linux/kernel/padata.c

1051 lines
25 KiB
C
Raw Normal View History

/*
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#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;
struct padata_parallel_queue *next_queue;
struct padata_priv *padata;
struct padata_list *reorder;
num_cpus = cpumask_weight(pd->cpumask.pcpu);
/*
* Calculate the percpu reorder queue and the sequence
* number of the next object.
*/
next_nr = pd->processed;
next_index = next_nr % num_cpus;
cpu = padata_index_to_cpu(pd, next_index);
next_queue = per_cpu_ptr(pd->pqueue, cpu);
padata = NULL;
reorder = &next_queue->reorder;
padata: avoid race in reordering Under extremely heavy uses of padata, crashes occur, and with list debugging turned on, this happens instead: [87487.298728] WARNING: CPU: 1 PID: 882 at lib/list_debug.c:33 __list_add+0xae/0x130 [87487.301868] list_add corruption. prev->next should be next (ffffb17abfc043d0), but was ffff8dba70872c80. (prev=ffff8dba70872b00). [87487.339011] [<ffffffff9a53d075>] dump_stack+0x68/0xa3 [87487.342198] [<ffffffff99e119a1>] ? console_unlock+0x281/0x6d0 [87487.345364] [<ffffffff99d6b91f>] __warn+0xff/0x140 [87487.348513] [<ffffffff99d6b9aa>] warn_slowpath_fmt+0x4a/0x50 [87487.351659] [<ffffffff9a58b5de>] __list_add+0xae/0x130 [87487.354772] [<ffffffff9add5094>] ? _raw_spin_lock+0x64/0x70 [87487.357915] [<ffffffff99eefd66>] padata_reorder+0x1e6/0x420 [87487.361084] [<ffffffff99ef0055>] padata_do_serial+0xa5/0x120 padata_reorder calls list_add_tail with the list to which its adding locked, which seems correct: spin_lock(&squeue->serial.lock); list_add_tail(&padata->list, &squeue->serial.list); spin_unlock(&squeue->serial.lock); This therefore leaves only place where such inconsistency could occur: if padata->list is added at the same time on two different threads. This pdata pointer comes from the function call to padata_get_next(pd), which has in it the following block: next_queue = per_cpu_ptr(pd->pqueue, cpu); padata = NULL; reorder = &next_queue->reorder; if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); spin_unlock(&reorder->lock); pd->processed++; goto out; } out: return padata; I strongly suspect that the problem here is that two threads can race on reorder list. Even though the deletion is locked, call to list_entry is not locked, which means it's feasible that two threads pick up the same padata object and subsequently call list_add_tail on them at the same time. The fix is thus be hoist that lock outside of that block. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Acked-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-03-23 11:24:43 +00:00
spin_lock(&reorder->lock);
if (!list_empty(&reorder->list)) {
padata = list_entry(reorder->list.next,
struct padata_priv, list);
list_del_init(&padata->list);
atomic_dec(&pd->reorder_objects);
pd->processed++;
padata: avoid race in reordering Under extremely heavy uses of padata, crashes occur, and with list debugging turned on, this happens instead: [87487.298728] WARNING: CPU: 1 PID: 882 at lib/list_debug.c:33 __list_add+0xae/0x130 [87487.301868] list_add corruption. prev->next should be next (ffffb17abfc043d0), but was ffff8dba70872c80. (prev=ffff8dba70872b00). [87487.339011] [<ffffffff9a53d075>] dump_stack+0x68/0xa3 [87487.342198] [<ffffffff99e119a1>] ? console_unlock+0x281/0x6d0 [87487.345364] [<ffffffff99d6b91f>] __warn+0xff/0x140 [87487.348513] [<ffffffff99d6b9aa>] warn_slowpath_fmt+0x4a/0x50 [87487.351659] [<ffffffff9a58b5de>] __list_add+0xae/0x130 [87487.354772] [<ffffffff9add5094>] ? _raw_spin_lock+0x64/0x70 [87487.357915] [<ffffffff99eefd66>] padata_reorder+0x1e6/0x420 [87487.361084] [<ffffffff99ef0055>] padata_do_serial+0xa5/0x120 padata_reorder calls list_add_tail with the list to which its adding locked, which seems correct: spin_lock(&squeue->serial.lock); list_add_tail(&padata->list, &squeue->serial.list); spin_unlock(&squeue->serial.lock); This