korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-29 23:24:11 +08:00
Code Issues Packages Projects Releases Wiki Activity
1f1475f38b
linux/arch/arm64/include/asm/atomic_ll_sc.h
Linus Torvalds e192832869 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

329 lines
10 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/atomic.h
*
* Copyright (C) 1996 Russell King.
* Copyright (C) 2002 Deep Blue Solutions Ltd.
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_ATOMIC_LL_SC_H
#define __ASM_ATOMIC_LL_SC_H
#ifndef __ARM64_IN_ATOMIC_IMPL
#error "please don't include this file directly"
#endif
/*
* AArch64 UP and SMP safe atomic ops. We use load exclusive and
* store exclusive to ensure that these are atomic. We may loop
* to ensure that the update happens.
*
* NOTE: these functions do *not* follow the PCS and must explicitly
* save any clobbered registers other than x0 (regardless of return
* value). This is achieved through -fcall-saved-* compiler flags for
* this file, which unfortunately don't work on a per-function basis
* (the optimize attribute silently ignores these options).
*/
#define ATOMIC_OP(op, asm_op) \
__LL_SC_INLINE void \
__LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v)) \
{ \
unsigned long tmp; \
int result; \
\
asm volatile("// atomic_" #op "\n" \
" prfm pstl1strm, %2\n" \
"1: ldxr %w0, %2\n" \
" " #asm_op " %w0, %w0, %w3\n" \
" stxr %w1, %w0, %2\n" \
" cbnz %w1, 1b" \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i)); \
} \
__LL_SC_EXPORT(arch_atomic_##op);
#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE int \
__LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v)) \
{ \
unsigned long tmp; \
int result; \
\
asm volatile("// atomic_" #op "_return" #name "\n" \
" prfm pstl1strm, %2\n" \
"1: ld" #acq "xr %w0, %2\n" \
" " #asm_op " %w0, %w0, %w3\n" \
" st" #rel "xr %w1, %w0, %2\n" \
" cbnz %w1, 1b\n" \
" " #mb \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
: cl); \
\
return result; \
} \
__LL_SC_EXPORT(arch_atomic_##op##_return##name);
#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE int \
__LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v)) \
{ \
unsigned long tmp; \
int val, result; \
\
asm volatile("// atomic_fetch_" #op #name "\n" \
" prfm pstl1strm, %3\n" \
"1: ld" #acq "xr %w0, %3\n" \
" " #asm_op " %w1, %w0, %w4\n" \
" st" #rel "xr %w2, %w1, %3\n" \
" cbnz %w2, 1b\n" \
" " #mb \
: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
: cl); \
\
return result; \
} \
__LL_SC_EXPORT(arch_atomic_fetch_##op##name);
#define ATOMIC_OPS(...) \
ATOMIC_OP(__VA_ARGS__) \
ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__)\
ATOMIC_OP_RETURN(_relaxed, , , , , __VA_ARGS__)\
ATOMIC_OP_RETURN(_acquire, , a, , "memory", __VA_ARGS__)\
ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__)\
ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\
ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\
ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\
ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__)
ATOMIC_OPS(add, add)
ATOMIC_OPS(sub, sub)
#undef ATOMIC_OPS
#define ATOMIC_OPS(...) \
ATOMIC_OP(__VA_ARGS__) \
ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\
ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\
ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\
ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__)
ATOMIC_OPS(and, and)
ATOMIC_OPS(andnot, bic)
ATOMIC_OPS(or, orr)
ATOMIC_OPS(xor, eor)
#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
#define ATOMIC64_OP(op, asm_op) \
__LL_SC_INLINE void \
__LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v)) \
{ \
s64 result; \
unsigned long tmp; \
\
asm volatile("// atomic64_" #op "\n" \
" prfm pstl1strm, %2\n" \
"1: ldxr %0, %2\n" \
" " #asm_op " %0, %0, %3\n" \
" stxr %w1, %0, %2\n" \
" cbnz %w1, 1b" \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i)); \
} \
__LL_SC_EXPORT(arch_atomic64_##op);
#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE s64 \
__LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
{ \
s64 result; \
unsigned long tmp; \
\
asm volatile("// atomic64_" #op "_return" #name "\n" \
" prfm pstl1strm, %2\n" \
"1: ld" #acq "xr %0, %2\n" \
" " #asm_op " %0, %0, %3\n" \
" st" #rel "xr %w1, %0, %2\n" \
" cbnz %w1, 1b\n" \
" " #mb \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
: cl); \
\
return result; \
} \
__LL_SC_EXPORT(arch_atomic64_##op##_return##name);
#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE s64 \
