#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
-#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>
-/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
-static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
-{
- if (bdi->wb.task) {
- wake_up_process(bdi->wb.task);
- } else {
- /*
- * The bdi thread isn't there, wake up the forker thread which
- * will create and run it.
- */
- wake_up_process(default_backing_dev_info.wb.task);
- }
-}
-
static void bdi_queue_work(struct backing_dev_info *bdi,
struct wb_writeback_work *work)
{
spin_lock_bh(&bdi->wb_lock);
list_add_tail(&work->list, &bdi->work_list);
- if (!bdi->wb.task)
- trace_writeback_nothread(bdi, work);
- bdi_wakeup_flusher(bdi);
spin_unlock_bh(&bdi->wb_lock);
+
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
}
static void
*/
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work) {
- if (bdi->wb.task) {
- trace_writeback_nowork(bdi);
- wake_up_process(bdi->wb.task);
- }
+ trace_writeback_nowork(bdi);
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
return;
}
* writeback as soon as there is no other work to do.
*/
trace_writeback_wake_background(bdi);
- spin_lock_bh(&bdi->wb_lock);
- bdi_wakeup_flusher(bdi);
- spin_unlock_bh(&bdi->wb_lock);
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
}
/*
/*
* Handle writeback of dirty data for the device backed by this bdi. Also
- * wakes up periodically and does kupdated style flushing.
+ * reschedules periodically and does kupdated style flushing.
*/
-int bdi_writeback_thread(void *data)
+void bdi_writeback_workfn(struct work_struct *work)
{
- struct bdi_writeback *wb = data;
+ struct bdi_writeback *wb = container_of(to_delayed_work(work),
+ struct bdi_writeback, dwork);
struct backing_dev_info *bdi = wb->bdi;
long pages_written;
current->flags |= PF_SWAPWRITE;
- set_freezable();
- wb->last_active = jiffies;
-
- /*
- * Our parent may run at a different priority, just set us to normal
- */
- set_user_nice(current, 0);
-
- trace_writeback_thread_start(bdi);
- while (!kthread_freezable_should_stop(NULL)) {
+ if (likely(!current_is_workqueue_rescuer() ||
+ list_empty(&bdi->bdi_list))) {
/*
- * Remove own delayed wake-up timer, since we are already awake
- * and we'll take care of the periodic write-back.
+ * The normal path. Keep writing back @bdi until its
+ * work_list is empty. Note that this path is also taken
+ * if @bdi is shutting down even when we're running off the
+ * rescuer as work_list needs to be drained.
*/
- del_timer(&wb->wakeup_timer);
-
- pages_written = wb_do_writeback(wb, 0);
-
+ do {
+ pages_written = wb_do_writeback(wb, 0);
+ trace_writeback_pages_written(pages_written);
+ } while (!list_empty(&bdi->work_list));
+ } else {
+ /*
+ * bdi_wq can't get enough workers and we're running off
+ * the emergency worker. Don't hog it. Hopefully, 1024 is
+ * enough for efficient IO.
+ */
+ pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+ WB_REASON_FORKER_THREAD);
trace_writeback_pages_written(pages_written);
-
- if (pages_written)
- wb->last_active = jiffies;
-
- set_current_state(TASK_INTERRUPTIBLE);
- if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
- __set_current_state(TASK_RUNNING);
- continue;
- }
-
- if (wb_has_dirty_io(wb) && dirty_writeback_interval)
- schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
- else {
- /*
- * We have nothing to do, so can go sleep without any
- * timeout and save power. When a work is queued or
- * something is made dirty - we will be woken up.
- */
- schedule();
- }
}
- /* Flush any work that raced with us exiting */
- if (!list_empty(&bdi->work_list))
- wb_do_writeback(wb, 1);
+ if (!list_empty(&bdi->work_list) ||
+ (wb_has_dirty_io(wb) && dirty_writeback_interval))
+ queue_delayed_work(bdi_wq, &wb->dwork,
+ msecs_to_jiffies(dirty_writeback_interval * 10));
- trace_writeback_thread_stop(bdi);
- return 0;
+ current->flags &= ~PF_SWAPWRITE;
}
-
/*
* Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
* the whole world.