therefore leaves only place where such inconsistency could occur: if padata->list is added at the same time on two different threads. This pdata pointer comes from the function call to padata_get_next(pd), which has in it the following block: next_queue = per_cpu_ptr(pd->pqueue, cpu); padata = NULL; reorder = &next_queue->reorder; if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); spin_unlock(&reorder->lock); pd->processed++; goto out; } out: return padata; I strongly suspect that the problem here is that two threads can race on reorder list. Even though the deletion is locked, call to list_entry is not locked, which means it's feasible that two threads pick up the same padata object and subsequently call list_add_tail on them at the same time. The fix is thus be hoist that lock outside of that block. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Acked-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-03-23 11:24:43 +00:00
spin_unlock(&reorder->lock);
goto out;
}
padata: avoid race in reordering Under extremely heavy uses of padata, crashes occur, and with list debugging turned on, this happens instead: [87487.298728] WARNING: CPU: 1 PID: 882 at lib/list_debug.c:33 __list_add+0xae/0x130 [87487.301868] list_add corruption. prev->next should be next (ffffb17abfc043d0), but was ffff8dba70872c80. (prev=ffff8dba70872b00). [87487.339011] [<ffffffff9a53d075>] dump_stack+0x68/0xa3 [87487.342198] [<ffffffff99e119a1>] ? console_unlock+0x281/0x6d0 [87487.345364] [<ffffffff99d6b91f>] __warn+0xff/0x140 [87487.348513] [<ffffffff99d6b9aa>] warn_slowpath_fmt+0x4a/0x50 [87487.351659] [<ffffffff9a58b5de>] __list_add+0xae/0x130 [87487.354772] [<ffffffff9add5094>] ? _raw_spin_lock+0x64/0x70 [87487.357915] [<ffffffff99eefd66>] padata_reorder+0x1e6/0x420 [87487.361084] [<ffffffff99ef0055>] padata_do_serial+0xa5/0x120 padata_reorder calls list_add_tail with the list to which its adding locked, which seems correct: spin_lock(&squeue->serial.lock); list_add_tail(&padata->list, &squeue->serial.list); spin_unlock(&squeue->serial.lock); This therefore leaves only place where such inconsistency could occur: if padata->list is added at the same time on two different threads. This pdata pointer comes from the function call to padata_get_next(pd), which has in it the following block: next_queue = per_cpu_ptr(pd->pqueue, cpu); padata = NULL; reorder = &next_queue->reorder; if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); spin_unlock(&reorder->lock); pd->processed++; goto out; } out: return padata; I strongly suspect that the problem here is that two threads can race on reorder list. Even though the deletion is locked, call to list_entry is not locked, which means it's feasible that two threads pick up the same padata object and subsequently call list_add_tail on them at the same time. The fix is thus be hoist that lock outside of that block. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Acked-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-03-23 11:24:43 +00:00
spin_unlock(&reorder->lock);
if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
padata = ERR_PTR(-ENODATA);
goto out;
}
padata = ERR_PTR(-EINPROGRESS);
out:
return padata;
}
static void padata_reorder(struct parallel_data *pd)
{
int cb_cpu;
struct padata_priv *padata;
struct padata_serial_queue *squeue;
struct padata_instance *pinst = pd->pinst;
/*
* We need to ensure that only one cpu can work on dequeueing of
* the reorder queue the time. Calculating in which percpu reorder
* queue the next object will arrive takes some time. A spinlock
* would be highly contended. Also it is not clear in which order
* the objects arrive to the reorder queues. So a cpu could wait to
* get the lock just to notice that there is nothing to do at the
* moment. Therefore we use a trylock and let the holder of the lock
* care for all the objects enqueued during the holdtime of the lock.
