns_ops;
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (pid_revalidate(dentry, 0))
return 0;
out:
return -ENOENT;
}
static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
{
struct task_struct *task = get_proc_task(file_inode(file));
const struct proc_ns_operations **entry, **last;
if (!task)
return -ENOENT;
if (!dir_emit_dots(file, ctx))
goto out;
if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
goto out;
entry = ns_entries + (ctx->pos - 2);
last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
while (entry <= last) {
const struct proc_ns_operations *ops = *entry;
if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
proc_ns_instantiate, task, ops))
break;
ctx->pos++;
entry++;
}
out:
put_task_struct(task);
return 0;
}
const struct file_operations proc_ns_dir_operations = {
.read = generic_read_dir,
.iterate_shared = proc_ns_dir_readdir,
.llseek = generic_file_llseek,
};
static struct dentry *proc_ns_dir_lookup(struct inode *dir,
struct dentry *dentry, unsigned int flags)
{
int error;
struct task_struct *task = get_proc_task(dir);
const struct proc_ns_operations **entry, **last;
unsigned int len = dentry->d_name.len;
error = -ENOENT;
if (!task)
goto out_no_task;
last = &ns_entries[ARRAY_SIZE(ns_entries)];
for (entry = ns_entries; entry < last; entry++) {
if (strlen((*entry)->name) != len)
continue;
if (!memcmp(dentry->d_name.name, (*entry)->name, len))
break;
}
if (entry == last)
goto out;
error = proc_ns_instantiate(dir, dentry, task, *entry);
out:
put_task_struct(task);
out_no_task:
return ERR_PTR(error);
}
const struct inode_operations proc_ns_dir_inode_operations = {
.lookup = proc_ns_dir_lookup,
.getattr = pid_getattr,
.setattr = proc_setattr,
};