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
  ...

1 files changed, 19 insertions, 19 deletions

diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index fd20ab5d4cf7..491ad53a0d4e 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -84,9 +84,9 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 
 #define ATOMIC64_INIT(i)  { (i) }
 
-static inline long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
 {
-	long c;
+	s64 c;
 
 	asm volatile(
 		"	lg	%0,%1\n"
@@ -94,49 +94,49 @@ static inline long atomic64_read(const atomic64_t *v)
 	return c;
 }
 
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void atomic64_set(atomic64_t *v, s64 i)
 {
 	asm volatile(
 		"	stg	%1,%0\n"
 		: "=Q" (v->counter) : "d" (i));
 }
 
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static inline s64 atomic64_add_return(s64 i, atomic64_t *v)
 {
-	return __atomic64_add_barrier(i, &v->counter) + i;
+	return __atomic64_add_barrier(i, (long *)&v->counter) + i;
 }
 
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	return __atomic64_add_barrier(i, &v->counter);
+	return __atomic64_add_barrier(i, (long *)&v->counter);
 }
 
-static inline void atomic64_add(long i, atomic64_t *v)
+static inline void atomic64_add(s64 i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
-		__atomic64_add_const(i, &v->counter);
+		__atomic64_add_const(i, (long *)&v->counter);
 		return;
 	}
 #endif
-	__atomic64_add(i, &v->counter);
+	__atomic64_add(i, (long *)&v->counter);
 }
 
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
-	return __atomic64_cmpxchg(&v->counter, old, new);
+	return __atomic64_cmpxchg((long *)&v->counter, old, new);
 }
 
 #define ATOMIC64_OPS(op)						\
-static inline void atomic64_##op(long i, atomic64_t *v)			\
+static inline void atomic64_##op(s64 i, atomic64_t *v)			\
 {									\
-	__atomic64_##op(i, &v->counter);				\
+	__atomic64_##op(i, (long *)&v->counter);			\
 }									\
-static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+static inline long atomic64_fetch_##op(s64 i, atomic64_t *v)		\
 {									\
-	return __atomic64_##op##_barrier(i, &v->counter);		\
+	return __atomic64_##op##_barrier(i, (long *)&v->counter);	\
 }
 
 ATOMIC64_OPS(and)
@@ -145,8 +145,8 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
-#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
-#define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
+#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(s64)(_i), _v)
+#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(s64)(_i), _v)
+#define atomic64_sub(_i, _v)		atomic64_add(-(s64)(_i), _v)
 
 #endif /* __ARCH_S390_ATOMIC__  */