[dm-devel] [PATCH 2/3] Introduce percpu rw semaphores

[Eric Dumazet]

On Sun, 2012-07-29 at 01:13 -0400, Mikulas Patocka wrote:

> Each cpu should have its own rw semaphore in its cache, so I don't see a 
> problem there.
> 
> When you change block size, all 4096 rw semaphores are locked for write, 
> but changing block size is not a performance sensitive operation.
> 
> > Really you shouldnt use rwlock in a path if this might hurt performance.
> > 
> > RCU is probably a better answer.
> 
> RCU is meaningless here. RCU allows lockless dereference of a pointer. 
> Here the problem is not pointer dereference, the problem is that integer 
> bd_block_size may change.

So add a pointer if you need to. Thats the point.

> 
> > (bdev->bd_block_size should be read exactly once )
> 
> Rewrite all direct and non-direct io code so that it reads block size just 
> once ...


You introduced percpu rw semaphores, thats only incentive for people to
use that infrastructure elsewhere.

And its a big hammer :

sizeof(struct rw_semaphore)=0x70 

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 ...

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);
	p->active_counters = p->counters;
	return 0;
}


static inline bool percpu_sem_down_read(struct percpu_rw_semaphore *p)
{
	unsigned int __percpu *counters = ACCESS_ONCE(p->active_counters);

	if (counters) {
		this_cpu_inc(*counters);
		return true;
	}
	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 *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;

	while (percpu_count(p->counters))
		schedule();
}

static inline void percpu_sem_up_write(struct percpu_rw_semaphore *p)
{
	p->active_counters = p->counters;
	up_write(&p->sem);
}