__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v)) \
{ \
s64 result, val; \
unsigned long tmp; \
\
asm volatile("// atomic64_fetch_" #op #name "\n" \
" prfm pstl1strm, %3\n" \
"1: ld" #acq "xr %0, %3\n" \
" " #asm_op " %1, %0, %4\n" \
" st" #rel "xr %w2, %1, %3\n" \
" cbnz %w2, 1b\n" \
" " #mb \
: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
: cl); \
\
return result; \
} \
__LL_SC_EXPORT(arch_atomic64_fetch_##op##name);
#define ATOMIC64_OPS(...) \
ATOMIC64_OP(__VA_ARGS__) \
ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__) \
ATOMIC64_OP_RETURN(_relaxed,, , , , __VA_ARGS__) \
ATOMIC64_OP_RETURN(_acquire,, a, , "memory", __VA_ARGS__) \
ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__) \
ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \
ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \
ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \
ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__)
ATOMIC64_OPS(add, add)
ATOMIC64_OPS(sub, sub)
#undef ATOMIC64_OPS
#define ATOMIC64_OPS(...) \
ATOMIC64_OP(__VA_ARGS__) \
ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \
ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \
ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \
ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__)
ATOMIC64_OPS(and, and)
ATOMIC64_OPS(andnot, bic)
ATOMIC64_OPS(or, orr)
ATOMIC64_OPS(xor, eor)
#undef ATOMIC64_OPS
#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
__LL_SC_INLINE s64
__LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
{
s64 result;
unsigned long tmp;
asm volatile("// atomic64_dec_if_positive\n"
" prfm pstl1strm, %2\n"
"1: ldxr %0, %2\n"
" subs %0, %0, #1\n"
" b.lt 2f\n"
" stlxr %w1, %0, %2\n"
" cbnz %w1, 1b\n"
" dmb ish\n"
"2:"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
:
: "cc", "memory");
return result;
}
__LL_SC_EXPORT(arch_atomic64_dec_if_positive);
#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl) \
__LL_SC_INLINE u##sz \
__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \
unsigned long old, \
u##sz new)) \
{ \
unsigned long tmp; \
u##sz oldval; \
\
/* \
* Sub-word sizes require explicit casting so that the compare \
* part of the cmpxchg doesn't end up interpreting non-zero \
* upper bits of the register containing "old". \
*/ \
if (sz < 32) \
old = (u##sz)old; \
\
asm volatile( \
" prfm pstl1strm, %[v]\n" \
"1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \
" eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \
" cbnz %" #w "[tmp], 2f\n" \
" st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \
" cbnz %w[tmp], 1b\n" \
" " #mb "\n" \
"2:" \
: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \
[v] "+Q" (*(u##sz *)ptr) \
: [old] "Kr" (old), [new] "r" (new) \
: cl); \
\
return oldval; \
} \
__LL_SC_EXPORT(__cmpxchg_case_##name##sz);
__CMPXCHG_CASE(w, b, , 8, , , , )
__CMPXCHG_CASE(w, h, , 16, , , , )
__CMPXCHG_CASE(w, , , 32, , , , )
__CMPXCHG_CASE( , , , 64, , , , )
__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory")
__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory")
__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory")
__CMPXCHG_CASE( , , acq_, 64, , a, , "memory")
__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory")
__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory")
__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory")
__CMPXCHG_CASE( , , rel_, 64, , , l, "memory")
__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory")
__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory")
__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory")
__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory")
#undef __CMPXCHG_CASE
#define __CMPXCHG_DBL(name, mb, rel, cl) \
__LL_SC_INLINE long \
__LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1, \
unsigned long old2, \
unsigned long new1, \
unsigned long new2, \
volatile void *ptr)) \
{ \
unsigned long tmp, ret; \
\
asm volatile("// __cmpxchg_double" #name "\n" \
" prfm pstl1strm, %2\n" \
"1: ldxp %0, %1, %2\n" \
" eor %0, %0, %3\n" \
" eor %1, %1, %4\n" \
" orr %1, %0, %1\n" \
" cbnz %1, 2f\n" \
" st" #rel "xp %w0, %5, %6, %2\n" \
" cbnz %w0, 1b\n" \
" " #mb "\n" \
"2:" \
: "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \
: "r" (old1), "r" (old2), "r" (new1), "r" (new2) \
: cl); \
\
return ret; \
} \
__LL_SC_EXPORT(__cmpxchg_double##name);
__CMPXCHG_DBL( , , , )
__CMPXCHG_DBL(_mb, dmb ish, l, "memory")
#undef __CMPXCHG_DBL
#endif /* __ASM_ATOMIC_LL_SC_H */
Reference in New Issue View Git Blame Copy Permalink