* Copyright (C) 2008, 2009 secunet Security Networks AG
* Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
*
+ * Copyright (c) 2020 Oracle and/or its affiliates.
+ * Author: Daniel Jordan <daniel.m.jordan@oracle.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.
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*/
+#include <linux/completion.h>
#include <linux/export.h>
#include <linux/cpumask.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/rcupdate.h>
-#include <linux/module.h>
-#define MAX_OBJ_NUM 1000
+#define PADATA_WORK_ONSTACK 1 /* Work's memory is on stack */
+
+struct padata_work {
+ struct work_struct pw_work;
+ struct list_head pw_list; /* padata_free_works linkage */
+ void *pw_data;
+};
+
+static DEFINE_SPINLOCK(padata_works_lock);
+static struct padata_work *padata_works;
+static LIST_HEAD(padata_free_works);
+
+struct padata_mt_job_state {
+ spinlock_t lock;
+ struct completion completion;
+ struct padata_mt_job *job;
+ int nworks;
+ int nworks_fini;
+ unsigned long chunk_size;
+};
static void padata_free_pd(struct parallel_data *pd);
+static void __init padata_mt_helper(struct work_struct *work);
static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
{
return padata_index_to_cpu(pd, cpu_index);
}
-static void padata_parallel_worker(struct work_struct *parallel_work)
+static struct padata_work *padata_work_alloc(void)
{
- struct padata_parallel_queue *pqueue;
- LIST_HEAD(local_list);
+ struct padata_work *pw;
- local_bh_disable();
- pqueue = container_of(parallel_work,
- struct padata_parallel_queue, work);
+ lockdep_assert_held(&padata_works_lock);
- spin_lock(&pqueue->parallel.lock);
- list_replace_init(&pqueue->parallel.list, &local_list);
- spin_unlock(&pqueue->parallel.lock);
+ if (list_empty(&padata_free_works))
+ return NULL; /* No more work items allowed to be queued. */
- while (!list_empty(&local_list)) {
- struct padata_priv *padata;
+ pw = list_first_entry(&padata_free_works, struct padata_work, pw_list);
+ list_del(&pw->pw_list);
+ return pw;
+}
- padata = list_entry(local_list.next,
- struct padata_priv, list);
+static void padata_work_init(struct padata_work *pw, work_func_t work_fn,
+ void *data, int flags)
+{
+ if (flags & PADATA_WORK_ONSTACK)
+ INIT_WORK_ONSTACK(&pw->pw_work, work_fn);
+ else
+ INIT_WORK(&pw->pw_work, work_fn);
+ pw->pw_data = data;
+}
- list_del_init(&padata->list);
+static int __init padata_work_alloc_mt(int nworks, void *data,
+ struct list_head *head)
+{
+ int i;
- padata->parallel(padata);
+ spin_lock(&padata_works_lock);
+ /* Start at 1 because the current task participates in the job. */
+ for (i = 1; i < nworks; ++i) {
+ struct padata_work *pw = padata_work_alloc();
+
+ if (!pw)
+ break;
+ padata_work_init(pw, padata_mt_helper, data, 0);
+ list_add(&pw->pw_list, head);
+ }
+ spin_unlock(&padata_works_lock);
+
+ return i;
+}
+
+static void padata_work_free(struct padata_work *pw)
+{
+ lockdep_assert_held(&padata_works_lock);
+ list_add(&pw->pw_list, &padata_free_works);
+}
+
+static void __init padata_works_free(struct list_head *works)
+{
+ struct padata_work *cur, *next;
+
+ if (list_empty(works))
+ return;
+
+ spin_lock(&padata_works_lock);
+ list_for_each_entry_safe(cur, next, works, pw_list) {
+ list_del(&cur->pw_list);
+ padata_work_free(cur);
}
+ spin_unlock(&padata_works_lock);
+}
