Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

45 files changed, 119 insertions, 56 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 75c151413fda..0d1ada8968d7 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -450,6 +450,7 @@ extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
+		rcu_read_lock_sched_held() ||				\
 		lockdep_is_held(&cgroup_mutex) ||			\
 		lockdep_is_held(&css_set_lock) ||			\
 		((task)->flags & PF_EXITING) || (__c))
@@ -791,11 +792,9 @@ static inline void cgroup_account_cputime(struct task_struct *task,
 
 	cpuacct_charge(task, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime(cgrp, delta_exec);
-	rcu_read_unlock();
 }
 
 static inline void cgroup_account_cputime_field(struct task_struct *task,
@@ -806,11 +805,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
 
 	cpuacct_account_field(task, index, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime_field(cgrp, index, delta_exec);
-	rcu_read_unlock();
 }
 
 #else	/* CONFIG_CGROUPS */
diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h
new file mode 100644
index 000000000000..d0cfe8025111
--- /dev/null
+++ b/include/linux/cgroup_api.h
@@ -0,0 +1 @@
+#include <linux/cgroup.h>
diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h
new file mode 100644
index 000000000000..83bd3ebe82b0
--- /dev/null
+++ b/include/linux/cpumask_api.h
@@ -0,0 +1 @@
+#include <linux/cpumask.h>
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 2e2b8d6140ed..141952f4fee8 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -454,10 +454,21 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
  *
  * Conditional reschedule with additional sanity checks.
  */
-void irqentry_exit_cond_resched(void);
+void raw_irqentry_exit_cond_resched(void);
 #ifdef CONFIG_PREEMPT_DYNAMIC
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
+#define irqentry_exit_cond_resched_dynamic_disabled	NULL
+DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void);
+#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
 #endif
+#else /* CONFIG_PREEMPT_DYNAMIC */
+#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
+#endif /* CONFIG_PREEMPT_DYNAMIC */
 
 /**
  * irqentry_exit - Handle return from exception that used irqentry_enter()
diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h
new file mode 100644
index 000000000000..83be38d6d413
--- /dev/null
+++ b/include/linux/fs_api.h
@@ -0,0 +1 @@
+#include <linux/fs.h>
diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h
new file mode 100644
index 000000000000..5a05a2764a86
--- /dev/null
+++ b/include/linux/gfp_api.h
@@ -0,0 +1 @@
+#include <linux/gfp.h>
diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h
new file mode 100644
index 000000000000..c268ac2c5c0e
--- /dev/null
+++ b/include/linux/hashtable_api.h
@@ -0,0 +1 @@
+#include <linux/hashtable.h>
diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h
new file mode 100644
index 000000000000..8d9700894468
--- /dev/null
+++ b/include/linux/hrtimer_api.h
@@ -0,0 +1 @@
+#include <linux/hrtimer.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 33f47a996513..a890428bcc1a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -99,7 +99,7 @@ struct user;
 extern int __cond_resched(void);
 # define might_resched() __cond_resched()
 
-#elif defined(CONFIG_PREEMPT_DYNAMIC)
+#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
 extern int __cond_resched(void);
 
@@ -110,6 +110,11 @@ static __always_inline void might_resched(void)
 	static_call_mod(might_resched)();
 }
 
+#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
+extern int dynamic_might_resched(void);
+# define might_resched() dynamic_might_resched()
+
 #else
 
