android_kernel_xiaomi_sm8350/include/linux/percpu-rwsem.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

139 lines
3.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PERCPU_RWSEM_H
#define _LINUX_PERCPU_RWSEM_H
#include <linux/atomic.h>
#include <linux/rwsem.h>
#include <linux/percpu.h>
#include <linux/rcuwait.h>
#include <linux/rcu_sync.h>
#include <linux/lockdep.h>
struct percpu_rw_semaphore {
struct rcu_sync rss;
unsigned int __percpu *read_count;
struct rw_semaphore rw_sem; /* slowpath */
struct rcuwait writer; /* blocked writer */
int readers_block;
};
#define __DEFINE_PERCPU_RWSEM(name, is_static) \
static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \
is_static struct percpu_rw_semaphore name = { \
.rss = __RCU_SYNC_INITIALIZER(name.rss), \
.read_count = &__percpu_rwsem_rc_##name, \
.rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \
.writer = __RCUWAIT_INITIALIZER(name.writer), \
}
#define DEFINE_PERCPU_RWSEM(name) \
__DEFINE_PERCPU_RWSEM(name, /* not static */)
#define DEFINE_STATIC_PERCPU_RWSEM(name) \
__DEFINE_PERCPU_RWSEM(name, static)
extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
extern void __percpu_up_read(struct percpu_rw_semaphore *);
static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
{
might_sleep();
rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_);
preempt_disable();
/*
* We are in an RCU-sched read-side critical section, so the writer
* cannot both change sem->state from readers_fast and start checking
* counters while we are here. So if we see !sem->state, we know that
* the writer won't be checking until we're past the preempt_enable()
* and that once the synchronize_rcu() is done, the writer will see
* anything we did within this RCU-sched read-size critical section.
*/
__this_cpu_inc(*sem->read_count);
if (unlikely(!rcu_sync_is_idle(&sem->rss)))
__percpu_down_read(sem, false); /* Unconditional memory barrier */
/*
* The preempt_enable() prevents the compiler from
* bleeding the critical section out.
*/
preempt_enable();
}
static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
{
int ret = 1;
preempt_disable();
/*
* Same as in percpu_down_read().
*/
__this_cpu_inc(*sem->read_count);
if (unlikely(!rcu_sync_is_idle(&sem->rss)))
ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
preempt_enable();
/*
* The barrier() from preempt_enable() prevents the compiler from
* bleeding the critical section out.
*/
if (ret)
rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_);
return ret;
}
static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
{
preempt_disable();
/*
* Same as in percpu_down_read().
*/
if (likely(rcu_sync_is_idle(&sem->rss)))
__this_cpu_dec(*sem->read_count);
else
__percpu_up_read(sem); /* Unconditional memory barrier */
preempt_enable();
rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);
}
extern void percpu_down_write(struct percpu_rw_semaphore *);
extern void percpu_up_write(struct percpu_rw_semaphore *);
extern int __percpu_init_rwsem(struct percpu_rw_semaphore *,
const char *, struct lock_class_key *);
extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
#define percpu_init_rwsem(sem) \
({ \
static struct lock_class_key rwsem_key; \
__percpu_init_rwsem(sem, #sem, &rwsem_key); \
})
#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
#define percpu_rwsem_assert_held(sem) \
lockdep_assert_held(&(sem)->rw_sem)
static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
lock_release(&sem->rw_sem.dep_map, 1, ip);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
if (!read)
atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
#endif
}
static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
if (!read)
atomic_long_set(&sem->rw_sem.owner, (long)current);
#endif
}
#endif