Peter Zijlstra says:

The most anticipated fix in this pull request is probably the horrible build
 fix for the RANDSTRUCT fail that didn't make -rc2. Also included is the cleanup
 that removes those BUILD_BUG_ON()s and replaces it with ugly unions.
 
 Also included is the try_to_wake_up() race fix that was first triggered by
 Paul's RCU-torture runs, but was independently hit by Dave Chinner's fstest
 runs as well.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAl74tMMACgkQEsHwGGHe
 VUqpAxAAnAiwPetkmCUn53wmv10oGC/vbnxprvNzoIANo9IFJYwKLYuRviT4r4KW
 0tEmpWtsy0CkVdCTpx4yXYUqtGswbjAvxSuwk8vR3bdtottMNJ77PPBKrywL3ymZ
 uQ0tpB/W9CFTOjKx4U/OyaK2Gf4mYzvuJSqhhTbopGf4H9SWflhepLZf0C4rhYa5
 tywch3etazAcNpq+dm31jKIVUkwULyJ4mXH2VDXo+jjl1A5g6h2UliS03e1/BChD
 hX78NRv7ezySdVVpLFhLVKCRdFFj6wIbLsx0yIQjw83dYhmDHK9iqN7m9+p4pZOr
 4qz/+eRYv+zZwWZP8IqOIAE4la1S/LToKEyxAehwl2sfIjhUXx68PvM/feWr8yfd
 z2CHEsI3Dn5XfM8FdPSA+JHE9IHwUyHrDRxcVGU7Nj/9s4L2DfxdrPl6qKGA3Tzm
 F7rK4vR5MNB8Sr7bzcCWV9FOsMNcXh2WThpZcsjfCUgwJza45N3HfocsXO5m4ShC
 FQ8RjE46Msd1WgIoslAkgQT7rFohe/sUKs5xVj4SwT/5i6lz55IGYmiV+hErrxU4
 ArSzUeOys/0EwzJX8PvxiElMq3btFW2XYV65XX5dIABt9IxgRvxHcUGPJDNvQKP7
 WdKVxRIzVXcfRiKUI05vLZU6yzfJuoAjvI1kyTYo64QIbeM7H6g=
 =EGOe
 -----END PGP SIGNATURE-----

Merge tag 'sched_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:
 "The most anticipated fix in this pull request is probably the horrible
  build fix for the RANDSTRUCT fail that didn't make -rc2. Also included
  is the cleanup that removes those BUILD_BUG_ON()s and replaces it with
  ugly unions.

  Also included is the try_to_wake_up() race fix that was first
  triggered by Paul's RCU-torture runs, but was independently hit by
  Dave Chinner's fstest runs as well"

* tag 'sched_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/cfs: change initial value of runnable_avg
  smp, irq_work: Continue smp_call_function*() and irq_work*() integration
  sched/core: s/WF_ON_RQ/WQ_ON_CPU/
  sched/core: Fix ttwu() race
  sched/core: Fix PI boosting between RT and DEADLINE tasks
  sched/deadline: Initialize ->dl_boosted
  sched/core: Check cpus_mask, not cpus_ptr in __set_cpus_allowed_ptr(), to fix mask corruption
  sched/core: Fix CONFIG_GCC_PLUGIN_RANDSTRUCT build fail

include/linux/irq_work.h

@@ -2,7 +2,7 @@
 #ifndef _LINUX_IRQ_WORK_H
 #define _LINUX_IRQ_WORK_H
 
-#include <linux/llist.h>
+#include <linux/smp_types.h>
 
 /*
  * An entry can be in one of four states:
@@ -13,24 +13,14 @@
  * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
  */
 
-/* flags share CSD_FLAG_ space */
-
-#define IRQ_WORK_PENDING	BIT(0)
-#define IRQ_WORK_BUSY		BIT(1)
-
-/* Doesn't want IPI, wait for tick: */
-#define IRQ_WORK_LAZY		BIT(2)
-/* Run hard IRQ context, even on RT */
-#define IRQ_WORK_HARD_IRQ	BIT(3)
-
-#define IRQ_WORK_CLAIMED	(IRQ_WORK_PENDING | IRQ_WORK_BUSY)
-
-/*
- * structure shares layout with single_call_data_t.
- */
 struct irq_work {
+	union {
+		struct __call_single_node node;
+		struct {
 			struct llist_node llnode;
 			atomic_t flags;
+		};
+	};
 	void (*func)(struct irq_work *);
 };
 

include/linux/sched.h

@@ -654,9 +654,8 @@ struct task_struct {
 	unsigned int			ptrace;
 
 #ifdef CONFIG_SMP
-	struct llist_node		wake_entry;
-	unsigned int			wake_entry_type;
 	int				on_cpu;
+	struct __call_single_node	wake_entry;
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* Current CPU: */
 	unsigned int			cpu;

include/linux/smp.h

@@ -12,29 +12,22 @@
 #include <linux/list.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
-#include <linux/llist.h>
+#include <linux/smp_types.h>
 
 typedef void (*smp_call_func_t)(void *info);
 typedef bool (*smp_cond_func_t)(int cpu, void *info);
 