 # define might_resched() do { } while (0)
diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h
new file mode 100644
index 000000000000..6e36a054c2d6
--- /dev/null
+++ b/include/linux/kobject_api.h
@@ -0,0 +1 @@
+#include <linux/kobject.h>
diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h
new file mode 100644
index 000000000000..d67e554721d2
--- /dev/null
+++ b/include/linux/kref_api.h
@@ -0,0 +1 @@
+#include <linux/kref.h>
diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h
new file mode 100644
index 000000000000..f697d493960f
--- /dev/null
+++ b/include/linux/ktime_api.h
@@ -0,0 +1 @@
+#include <linux/ktime.h>
diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h
new file mode 100644
index 000000000000..625bec0393a1
--- /dev/null
+++ b/include/linux/llist_api.h
@@ -0,0 +1 @@
+#include <linux/llist.h>
diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h
new file mode 100644
index 000000000000..907e66979ab2
--- /dev/null
+++ b/include/linux/lockdep_api.h
@@ -0,0 +1 @@
+#include <linux/lockdep.h>
diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h
new file mode 100644
index 000000000000..a5ace2b198b8
--- /dev/null
+++ b/include/linux/mm_api.h
@@ -0,0 +1 @@
+#include <linux/mm.h>
diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h
new file mode 100644
index 000000000000..85ab9491e13e
--- /dev/null
+++ b/include/linux/mutex_api.h
@@ -0,0 +1 @@
+#include <linux/mutex.h>
diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h
new file mode 100644
index 000000000000..c2fd6048b790
--- /dev/null
+++ b/include/linux/perf_event_api.h
@@ -0,0 +1 @@
+#include <linux/perf_event.h>
diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h
new file mode 100644
index 000000000000..ff367a4ba8c4
--- /dev/null
+++ b/include/linux/pgtable_api.h
@@ -0,0 +1 @@
+#include <linux/pgtable.h>
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 7f7d1d88c3bb..89784763d19e 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -6,6 +6,7 @@
 #include <linux/psi_types.h>
 #include <linux/sched.h>
 #include <linux/poll.h>
+#include <linux/cgroup-defs.h>
 
 struct seq_file;
 struct css_set;
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 1a3cef26d129..c7fe7c089718 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -141,6 +141,9 @@ struct psi_trigger {
 	 * events to one per window
 	 */
 	u64 last_event_time;
+
+	/* Deferred event(s) from previous ratelimit window */
+	bool pending_event;
 };
 
 struct psi_group {
diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h
new file mode 100644
index 000000000000..26e7d275ad8d
--- /dev/null
+++ b/include/linux/ptrace_api.h
@@ -0,0 +1 @@
+#include <linux/ptrace.h>
diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h
new file mode 100644
index 000000000000..f962e28544dd
--- /dev/null
+++ b/include/linux/rcuwait_api.h
@@ -0,0 +1 @@
+#include <linux/rcuwait.h>
diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h
new file mode 100644
index 000000000000..5f032589f568
--- /dev/null
+++ b/include/linux/refcount_api.h
@@ -0,0 +1 @@
+#include <linux/refcount.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index aab75966396f..fee34a8a8fe8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1626,19 +1626,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
-static inline unsigned int task_state_index(struct task_struct *tsk)
+static inline unsigned int __task_state_index(unsigned int tsk_state,
+					      unsigned int tsk_exit_state)
 {
-	unsigned int tsk_state = READ_ONCE(tsk->__state);
-	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
+	unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
 
 	BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
 
 	if (tsk_state == TASK_IDLE)
 		state = TASK_REPORT_IDLE;
 
+	/*
+	 * We're lying here, but rather than expose a completely new task state
+	 * to userspace, we can make this appear as if the task has gone through
+	 * a regular rt_mutex_lock() call.
+	 */
+	if (tsk_state == TASK_RTLOCK_WAIT)
+		state = TASK_UNINTERRUPTIBLE;
+
 	return fls(state);
 }
 
+static inline unsigned int task_state_index(struct task_struct *tsk)
+{
+	return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
+}
+
 static inline char task_index_to_char(unsigned int state)
 {
 	static const char state_char[] = "RSDTtXZPI";
@@ -2021,7 +2034,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
 extern int __cond_resched(void);
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
@@ -2030,6 +2043,14 @@ static __always_inline int _cond_resched(void)
 	return static_call_mod(cond_resched)();
 }
 
