summaryrefslogtreecommitdiff
path: root/fs/exec.c
diff options
context:
space:
mode:
authorAndrei Vagin <avagin@gmail.com>2022-06-13 09:07:22 +0300
committerKees Cook <keescook@chromium.org>2022-06-15 17:58:04 +0300
commit133e2d3e81de5d9706cab2dd1d52d231c27382e5 (patch)
tree04ff6fdda3b663c9069512108da2b73483134af8 /fs/exec.c
parentb13baccc3850ca8b8cccbf8ed9912dbaa0fdf7f3 (diff)
downloadlinux-133e2d3e81de5d9706cab2dd1d52d231c27382e5.tar.xz
fs/exec: allow to unshare a time namespace on vfork+exec
Right now, a new process can't be forked in another time namespace if it shares mm with its parent. It is prohibited, because each time namespace has its own vvar page that is mapped into a process address space. When a process calls exec, it gets a new mm and so it could be "legal" to switch time namespace in that case. This was not implemented and now if we want to do this, we need to add another clone flag to not break backward compatibility. We don't have any user requests to switch times on exec except the vfork+exec combination, so there is no reason to add a new clone flag. As for vfork+exec, this should be safe to allow switching timens with the current clone flag. Right now, vfork (CLONE_VFORK | CLONE_VM) fails if a child is forked into another time namespace. With this change, vfork creates a new process in parent's timens, and the following exec does the actual switch to the target time namespace. Suggested-by: Florian Weimer <fweimer@redhat.com> Signed-off-by: Andrei Vagin <avagin@gmail.com> Acked-by: Christian Brauner (Microsoft) <brauner@kernel.org> Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20220613060723.197407-1-avagin@gmail.com
Diffstat (limited to 'fs/exec.c')
-rw-r--r--fs/exec.c7
1 files changed, 7 insertions, 0 deletions
diff --git a/fs/exec.c b/fs/exec.c
index 0989fb8472a1..347e8f55bc2b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -65,6 +65,7 @@
#include <linux/io_uring.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/coredump.h>
+#include <linux/time_namespace.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -982,10 +983,12 @@ 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)
@@ -1030,6 +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);
+
if (old_mm) {
mmap_read_unlock(old_mm);
BUG_ON(active_mm != old_mm);