Peter Zijlstra says:

"Lots of cleanups and preparation; highlights:
 
  - futex: Cleanup and remove runtime futex_cmpxchg detection
 
  - rtmutex: Some fixes for the PREEMPT_RT locking infrastructure
 
  - kcsan: Share owner_on_cpu() between mutex,rtmutex and rwsem and
    annotate the racy owner->on_cpu access *once*.
 
  - atomic64: Dead-Code-Elemination"
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmHdvssACgkQEsHwGGHe
 VUrbBg//VQvz5BwddIJDj9utt5AvSixNcTF5mJyFKCSIqO0S4J8nCNcvJjZ2bs4S
 w1YmInFbp0WFGUhaIZiw0e6KWJUoINTng4MfHDZosS1doT2of53ZaQqXs3i81jDz
 87w8ADVHL0x4+BNjdsIwbcuPSDTmJFoyFOdeXTIl9hv9ZULT8m4Mt+LJuUHNZ+vF
 rS1jyseVPWkcm5y+Yie0rhip+ygzbfbt0ArsLfRcrBJsKr6oxLxV2DDF+2djXuuP
 d2OgGT7VkbgAhoKpzVXUiHsT6ppR5Mn5TLSa4EZ4bPPCUFldOhKuCAImF3T6yVIa
 44iX5vQN9v5VHBy6ocPbdOIBuYBYVGCMurh1t7pbpB6G+mmSxMiyta5MY37POwjv
 K2JT9mC2A6a4d17gue5FT3mnJMBB4eHwVaDfAwCZs/5rRNuoTz4aY5Xy04Mq0ltI
 39uarwBd5hwSugBWg44AS5E9h52E654FQ7g6iS4NtUvJuuaXBTl43EcZWx2+mnPL
 zY+iOMVMgg33VIVcm/mlf/6zWL0LXPmILUiA1fp4Q9/n8u1EuOOyeA/GsC9Pl3wO
 HY3KpYJA5eQpIk/JEnzKm5ZE3pCrUdH6VDC/SB4owQtafQG6OxyQVP1Gj7KYxZsD
 NqqpJ4nkKooc5f5DqVEN8wrjyYsnVxEfriEG09OoR6wI3MqyUA4=
 =vrYy
 -----END PGP SIGNATURE-----

Merge tag 'locking_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Borislav Petkov:
 "Lots of cleanups and preparation. Highlights:

   - futex: Cleanup and remove runtime futex_cmpxchg detection

   - rtmutex: Some fixes for the PREEMPT_RT locking infrastructure

   - kcsan: Share owner_on_cpu() between mutex,rtmutex and rwsem and
     annotate the racy owner->on_cpu access *once*.

   - atomic64: Dead-Code-Elemination"

[ Description above by Peter Zijlstra ]

* tag 'locking_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/atomic: atomic64: Remove unusable atomic ops
  futex: Fix additional regressions
  locking: Allow to include asm/spinlock_types.h from linux/spinlock_types_raw.h
  x86/mm: Include spinlock_t definition in pgtable.
  locking: Mark racy reads of owner->on_cpu
  locking: Make owner_on_cpu() into <linux/sched.h>
  lockdep/selftests: Adapt ww-tests for PREEMPT_RT
  lockdep/selftests: Skip the softirq related tests on PREEMPT_RT
  lockdep/selftests: Unbalanced migrate_disable() & rcu_read_lock().
  lockdep/selftests: Avoid using local_lock_{acquire|release}().
  lockdep: Remove softirq accounting on PREEMPT_RT.
  locking/rtmutex: Add rt_mutex_lock_nest_lock() and rt_mutex_lock_killable().
  locking/rtmutex: Squash self-deadlock check for ww_rt_mutex.
  locking: Remove rt_rwlock_is_contended().
  sched: Trigger warning if ->migration_disabled counter underflows.
  futex: Fix sparc32/m68k/nds32 build regression
  futex: Remove futex_cmpxchg detection
  futex: Ensure futex_atomic_cmpxchg_inatomic() is present
  kernel/locking: Use a pointer in ww_mutex_trylock().

include/linux/irqflags.h

@@ -71,14 +71,6 @@ do {						\
 do {						\
 	__this_cpu_dec(hardirq_context);	\
 } while (0)
-# define lockdep_softirq_enter()		\
-do {						\
-	current->softirq_context++;		\
-} while (0)
-# define lockdep_softirq_exit()			\
-do {						\
-	current->softirq_context--;		\
-} while (0)
 
 # define lockdep_hrtimer_enter(__hrtimer)		\
 ({							\
@@ -140,6 +132,21 @@ do {						\
 # define lockdep_irq_work_exit(__work)		do { } while (0)
 #endif
 
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT)
+# define lockdep_softirq_enter()		\
+do {						\
+	current->softirq_context++;		\
+} while (0)
+# define lockdep_softirq_exit()			\
+do {						\
+	current->softirq_context--;		\
+} while (0)
+
+#else
+# define lockdep_softirq_enter()		do { } while (0)
+# define lockdep_softirq_exit()			do { } while (0)
+#endif
+
 #if defined(CONFIG_IRQSOFF_TRACER) || \
 	defined(CONFIG_PREEMPT_TRACER)
  extern void stop_critical_timings(void);

include/linux/ratelimit_types.h

@@ -4,7 +4,7 @@
 
 #include <linux/bits.h>
 #include <linux/param.h>
-#include <linux/spinlock_types.h>
+#include <linux/spinlock_types_raw.h>
 
 #define DEFAULT_RATELIMIT_INTERVAL	(5 * HZ)
 #define DEFAULT_RATELIMIT_BURST		10

include/linux/rtmutex.h

@@ -99,13 +99,22 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass);
+extern void _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock);
 #define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0)
+#define rt_mutex_lock_nest_lock(lock, nest_lock)			\
+	do {								\
+		typecheck(struct lockdep_map *, &(nest_lock)->dep_map);	\
+		_rt_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);	\
+	} while (0)
+
 #else
 extern void rt_mutex_lock(struct rt_mutex *lock);
 #define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock)
+#define rt_mutex_lock_nest_lock(lock, nest_lock) rt_mutex_lock(lock)
 #endif
 
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 
 extern void rt_mutex_unlock(struct rt_mutex *lock);

include/linux/sched.h

@@ -2178,6 +2178,15 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #endif
 
 #ifdef CONFIG_SMP
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner));
+}
+
 /* Returns effective CPU energy utilization, as seen by the scheduler */
 unsigned long sched_cpu_util(int cpu, unsigned long max);
 #endif /* CONFIG_SMP */

include/linux/spinlock_types_up.h

@@ -1,7 +1,7 @@
 #ifndef __LINUX_SPINLOCK_TYPES_UP_H
 #define __LINUX_SPINLOCK_TYPES_UP_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
 # error "please don't include this file directly"
 #endif