| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4EC4F348.6020101@parallels.com>
Date: Thu, 17 Nov 2011 15:43:04 +0400
From: Pavel Emelyanov <xemul@...allels.com>
To: Linus Torvalds <torvalds@...ux-foundation.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Alan Cox <alan@...ux.intel.com>,
Roland McGrath <roland@...k.frob.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
CC: Tejun Heo <tj@...nel.org>, Oleg Nesterov <oleg@...hat.com>,
Cyrill Gorcunov <gorcunov@...nvz.org>,
James Bottomley <jbottomley@...allels.com>
Subject: [PATCH 3/3] pids: Make it possible to clone tasks with given pids
When restoring a task (or a set of tasks) we need to recreate them
with exactly the same pid(s) as they had before. Thus we need the
ability to create a task with specified pid. The proposal is to reuse
the already free CLONE_STOPPED clone flag, introduce the new one
called CLONE_CHILD_USEPIDS and point to the desired pids with the
child_tidptr.
The child_tidptr points to an array of pids for current namespace and
its ancestors. When 0 is met in this array the pid number for the
corresponding namespace is generated, rather than set.
For security reasons after a regular clone/fork is done in a namespace
further cloning with predefined pid is not allowed.
Signed-off-by: Pavel Emelyanov <xemul@...allels.com>
---
include/linux/pid.h | 2 +-
include/linux/sched.h | 3 +-
kernel/fork.c | 4 ++-
kernel/pid.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 53 insertions(+), 6 deletions(-)
diff --git a/include/linux/pid.h b/include/linux/pid.h
index b152d44..95aa618 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -119,7 +119,7 @@ extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last);
-extern struct pid *alloc_pid(struct pid_namespace *ns);
+extern struct pid *alloc_pid(struct pid_namespace *ns, int __user *want_pids);
extern void free_pid(struct pid *pid);
/*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 41d0237..5472c4e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -21,8 +21,7 @@
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
-/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
- and is now available for re-use. */
+#define CLONE_CHILD_USEPIDS 0x02000000 /* use the pids given by user */
#define CLONE_NEWUTS 0x04000000 /* New utsname group? */
#define CLONE_NEWIPC 0x08000000 /* New ipcs */
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
diff --git a/kernel/fork.c b/kernel/fork.c
index 45a5f54..26c67ff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1253,7 +1253,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
- pid = alloc_pid(p->nsproxy->pid_ns);
+ pid = alloc_pid(p->nsproxy->pid_ns,
+ (clone_flags & CLONE_CHILD_USEPIDS) ?
+ child_tidptr : NULL);
if (IS_ERR(pid)) {
retval = PTR_ERR(pid);
goto bad_fork_cleanup_io;
diff --git a/kernel/pid.c b/kernel/pid.c
index 86bf7d2..fc7d35c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -224,6 +224,38 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
return -ENOMEM;
}
+static int set_pidmap(struct pid_namespace *pid_ns, int pid)
+{
+ int offset;
+ struct pidmap *map;
+
+ /*
+ * When creating a new pid namespace we must make its init
+ * have pid == 1 in it.
+ */
+ if (pid_ns->child_reaper == NULL)
+ return 0;
+
+ /*
+ * Don't allow to create a task with a pid which has recently
+ * belonged to some other (dead already) task. Only init (of
+ * a freshly created namespace) and his clones can do this.
+ */
+ if (pid_ns->last_pid != 1)
+ return -EPERM;
+
+ map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
+ offset = pid & BITS_PER_PAGE_MASK;
+
+ if (alloc_pidmap_page(map))
+ return -ENOMEM;
+
+ if (test_and_set_bit(offset, map->page))
+ return -EBUSY;
+
+ return pid;
+}
+
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
{
int offset;
@@ -284,7 +316,7 @@ void free_pid(struct pid *pid)
call_rcu(&pid->rcu, delayed_put_pid);
}
-struct pid *alloc_pid(struct pid_namespace *ns)
+struct pid *alloc_pid(struct pid_namespace *ns, int __user *want_pids)
{
struct pid *pid;
enum pid_type type;
@@ -298,7 +330,21 @@ struct pid *alloc_pid(struct pid_namespace *ns)
tmp = ns;
for (i = ns->level; i >= 0; i--) {
- nr = alloc_pidmap(tmp);
+ nr = 0;
+ if (unlikely(want_pids != NULL)) {
+ if (get_user(nr, want_pids)) {
+ nr = -EFAULT;
+ goto out_free;
+ }
+
+ if (nr != 0) {
+ want_pids++;
+ nr = set_pidmap(tmp, nr);
+ } else
+ want_pids = NULL; /* optimize above */
+ }
+ if (nr == 0)
+ nr = alloc_pidmap(tmp);
if (nr < 0)
goto out_free;
--
1.5.5.6
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists