diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/exit.c | 13 | ||||
| -rw-r--r-- | kernel/fork.c | 42 | ||||
| -rw-r--r-- | kernel/sys.c | 22 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 4 | ||||
| -rw-r--r-- | kernel/ucount.c | 6 |
5 files changed, 76 insertions, 11 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index 580da79e38ee..9960accbf2ab 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -607,15 +607,18 @@ static struct task_struct *find_new_reaper(struct task_struct *father, return thread; if (father->signal->has_child_subreaper) { + unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. - * We start from father to ensure we can not look into another - * namespace, this is safe because all its threads are dead. + * We can't check reaper != child_reaper to ensure we do not + * cross the namespaces, the exiting parent could be injected + * by setns() + fork(). + * We check pid->level, this is slightly more efficient than + * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ - for (reaper = father; - !same_thread_group(reaper, child_reaper); + for (reaper = father->real_parent; + task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { - /* call_usermodehelper() descendants need this check */ if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) diff --git a/kernel/fork.c b/kernel/fork.c index d12fcc4db8a3..348fe73155bc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1377,9 +1377,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; - sig->has_child_subreaper = current->signal->has_child_subreaper || - current->signal->is_child_subreaper; - mutex_init(&sig->cred_guard_mutex); return 0; @@ -1814,6 +1811,13 @@ static __latent_entropy struct task_struct *copy_process( p->signal->leader_pid = pid; p->signal->tty = tty_kref_get(current->signal->tty); + /* + * Inherit has_child_subreaper flag under the same + * tasklist_lock with adding child to the process tree + * for propagate_has_child_subreaper optimization. + */ + p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || + p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_PGID); @@ -2067,6 +2071,38 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, } #endif +void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) +{ + struct task_struct *leader, *parent, *child; + int res; + + read_lock(&tasklist_lock); + leader = top = top->group_leader; +down: + for_each_thread(leader, parent) { + list_for_each_entry(child, &parent->children, sibling) { + res = visitor(child, data); + if (res) { + if (res < 0) + goto out; + leader = child; + goto down; + } +up: + ; + } + } + + if (leader != top) { + child = leader; + parent = child->real_parent; + leader = parent->group_leader; + goto up; + } +out: + read_unlock(&tasklist_lock); +} + #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif diff --git a/kernel/sys.c b/kernel/sys.c index 7d4a9a6df956..b07adca97ea3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2063,6 +2063,24 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) } #endif +static int propagate_has_child_subreaper(struct task_struct *p, void *data) +{ + /* + * If task has has_child_subreaper - all its decendants + * already have these flag too and new decendants will + * inherit it on fork, skip them. + * + * If we've found child_reaper - skip descendants in + * it's subtree as they will never get out pidns. + */ + if (p->signal->has_child_subreaper || + is_child_reaper(task_pid(p))) + return 0; + + p->signal->has_child_subreaper = 1; + return 1; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2214,6 +2232,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; + if (!arg2) + break; + + walk_process_tree(me, propagate_has_child_subreaper, NULL); break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d7449783987a..310f0ea0d1a2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7503,7 +7503,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) ftrace_init_tracefs(tr, d_tracer); } -static struct vfsmount *trace_automount(void *ingore) +static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) { struct vfsmount *mnt; struct file_system_type *type; @@ -7516,7 +7516,7 @@ static struct vfsmount *trace_automount(void *ingore) type = get_fs_type("tracefs"); if (!type) return NULL; - mnt = vfs_kern_mount(type, 0, "tracefs", NULL); + mnt = vfs_submount(mntpt, type, "tracefs", NULL); put_filesystem(type); if (IS_ERR(mnt)) return NULL; diff --git a/kernel/ucount.c b/kernel/ucount.c index 95c6336fc2b3..8a11fc0cb459 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -57,7 +57,7 @@ static struct ctl_table_root set_root = { static int zero = 0; static int int_max = INT_MAX; -#define UCOUNT_ENTRY(name) \ +#define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(int), \ @@ -74,6 +74,10 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), +#ifdef CONFIG_INOTIFY_USER + UCOUNT_ENTRY("max_inotify_instances"), + UCOUNT_ENTRY("max_inotify_watches"), +#endif { } }; #endif /* CONFIG_SYSCTL */ |