summaryrefslogtreecommitdiff
path: root/arch/arc
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-08 16:12:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-08 16:12:03 -0700
commite1928328699a582a540b105e5f4c160832a7fdcb (patch)
treef36bb303b8648189d7b5a7feb27e58fe9fe3b9f0 /arch/arc
parent46f1ec23a46940846f86a91c46f7119d8a8b5de1 (diff)
parent9156e545765e467e6268c4814cfa609ebb16237e (diff)
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 ...
Diffstat (limited to 'arch/arc')
-rw-r--r--arch/arc/include/asm/atomic.h41
1 files changed, 20 insertions, 21 deletions
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 17cf1c657cb3..7298ce84762e 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -321,14 +321,14 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
*/
typedef struct {
- aligned_u64 counter;
+ s64 __aligned(8) counter;
} atomic64_t;
#define ATOMIC64_INIT(a) { (a) }
-static inline long long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
{
- unsigned long long val;
+ s64 val;
__asm__ __volatile__(
" ldd %0, [%1] \n"
@@ -338,7 +338,7 @@ static inline long long atomic64_read(const atomic64_t *v)
return val;
}
-static inline void atomic64_set(atomic64_t *v, long long a)
+static inline void atomic64_set(atomic64_t *v, s64 a)
{
/*
* This could have been a simple assignment in "C" but would need
@@ -359,9 +359,9 @@ static inline void atomic64_set(atomic64_t *v, long long a)
}
#define ATOMIC64_OP(op, op1, op2) \
-static inline void atomic64_##op(long long a, atomic64_t *v) \
+static inline void atomic64_##op(s64 a, atomic64_t *v) \
{ \
- unsigned long long val; \
+ s64 val; \
\
__asm__ __volatile__( \
"1: \n" \
@@ -372,13 +372,13 @@ static inline void atomic64_##op(long long a, atomic64_t *v) \
" bnz 1b \n" \
: "=&r"(val) \
: "r"(&v->counter), "ir"(a) \
- : "cc"); \
+ : "cc"); \
} \
#define ATOMIC64_OP_RETURN(op, op1, op2) \
-static inline long long atomic64_##op##_return(long long a, atomic64_t *v) \
+static inline s64 atomic64_##op##_return(s64 a, atomic64_t *v) \
{ \
- unsigned long long val; \
+ s64 val; \
\
smp_mb(); \
\
@@ -399,9 +399,9 @@ static inline long long atomic64_##op##_return(long long a, atomic64_t *v) \
}
#define ATOMIC64_FETCH_OP(op, op1, op2) \
-static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \
+static inline s64 atomic64_fetch_##op(s64 a, atomic64_t *v) \
{ \
- unsigned long long val, orig; \
+ s64 val, orig; \
\
smp_mb(); \
\
@@ -441,10 +441,10 @@ ATOMIC64_OPS(xor, xor, xor)
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
-static inline long long
-atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
+static inline s64
+atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
{
- long long prev;
+ s64 prev;
smp_mb();
@@ -464,9 +464,9 @@ atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
return prev;
}
-static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+static inline s64 atomic64_xchg(atomic64_t *ptr, s64 new)
{
- long long prev;
+ s64 prev;
smp_mb();
@@ -492,9 +492,9 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
* the atomic variable, v, was not decremented.
*/
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 atomic64_dec_if_positive(atomic64_t *v)
{
- long long val;
+ s64 val;
smp_mb();
@@ -525,10 +525,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
* Atomically adds @a to @v, if it was not @u.
* Returns the old value of @v
*/
-static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
- long long u)
+static inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
- long long old, temp;
+ s64 old, temp;
smp_mb();