#include <linux/writeback.h>
#include <linux/atomic.h>
#include <linux/sysctl.h>
+#include <linux/workqueue.h>
struct page;
struct device;
* Bits in backing_dev_info.state
*/
enum bdi_state {
- BDI_pending, /* On its way to being activated */
BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
unsigned int nr;
unsigned long last_old_flush; /* last old data flush */
- unsigned long last_active; /* last time bdi thread was active */
- struct task_struct *task; /* writeback thread */
- struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
+ struct delayed_work dwork; /* work item used for writeback */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
void bdi_start_background_writeback(struct backing_dev_info *bdi);
-int bdi_writeback_thread(void *data);
+void bdi_writeback_workfn(struct work_struct *work);
int bdi_has_dirty_io(struct backing_dev_info *bdi);
void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
+extern struct workqueue_struct *bdi_wq;
+
static inline int wb_has_dirty_io(struct bdi_writeback *wb)
{
return !list_empty(&wb->b_dirty) ||
return bdi->capabilities & BDI_CAP_SWAP_BACKED;
}
-static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
-{
- return bdi == &default_backing_dev_info;
-}
-
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
+/* bdi_wq serves all asynchronous writeback tasks */
+struct workqueue_struct *bdi_wq;
+
void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
{
if (wb1 < wb2) {
{
int err;
+ bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
+ WQ_UNBOUND, 0);
+ if (!bdi_wq)
+ return -ENOMEM;
+
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
return wb_has_dirty_io(&bdi->wb);
}
-static void wakeup_timer_fn(unsigned long data)
-{
- struct backing_dev_info *bdi = (struct backing_dev_info *)data;
-
- spin_lock_bh(&bdi->wb_lock);
- if (bdi->wb.task) {
- trace_writeback_wake_thread(bdi);
- wake_up_process(bdi->wb.task);
- } else if (bdi->dev) {
- /*
- * When bdi tasks are inactive for long time, they are killed.
- * In this case we have to wake-up the forker thread which
- * should create and run the bdi thread.
- */
- trace_writeback_wake_forker_thread(bdi);
- wake_up_process(default_backing_dev_info.wb.task);
- }
- spin_unlock_bh(&bdi->wb_lock);
-}
-
/*
* This function is used when the first inode for this bdi is marked dirty. It
* wakes-up the corresponding bdi thread which should then take care of the
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
- mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
-}
-
-/*
- * Calculate the longest interval (jiffies) bdi threads are allowed to be
- * inactive.
- */
-static unsigned long bdi_longest_inactive(void)
-{
- unsigned long interval;
-
- interval = msecs_to_jiffies(dirty_writeback_interval * 10);
- return max(5UL * 60 * HZ, interval);
-}
-
-/*
- * Clear pending bit and wakeup anybody waiting for flusher thread creation or
- * shutdown
- */
-static void bdi_clear_pending(struct backing_dev_info *bdi)
-{
- clear_bit(BDI_pending, &bdi->state);
- smp_mb__after_clear_bit();
- wake_up_bit(&bdi->state, BDI_pending);
-}
-
-static int bdi_forker_thread(void *ptr)
-{
- struct bdi_writeback *me = ptr;
-
- current->flags |= PF_SWAPWRITE;
- set_freezable();
-
- /*
- * Our parent may run at a different priority, just set us to normal
- */
- set_user_nice(current, 0);
-
- for (;;) {
- struct task_struct *task = NULL;
- struct backing_dev_info *bdi;
- enum {
- NO_ACTION, /* Nothing to do */
- FORK_THREAD, /* Fork bdi thread */
- KILL_THREAD, /* Kill inactive bdi thread */
- } action = NO_ACTION;
-
- /*
- * Temporary measure, we want to make sure we don't see
- * dirty data on the default backing_dev_info
- */
- if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
- del_timer(&me->wakeup_timer);
- wb_do_writeback(me, 0);
- }
-
- spin_lock_bh(&bdi_lock);
- /*
- * In the following loop we are going to check whether we have
- * some work to do without any synchronization with tasks
- * waking us up to do work for them. Set the task state here
- * so that we don't miss wakeups after verifying conditions.
- */
- set_current_state(TASK_INTERRUPTIBLE);
-
- list_for_each_entry(bdi, &bdi_list, bdi_list) {
- bool have_dirty_io;
-
- if (!bdi_cap_writeback_dirty(bdi) ||
- bdi_cap_flush_forker(bdi))
- continue;
-
- WARN(!test_bit(BDI_registered, &bdi->state),
- "bdi %p/%s is not registered!\n", bdi, bdi->name);
-
- have_dirty_io = !list_empty(&bdi->work_list) ||
- wb_has_dirty_io(&bdi->wb);
-
- /*
- * If the bdi has work to do, but the thread does not
- * exist - create it.
