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, 23 insertions, 21 deletions

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 9038aeb900a6..96f95c9ebd97 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -38,11 +38,11 @@ static __always_inline void atomic_set(atomic_t *v, int i)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC64_INIT(i) { (i) }
-static __always_inline long atomic64_read(const atomic64_t *v)
+static __always_inline s64 atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE(v->counter);
 }
-static __always_inline void atomic64_set(atomic64_t *v, long i)
+static __always_inline void atomic64_set(atomic64_t *v, s64 i)
 {
 	WRITE_ONCE(v->counter, i);
 }
@@ -66,11 +66,11 @@ void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_OP (op, asm_op, I, w,  int,   )
+        ATOMIC_OP (op, asm_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_OP (op, asm_op, I, w,  int,   )				\
-        ATOMIC_OP (op, asm_op, I, d, long, 64)
+        ATOMIC_OP (op, asm_op, I, w, int,   )				\
+        ATOMIC_OP (op, asm_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(add, add,  i)
@@ -127,14 +127,14 @@ c_type atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v)	\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )		\
-        ATOMIC_FETCH_OP( op, asm_op,       I, d, long, 64)		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, long, 64)
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )		\
+        ATOMIC_FETCH_OP( op, asm_op,       I, d, s64, 64)		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(add, add, +,  i)
@@ -166,11 +166,11 @@ ATOMIC_OPS(sub, add, +, -i)
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )			\
-        ATOMIC_FETCH_OP(op, asm_op, I, d, long, 64)
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )			\
+        ATOMIC_FETCH_OP(op, asm_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(and, and, i)
@@ -219,9 +219,10 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-       long prev, rc;
+       s64 prev;
+       long rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.d     %[p],  %[c]\n"
@@ -290,11 +291,11 @@ c_t atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n)	\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS()							\
-	ATOMIC_OP( int,   , 4)
+	ATOMIC_OP(int,   , 4)
 #else
 #define ATOMIC_OPS()							\
-	ATOMIC_OP( int,   , 4)						\
-	ATOMIC_OP(long, 64, 8)
+	ATOMIC_OP(int,   , 4)						\
+	ATOMIC_OP(s64, 64, 8)
 #endif
 
 ATOMIC_OPS()
@@ -332,9 +333,10 @@ static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(v, 1)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_sub_if_positive(atomic64_t *v, int offset)
+static __always_inline s64 atomic64_sub_if_positive(atomic64_t *v, s64 offset)
 {
-       long prev, rc;
+       s64 prev;
+       long rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.d     %[p],  %[c]\n"