Change ptrace_stop() and do_signal_stop() to use freezable_schedule() rather than rely on subsequent try_to_freeze().
This allows to remove the task_is_stopped_or_traced() checks from try_to_freeze_tasks() and update_if_frozen(), and this fixes the unlikely race with ptrace_stop(). If the tracee does not schedule() it can miss a freezing condition. Signed-off-by: Oleg Nesterov <o...@redhat.com> --- include/linux/freezer.h | 7 +++---- kernel/cgroup_freezer.c | 3 +-- kernel/freezer.c | 11 ++--------- kernel/power/process.c | 13 +------------ kernel/signal.c | 11 ++--------- 5 files changed, 9 insertions(+), 36 deletions(-) diff --git a/include/linux/freezer.h b/include/linux/freezer.h index ee89932..8039893 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -134,10 +134,9 @@ static inline bool freezer_should_skip(struct task_struct *p) } /* - * These macros are intended to be used whenever you want allow a task that's - * sleeping in TASK_UNINTERRUPTIBLE or TASK_KILLABLE state to be frozen. Note - * that neither return any clear indication of whether a freeze event happened - * while in this function. + * These macros are intended to be used whenever you want allow a sleeping + * task to be frozen. Note that neither return any clear indication of + * whether a freeze event happened while in this function. */ /* Like schedule(), but should not block the freezer. */ diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 8a92b0e..bedefd9 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -198,8 +198,7 @@ static void update_if_frozen(struct cgroup *cgroup, struct freezer *freezer) * completion. Consider it frozen in addition to * the usual frozen condition. */ - if (!frozen(task) && !task_is_stopped_or_traced(task) && - !freezer_should_skip(task)) + if (!frozen(task) && !freezer_should_skip(task)) goto notyet; } } diff --git a/kernel/freezer.c b/kernel/freezer.c index 11f82a4..c38893b 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -116,17 +116,10 @@ bool freeze_task(struct task_struct *p) return false; } - if (!(p->flags & PF_KTHREAD)) { + if (!(p->flags & PF_KTHREAD)) fake_signal_wake_up(p); - /* - * fake_signal_wake_up() goes through p's scheduler - * lock and guarantees that TASK_STOPPED/TRACED -> - * TASK_RUNNING transition can't race with task state - * testing in try_to_freeze_tasks(). - */ - } else { + else wake_up_state(p, TASK_INTERRUPTIBLE); - } spin_unlock_irqrestore(&freezer_lock, flags); return true; diff --git a/kernel/power/process.c b/kernel/power/process.c index 87da817..d5a258b 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -48,18 +48,7 @@ static int try_to_freeze_tasks(bool user_only) if (p == current || !freeze_task(p)) continue; - /* - * Now that we've done set_freeze_flag, don't - * perturb a task in TASK_STOPPED or TASK_TRACED. - * It is "frozen enough". If the task does wake - * up, it will immediately call try_to_freeze. - * - * Because freeze_task() goes through p's scheduler lock, it's - * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING - * transition can't race with task state testing here. - */ - if (!task_is_stopped_or_traced(p) && - !freezer_should_skip(p)) + if (!freezer_should_skip(p)) todo++; } while_each_thread(g, p); read_unlock(&tasklist_lock); diff --git a/kernel/signal.c b/kernel/signal.c index 0af8868..1660d7d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1908,7 +1908,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) preempt_disable(); read_unlock(&tasklist_lock); preempt_enable_no_resched(); - schedule(); + freezable_schedule(); } else { /* * By the time we got the lock, our tracer went away. @@ -1930,13 +1930,6 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) } /* - * While in TASK_TRACED, we were considered "frozen enough". - * Now that we woke up, it's crucial if we're supposed to be - * frozen that we freeze now before running anything substantial. - */ - try_to_freeze(); - - /* * We are back. Now reacquire the siglock before touching * last_siginfo, so that we are sure to have synchronized with * any signal-sending on another CPU that wants to examine it. @@ -2092,7 +2085,7 @@ static bool do_signal_stop(int signr) } /* Now we don't run again until woken by SIGCONT or SIGKILL */ - schedule(); + freezable_schedule(); return true; } else { /* -- 1.5.5.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/