+#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+extern int dynamic_cond_resched(void);
+
+static __always_inline int _cond_resched(void)
+{
+	return dynamic_cond_resched();
+}
+
 #else
 
 static inline int _cond_resched(void)
diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/affinity.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/cond_resched.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1aff00b65f3c..7c83d4d5a971 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -6,6 +6,8 @@
  * NORMAL/BATCH tasks.
  */
 
+#include <linux/sched.h>
+
 #define MAX_DL_PRIO		0
 
 static inline int dl_prio(int prio)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index cc9f393e2a70..8c15abd67aed 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -5,54 +5,55 @@
 #include <linux/init.h>
 #include <linux/tick.h>
 
-enum hk_flags {
-	HK_FLAG_TIMER		= 1,
-	HK_FLAG_RCU		= (1 << 1),
-	HK_FLAG_MISC		= (1 << 2),
-	HK_FLAG_SCHED		= (1 << 3),
-	HK_FLAG_TICK		= (1 << 4),
-	HK_FLAG_DOMAIN		= (1 << 5),
-	HK_FLAG_WQ		= (1 << 6),
-	HK_FLAG_MANAGED_IRQ	= (1 << 7),
-	HK_FLAG_KTHREAD		= (1 << 8),
+enum hk_type {
+	HK_TYPE_TIMER,
+	HK_TYPE_RCU,
+	HK_TYPE_MISC,
+	HK_TYPE_SCHED,
+	HK_TYPE_TICK,
+	HK_TYPE_DOMAIN,
+	HK_TYPE_WQ,
+	HK_TYPE_MANAGED_IRQ,
+	HK_TYPE_KTHREAD,
+	HK_TYPE_MAX
 };
 
 #ifdef CONFIG_CPU_ISOLATION
 DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
-extern int housekeeping_any_cpu(enum hk_flags flags);
-extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
-extern bool housekeeping_enabled(enum hk_flags flags);
-extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
-extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
+extern int housekeeping_any_cpu(enum hk_type type);
+extern const struct cpumask *housekeeping_cpumask(enum hk_type type);
+extern bool housekeeping_enabled(enum hk_type type);
+extern void housekeeping_affine(struct task_struct *t, enum hk_type type);
+extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
 extern void __init housekeeping_init(void);
 
 #else
 
-static inline int housekeeping_any_cpu(enum hk_flags flags)
+static inline int housekeeping_any_cpu(enum hk_type type)
 {
 	return smp_processor_id();
 }
 
-static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+static inline const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	return cpu_possible_mask;
 }
 
-static inline bool housekeeping_enabled(enum hk_flags flags)
+static inline bool housekeeping_enabled(enum hk_type type)
 {
 	return false;
 }
 
 static inline void housekeeping_affine(struct task_struct *t,
-				       enum hk_flags flags) { }
+				       enum hk_type type) { }
 static inline void housekeeping_init(void) { }
 #endif /* CONFIG_CPU_ISOLATION */
 
-static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 {
 #ifdef CONFIG_CPU_ISOLATION
 	if (static_branch_unlikely(&housekeeping_overridden))
-		return housekeeping_test_cpu(cpu, flags);
+		return housekeeping_test_cpu(cpu, type);
 #endif
 	return true;
 }
diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h
new file mode 100644
index 000000000000..523a381d6c88
--- /dev/null
+++ b/include/linux/sched/posix-timers.h
@@ -0,0 +1 @@
+#include <linux/posix-timers.h>
diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h
new file mode 100644
index 000000000000..cf2af72693e1
--- /dev/null
+++ b/include/linux/sched/rseq_api.h
@@ -0,0 +1 @@
+#include <linux/rseq.h>
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c19dd5a2c05c..3f2b70f8d32c 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
-#ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
-#endif
-
 extern int sysctl_sched_rr_timeslice;
 extern int sched_rr_timeslice;
 
diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/task_flags.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h
new file mode 100644
index 000000000000..2c60fbc16c08
--- /dev/null
+++ b/include/linux/sched/thread_info_api.h
@@ -0,0 +1 @@
+#include <linux/thread_info.h>
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8054641c0a7b..56cffe42abbc 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -93,6 +93,7 @@ struct sched_domain {
 	unsigned int busy_factor;	/* less balancing by factor if busy */
 	unsigned int imbalance_pct;	/* No balance until over watermark */
 	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int imb_numa_nr;	/* Nr running tasks that allows a NUMA imbalance */
 