*/
if (!spin_trylock_bh(&pd->lock))
return;
while (1) {
padata = padata_get_next(pd);
/*
* All reorder queues are empty, or the next object that needs
* serialization is parallel processed by another cpu and is
* still on it's way to the cpu's reorder queue, nothing to
* do for now.
*/
if (!padata || PTR_ERR(padata) == -EINPROGRESS)
break;
/*
* This cpu has to do the parallel processing of the next
* object. It's waiting in the cpu's parallelization queue,
* so exit immediately.
*/
if (PTR_ERR(padata) == -ENODATA) {
del_timer(&pd->timer);
spin_unlock_bh(&pd->lock);
return;
}
cb_cpu = padata->cb_cpu;
squeue = per_cpu_ptr(pd->squeue, cb_cpu);
spin_lock(&squeue->serial.lock);
list_add_tail(&padata->list, &squeue->serial.list);
spin_unlock(&squeue->serial.lock);
queue_work_on(cb_cpu, pinst->wq, &squeue->work);
}
spin_unlock_bh(&pd->lock);
/*
* The next object that needs serialization might have arrived to
* the reorder queues in the meantime, we will be called again
* from the timer function if no one else cares for it.
*/
if (atomic_read(&pd->reorder_objects)
&& !(pinst->flags & PADATA_RESET))
mod_timer(&pd->timer, jiffies + HZ);
else
del_timer(&pd->timer);
return;
}
static void padata_reorder_timer(unsigned long arg)
{
struct parallel_data *pd = (struct parallel_data *)arg;
padata_reorder(pd);
}
static void padata_serial_worker(struct work_struct *serial_work)
{
struct padata_serial_queue *squeue;
struct parallel_data *pd;
LIST_HEAD(local_list);
local_bh_disable();
squeue = container_of(serial_work, struct padata_serial_queue, work);
pd = squeue->pd;
spin_lock(&squeue->serial.lock);
list_replace_init(&squeue->serial.list, &local_list);
spin_unlock(&squeue->serial.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->serial(padata);
atomic_dec(&pd->refcnt);
}
local_bh_enable();
}
/**
* padata_do_serial - padata serialization function
*
* @padata: object to be serialized.
*
* padata_do_serial must be called for every parallelized object.
* The serialization callback function will run with BHs off.
*/
void padata_do_serial(struct padata_priv *padata)
{
int cpu;
struct padata_parallel_queue *pqueue;
struct parallel_data *pd;
pd = padata->pd;
cpu = get_cpu();
pqueue = per_cpu_ptr(pd->pqueue, cpu);
spin_lock(&pqueue->reorder.lock);
atomic_inc(&pd->reorder_objects);
list_add_tail(&padata->list, &pqueue->reorder.list);
spin_unlock(&pqueue->reorder.lock);
put_cpu();
padata_reorder(pd);
}
EXPORT_SYMBOL(padata_do_serial);
static int padata_setup_cpumasks(struct parallel_data *pd,
const struct cpumask *pcpumask,
const struct cpumask *cbcpumask)
{
if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
return -ENOMEM;
cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
free_cpumask_var(pd->cpumask.cbcpu);
return -ENOMEM;
}
cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_online_mask);
return 0;
}
static void __padata_list_init(struct padata_list *pd_list)
{
INIT_LIST_HEAD(&pd_list->list);
spin_lock_init(&pd_list->lock);
}
/* Initialize all percpu queues used by serial workers */
static void padata_init_squeues(struct parallel_data *pd)
{
int cpu;
struct padata_serial_queue *squeue;
for_each_cpu(cpu, pd->cpumask.cbcpu) {
squeue = per_cpu_ptr(pd->squeue, cpu);
squeue->pd = pd;
__padata_list_init(&squeue->serial);
INIT_WORK(&squeue->work, padata_serial_worker);
}
}
/* Initialize all percpu queues used by parallel workers */
static void padata_init_pqueues(struct parallel_data *pd)
{
int cpu_index, cpu;
struct padata_parallel_queue *pqueue;
cpu_index = 0;
for_each_cpu(cpu, pd->cpumask.pcpu) {
pqueue = per_cpu_ptr(pd->pqueue, cpu);
