Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-android

[firefly-linux-kernel-4.4.55.git] / kernel / fork.c

diff --git a/kernel/fork.c b/kernel/fork.c
index c271467da4f9602fbac045b1e718ab9f5c041522..8011604b3317d23386615cbbebd5456e149b61b3 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -198,6 +198,9 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+/* Notifier list called when a task struct is freed */
+static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
+
 static void account_kernel_stack(struct thread_info *ti, int account)
 {
        struct zone *zone = page_zone(virt_to_page(ti));
@@ -231,6 +234,18 @@ static inline void put_signal_struct(struct signal_struct *sig)
                free_signal_struct(sig);
 }
 
+int task_free_register(struct notifier_block *n)
+{
+       return atomic_notifier_chain_register(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_register);
+
+int task_free_unregister(struct notifier_block *n)
+{
+       return atomic_notifier_chain_unregister(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_unregister);
+
 void __put_task_struct(struct task_struct *tsk)
 {
        WARN_ON(!tsk->exit_state);
@@ -242,6 +257,7 @@ void __put_task_struct(struct task_struct *tsk)
        delayacct_tsk_free(tsk);
        put_signal_struct(tsk->signal);
 
+       atomic_notifier_call_chain(&task_free_notifier, 0, tsk);
        if (!profile_handoff_task(tsk))
                free_task(tsk);
 }
@@ -311,6 +327,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
                goto free_ti;
 
        tsk->stack = ti;
+#ifdef CONFIG_SECCOMP
+       /*
+        * We must handle setting up seccomp filters once we're under
+        * the sighand lock in case orig has changed between now and
+        * then. Until then, filter must be NULL to avoid messing up
+        * the usage counts on the error path calling free_task.
+        */
+       tsk->seccomp.filter = NULL;
+#endif
 
        setup_thread_stack(tsk, orig);
        clear_user_return_notifier(tsk);
@@ -697,7 +722,8 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 
        mm = get_task_mm(task);
        if (mm && mm != current->mm &&
-                       !ptrace_may_access(task, mode)) {
+                       !ptrace_may_access(task, mode) &&
+                       !capable(CAP_SYS_RESOURCE)) {
                mmput(mm);
                mm = ERR_PTR(-EACCES);
        }
@@ -1045,6 +1071,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
        sig->nr_threads = 1;
        atomic_set(&sig->live, 1);
        atomic_set(&sig->sigcnt, 1);
+
+       /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+       sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+       tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
        init_waitqueue_head(&sig->wait_chldexit);
        sig->curr_target = tsk;
        init_sigpending(&sig->shared_pending);
@@ -1086,6 +1117,39 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
        p->flags = new_flags;
 }
 
+static void copy_seccomp(struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+       /*
+        * Must be called with sighand->lock held, which is common to
+        * all threads in the group. Holding cred_guard_mutex is not
+        * needed because this new task is not yet running and cannot
+        * be racing exec.
+        */
+       BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+       /* Ref-count the new filter user, and assign it. */
+       get_seccomp_filter(current);
+       p->seccomp = current->seccomp;
+
+       /*
+        * Explicitly enable no_new_privs here in case it got set
+        * between the task_struct being duplicated and holding the
+        * sighand lock. The seccomp state and nnp must be in sync.
+        */
+       if (task_no_new_privs(current))
+               task_set_no_new_privs(p);
+
+       /*
+        * If the parent gained a seccomp mode after copying thread
+        * flags and between before we held the sighand lock, we have
+        * to manually enable the seccomp thread flag here.
+        */
+       if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
+               set_tsk_thread_flag(p, TIF_SECCOMP);
+#endif
+}
+
 SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
        current->clear_child_tid = tidptr;
@@ -1190,7 +1254,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                goto fork_out;
 
        ftrace_graph_init_task(p);
-       get_seccomp_filter(p);
 
        rt_mutex_init_task(p);
 
@@ -1319,7 +1382,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                goto bad_fork_cleanup_policy;
        retval = audit_alloc(p);
        if (retval)
-               goto bad_fork_cleanup_policy;
+               goto bad_fork_cleanup_perf;
        /* copy all the process information */
        retval = copy_semundo(clone_flags, p);
        if (retval)
@@ -1432,6 +1495,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
        spin_lock(&current->sighand->siglock);
 
+       /*
+        * Copy seccomp details explicitly here, in case they were changed
+        * before holding sighand lock.
+        */
+       copy_seccomp(p);
+
        /*
         * Process group and session signals need to be delivered to just the
         * parent before the fork or both the parent and the child after the
@@ -1471,6 +1540,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                        p->group_leader = current->group_leader;
                        list_add_tail_rcu(&p->thread_group,
                                          &p->group_leader->thread_group);
+                       list_add_tail_rcu(&p->thread_node,
+                                         &p->signal->thread_head);
                }
                attach_pid(p, PIDTYPE_PID, pid);
                nr_threads++;
@@ -1515,8 +1586,9 @@ bad_fork_cleanup_semundo:
        exit_sem(p);
 bad_fork_cleanup_audit:
        audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
        perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
        mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup: