#define CREATE_TRACE_POINTS
#include <trace/events/task.h>
+#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+#else
+#define unprivileged_userns_clone 0
+#endif
/*
* Minimum number of threads to boot the kernel
if (!s)
continue;
-#ifdef CONFIG_DEBUG_KMEMLEAK
/* Clear stale pointers from reused stack. */
memset(s->addr, 0, THREAD_SIZE);
-#endif
+
tsk->stack_vm_area = s;
return s->addr;
}
continue;
}
charge = 0;
+ /*
+ * Don't duplicate many vmas if we've been oom-killed (for
+ * example)
+ */
+ if (fatal_signal_pending(current)) {
+ retval = -EINTR;
+ goto out;
+ }
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned long len = vma_pages(mpnt);
struct inode *inode = file_inode(file);
struct address_space *mapping = file->f_mapping;
- get_file(file);
+ vma_get_file(tmp);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
i_mmap_lock_write(mapping);
if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
return ERR_PTR(-EINVAL);
+ if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone)
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
posix_cpu_timers_init(p);
- p->start_time = ktime_get_ns();
- p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
p->sequential_io = 0;
p->sequential_io_avg = 0;
#endif
+#ifdef CONFIG_SECURITY
+ p->security = NULL;
+#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
retval = sched_fork(clone_flags, p);
if (retval)
goto bad_fork_free_pid;
+ /*
+ * From this point on we must avoid any synchronous user-space
+ * communication until we take the tasklist-lock. In particular, we do
+ * not want user-space to be able to predict the process start-time by
+ * stalling fork(2) after we recorded the start_time but before it is
+ * visible to the system.
+ */
+
+ p->start_time = ktime_get_ns();
+ p->real_start_time = ktime_get_boot_ns();
+
/*
* Make it visible to the rest of the system, but dont wake it up yet.
* Need tasklist lock for parent etc handling!
if (unshare_flags & CLONE_NEWNS)
unshare_flags |= CLONE_FS;
+ if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) {
+ err = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto bad_unshare_out;
+ }
+
err = check_unshare_flags(unshare_flags);
if (err)
goto bad_unshare_out;