pqueue->pd = pd;
pqueue->cpu_index = cpu_index;
cpu_index++;
__padata_list_init(&pqueue->reorder);
__padata_list_init(&pqueue->parallel);
INIT_WORK(&pqueue->work, padata_parallel_worker);
atomic_set(&pqueue->num_obj, 0);
}
}
/* Allocate and initialize the internal cpumask dependend resources. */
static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
const struct cpumask *pcpumask,
const struct cpumask *cbcpumask)
{
struct parallel_data *pd;
pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
if (!pd)
goto err;
pd->pqueue = alloc_percpu(struct padata_parallel_queue);
if (!pd->pqueue)
goto err_free_pd;
pd->squeue = alloc_percpu(struct padata_serial_queue);
if (!pd->squeue)
goto err_free_pqueue;
if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0)
goto err_free_squeue;
padata_init_pqueues(pd);
padata_init_squeues(pd);
setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
atomic_set(&pd->seq_nr, -1);
atomic_set(&pd->reorder_objects, 0);
atomic_set(&pd->refcnt, 0);
pd->pinst = pinst;
spin_lock_init(&pd->lock);
return pd;
err_free_squeue:
free_percpu(pd->squeue);
err_free_pqueue:
free_percpu(pd->pqueue);
err_free_pd:
kfree(pd);
err:
return NULL;
}
static void padata_free_pd(struct parallel_data *pd)
{
free_cpumask_var(pd->cpumask.pcpu);
free_cpumask_var(pd->cpumask.cbcpu);
free_percpu(pd->pqueue);
free_percpu(pd->squeue);
kfree(pd);
}
/* Flush all objects out of the padata queues. */
static void padata_flush_queues(struct parallel_data *pd)
{
int cpu;
struct padata_parallel_queue *pqueue;
struct padata_serial_queue *squeue;
for_each_cpu(cpu, pd->cpumask.pcpu) {
pqueue = per_cpu_ptr(pd->pqueue, cpu);
flush_work(&pqueue->work);
}
del_timer_sync(&pd->timer);
if (atomic_read(&pd->reorder_objects))
padata_reorder(pd);
for_each_cpu(cpu, pd->cpumask.cbcpu) {
squeue = per_cpu_ptr(pd->squeue, cpu);
flush_work(&squeue->work);
}
BUG_ON(atomic_read(&pd->refcnt) != 0);
}
static void __padata_start(struct padata_instance *pinst)
{
pinst->flags |= PADATA_INIT;
}
static void __padata_stop(struct padata_instance *pinst)
{
if (!(pinst->flags & PADATA_INIT))
return;
pinst->flags &= ~PADATA_INIT;
synchronize_rcu();
get_online_cpus();
padata_flush_queues(pinst->pd);
put_online_cpus();
}
/* Replace the internal control structure with a new one. */
static void padata_replace(struct padata_instance *pinst,
struct parallel_data *pd_new)
{
struct parallel_data *pd_old = pinst->pd;
int notification_mask = 0;
pinst->flags |= PADATA_RESET;
rcu_assign_pointer(pinst->pd, pd_new);
synchronize_rcu();
if (!cpumask_equal(pd_old->cpumask.pcpu, pd_new->cpumask.pcpu))
notification_mask |= PADATA_CPU_PARALLEL;
if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu))
notification_mask |= PADATA_CPU_SERIAL;
padata_flush_queues(pd_old);
padata_free_pd(pd_old);
if (notification_mask)
blocking_notifier_call_chain(&pinst->cpumask_change_notifier,
notification_mask,
&pd_new->cpumask);
pinst->flags &= ~PADATA_RESET;
}
/**
* padata_register_cpumask_notifier - Registers a notifier that will be called
* if either pcpu or cbcpu or both cpumasks change.
*
* @pinst: A poineter to padata instance
* @nblock: A pointer to notifier block.
*/
int padata_register_cpumask_notifier(struct padata_instance *pinst,
struct notifier_block *nblock)
{
return blocking_notifier_chain_register(&pinst->cpumask_change_notifier,
nblock);
}
EXPORT_SYMBOL(padata_register_cpumask_notifier);
/**
* padata_unregister_cpumask_notifier - Unregisters cpumask notifier
* registered earlier using padata_register_cpumask_notifier
*
* @pinst: A pointer to data instance.