+static void padata_parallel_worker(struct work_struct *parallel_work)
+{
+ struct padata_work *pw = container_of(parallel_work, struct padata_work,
+ pw_work);
+ struct padata_priv *padata = pw->pw_data;
+
+ local_bh_disable();
+ padata->parallel(padata);
+ spin_lock(&padata_works_lock);
+ padata_work_free(pw);
+ spin_unlock(&padata_works_lock);
local_bh_enable();
}
struct padata_priv *padata, int *cb_cpu)
{
struct padata_instance *pinst = ps->pinst;
- int i, cpu, cpu_index, target_cpu, err;
- struct padata_parallel_queue *queue;
+ int i, cpu, cpu_index, err;
struct parallel_data *pd;
+ struct padata_work *pw;
rcu_read_lock_bh();
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;
- padata->seq_nr = atomic_inc_return(&pd->seq_nr);
- target_cpu = padata_cpu_hash(pd, padata->seq_nr);
- padata->cpu = target_cpu;
- 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);
+ rcu_read_unlock_bh();
- queue_work(pinst->parallel_wq, &queue->work);
+ spin_lock(&padata_works_lock);
+ padata->seq_nr = ++pd->seq_nr;
+ pw = padata_work_alloc();
+ spin_unlock(&padata_works_lock);
+ if (pw) {
+ padata_work_init(pw, padata_parallel_worker, padata, 0);
+ queue_work(pinst->parallel_wq, &pw->pw_work);
+ } else {
+ /* Maximum works limit exceeded, run in the current task. */
+ padata->parallel(padata);
+ }
+ return 0;
out:
rcu_read_unlock_bh();
static struct padata_priv *padata_find_next(struct parallel_data *pd,
bool remove_object)
{
- struct padata_parallel_queue *next_queue;
struct padata_priv *padata;
struct padata_list *reorder;
int cpu = pd->cpu;
- next_queue = per_cpu_ptr(pd->pqueue, cpu);
- reorder = &next_queue->reorder;
+ reorder = per_cpu_ptr(pd->reorder_list, cpu);
spin_lock(&reorder->lock);
if (list_empty(&reorder->list)) {
int cb_cpu;
struct padata_priv *padata;
struct padata_serial_queue *squeue;
- struct padata_parallel_queue *next_queue;
+ struct padata_list *reorder;
/*
* We need to ensure that only one cpu can work on dequeueing of
*
* Ensure reorder queue is read after pd->lock is dropped so we see
* new objects from another task in padata_do_serial. Pairs with
- * smp_mb__after_atomic in padata_do_serial.
+ * smp_mb in padata_do_serial.
*/
smp_mb();
- next_queue = per_cpu_ptr(pd->pqueue, pd->cpu);
- if (!list_empty(&next_queue->reorder.list) &&
- padata_find_next(pd, false))
+ reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
+ if (!list_empty(&reorder->list) && padata_find_next(pd, false))
queue_work(pinst->serial_wq, &pd->reorder_work);
}
void padata_do_serial(struct padata_priv *padata)
{
struct parallel_data *pd = padata->pd;
- struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue,
- padata->cpu);
+ int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr);
+ struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
struct padata_priv *cur;
- spin_lock(&pqueue->reorder.lock);
+ spin_lock(&reorder->lock);
/* Sort in ascending order of sequence number. */
- list_for_each_entry_reverse(cur, &pqueue->reorder.list, list)
+ list_for_each_entry_reverse(cur, &reorder->list, list)
if (cur->seq_nr < padata->seq_nr)
break;
list_add(&padata->list, &cur->list);
- spin_unlock(&pqueue->reorder.lock);
+ spin_unlock(&reorder->lock);
/*
* Ensure the addition to the reorder list is ordered correctly
* with the trylock of pd->lock in padata_reorder. Pairs with smp_mb
* in padata_reorder.
