1 files changed, 92 insertions, 48 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2b037f195473..7fa8e74ad2ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3486,8 +3486,36 @@ void scheduler_tick(void)
 
 struct tick_work {
 	int			cpu;
+	atomic_t		state;
 	struct delayed_work	work;
 };
+/* Values for ->state, see diagram below. */
+#define TICK_SCHED_REMOTE_OFFLINE	0
+#define TICK_SCHED_REMOTE_OFFLINING	1
+#define TICK_SCHED_REMOTE_RUNNING	2
+
+/*
+ * State diagram for ->state:
+ *
+ *
+ *          TICK_SCHED_REMOTE_OFFLINE
+ *                    |   ^
+ *                    |   |
+ *                    |   | sched_tick_remote()
+ *                    |   |
+ *                    |   |
+ *                    +--TICK_SCHED_REMOTE_OFFLINING
+ *                    |   ^
+ *                    |   |
+ * sched_tick_start() |   | sched_tick_stop()
+ *                    |   |
+ *                    V   |
+ *          TICK_SCHED_REMOTE_RUNNING
+ *
+ *
+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
+ * and sched_tick_start() are happy to leave the state in RUNNING.
+ */
 
 static struct tick_work __percpu *tick_work_cpu;
 
@@ -3500,6 +3528,7 @@ static void sched_tick_remote(struct work_struct *work)
 	struct task_struct *curr;
 	struct rq_flags rf;
 	u64 delta;
+	int os;
 
 	/*
 	 * Handle the tick only if it appears the remote CPU is running in full
@@ -3513,7 +3542,7 @@ static void sched_tick_remote(struct work_struct *work)
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr))
+	if (is_idle_task(curr) || cpu_is_offline(cpu))
 		goto out_unlock;
 
 	update_rq_clock(rq);
@@ -3533,13 +3562,18 @@ out_requeue:
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
-	 * to keep scheduler internal stats reasonably up to date.
+	 * to keep scheduler internal stats reasonably up to date.  But
+	 * first update state to reflect hotplug activity if required.
 	 */
-	queue_delayed_work(system_unbound_wq, dwork, HZ);
+	os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
+	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
+	if (os == TICK_SCHED_REMOTE_RUNNING)
+		queue_delayed_work(system_unbound_wq, dwork, HZ);
 }
 
 static void sched_tick_start(int cpu)
 {
+	int os;
 	struct tick_work *twork;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
@@ -3548,15 +3582,20 @@ static void sched_tick_start(int cpu)
 	WARN_ON_ONCE(!tick_work_cpu);
 
 	twork = per_cpu_ptr(tick_work_cpu, cpu);
-	twork->cpu = cpu;
-	INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
-	queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
+	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
+	if (os == TICK_SCHED_REMOTE_OFFLINE) {
+		twork->cpu = cpu;
+		INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+		queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 static void sched_tick_stop(int cpu)
 {
 	struct tick_work *twork;
+	int os;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
 		return;
@@ -3564,7 +3603,10 @@ static void sched_tick_stop(int cpu)
 	WARN_ON_ONCE(!tick_work_cpu);
 
 	twork = per_cpu_ptr(tick_work_cpu, cpu);
-	cancel_delayed_work_sync(&twork->work);
+	/* There cannot be competing actions, but don't rely on stop-machine. */
+	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
+	WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
+	/* Don't cancel, as this would mess up the state machine. */
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -3572,7 +3614,6 @@ int __init sched_tick_offload_init(void)
 {
 	tick_work_cpu = alloc_percpu(struct tick_work);
 	BUG_ON(!tick_work_cpu);
-
 	return 0;
 }
 
@@ -3904,7 +3945,7 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
-	if (!tsk->state || tsk_is_pi_blocked(tsk))
+	if (!tsk->state)
 		return;
 
 	/*
@@ -3920,6 +3961,9 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		preempt_enable_no_resched();
 	}
 
+	if (tsk_is_pi_blocked(tsk))
+		return;
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -5102,37 +5146,40 @@ out_unlock:
 	return retval;
 }
 
-static int sched_read_attr(struct sched_attr __user *uattr,
-			   struct sched_attr *attr,
-			   unsigned int usize)
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+			struct sched_attr *kattr,
+			unsigned int usize)
 {
-	int ret;
+	unsigned int ksize = sizeof(*kattr);
 
 	if (!access_ok(uattr, usize))
 		return -EFAULT;
 
 	/*
-	 * If we're handed a smaller struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. old
-	 * user-space does not get uncomplete information.
+	 * sched_getattr() ABI forwards and backwards compatibility:
+	 *
+	 * If usize == ksize then we just copy everything to user-space and all is good.
+	 *
+	 * If usize < ksize then we only copy as much as user-space has space for,
+	 * this keeps ABI compatibility as well. We skip the rest.
+	 *
+	 * If usize > ksize then user-space is using a newer version of the ABI,
+	 * which part the kernel doesn't know about. Just ignore it - tooling can
+	 * detect the kernel's knowledge of attributes from the attr->size value
+	 * which is set to ksize in this case.
 	 */
-	if (usize < sizeof(*attr)) {
-		unsigned char *addr;
-		unsigned char *end;
+	kattr->size = min(usize, ksize);
 
-		addr = (void *)attr + usize;
-		end  = (void *)attr + sizeof(*attr);
-
-		for (; addr < end; addr++) {
-			if (*addr)
-				return -EFBIG;
-		}
-
-		attr->size = usize;
-	}
-
-	ret = copy_to_user(uattr, attr, attr->size);
-	if (ret)
+	if (copy_to_user(uattr, kattr, kattr->size))
 		return -EFAULT;
 
 	return 0;
@@ -5142,20 +5189,18 @@ static int sched_read_attr(struct sched_attr __user *uattr,
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
- * @size: sizeof(attr) for fwd/bwd comp.
+ * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
  * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-		unsigned int, size, unsigned int, flags)
+		unsigned int, usize, unsigned int, flags)
 {
-	struct sched_attr attr = {
-		.size = sizeof(struct sched_attr),
-	};
+	struct sched_attr kattr = { };
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0 || size > PAGE_SIZE ||
-	    size < SCHED_ATTR_SIZE_VER0 || flags)
+	if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+	    usize < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -5168,25 +5213,24 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (retval)
 		goto out_unlock;
 
-	attr.sched_policy = p->policy;
+	kattr.sched_policy = p->policy;
 	if (p->sched_reset_on_fork)
-		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 	if (task_has_dl_policy(p))
-		__getparam_dl(p, &attr);
+		__getparam_dl(p, &kattr);
 	else if (task_has_rt_policy(p))
-		attr.sched_priority = p->rt_priority;
+		kattr.sched_priority = p->rt_priority;
 	else
-		attr.sched_nice = task_nice(p);
+		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
-	attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-	attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
 
 	rcu_read_unlock();
 
-	retval = sched_read_attr(uattr, &attr, size);
-	return retval;
+	return sched_attr_copy_to_user(uattr, &kattr, usize);
 
 out_unlock:
 	rcu_read_unlock();