On Sun, 2012-07-29 at 12:10 +0200, Eric Dumazet wrote:
> You can probably design something needing no more than 4 bytes per cpu,
> and this thing could use non locked operations as bonus.
>
> like the following ...
Coming back from my bike ride, here is a more polished version with
proper synchronization/ barriers.
struct percpu_rw_semaphore {
/* percpu_sem_down_read() use the following in fast path */
unsigned int __percpu *active_counters;
unsigned int __percpu *counters;
struct rw_semaphore sem; /* used in slow path and by writers */
};
static inline int percpu_sem_init(struct percpu_rw_semaphore *p)
{
p->counters = alloc_percpu(unsigned int);
if (!p->counters)
return -ENOMEM;
init_rwsem(&p->sem);
rcu_assign_pointer(p->active_counters, p->counters);
return 0;
}
static inline bool percpu_sem_down_read(struct percpu_rw_semaphore *p)
{
unsigned int __percpu *counters;
rcu_read_lock();
counters = rcu_dereference(p->active_counters);
if (counters) {
this_cpu_inc(*counters);
smp_wmb(); /* paired with smp_rmb() in percpu_count() */
rcu_read_unlock();
return true;
}
rcu_read_unlock();
down_read(&p->sem);
return false;
}
static inline void percpu_sem_up_read(struct percpu_rw_semaphore *p, bool fastpath)
{
if (fastpath)
this_cpu_dec(*p->counters);
else
up_read(&p->sem);
}
static inline unsigned int percpu_count(unsigned int __percpu *counters)
{
unsigned int total = 0;
int cpu;
for_each_possible_cpu(cpu)
total += *per_cpu_ptr(counters, cpu);
return total;
}
static inline void percpu_sem_down_write(struct percpu_rw_semaphore *p)
{
down_write(&p->sem);
p->active_counters = NULL;
synchronize_rcu();
smp_rmb(); /* paired with smp_wmb() in percpu_sem_down_read() */
while (percpu_count(p->counters))
schedule();
}
static inline void percpu_sem_up_write(struct percpu_rw_semaphore *p)
{
rcu_assign_pointer(p->active_counters, p->counters);
up_write(&p->sem);
}
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel
