Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - rwsem scalability improvements, phase #2, by Waiman Long, which are
     rather impressive:

       "On a 2-socket 40-core 80-thread Skylake system with 40 reader
        and writer locking threads, the min/mean/max locking operations
        done in a 5-second testing window before the patchset were:

         40 readers, Iterations Min/Mean/Max = 1,807/1,808/1,810
         40 writers, Iterations Min/Mean/Max = 1,807/50,344/151,255

        After the patchset, they became:

         40 readers, Iterations Min/Mean/Max = 30,057/31,359/32,741
         40 writers, Iterations Min/Mean/Max = 94,466/95,845/97,098"

     There's a lot of changes to the locking implementation that makes
     it similar to qrwlock, including owner handoff for more fair
     locking.

     Another microbenchmark shows how across the spectrum the
     improvements are:

       "With a locking microbenchmark running on 5.1 based kernel, the
        total locking rates (in kops/s) on a 2-socket Skylake system
        with equal numbers of readers and writers (mixed) before and
        after this patchset were:

        # of Threads   Before Patch      After Patch
        ------------   ------------      -----------
             2            2,618             4,193
             4            1,202             3,726
             8              802             3,622
            16              729             3,359
            32              319             2,826
            64              102             2,744"

     The changes are extensive and the patch-set has been through
     several iterations addressing various locking workloads. There
     might be more regressions, but unless they are pathological I
     believe we want to use this new implementation as the baseline
     going forward.

   - jump-label optimizations by Daniel Bristot de Oliveira: the primary
     motivation was to remove IPI disturbance of isolated RT-workload
     CPUs, which resulted in the implementation of batched jump-label
     updates. Beyond the improvement of the real-time characteristics
     kernel, in one test this patchset improved static key update
     overhead from 57 msecs to just 1.4 msecs - which is a nice speedup
     as well.

   - atomic64_t cross-arch type cleanups by Mark Rutland: over the last
     ~10 years of atomic64_t existence the various types used by the
     APIs only had to be self-consistent within each architecture -
     which means they became wildly inconsistent across architectures.
     Mark puts and end to this by reworking all the atomic64
     implementations to use 's64' as the base type for atomic64_t, and
     to ensure that this type is consistently used for parameters and
     return values in the API, avoiding further problems in this area.

   - A large set of small improvements to lockdep by Yuyang Du: type
     cleanups, output cleanups, function return type and othr cleanups
     all around the place.

   - A set of percpu ops cleanups and fixes by Peter Zijlstra.

   - Misc other changes - please see the Git log for more details"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  locking/lockdep: increase size of counters for lockdep statistics
  locking/atomics: Use sed(1) instead of non-standard head(1) option
  locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING
  x86/jump_label: Make tp_vec_nr static
  x86/percpu: Optimize raw_cpu_xchg()
  x86/percpu, sched/fair: Avoid local_clock()
  x86/percpu, x86/irq: Relax {set,get}_irq_regs()
  x86/percpu: Relax smp_processor_id()
  x86/percpu: Differentiate this_cpu_{}() and __this_cpu_{}()
  locking/rwsem: Guard against making count negative
  locking/rwsem: Adaptive disabling of reader optimistic spinning
  locking/rwsem: Enable time-based spinning on reader-owned rwsem
  locking/rwsem: Make rwsem->owner an atomic_long_t
  locking/rwsem: Enable readers spinning on writer
  locking/rwsem: Clarify usage of owner's nonspinaable bit
  locking/rwsem: Wake up almost all readers in wait queue
  locking/rwsem: More optimal RT task handling of null owner
  locking/rwsem: Always release wait_lock before waking up tasks
  locking/rwsem: Implement lock handoff to prevent lock starvation
  locking/rwsem: Make rwsem_spin_on_owner() return owner state
  ...

2 files changed, 20 insertions, 20 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 6629cab453e8..06d9c9d70385 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1095,7 +1095,7 @@ config PROVE_LOCKING
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
-	select DEBUG_RWSEMS if RWSEM_SPIN_ON_OWNER
+	select DEBUG_RWSEMS
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
 	select TRACE_IRQFLAGS
@@ -1199,10 +1199,10 @@ config DEBUG_WW_MUTEX_SLOWPATH
 
 config DEBUG_RWSEMS
 	bool "RW Semaphore debugging: basic checks"
-	depends on DEBUG_KERNEL && RWSEM_SPIN_ON_OWNER
+	depends on DEBUG_KERNEL
 	help
-	  This debugging feature allows mismatched rw semaphore locks and unlocks
-	  to be detected and reported.
+	  This debugging feature allows mismatched rw semaphore locks
+	  and unlocks to be detected and reported.
 
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 7e6905751522..e98c85a99787 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -42,11 +42,11 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 	return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
 }
 
-long long atomic64_read(const atomic64_t *v)
+s64 atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -55,7 +55,7 @@ long long atomic64_read(const atomic64_t *v)
 }
 EXPORT_SYMBOL(atomic64_read);
 
-void atomic64_set(atomic64_t *v, long long i)
+void atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -67,7 +67,7 @@ void atomic64_set(atomic64_t *v, long long i)
 EXPORT_SYMBOL(atomic64_set);
 
 #define ATOMIC64_OP(op, c_op)						\
-void atomic64_##op(long long a, atomic64_t *v)				\
+void atomic64_##op(s64 a, atomic64_t *v)				\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
@@ -79,11 +79,11 @@ void atomic64_##op(long long a, atomic64_t *v)				\
 EXPORT_SYMBOL(atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(op, c_op)					\
-long long atomic64_##op##_return(long long a, atomic64_t *v)		\
+s64 atomic64_##op##_return(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
-	long long val;							\
+	s64 val;							\
 									\
 	raw_spin_lock_irqsave(lock, flags);				\
 	val = (v->counter c_op a);					\
@@ -93,11 +93,11 @@ long long atomic64_##op##_return(long long a, atomic64_t *v)		\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
 #define ATOMIC64_FETCH_OP(op, c_op)					\
-long long atomic64_fetch_##op(long long a, atomic64_t *v)		\
+s64 atomic64_fetch_##op(s64 a, atomic64_t *v)				\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
-	long long val;							\
+	s64 val;							\
 									\
 	raw_spin_lock_irqsave(lock, flags);				\
 	val = v->counter;						\
@@ -130,11 +130,11 @@ ATOMIC64_OPS(xor, ^=)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-long long atomic64_dec_if_positive(atomic64_t *v)
+s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter - 1;
@@ -145,11 +145,11 @@ long long atomic64_dec_if_positive(atomic64_t *v)
 }
 EXPORT_SYMBOL(atomic64_dec_if_positive);
 
-long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -160,11 +160,11 @@ long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
 }
 EXPORT_SYMBOL(atomic64_cmpxchg);
 
-long long atomic64_xchg(atomic64_t *v, long long new)
+s64 atomic64_xchg(atomic64_t *v, s64 new)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -174,11 +174,11 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
+s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;