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 ...
2019-07-08 16:12:03 -07:00
commit e192832869
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -297,24 +297,24 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)

 #define ATOMIC64_INIT(i)	{ (i) }

-static __inline__ long atomic64_read(const atomic64_t *v)
+static __inline__ s64 atomic64_read(const atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m"(v->counter));

 	return t;
 }

-static __inline__ void atomic64_set(atomic64_t *v, long i)
+static __inline__ void atomic64_set(atomic64_t *v, s64 i)
 {
 	__asm__ __volatile__("std%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i));
 }

 #define ATOMIC64_OP(op, asm_op)						\
-static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
+static __inline__ void atomic64_##op(s64 a, atomic64_t *v)		\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
@@ -327,10 +327,10 @@ static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
 }

 #define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
@@ -345,10 +345,10 @@ atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
 }

 #define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_fetch_##op##_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long res, t;							\
+	s64 res, t;							\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
@@ -396,7 +396,7 @@ ATOMIC64_OPS(xor, xor)

 static __inline__ void atomic64_inc(atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc\n\
@@ -409,9 +409,9 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 }
 #define atomic64_inc atomic64_inc

-static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
@@ -427,7 +427,7 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)

 static __inline__ void atomic64_dec(atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec\n\
@@ -440,9 +440,9 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 }
 #define atomic64_dec atomic64_dec

-static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_dec_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
@@ -463,9 +463,9 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 * Atomically test *v and decrement if it is greater than 0.
 * The function returns the old value of *v minus 1.
 */
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
+static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__(
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -502,9 +502,9 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 * Atomically adds @a to @v, so long as it was not @u.
 * Returns the old value of @v.
 */
-static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long t;
+	s64 t;

 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -534,7 +534,7 @@ static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 */
 static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 {
-	long t1, t2;
+	s64 t1, t2;

 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER