/*
* padata.c - generic interface to process data streams in parallel
*
* See Documentation/padata.txt for an api documentation.
*
* Copyright (C) 2008, 2009 secunet Security Networks AG
* Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include <linux/export.h>
#include <linux/cpumask.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/padata.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
#define MAX_OBJ_NUM 1000
static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
{
int cpu, target_cpu;
target_cpu = cpumask_first(pd->cpumask.pcpu);
for (cpu = 0; cpu < cpu_index; cpu++)
target_cpu = cpumask_next(target_cpu, pd->cpumask.pcpu);
return target_cpu;
}
static int padata_cpu_hash(struct parallel_data *pd)
{
unsigned int seq_nr;
int cpu_index;
/*
* Hash the sequence numbers to the cpus by taking
* seq_nr mod. number of cpus in use.
*/
seq_nr = atomic_inc_return(&pd->seq_nr);
cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu);
return padata_index_to_cpu(pd, cpu_index);
}
static void padata_parallel_worker(struct work_struct *parallel_work)
{
struct padata_parallel_queue *pqueue;
LIST_HEAD(local_list);
local_bh_disable();
pqueue = container_of(parallel_work,
struct padata_parallel_queue, work);
spin_lock(&pqueue->parallel.lock);
list_replace_init(&pqueue->parallel.list, &local_list);
spin_unlock(&pqueue->parallel.lock);
while (!list_empty(&local_list)) {
struct padata_priv *padata;
padata = list_entry(local_list.next,
struct padata_priv, list);
list_del_init(&padata->list);
padata->parallel(padata);
}
local_bh_enable();
}
/**
* padata_do_parallel - padata parallelization function
*
* @pinst: padata instance
* @padata: object to be parallelized
* @cb_cpu: cpu the serialization callback function will run on,
* must be in the serial cpumask of padata(i.e. cpumask.cbcpu).
*
* The parallelization callback function will run with BHs off.
* Note: Every object which is parallelized by padata_do_parallel
* must be seen by padata_do_serial.
*/
int padata_do_parallel(struct padata_instance *pinst,
struct padata_priv *padata, int cb_cpu)
{
int target_cpu, err;
struct padata_parallel_queue *queue;
struct parallel_data *pd;
rcu_read_lock_bh();
pd = rcu_dereference_bh(pinst->pd);
err = -EINVAL;
if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
goto out;
if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu))
goto out;
err = -EBUSY;
if ((pinst->flags & PADATA_RESET))
goto out;
if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
goto out;
err = 0;
atomic_inc(&pd->refcnt);
padata->pd = pd;
padata->cb_cpu = cb_cpu;
target_cpu = padata_cpu_hash(pd);
queue = per_cpu_ptr(pd->pqueue, target_cpu);
spin_lock(&queue->parallel.lock);
list_add_tail(&padata->list, &queue->parallel.list);
spin_unlock(&queue->parallel.lock);
queue_work_on(target_cpu, pinst->wq, &queue->work);
out:
rcu_read_unlock_bh();
return err;
}
EXPORT_SYMBOL(padata_do_parallel);
/*
* padata_get_next - Get the next object that needs serialization.
*
* Return values are:
*
* A pointer to the control struct of the next object that needs
* serialization, if present in one of the percpu reorder queues.
*
* NULL, if all percpu reorder queues are empty.
*
* -EINPROGRESS, if the next object that needs serialization will
* be parallel processed by another cpu and is not yet present in
* the cpu's reorder queue.
*
* -ENODATA, if this cpu has to do the parallel processing for
* the next object.
*/
static struct padata_priv *padata_get_next(struct parallel_data *pd)
{
int cpu, num_cpus;
unsigned int next_nr, next_index;