Merge tag 'locking-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - rwsem cleanups & optimizations/fixes:
    - Conditionally wake waiters in reader/writer slowpaths
    - Always try to wake waiters in out_nolock path

 - Add try_cmpxchg64() implementation, with arch optimizations - and use
   it to micro-optimize sched_clock_{local,remote}()

 - Various force-inlining fixes to address objdump instrumentation-check
   warnings

 - Add lock contention tracepoints:

    lock:contention_begin
    lock:contention_end

 - Misc smaller fixes & cleanups

* tag 'locking-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/clock: Use try_cmpxchg64 in sched_clock_{local,remote}
  locking/atomic/x86: Introduce arch_try_cmpxchg64
  locking/atomic: Add generic try_cmpxchg64 support
  futex: Remove a PREEMPT_RT_FULL reference.
  locking/qrwlock: Change "queue rwlock" to "queued rwlock"
  lockdep: Delete local_irq_enable_in_hardirq()
  locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning
  locking: Apply contention tracepoints in the slow path
  locking: Add lock contention tracepoints
  locking/rwsem: Always try to wake waiters in out_nolock path
  locking/rwsem: Conditionally wake waiters in reader/writer slowpaths
  locking/rwsem: No need to check for handoff bit if wait queue empty
  lockdep: Fix -Wunused-parameter for _THIS_IP_
  x86/mm: Force-inline __phys_addr_nodebug()
  x86/kvm/svm: Force-inline GHCB accessors
  task_stack, x86/cea: Force-inline stack helpers

1 files changed, 60 insertions, 3 deletions

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index d7512129a324..9ebd081e057e 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -5,11 +5,22 @@
 #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_LOCK_H
 
-#include <linux/lockdep.h>
+#include <linux/sched.h>
 #include <linux/tracepoint.h>
 
+/* flags for lock:contention_begin */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
+
+
 #ifdef CONFIG_LOCKDEP
 
+#include <linux/lockdep.h>
+
 TRACE_EVENT(lock_acquire,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
@@ -78,8 +89,54 @@ DEFINE_EVENT(lock, lock_acquired,
 	TP_ARGS(lock, ip)
 );
 
-#endif
-#endif
+#endif /* CONFIG_LOCK_STAT */
+#endif /* CONFIG_LOCKDEP */
+
+TRACE_EVENT(contention_begin,
+
+	TP_PROTO(void *lock, unsigned int flags),
+
+	TP_ARGS(lock, flags),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->flags = flags;
+	),
+
+	TP_printk("%p (flags=%s)", __entry->lock_addr,
+		  __print_flags(__entry->flags, "|",
+				{ LCB_F_SPIN,		"SPIN" },
+				{ LCB_F_READ,		"READ" },
+				{ LCB_F_WRITE,		"WRITE" },
+				{ LCB_F_RT,		"RT" },
+				{ LCB_F_PERCPU,		"PERCPU" },
+				{ LCB_F_MUTEX,		"MUTEX" }
+			  ))
+);
+
+TRACE_EVENT(contention_end,
+
+	TP_PROTO(void *lock, int ret),
+
+	TP_ARGS(lock, ret),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->ret = ret;
+	),
+
+	TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
+);
 
 #endif /* _TRACE_LOCK_H */