* @nlock: A pointer to notifier block.
*/
int padata_unregister_cpumask_notifier(struct padata_instance *pinst,
struct notifier_block *nblock)
{
return blocking_notifier_chain_unregister(
&pinst->cpumask_change_notifier,
nblock);
}
EXPORT_SYMBOL(padata_unregister_cpumask_notifier);
/* If cpumask contains no active cpu, we mark the instance as invalid. */
static bool padata_validate_cpumask(struct padata_instance *pinst,
const struct cpumask *cpumask)
{
if (!cpumask_intersects(cpumask, cpu_online_mask)) {
pinst->flags |= PADATA_INVALID;
return false;
}
pinst->flags &= ~PADATA_INVALID;
return true;
}
static int __padata_set_cpumasks(struct padata_instance *pinst,
cpumask_var_t pcpumask,
cpumask_var_t cbcpumask)
{
int valid;
struct parallel_data *pd;
valid = padata_validate_cpumask(pinst, pcpumask);
if (!valid) {
__padata_stop(pinst);
goto out_replace;
}
valid = padata_validate_cpumask(pinst, cbcpumask);
if (!valid)
__padata_stop(pinst);
out_replace:
pd = padata_alloc_pd(pinst, pcpumask, cbcpumask);
if (!pd)
return -ENOMEM;
cpumask_copy(pinst->cpumask.pcpu, pcpumask);
cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
padata_replace(pinst, pd);
if (valid)
__padata_start(pinst);
return 0;
}
/**
* padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value
* equivalent to @cpumask.
*
* @pinst: padata instance
* @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding
* to parallel and serial cpumasks respectively.
* @cpumask: the cpumask to use
*/
int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
cpumask_var_t cpumask)
{
struct cpumask *serial_mask, *parallel_mask;
int err = -EINVAL;
mutex_lock(&pinst->lock);
get_online_cpus();
switch (cpumask_type) {
case PADATA_CPU_PARALLEL:
serial_mask = pinst->cpumask.cbcpu;
parallel_mask = cpumask;
break;
case PADATA_CPU_SERIAL:
parallel_mask = pinst->cpumask.pcpu;
serial_mask = cpumask;
break;
default:
goto out;
}
err = __padata_set_cpumasks(pinst, parallel_mask, serial_mask);
out:
put_online_cpus();
mutex_unlock(&pinst->lock);
return err;
}
EXPORT_SYMBOL(padata_set_cpumask);
/**
* padata_start - start the parallel processing
*
* @pinst: padata instance to start
*/
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 parallel_data *pd;
if (cpumask_test_cpu(cpu, cpu_online_mask)) {
pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu,
pinst->cpumask.cbcpu);
if (!pd)
return -ENOMEM;
padata_replace(pinst, pd);
if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) &&
padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
__padata_start(pinst);
}
return 0;
}
static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
{
struct parallel_data *pd = NULL;
if (cpumask_test_cpu(cpu, cpu_online_mask)) {
if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) ||
!padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
__padata_stop(pinst);
pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu,
pinst->cpumask.cbcpu);
if (!pd)
return -ENOMEM;
padata_replace(pinst, pd);
cpumask_clear_cpu(cpu, pd->cpumask.cbcpu);
cpumask_clear_cpu(cpu, pd->cpumask.pcpu);
}
return 0;
}
/**
* padata_remove_cpu - remove a cpu from the one or both(serial and parallel)
* padata cpumasks.
