Merge tag 'sched_urgent_for_v6.1_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Fix a small race on the task's exit path where there's a
   misunderstanding whether the task holds rq->lock or not

 - Prevent processes from getting killed when using deprecated or
   unknown rseq ABI flags in order to be able to fuzz the rseq() syscall
   with syzkaller

* tag 'sched_urgent_for_v6.1_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Fix race in task_call_func()
  rseq: Use pr_warn_once() when deprecated/unknown ABI flags are encountered

2 files changed, 52 insertions, 19 deletions

diff --git a/kernel/rseq.c b/kernel/rseq.c
index bda8175f8f99..d38ab944105d 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -171,12 +171,27 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	return 0;
 }
 
+static bool rseq_warn_flags(const char *str, u32 flags)
+{
+	u32 test_flags;
+
+	if (!flags)
+		return false;
+	test_flags = flags & RSEQ_CS_NO_RESTART_FLAGS;
+	if (test_flags)
+		pr_warn_once("Deprecated flags (%u) in %s ABI structure", test_flags, str);
+	test_flags = flags & ~RSEQ_CS_NO_RESTART_FLAGS;
+	if (test_flags)
+		pr_warn_once("Unknown flags (%u) in %s ABI structure", test_flags, str);
+	return true;
+}
+
 static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 {
 	u32 flags, event_mask;
 	int ret;
 
-	if (WARN_ON_ONCE(cs_flags & RSEQ_CS_NO_RESTART_FLAGS) || cs_flags)
+	if (rseq_warn_flags("rseq_cs", cs_flags))
 		return -EINVAL;
 
 	/* Get thread flags. */
@@ -184,7 +199,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	if (ret)
 		return ret;
 
-	if (WARN_ON_ONCE(flags & RSEQ_CS_NO_RESTART_FLAGS) || flags)
+	if (rseq_warn_flags("rseq", flags))
 		return -EINVAL;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cb2aa2b54c7a..daff72f00385 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4200,6 +4200,40 @@ out:
 	return success;
 }
 
+static bool __task_needs_rq_lock(struct task_struct *p)
+{
+	unsigned int state = READ_ONCE(p->__state);
+
+	/*
+	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
+	 * the task is blocked. Make sure to check @state since ttwu() can drop
+	 * locks at the end, see ttwu_queue_wakelist().
+	 */
+	if (state == TASK_RUNNING || state == TASK_WAKING)
+		return true;
+
+	/*
+	 * Ensure we load p->on_rq after p->__state, otherwise it would be
+	 * possible to, falsely, observe p->on_rq == 0.
+	 *
+	 * See try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+	if (p->on_rq)
+		return true;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Ensure the task has finished __schedule() and will not be referenced
+	 * anymore. Again, see try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+	smp_cond_load_acquire(&p->on_cpu, !VAL);
+#endif
+
+	return false;
+}
+
 /**
  * task_call_func - Invoke a function on task in fixed state
  * @p: Process for which the function is to be invoked, can be @current.
@@ -4217,28 +4251,12 @@ out:
 int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 {
 	struct rq *rq = NULL;
-	unsigned int state;
 	struct rq_flags rf;
 	int ret;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 
-	state = READ_ONCE(p->__state);
-
-	/*
-	 * Ensure we load p->on_rq after p->__state, otherwise it would be
-	 * possible to, falsely, observe p->on_rq == 0.
-	 *
-	 * See try_to_wake_up() for a longer comment.
-	 */
-	smp_rmb();
-
-	/*
-	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
-	 * the task is blocked. Make sure to check @state since ttwu() can drop
-	 * locks at the end, see ttwu_queue_wakelist().
-	 */
-	if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq)
+	if (__task_needs_rq_lock(p))
 		rq = __task_rq_lock(p, &rf);
 
 	/*