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().

6 files changed, 46 insertions, 30 deletions

diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index f4c3470480c7..2a19215baae5 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -6,15 +6,22 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifndef futex_atomic_cmpxchg_inatomic
 #ifndef CONFIG_SMP
 /*
  * The following implementation only for uniprocessor machines.
  * It relies on preempt_disable() ensuring mutual exclusion.
  *
  */
+#define futex_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval) \
+	futex_atomic_cmpxchg_inatomic_local(uval, uaddr, oldval, newval)
+#define arch_futex_atomic_op_inuser(op, oparg, oval, uaddr) \
+	futex_atomic_op_inuser_local(op, oparg, oval, uaddr)
+#endif /* CONFIG_SMP */
+#endif
 
 /**
- * arch_futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ * futex_atomic_op_inuser_local() - Atomic arithmetic operation with constant
  *			  argument and comparison of the previous
  *			  futex value with another constant.
  *
@@ -28,7 +35,7 @@
  * -ENOSYS - Operation not supported
  */
 static inline int
-arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
+futex_atomic_op_inuser_local(int op, u32 oparg, int *oval, u32 __user *uaddr)
 {
 	int oldval, ret;
 	u32 tmp;
@@ -75,7 +82,7 @@ out_pagefault_enable:
 }
 
 /**
- * futex_atomic_cmpxchg_inatomic() - Compare and exchange the content of the
+ * futex_atomic_cmpxchg_inatomic_local() - Compare and exchange the content of the
  *				uaddr with newval if the current value is
  *				oldval.
  * @uval:	pointer to store content of @uaddr
@@ -87,10 +94,9 @@ out_pagefault_enable:
  * 0 - On success
  * -EFAULT - User access resulted in a page fault
  * -EAGAIN - Atomic operation was unable to complete due to contention
- * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG)
  */
 static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+futex_atomic_cmpxchg_inatomic_local(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
 	u32 val;
@@ -112,19 +118,4 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	return 0;
 }
 
-#else
-static inline int
-arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
-{
-	return -ENOSYS;
-}
-
-static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_SMP */
 #endif
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 600c10da321a..4b140938b03e 100644
--- a/include/linux/irqflags.h
+++ b/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);
diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h
index b676aa419eef..c21c7f8103e2 100644
--- a/include/linux/ratelimit_types.h
+++ b/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
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 9deedfeec2b1..7d049883a08a 100644
--- a/include/linux/rtmutex.h
+++ b/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);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4d0a12618e3c..7a1f16df66e3 100644
--- a/include/linux/sched.h
+++ b/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 */
diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h
index c09b6407ae1b..7f86a2016ac5 100644
--- a/include/linux/spinlock_types_up.h
+++ b/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