*
* @pinst: padata instance
* @cpu: cpu to remove
* @mask: bitmask specifying from which cpumask @cpu should be removed
* The @mask may be any combination of the following flags:
* PADATA_CPU_SERIAL - serial cpumask
* PADATA_CPU_PARALLEL - parallel cpumask
*/
int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask)
{
int err;
if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL)))
return -EINVAL;
mutex_lock(&pinst->lock);
get_online_cpus();
if (mask & PADATA_CPU_SERIAL)
cpumask_clear_cpu(cpu, pinst->cpumask.cbcpu);
if (mask & PADATA_CPU_PARALLEL)
cpumask_clear_cpu(cpu, pinst->cpumask.pcpu);
err = __padata_remove_cpu(pinst, cpu);
put_online_cpus();
mutex_unlock(&pinst->lock);
return err;
}
EXPORT_SYMBOL(padata_remove_cpu);
static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu)
{
return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) ||
cpumask_test_cpu(cpu, pinst->cpumask.cbcpu);
}
static int padata_cpu_online(unsigned int cpu, struct hlist_node *node)
{
struct padata_instance *pinst;
int ret;
pinst = hlist_entry_safe(node, struct padata_instance, node);
if (!pinst_has_cpu(pinst, cpu))
return 0;
mutex_lock(&pinst->lock);
ret = __padata_add_cpu(pinst, cpu);
mutex_unlock(&pinst->lock);
return ret;
}
static int padata_cpu_prep_down(unsigned int cpu, struct hlist_node *node)
{
struct padata_instance *pinst;
int ret;
pinst = hlist_entry_safe(node, struct padata_instance, node);
if (!pinst_has_cpu(pinst, cpu))
return 0;
mutex_lock(&pinst->lock);
ret = __padata_remove_cpu(pinst, cpu);
mutex_unlock(&pinst->lock);
return ret;
}
static enum cpuhp_state hp_online;
#endif
static void __padata_free(struct padata_instance *pinst)
{
#ifdef CONFIG_HOTPLUG_CPU
cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node);
#endif
padata_stop(pinst);
padata_free_pd(pinst->pd);
free_cpumask_var(pinst->cpumask.pcpu);
free_cpumask_var(pinst->cpumask.cbcpu);
kfree(pinst);
}
#define kobj2pinst(_kobj) \
container_of(_kobj, struct padata_instance, kobj)
#define attr2pentry(_attr) \
container_of(_attr, struct padata_sysfs_entry, attr)
static void padata_sysfs_release(struct kobject *kobj)
{
struct padata_instance *pinst = kobj2pinst(kobj);
__padata_free(pinst);
}
struct padata_sysfs_entry {
struct attribute attr;
ssize_t (*show)(struct padata_instance *, struct attribute *, char *);
ssize_t (*store)(struct padata_instance *, struct attribute *,
const char *, size_t);
};
static ssize_t show_cpumask(struct padata_instance *pinst,
struct attribute *attr, char *buf)
{
struct cpumask *cpumask;
ssize_t len;
mutex_lock(&pinst->lock);
if (!strcmp(attr->name, "serial_cpumask"))
cpumask = pinst->cpumask.cbcpu;
else
cpumask = pinst->cpumask.pcpu;
len = snprintf(buf, PAGE_SIZE, "%*pb\n",
nr_cpu_ids, cpumask_bits(cpumask));
mutex_unlock(&pinst->lock);
return len < PAGE_SIZE ? len : -EINVAL;
}
static ssize_t store_cpumask(struct padata_instance *pinst,
struct attribute *attr,
const char *buf, size_t count)
{
cpumask_var_t new_cpumask;
ssize_t ret;
int mask_type;
if (!alloc_cpumask_var(&new_cpumask, GFP_KERNEL))
return -ENOMEM;
ret = bitmap_parse(buf, count, cpumask_bits(new_cpumask),
nr_cpumask_bits);
if (ret < 0)
goto out;
mask_type = !strcmp(attr->name, "serial_cpumask") ?
