linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: rjw@rjwysocki.net, oleg@redhat.com, mingo@kernel.org,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, mgorman@suse.de, ebiederm@xmission.com,
	bigeasy@linutronix.de, Will Deacon <will@kernel.org>
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
	tj@kernel.org, linux-pm@vger.kernel.org
Subject: [PATCH 1/5] sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state
Date: Tue, 12 Apr 2022 13:44:22 +0200	[thread overview]
Message-ID: <20220412114853.782838521@infradead.org> (raw)
In-Reply-To: 20220412114421.691372568@infradead.org

Currently ptrace_stop() / do_signal_stop() rely on the special states
TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this
state exists only in task->__state and nowhere else.

There's two spots of bother with this:

 - PREEMPT_RT has task->saved_state which complicates matters,
   meaning task_is_{traced,stopped}() needs to check an additional
   variable.

 - An alternative freezer implementation that itself relies on a
   special TASK state would loose TASK_TRACED/TASK_STOPPED and will
   result in misbehaviour.

As such, add additional state to task->jobctl to track this state
outside of task->__state.

NOTE: this doesn't actually fix anything yet, just adds extra state.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/sched.h        |    8 +++-----
 include/linux/sched/jobctl.h |    8 ++++++++
 include/linux/sched/signal.h |   15 ++++++++++++++-
 kernel/ptrace.c              |   18 ++++++++++++++----
 kernel/signal.c              |    9 ++++++---
 5 files changed, 45 insertions(+), 13 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,11 +118,9 @@ struct task_group;
 
 #define task_is_running(task)		(READ_ONCE((task)->__state) == TASK_RUNNING)
 
-#define task_is_traced(task)		((READ_ONCE(task->__state) & __TASK_TRACED) != 0)
-
-#define task_is_stopped(task)		((READ_ONCE(task->__state) & __TASK_STOPPED) != 0)
-
-#define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
+#define task_is_traced(task)		((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0)
+#define task_is_stopped(task)		((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0)
+#define task_is_stopped_or_traced(task)	((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0)
 
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -20,6 +20,10 @@ struct task_struct;
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
 
+#define JOBCTL_STOPPED_BIT	24
+#define JOBCTL_TRACED_BIT	25
+#define JOBCTL_TRACED_FROZEN_BIT 26
+
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
 #define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
@@ -29,6 +33,10 @@ struct task_struct;
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
 
+#define JOBCTL_STOPPED		(1UL << JOBCTL_STOPPED_BIT)
+#define JOBCTL_TRACED		(1UL << JOBCTL_TRACED_BIT)
+#define JOBCTL_TRACED_FROZEN	(1UL << JOBCTL_TRACED_FROZEN_BIT)
+
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(
 static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
@@ -437,10 +439,21 @@ extern void signal_wake_up_state(struct
 
 static inline void signal_wake_up(struct task_struct *t, bool resume)
 {
+	lockdep_assert_held(&t->sighand->siglock);
+
+	if (resume && !(t->jobctl & JOBCTL_TRACED_FROZEN))
+		t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
+
 	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
 }
+
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
+	lockdep_assert_held(&t->sighand->siglock);
+
+	if (resume)
+		t->jobctl &= ~JOBCTL_TRACED;
+
 	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
 }
 
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -185,7 +185,12 @@ static bool looks_like_a_spurious_pid(st
 	return true;
 }
 
-/* Ensure that nothing can wake it up, even SIGKILL */
+/*
+ * Ensure that nothing can wake it up, even SIGKILL
+ *
+ * A task is switched to this state while a ptrace operation is in progress;
+ * such that the ptrace operation is uninterruptible.
+ */
 static bool ptrace_freeze_traced(struct task_struct *task)
 {
 	bool ret = false;
@@ -197,6 +202,7 @@ static bool ptrace_freeze_traced(struct
 	spin_lock_irq(&task->sighand->siglock);
 	if (task_is_traced(task) && !looks_like_a_spurious_pid(task) &&
 	    !__fatal_signal_pending(task)) {
+		task->jobctl |= JOBCTL_TRACED_FROZEN;
 		WRITE_ONCE(task->__state, __TASK_TRACED);
 		ret = true;
 	}
@@ -218,9 +224,11 @@ static void ptrace_unfreeze_traced(struc
 	 */
 	spin_lock_irq(&task->sighand->siglock);
 	if (READ_ONCE(task->__state) == __TASK_TRACED) {
-		if (__fatal_signal_pending(task))
+		task->jobctl &= ~JOBCTL_TRACED_FROZEN;
+		if (__fatal_signal_pending(task)) {
+			task->jobctl &= ~JOBCTL_TRACED;
 			wake_up_state(task, __TASK_TRACED);
-		else
+		} else
 			WRITE_ONCE(task->__state, TASK_TRACED);
 	}
 	spin_unlock_irq(&task->sighand->siglock);
@@ -475,8 +483,10 @@ static int ptrace_attach(struct task_str
 	 * in and out of STOPPED are protected by siglock.
 	 */
 	if (task_is_stopped(task) &&
-	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_STOPPED;
 		signal_wake_up_state(task, __TASK_STOPPED);
+	}
 
 	spin_unlock(&task->sighand->siglock);
 