-enum {
-	CSD_FLAG_LOCK		= 0x01,
-
-	/* IRQ_WORK_flags */
-
-	CSD_TYPE_ASYNC		= 0x00,
-	CSD_TYPE_SYNC		= 0x10,
-	CSD_TYPE_IRQ_WORK	= 0x20,
-	CSD_TYPE_TTWU		= 0x30,
-	CSD_FLAG_TYPE_MASK	= 0xF0,
-};
-
 /*
  * structure shares (partial) layout with struct irq_work
  */
 struct __call_single_data {
+	union {
+		struct __call_single_node node;
+		struct {
 			struct llist_node llist;
 			unsigned int flags;
+		};
+	};
 	smp_call_func_t func;
 	void *info;
 };

include/linux/smp_types.h

@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SMP_TYPES_H
+#define __LINUX_SMP_TYPES_H
+
+#include <linux/llist.h>
+
+enum {
+	CSD_FLAG_LOCK		= 0x01,
+
+	IRQ_WORK_PENDING	= 0x01,
+	IRQ_WORK_BUSY		= 0x02,
+	IRQ_WORK_LAZY		= 0x04, /* No IPI, wait for tick */
+	IRQ_WORK_HARD_IRQ	= 0x08, /* IRQ context on PREEMPT_RT */
+
+	IRQ_WORK_CLAIMED	= (IRQ_WORK_PENDING | IRQ_WORK_BUSY),
+
+	CSD_TYPE_ASYNC		= 0x00,
+	CSD_TYPE_SYNC		= 0x10,
+	CSD_TYPE_IRQ_WORK	= 0x20,
+	CSD_TYPE_TTWU		= 0x30,
+
+	CSD_FLAG_TYPE_MASK	= 0xF0,
+};
+
+/*
+ * struct __call_single_node is the primary type on
+ * smp.c:call_single_queue.
+ *
+ * flush_smp_call_function_queue() only reads the type from
+ * __call_single_node::u_flags as a regular load, the above
+ * (anonymous) enum defines all the bits of this word.
+ *
+ * Other bits are not modified until the type is known.
+ *
+ * CSD_TYPE_SYNC/ASYNC:
+ *	struct {
+ *		struct llist_node node;
+ *		unsigned int flags;
+ *		smp_call_func_t func;
+ *		void *info;
+ *	};
+ *
+ * CSD_TYPE_IRQ_WORK:
+ *	struct {
+ *		struct llist_node node;
+ *		atomic_t flags;
+ *		void (*func)(struct irq_work *);
+ *	};
+ *
+ * CSD_TYPE_TTWU:
+ *	struct {
+ *		struct llist_node node;
+ *		unsigned int flags;
+ *	};
+ *
+ */
+
+struct __call_single_node {
+	struct llist_node	llist;
+	union {
+		unsigned int	u_flags;
+		atomic_t	a_flags;
+	};
+};
+
+#endif /* __LINUX_SMP_TYPES_H */

kernel/sched/core.c

@@ -1637,7 +1637,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	/*
@@ -2293,8 +2293,15 @@ void sched_ttwu_pending(void *arg)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -2322,7 +2329,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	__smp_call_single_queue(cpu, &p->wake_entry);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2369,7 +2376,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	 * the soon-to-be-idle CPU as the current CPU is likely busy.
 	 * nr_running is checked to avoid unnecessary task stacking.
 	 */
-	if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1)
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
 		return true;
 
 	return false;
@@ -2378,6 +2385,9 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -2528,7 +2538,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2550,7 +2559,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2614,8 +2622,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * which potentially sends an IPI instead of spinning on p->on_cpu to
 	 * let the waker make forward progress. This is safe because IRQs are
 	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
 	 */
-	if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ))
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
 		goto unlock;
 
 	/*
@@ -2635,6 +2656,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2642,7 +2665,7 @@ unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
@@ -2763,7 +2786,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
-	p->wake_entry_type = CSD_TYPE_TTWU;
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 #endif
 }
 
@@ -4533,7 +4556,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else

kernel/sched/deadline.c

@@ -2692,6 +2692,7 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
+	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;

kernel/sched/fair.c

@@ -806,7 +806,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 		}
 	}
 
-	sa->runnable_avg = cpu_scale;
+	sa->runnable_avg = sa->util_avg;
 
 	if (p->sched_class != &fair_sched_class) {
 		/*

kernel/sched/sched.h

@@ -1682,7 +1682,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
 #define WF_MIGRATED		0x04		/* Internal use, task got migrated */
-#define WF_ON_RQ		0x08		/* Wakee is on_rq */
+#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution

kernel/smp.c

@@ -669,24 +669,6 @@ void __init smp_init(void)
 {
 	int num_nodes, num_cpus;
 
-	/*
-	 * Ensure struct irq_work layout matches so that
-	 * flush_smp_call_function_queue() can do horrible things.
-	 */
-	BUILD_BUG_ON(offsetof(struct irq_work, llnode) !=
-		     offsetof(struct __call_single_data, llist));
-	BUILD_BUG_ON(offsetof(struct irq_work, func) !=
-		     offsetof(struct __call_single_data, func));
-	BUILD_BUG_ON(offsetof(struct irq_work, flags) !=
-		     offsetof(struct __call_single_data, flags));
-
-	/*
-	 * Assert the CSD_TYPE_TTWU layout is similar enough
-	 * for task_struct to be on the @call_single_queue.
-	 */
-	BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) !=
-		     offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist));
-
 	idle_threads_init();
 	cpuhp_threads_init();