PADATA_CPU_SERIAL : PADATA_CPU_PARALLEL;
ret = padata_set_cpumask(pinst, mask_type, new_cpumask);
if (!ret)
ret = count;
out:
free_cpumask_var(new_cpumask);
return ret;
}
#define PADATA_ATTR_RW(_name, _show_name, _store_name) \
static struct padata_sysfs_entry _name##_attr = \
__ATTR(_name, 0644, _show_name, _store_name)
#define PADATA_ATTR_RO(_name, _show_name) \
static struct padata_sysfs_entry _name##_attr = \
__ATTR(_name, 0400, _show_name, NULL)
PADATA_ATTR_RW(serial_cpumask, show_cpumask, store_cpumask);
PADATA_ATTR_RW(parallel_cpumask, show_cpumask, store_cpumask);
/*
* Padata sysfs provides the following objects:
* serial_cpumask [RW] - cpumask for serial workers
* parallel_cpumask [RW] - cpumask for parallel workers
*/
static struct attribute *padata_default_attrs[] = {
&serial_cpumask_attr.attr,
&parallel_cpumask_attr.attr,
NULL,
};
static ssize_t padata_sysfs_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct padata_instance *pinst;
struct padata_sysfs_entry *pentry;
ssize_t ret = -EIO;
pinst = kobj2pinst(kobj);
pentry = attr2pentry(attr);
if (pentry->show)
ret = pentry->show(pinst, attr, buf);
return ret;
}
static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct padata_instance *pinst;
struct padata_sysfs_entry *pentry;
ssize_t ret = -EIO;
pinst = kobj2pinst(kobj);
pentry = attr2pentry(attr);
if (pentry->show)
ret = pentry->store(pinst, attr, buf, count);
return ret;
}
static const struct sysfs_ops padata_sysfs_ops = {
.show = padata_sysfs_show,
.store = padata_sysfs_store,
};
static struct kobj_type padata_attr_type = {
.sysfs_ops = &padata_sysfs_ops,
.default_attrs = padata_default_attrs,
.release = padata_sysfs_release,
};
/**
* padata_alloc_possible - Allocate and initialize padata instance.
* Use the cpu_possible_mask for serial and
* parallel workers.
*
* @wq: workqueue to use for the allocated padata instance
*/
struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
{
return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
}
EXPORT_SYMBOL(padata_alloc_possible);
/**
* padata_alloc - allocate and initialize a padata instance and specify
* cpumasks for serial and parallel workers.
*
* @wq: workqueue to use for the allocated padata instance
* @pcpumask: cpumask that will be used for padata parallelization
* @cbcpumask: cpumask that will be used for padata serialization
*/
struct padata_instance *padata_alloc(struct workqueue_struct *wq,
const struct cpumask *pcpumask,
const struct cpumask *cbcpumask)
{
struct padata_instance *pinst;
struct parallel_data *pd = NULL;
pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL);
if (!pinst)
goto err;
get_online_cpus();
if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
goto err_free_inst;
if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
free_cpumask_var(pinst->cpumask.pcpu);
goto err_free_inst;
}
if (!padata_validate_cpumask(pinst, pcpumask) ||
!padata_validate_cpumask(pinst, cbcpumask))
goto err_free_masks;
pd = padata_alloc_pd(pinst, pcpumask, cbcpumask);
if (!pd)
goto err_free_masks;
rcu_assign_pointer(pinst->pd, pd);
pinst->wq = wq;
cpumask_copy(pinst->cpumask.pcpu, pcpumask);
cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
pinst->flags = 0;
put_online_cpus();
BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier);
kobject_init(&pinst->kobj, &padata_attr_type);
mutex_init(&pinst->lock);
#ifdef CONFIG_HOTPLUG_CPU
cpuhp_state_add_instance_nocalls(hp_online, &pinst->node);
#endif
return pinst;
err_free_masks:
free_cpumask_var(pinst->cpumask.pcpu);
free_cpumask_var(pinst->cpumask.cbcpu);
err_free_inst:
kfree(pinst);
put_online_cpus();
err:
return NULL;
}
/**
* padata_free - free a padata instance
*
* @padata_inst: padata instance to free
*/
void padata_free(struct padata_instance *pinst)
{
kobject_put(&pinst->kobj);
}
EXPORT_SYMBOL(padata_free);
#ifdef CONFIG_HOTPLUG_CPU
static __init int padata_driver_init(void)
{
int ret;
ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online",
padata_cpu_online,
padata_cpu_prep_down);
if (ret < 0)
return ret;
hp_online = ret;
return 0;
}
module_init(padata_driver_init);
static __exit void padata_driver_exit(void)
{
cpuhp_remove_multi_state(hp_online);
}
module_exit(padata_driver_exit);
#endif