*/
- smp_mb__after_atomic();
+ smp_mb();
padata_reorder(pd);
}
return err;
}
-static int pd_setup_cpumasks(struct parallel_data *pd,
- const struct cpumask *pcpumask,
- const struct cpumask *cbcpumask)
+static void __init padata_mt_helper(struct work_struct *w)
{
- int err = -ENOMEM;
+ struct padata_work *pw = container_of(w, struct padata_work, pw_work);
+ struct padata_mt_job_state *ps = pw->pw_data;
+ struct padata_mt_job *job = ps->job;
+ bool done;
- if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
- goto out;
- if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
- goto free_pcpu_mask;
+ spin_lock(&ps->lock);
- cpumask_copy(pd->cpumask.pcpu, pcpumask);
- cpumask_copy(pd->cpumask.cbcpu, cbcpumask);
+ while (job->size > 0) {
+ unsigned long start, size, end;
- return 0;
+ start = job->start;
+ /* So end is chunk size aligned if enough work remains. */
+ size = roundup(start + 1, ps->chunk_size) - start;
+ size = min(size, job->size);
+ end = start + size;
-free_pcpu_mask:
- free_cpumask_var(pd->cpumask.pcpu);
-out:
- return err;
+ job->start = end;
+ job->size -= size;
+
+ spin_unlock(&ps->lock);
+ job->thread_fn(start, end, job->fn_arg);
+ spin_lock(&ps->lock);
+ }
+
+ ++ps->nworks_fini;
+ done = (ps->nworks_fini == ps->nworks);
+ spin_unlock(&ps->lock);
+
+ if (done)
+ complete(&ps->completion);
+}
+
+/**
+ * padata_do_multithreaded - run a multithreaded job
+ * @job: Description of the job.
+ *
+ * See the definition of struct padata_mt_job for more details.
+ */
+void __init padata_do_multithreaded(struct padata_mt_job *job)
+{
+ /* In case threads finish at different times. */
+ static const unsigned long load_balance_factor = 4;
+ struct padata_work my_work, *pw;
+ struct padata_mt_job_state ps;
+ LIST_HEAD(works);
+ int nworks;
+
+ if (job->size == 0)
+ return;
+
+ /* Ensure at least one thread when size < min_chunk. */
+ nworks = max(job->size / job->min_chunk, 1ul);
+ nworks = min(nworks, job->max_threads);
+
+ if (nworks == 1) {
+ /* Single thread, no coordination needed, cut to the chase. */
+ job->thread_fn(job->start, job->start + job->size, job->fn_arg);
+ return;
+ }
+
+ spin_lock_init(&ps.lock);
+ init_completion(&ps.completion);
+ ps.job = job;
+ ps.nworks = padata_work_alloc_mt(nworks, &ps, &works);
+ ps.nworks_fini = 0;
+
+ /*
+ * Chunk size is the amount of work a helper does per call to the
+ * thread function. Load balance large jobs between threads by
+ * increasing the number of chunks, guarantee at least the minimum
+ * chunk size from the caller, and honor the caller's alignment.
+ */
+ ps.chunk_size = job->size / (ps.nworks * load_balance_factor);
+ ps.chunk_size = max(ps.chunk_size, job->min_chunk);
+ ps.chunk_size = roundup(ps.chunk_size, job->align);
+
+ list_for_each_entry(pw, &works, pw_list)
+ queue_work(system_unbound_wq, &pw->pw_work);
+
+ /* Use the current thread, which saves starting a workqueue worker. */
+ padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
+ padata_mt_helper(&my_work.pw_work);
+
+ /* Wait for all the helpers to finish. */
+ wait_for_completion(&ps.completion);
+
+ destroy_work_on_stack(&my_work.pw_work);
+ padata_works_free(&works);
}
static void __padata_list_init(struct padata_list *pd_list)
}
}
-/* Initialize all percpu queues used by parallel workers */
-static void padata_init_pqueues(struct parallel_data *pd)
+/* Initialize per-CPU reorder lists */
+static void padata_init_reorder_list(struct parallel_data *pd)
{
int cpu;
- struct padata_parallel_queue *pqueue;
+ struct padata_list *list;
for_each_cpu(cpu, pd->cpumask.pcpu) {
- pqueue = per_cpu_ptr(pd->pqueue, cpu);
-
- __padata_list_init(&pqueue->reorder);
- __padata_list_init(&pqueue->parallel);
- INIT_WORK(&pqueue->work, padata_parallel_worker);
- atomic_set(&pqueue->num_obj, 0);
+ list = per_cpu_ptr(pd->reorder_list, cpu);
+ __padata_list_init(list);
}
}
static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
