On Tue, Aug 30, 2022 at 6:18 PM Andrei Vagin <avagin@xxxxxxxxx> wrote:
>On Tue, Aug 30, 2022 at 10:49:43PM +0300, Alexey Izbyshev wrote:
<snip>
>> @@ -1030,6 +1033,10 @@ static int exec_mmap(struct mm_struct *mm)
>> tsk->mm->vmacache_seqnum = 0;
>> vmacache_flush(tsk);
>> task_unlock(tsk);
>> +
>> + if (vfork)
>> + timens_on_fork(tsk->nsproxy, tsk);
>> +
>>
>> Similarly, even after a normal vfork(), time namespace switch could be
>> silently skipped if the parent dies before "tsk->vfork_done" is read. Again,
>> I don't know whether anybody cares, but this behavior seems non-obvious and
>> probably unintended to me.
> This is the more interesting case. I will try to find out how we can
> handle it properly.
It might not be a good idea to use vfork_done in this case. Let's
think about what we have and what we want to change. We don't want to
allow switching timens if a process mm is used by someone else. But we
forgot to handle execve that creates a new mm, and we can't change this
behavior right now because it can affect current users. Right?
So maybe the best choice, in this case, is to change behavior by adding
a new control that enables it. The first interface that comes to my mind
is to introduce a new ioctl for a namespace file descriptor. Here is a
draft patch below that should help to understand what I mean.
---
fs/exec.c | 4 +---
fs/nsfs.c | 3 +++
include/linux/proc_ns.h | 1 +
include/linux/time_namespace.h | 1 +
include/uapi/linux/nsfs.h | 2 ++
kernel/fork.c | 3 ++-
kernel/time/namespace.c | 15 +++++++++++++++
tools/testing/selftests/timens/vfork_exec.c | 14 +++++++++++++-
8 files changed, 38 insertions(+), 5 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index 9a5ca7b82bfc..961348084257 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -979,12 +979,10 @@ static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
struct mm_struct *old_mm, *active_mm;
- bool vfork;
int ret;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
- vfork = !!tsk->vfork_done;
old_mm = current->mm;
exec_mm_release(tsk, old_mm);
if (old_mm)
@@ -1030,7 +1028,7 @@ static int exec_mmap(struct mm_struct *mm)
vmacache_flush(tsk);
task_unlock(tsk);
- if (vfork)
+ if (READ_ONCE(tsk->nsproxy->time_ns_for_children->switch_on_exec))
timens_on_fork(tsk->nsproxy, tsk);
if (old_mm) {
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 800c1d0eb0d0..723ab5f69bcd 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -11,6 +11,7 @@
#include <linux/user_namespace.h>
#include <linux/nsfs.h>
#include <linux/uaccess.h>
+#include <linux/nsfs.h>
#include "internal.h"
@@ -210,6 +211,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
uid = from_kuid_munged(current_user_ns(), user_ns->owner);
return put_user(uid, argp);
default:
+ if (ns->ops->ioctl)
+ return ns->ops->ioctl(ns, ioctl, arg);
return -ENOTTY;
}
}
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 75807ecef880..b690eb1a3468 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -22,6 +22,7 @@ struct proc_ns_operations {
int (*install)(struct nsset *nsset, struct ns_common *ns);
struct user_namespace *(*owner)(struct ns_common *ns);
struct ns_common *(*get_parent)(struct ns_common *ns);
+ long (*ioctl)(struct ns_common *ns, unsigned int ioctl, unsigned long arg);
} __randomize_layout;
extern const struct proc_ns_operations netns_operations;
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 3146f1c056c9..6569300d68ce 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -24,6 +24,7 @@ struct time_namespace {
struct page *vvar_page;
/* If set prevents changing offsets after any task joined namespace. */
bool frozen_offsets;
+ bool switch_on_exec;
} __randomize_layout;
extern struct time_namespace init_time_ns;
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index a0c8552b64ee..ce3a9f9b1bcf 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -16,4 +16,6 @@
/* Get owner UID (in the caller's user namespace) for a user namespace */
#define NS_GET_OWNER_UID _IO(NSIO, 0x4)
+#define TIMENS_SET_SWITCH_ON_EXEC _IO(NSIO, 0x100)
+
#endif /* __LINUX_NSFS_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 90c85b17bf69..1f7bf2a087e9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2050,7 +2050,8 @@ static __latent_entropy struct task_struct *copy_process(
* On vfork, the child process enters the target time namespace only
* after exec.
*/
- if ((clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) {
+ if ((clone_flags & CLONE_THREAD) ||
+ (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) {
if (nsp->time_ns != nsp->time_ns_for_children)
return ERR_PTR(-EINVAL);
}
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index aec832801c26..9966e0bdefa7 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -17,6 +17,7 @@
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/mm.h>
+#include <linux/nsfs.h>
#include <vdso/datapage.h>
@@ -439,6 +440,18 @@ int proc_timens_set_offset(struct file *file, struct task_struct *p,
return err;
}
+static long timens_ioctl(struct ns_common *ns, unsigned int ioctl, unsigned long arg)
+{
+ struct time_namespace *time_ns = to_time_ns(ns);
+
+ switch (ioctl) {
+ case TIMENS_SET_SWITCH_ON_EXEC:
+ WRITE_ONCE(time_ns->switch_on_exec, true);
+ return 0;
+ }
+ return -ENOTTY;
+}
+
const struct proc_ns_operations timens_operations = {
.name = "time",
.type = CLONE_NEWTIME,
@@ -446,6 +459,7 @@ const struct proc_ns_operations timens_operations = {
.put = timens_put,
.install = timens_install,
.owner = timens_owner,
+ .ioctl = timens_ioctl,
};
const struct proc_ns_operations timens_for_children_operations = {
@@ -456,6 +470,7 @@ const struct proc_ns_operations timens_for_children_operations = {
.put = timens_put,
.install = timens_install,
.owner = timens_owner,
+ .ioctl = timens_ioctl,
};
struct time_namespace init_time_ns = {
diff --git a/tools/testing/selftests/timens/vfork_exec.c b/tools/testing/selftests/timens/vfork_exec.c
index e6ccd900f30a..5f4e2043e0a7 100644
--- a/tools/testing/selftests/timens/vfork_exec.c
+++ b/tools/testing/selftests/timens/vfork_exec.c
@@ -12,6 +12,11 @@
#include <time.h>
#include <unistd.h>
#include <string.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <linux/nsfs.h>
+
+#define TIMENS_SET_SWITCH_ON_EXEC _IO(NSIO, 0x100)
#include "log.h"
#include "timens.h"
@@ -21,7 +26,7 @@
int main(int argc, char *argv[])
{
struct timespec now, tst;
- int status, i;
+ int status, i, nsfd;
pid_t pid;
if (argc > 1) {
@@ -45,6 +50,13 @@ int main(int argc, char *argv[])
if (unshare_timens())
return 1;
+ nsfd = open("/proc/self/ns/time_for_children", O_RDONLY);
+ if (nsfd < 0)
+ return pr_perror("open");
+ if (ioctl(nsfd, TIMENS_SET_SWITCH_ON_EXEC))
+ return pr_perror("ioctl");
+ close(nsfd);
+
if (_settime(CLOCK_MONOTONIC, OFFSET))
return 1;
--
2.37.2
