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, 27 insertions, 27 deletions

diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 23c378606aed..c8c850bc3dfb 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -122,9 +122,9 @@ ATOMIC_OPS(xor, eor)
 
 #define ATOMIC64_OP(op, asm_op)						\
 __LL_SC_INLINE void							\
-__LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v))		\
+__LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 {									\
-	long result;							\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_" #op "\n"				\
@@ -139,10 +139,10 @@ __LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v))		\
 __LL_SC_EXPORT(arch_atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
-__LL_SC_INLINE long							\
-__LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\
+__LL_SC_INLINE s64							\
+__LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 {									\
-	long result;							\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_" #op "_return" #name "\n"		\
@@ -161,10 +161,10 @@ __LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\
 __LL_SC_EXPORT(arch_atomic64_##op##_return##name);
 
 #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
-__LL_SC_INLINE long							\
-__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v))	\
+__LL_SC_INLINE s64							\
+__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 {									\
-	long result, val;						\
+	s64 result, val;						\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_fetch_" #op #name "\n"		\
@@ -214,10 +214,10 @@ ATOMIC64_OPS(xor, eor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-__LL_SC_INLINE long
+__LL_SC_INLINE s64
 __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
 {
-	long result;
+	s64 result;
 	unsigned long tmp;
 
 	asm volatile("// atomic64_dec_if_positive\n"
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 45e030d54332..69acb1c19a15 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -213,9 +213,9 @@ ATOMIC_FETCH_OP_SUB(        , al, "memory")
 
 #define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(arch_atomic64_##op)
 #define ATOMIC64_OP(op, asm_op)						\
-static inline void arch_atomic64_##op(long i, atomic64_t *v)		\
+static inline void arch_atomic64_##op(s64 i, atomic64_t *v)		\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op),	\
@@ -233,9 +233,9 @@ ATOMIC64_OP(add, stadd)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
-static inline long arch_atomic64_fetch_##op##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -265,9 +265,9 @@ ATOMIC64_FETCH_OPS(add, ldadd)
 #undef ATOMIC64_FETCH_OPS
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
-static inline long arch_atomic64_add_return##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_add_return##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -291,9 +291,9 @@ ATOMIC64_OP_ADD_RETURN(        , al, "memory")
 
 #undef ATOMIC64_OP_ADD_RETURN
 
-static inline void arch_atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	register long x0 asm ("x0") = i;
+	register s64 x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
@@ -309,9 +309,9 @@ static inline void arch_atomic64_and(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
-static inline long arch_atomic64_fetch_and##name(long i, atomic64_t *v)	\
+static inline s64 arch_atomic64_fetch_and##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -335,9 +335,9 @@ ATOMIC64_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_AND
 
-static inline void arch_atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
-	register long x0 asm ("x0") = i;
+	register s64 x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
@@ -353,9 +353,9 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
-static inline long arch_atomic64_sub_return##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_sub_return##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -381,9 +381,9 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 #undef ATOMIC64_OP_SUB_RETURN
 
 #define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
-static inline long arch_atomic64_fetch_sub##name(long i, atomic64_t *v)	\
+static inline s64 arch_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -407,7 +407,7 @@ ATOMIC64_FETCH_OP_SUB(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_SUB
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	register long x0 asm ("x0") = (long)v;