{
struct padata_instance *pinst = ps->pinst;
- const struct cpumask *cbcpumask;
- const struct cpumask *pcpumask;
struct parallel_data *pd;
- cbcpumask = pinst->rcpumask.cbcpu;
- pcpumask = pinst->rcpumask.pcpu;
-
pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
if (!pd)
goto err;
- pd->pqueue = alloc_percpu(struct padata_parallel_queue);
- if (!pd->pqueue)
+ pd->reorder_list = alloc_percpu(struct padata_list);
+ if (!pd->reorder_list)
goto err_free_pd;
pd->squeue = alloc_percpu(struct padata_serial_queue);
if (!pd->squeue)
- goto err_free_pqueue;
+ goto err_free_reorder_list;
pd->ps = ps;
- if (pd_setup_cpumasks(pd, pcpumask, cbcpumask))
+
+ if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
goto err_free_squeue;
+ if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
+ goto err_free_pcpu;
+
+ cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask);
+ cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask);
- padata_init_pqueues(pd);
+ padata_init_reorder_list(pd);
padata_init_squeues(pd);
- atomic_set(&pd->seq_nr, -1);
+ pd->seq_nr = -1;
atomic_set(&pd->refcnt, 1);
spin_lock_init(&pd->lock);
pd->cpu = cpumask_first(pd->cpumask.pcpu);
return pd;
+err_free_pcpu:
+ free_cpumask_var(pd->cpumask.pcpu);
err_free_squeue:
free_percpu(pd->squeue);
-err_free_pqueue:
- free_percpu(pd->pqueue);
+err_free_reorder_list:
+ free_percpu(pd->reorder_list);
err_free_pd:
kfree(pd);
err:
{
free_cpumask_var(pd->cpumask.pcpu);
free_cpumask_var(pd->cpumask.cbcpu);
- free_percpu(pd->pqueue);
+ free_percpu(pd->reorder_list);
free_percpu(pd->squeue);
kfree(pd);
}
pinst->flags |= PADATA_RESET;
- cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu,
- cpu_online_mask);
-
- cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu,
- cpu_online_mask);
-
list_for_each_entry(ps, &pinst->pslist, list) {
err = padata_replace_one(ps);
if (err)
}
EXPORT_SYMBOL(padata_set_cpumask);
-/**
- * padata_start - start the parallel processing
- *
- * @pinst: padata instance to start
- *
- * Return: 0 on success or negative error code
- */
-int padata_start(struct padata_instance *pinst)
-{
- int err = 0;
-
- mutex_lock(&pinst->lock);
-
- if (pinst->flags & PADATA_INVALID)
- err = -EINVAL;
-
- __padata_start(pinst);
-
- mutex_unlock(&pinst->lock);
-
- return err;
-}
-EXPORT_SYMBOL(padata_start);
-
-/**
- * padata_stop - stop the parallel processing
- *
- * @pinst: padata instance to stop
- */
-void padata_stop(struct padata_instance *pinst)
-{
- mutex_lock(&pinst->lock);
- __padata_stop(pinst);
- mutex_unlock(&pinst->lock);
-}
-EXPORT_SYMBOL(padata_stop);
-
#ifdef CONFIG_HOTPLUG_CPU
static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
struct padata_instance *pinst;
int ret;
- pinst = hlist_entry_safe(node, struct padata_instance, node);
+ pinst = hlist_entry_safe(node, struct padata_instance, cpu_online_node);
if (!pinst_has_cpu(pinst, cpu))
return 0;
struct padata_instance *pinst;
int ret;
- pinst = hlist_entry_safe(node, struct padata_instance, node);
+ pinst = hlist_entry_safe(node, struct padata_instance, cpu_dead_node);
if (!pinst_has_cpu(pinst, cpu))
return 0;
static void __padata_free(struct padata_instance *pinst)
{
#ifdef CONFIG_HOTPLUG_CPU
- cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD, &pinst->node);
- cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node);
+ cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD,
+ &pinst->cpu_dead_node);
+ cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpu_online_node);
#endif
WARN_ON(!list_empty(&pinst->pslist));
- padata_stop(pinst);
- free_cpumask_var(pinst->rcpumask.cbcpu);
- free_cpumask_var(pinst->rcpumask.pcpu);
free_cpumask_var(pinst->cpumask.pcpu);
free_cpumask_var(pinst->cpumask.cbcpu);
destroy_workqueue(pinst->serial_wq);
};
/**
- * padata_alloc - allocate and initialize a padata instance and specify
- * cpumasks for serial and parallel workers.