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -884,7 +884,7 @@ static int check_kill_permission(int sig
 static void ptrace_trap_notify(struct task_struct *t)
 {
 	WARN_ON_ONCE(!(t->ptrace & PT_SEIZED));
-	assert_spin_locked(&t->sighand->siglock);
+	lockdep_assert_held(&t->sighand->siglock);
 
 	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
 	ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
@@ -930,9 +930,10 @@ static bool prepare_signal(int sig, stru
 		for_each_thread(p, t) {
 			flush_sigqueue_mask(&flush, &t->pending);
 			task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
-			if (likely(!(t->ptrace & PT_SEIZED)))
+			if (likely(!(t->ptrace & PT_SEIZED))) {
+				t->jobctl &= ~JOBCTL_STOPPED;
 				wake_up_state(t, __TASK_STOPPED);
-			else
+			} else
 				ptrace_trap_notify(t);
 		}
 
@@ -2219,6 +2220,7 @@ static int ptrace_stop(int exit_code, in
 	 * schedule() will not sleep if there is a pending signal that
 	 * can awaken the task.
 	 */
+	current->jobctl |= JOBCTL_TRACED;
 	set_special_state(TASK_TRACED);
 
 	/*
@@ -2460,6 +2462,7 @@ static bool do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 



  reply	other threads:[~2022-04-12 12:31 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-12 11:44 [PATCH 0/5] ptrace-vs-PREEMPT_RT and freezer rewrite Peter Zijlstra
2022-04-12 11:44 ` Peter Zijlstra [this message]
2022-04-13 13:29   ` [PATCH 1/5] sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state Oleg Nesterov
2022-04-13 16:47     ` Peter Zijlstra
2022-04-12 11:44 ` [PATCH 2/5] sched,ptrace: Fix ptrace_check_attach() vs PREEMPT_RT Peter Zijlstra
2022-04-13 13:24   ` Oleg Nesterov
2022-04-13 16:58     ` Peter Zijlstra
2022-04-13 18:57     ` Oleg Nesterov
2022-04-13 18:59       ` Oleg Nesterov
2022-04-13 19:20         ` Peter Zijlstra
2022-04-13 19:56           ` Peter Zijlstra
2022-04-14 11:54             ` Oleg Nesterov
2022-04-14 12:08               ` Oleg Nesterov
2022-04-14 18:34               ` Oleg Nesterov
2022-04-14 22:45                 ` Peter Zijlstra
2022-04-15 10:16                   ` Oleg Nesterov
2022-04-15 10:57                     ` Oleg Nesterov
2022-04-15 12:01                       ` Peter Zijlstra
2022-04-18 17:01                         ` Oleg Nesterov
2022-04-18 17:19                           ` Oleg Nesterov
2022-04-20 13:17                           ` Peter Zijlstra
2022-04-20 18:03                             ` Oleg Nesterov
2022-04-20 20:54                               ` [RFC][PATCH] ptrace: Don't change __state Eric W. Biederman
2022-04-21  7:21                                 ` Peter Zijlstra
2022-04-21 10:26                                   ` Peter Zijlstra
2022-04-21 10:49                                     ` Oleg Nesterov
2022-04-21 11:50                                       ` Peter Zijlstra
2022-04-21 14:45                                   ` Eric W. Biederman
2022-04-21  9:46                                 ` Oleg Nesterov
2022-04-21 15:01                                   ` Eric W. Biederman
2022-04-20 10:20                       ` [PATCH 2/5] sched,ptrace: Fix ptrace_check_attach() vs PREEMPT_RT Peter Zijlstra
2022-04-20 11:35                         ` Oleg Nesterov
2022-04-15 12:00                     ` Peter Zijlstra
2022-04-15 12:56                       ` Oleg Nesterov
2022-04-12 11:44 ` [PATCH 3/5] freezer: Have {,un}lock_system_sleep() save/restore flags Peter Zijlstra
2022-04-12 11:44 ` [PATCH 4/5] freezer,umh: Clean up freezer/initrd interaction Peter Zijlstra
2022-04-12 11:44 ` [PATCH 5/5] freezer,sched: Rewrite core freezer logic Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220412114853.782838521@infradead.org \
    --to=peterz@infradead.org \
    --cc=bigeasy@linutronix.de \
    --cc=dietmar.eggemann@arm.com \
    --cc=ebiederm@xmission.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=rjw@rjwysocki.net \
    --cc=rostedt@goodmis.org \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).