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, 16 insertions, 2 deletions

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 5e3585950ec8..d973fe6041bf 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -30,6 +30,9 @@
 #include <linux/debug_locks.h>
 #include <linux/osq_lock.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/lock.h>
+
 #ifndef CONFIG_PREEMPT_RT
 #include "mutex.h"
 
@@ -599,12 +602,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
+	trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
 	if (__mutex_trylock(lock) ||
 	    mutex_optimistic_spin(lock, ww_ctx, NULL)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
 		if (ww_ctx)
 			ww_mutex_set_context_fastpath(ww, ww_ctx);
+		trace_contention_end(lock, 0);
 		preempt_enable();
 		return 0;
 	}
@@ -641,6 +646,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 
 	set_current_state(state);
+	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
 		bool first;
 
@@ -680,10 +686,16 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		 * state back to RUNNING and fall through the next schedule(),
 		 * or we must see its unlock and acquire.
 		 */
-		if (__mutex_trylock_or_handoff(lock, first) ||
-		    (first && mutex_optimistic_spin(lock, ww_ctx, &waiter)))
+		if (__mutex_trylock_or_handoff(lock, first))
 			break;
 
+		if (first) {
+			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
+				break;
+			trace_contention_begin(lock, LCB_F_MUTEX);
+		}
+
 		raw_spin_lock(&lock->wait_lock);
 	}
 	raw_spin_lock(&lock->wait_lock);
@@ -707,6 +719,7 @@ acquired:
 skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
+	trace_contention_end(lock, 0);
 
 	if (ww_ctx)
 		ww_mutex_lock_acquired(ww, ww_ctx);
@@ -719,6 +732,7 @@ err:
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
+	trace_contention_end(lock, ret);
 	raw_spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, ip);