 	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 835ee87ed792..cb41c5edb4d4 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -5,6 +5,8 @@
 #ifndef LINUX_SCHED_CLOCK
 #define LINUX_SCHED_CLOCK
 
+#include <linux/types.h>
+
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
 /**
  * struct clock_read_data - data required to read from sched_clock()
diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h
new file mode 100644
index 000000000000..be91e7d3b826
--- /dev/null
+++ b/include/linux/seqlock_api.h
@@ -0,0 +1 @@
+#include <linux/seqlock.h>
diff --git a/include/linux/softirq.h b/include/linux/softirq.h
new file mode 100644
index 000000000000..c73d7dcb4cb5
--- /dev/null
+++ b/include/linux/softirq.h
@@ -0,0 +1 @@
+#include <linux/interrupt.h>
diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h
new file mode 100644
index 000000000000..6338b27f98df
--- /dev/null
+++ b/include/linux/spinlock_api.h
@@ -0,0 +1 @@
+#include <linux/spinlock.h>
diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h
new file mode 100644
index 000000000000..1eeaaaaa5ea7
--- /dev/null
+++ b/include/linux/swait_api.h
@@ -0,0 +1 @@
+#include <linux/swait.h>
diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h
new file mode 100644
index 000000000000..23e012b04db4
--- /dev/null
+++ b/include/linux/syscalls_api.h
@@ -0,0 +1 @@
+#include <linux/syscalls.h>
diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h
new file mode 100644
index 000000000000..c72ca63da44b
--- /dev/null
+++ b/include/linux/u64_stats_sync_api.h
@@ -0,0 +1 @@
+#include <linux/u64_stats_sync.h>
diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h
new file mode 100644
index 000000000000..4e930548935a
--- /dev/null
+++ b/include/linux/wait_api.h
@@ -0,0 +1 @@
+#include <linux/wait.h>
diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h
new file mode 100644
index 000000000000..77debb5d2760
--- /dev/null
+++ b/include/linux/workqueue_api.h
@@ -0,0 +1 @@
+#include <linux/workqueue.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 94640482cfe7..65e786756321 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt,
+					      unsigned int prev_state,
+					      struct task_struct *p)
 {
 	unsigned int state;
 
@@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 	 * it for left shift operation to get the correct task->state
 	 * mapping.
 	 */
-	state = task_state_index(p);
+	state = __task_state_index(prev_state, p->exit_state);
 
 	return state ? (1 << (state - 1)) : state;
 }
@@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 TRACE_EVENT(sched_switch,
 
 	TP_PROTO(bool preempt,
+		 unsigned int prev_state,
 		 struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(preempt, prev, next),
+	TP_ARGS(preempt, prev_state, prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(preempt, prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 9a402fdb60e9..77ee207623a9 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -105,23 +105,11 @@ struct rseq {
 	 * Read and set by the kernel. Set by user-space with single-copy
 	 * atomicity semantics. This field should only be updated by the
 	 * thread which registered this data structure. Aligned on 64-bit.
+	 *
+	 * 32-bit architectures should update the low order bits of the
+	 * rseq_cs field, leaving the high order bits initialized to 0.
 	 */
-	union {
-		__u64 ptr64;
-#ifdef __LP64__
-		__u64 ptr;
-#else
-		struct {
-#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN)
-			__u32 padding;		/* Initialized to zero. */
-			__u32 ptr32;
-#else /* LITTLE */
-			__u32 ptr32;
-			__u32 padding;		/* Initialized to zero. */
-#endif /* ENDIAN */
-		} ptr;
-#endif
-	} rseq_cs;
+	__u64 rseq_cs;
 
 	/*
 	 * Restartable sequences flags field.