- *
+ * padata_alloc - allocate and initialize a padata instance
* @name: used to identify the instance
- * @pcpumask: cpumask that will be used for padata parallelization
- * @cbcpumask: cpumask that will be used for padata serialization
*
* Return: new instance on success, NULL on error
*/
-static struct padata_instance *padata_alloc(const char *name,
- const struct cpumask *pcpumask,
- const struct cpumask *cbcpumask)
+struct padata_instance *padata_alloc(const char *name)
{
struct padata_instance *pinst;
free_cpumask_var(pinst->cpumask.pcpu);
goto err_free_serial_wq;
}
- if (!padata_validate_cpumask(pinst, pcpumask) ||
- !padata_validate_cpumask(pinst, cbcpumask))
- goto err_free_masks;
-
- if (!alloc_cpumask_var(&pinst->rcpumask.pcpu, GFP_KERNEL))
- goto err_free_masks;
- if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL))
- goto err_free_rcpumask_pcpu;
INIT_LIST_HEAD(&pinst->pslist);
- cpumask_copy(pinst->cpumask.pcpu, pcpumask);
- cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
- cpumask_and(pinst->rcpumask.pcpu, pcpumask, cpu_online_mask);
- cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask);
+ cpumask_copy(pinst->cpumask.pcpu, cpu_possible_mask);
+ cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask);
if (padata_setup_cpumasks(pinst))
- goto err_free_rcpumask_cbcpu;
+ goto err_free_masks;
- pinst->flags = 0;
+ __padata_start(pinst);
kobject_init(&pinst->kobj, &padata_attr_type);
mutex_init(&pinst->lock);
#ifdef CONFIG_HOTPLUG_CPU
- cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node);
+ cpuhp_state_add_instance_nocalls_cpuslocked(hp_online,
+ &pinst->cpu_online_node);
cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD,
- &pinst->node);
+ &pinst->cpu_dead_node);
#endif
put_online_cpus();
return pinst;
-err_free_rcpumask_cbcpu:
- free_cpumask_var(pinst->rcpumask.cbcpu);
-err_free_rcpumask_pcpu:
- free_cpumask_var(pinst->rcpumask.pcpu);
err_free_masks:
free_cpumask_var(pinst->cpumask.pcpu);
free_cpumask_var(pinst->cpumask.cbcpu);
err:
return NULL;
}
-
-/**
- * padata_alloc_possible - Allocate and initialize padata instance.
- * Use the cpu_possible_mask for serial and
- * parallel workers.
- *
- * @name: used to identify the instance
- *
- * Return: new instance on success, NULL on error
- */
-struct padata_instance *padata_alloc_possible(const char *name)
-{
- return padata_alloc(name, cpu_possible_mask, cpu_possible_mask);
-}
-EXPORT_SYMBOL(padata_alloc_possible);
+EXPORT_SYMBOL(padata_alloc);
/**
* padata_free - free a padata instance
}
EXPORT_SYMBOL(padata_free_shell);
-#ifdef CONFIG_HOTPLUG_CPU
-
-static __init int padata_driver_init(void)
+void __init padata_init(void)
{
+ unsigned int i, possible_cpus;
+#ifdef CONFIG_HOTPLUG_CPU
int ret;
ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online",
padata_cpu_online, NULL);
if (ret < 0)
- return ret;
+ goto err;
hp_online = ret;
ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead",
NULL, padata_cpu_dead);
- if (ret < 0) {
- cpuhp_remove_multi_state(hp_online);
- return ret;
- }
- return 0;
-}
-module_init(padata_driver_init);
+ if (ret < 0)
+ goto remove_online_state;
+#endif
-static __exit void padata_driver_exit(void)
-{
+ possible_cpus = num_possible_cpus();
+ padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work),
+ GFP_KERNEL);
+ if (!padata_works)
+ goto remove_dead_state;
+
+ for (i = 0; i < possible_cpus; ++i)
+ list_add(&padata_works[i].pw_list, &padata_free_works);
+
+ return;
+
+remove_dead_state:
+#ifdef CONFIG_HOTPLUG_CPU
cpuhp_remove_multi_state(CPUHP_PADATA_DEAD);
+remove_online_state:
cpuhp_remove_multi_state(hp_online);
-}
-module_exit(padata_driver_exit);
+err:
#endif
+ pr_warn("padata: initialization failed\n");
+}
projects / linux-2.6-microblaze.git / blobdiff