- */
- if (!bdi->wb.task && have_dirty_io) {
- /*
- * Set the pending bit - if someone will try to
- * unregister this bdi - it'll wait on this bit.
- */
- set_bit(BDI_pending, &bdi->state);
- action = FORK_THREAD;
- break;
- }
-
- spin_lock(&bdi->wb_lock);
-
- /*
- * If there is no work to do and the bdi thread was
- * inactive long enough - kill it. The wb_lock is taken
- * to make sure no-one adds more work to this bdi and
- * wakes the bdi thread up.
- */
- if (bdi->wb.task && !have_dirty_io &&
- time_after(jiffies, bdi->wb.last_active +
- bdi_longest_inactive())) {
- task = bdi->wb.task;
- bdi->wb.task = NULL;
- spin_unlock(&bdi->wb_lock);
- set_bit(BDI_pending, &bdi->state);
- action = KILL_THREAD;
- break;
- }
- spin_unlock(&bdi->wb_lock);
- }
- spin_unlock_bh(&bdi_lock);
-
- /* Keep working if default bdi still has things to do */
- if (!list_empty(&me->bdi->work_list))
- __set_current_state(TASK_RUNNING);
-
- switch (action) {
- case FORK_THREAD:
- __set_current_state(TASK_RUNNING);
- task = kthread_create(bdi_writeback_thread, &bdi->wb,
- "flush-%s", dev_name(bdi->dev));
- if (IS_ERR(task)) {
- /*
- * If thread creation fails, force writeout of
- * the bdi from the thread. Hopefully 1024 is
- * large enough for efficient IO.
- */
- writeback_inodes_wb(&bdi->wb, 1024,
- WB_REASON_FORKER_THREAD);
- } else {
- /*
- * The spinlock makes sure we do not lose
- * wake-ups when racing with 'bdi_queue_work()'.
- * And as soon as the bdi thread is visible, we
- * can start it.
- */
- spin_lock_bh(&bdi->wb_lock);
- bdi->wb.task = task;
- spin_unlock_bh(&bdi->wb_lock);
- wake_up_process(task);
- }
- bdi_clear_pending(bdi);
- break;
-
- case KILL_THREAD:
- __set_current_state(TASK_RUNNING);
- kthread_stop(task);
- bdi_clear_pending(bdi);
- break;
-
- case NO_ACTION:
- if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
- /*
- * There are no dirty data. The only thing we
- * should now care about is checking for
- * inactive bdi threads and killing them. Thus,
- * let's sleep for longer time, save energy and
- * be friendly for battery-driven devices.
- */
- schedule_timeout(bdi_longest_inactive());
- else
- schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
- try_to_freeze();
- break;
- }
- }
-
- return 0;
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
}
/*
spin_unlock_bh(&bdi_lock);
synchronize_rcu_expedited();
+
+ /* bdi_list is now unused, clear it to mark @bdi dying */
+ INIT_LIST_HEAD(&bdi->bdi_list);
}
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
bdi->dev = dev;
- /*
- * Just start the forker thread for our default backing_dev_info,
- * and add other bdi's to the list. They will get a thread created
- * on-demand when they need it.
- */
- if (bdi_cap_flush_forker(bdi)) {
- struct bdi_writeback *wb = &bdi->wb;
-
- wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
- dev_name(dev));
- if (IS_ERR(wb->task))
- return PTR_ERR(wb->task);
- }
-
bdi_debug_register(bdi, dev_name(dev));
set_bit(BDI_registered, &bdi->state);
*/
static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- struct task_struct *task;
-
if (!bdi_cap_writeback_dirty(bdi))
return;
bdi_remove_from_list(bdi);
/*
- * If setup is pending, wait for that to complete first
+ * Drain work list and shutdown the delayed_work. At this point,
+ * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
+ * is dying and its work_list needs to be drained no matter what.
*/
- wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
- TASK_UNINTERRUPTIBLE);
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+ flush_delayed_work(&bdi->wb.dwork);
+ WARN_ON(!list_empty(&bdi->work_list));
/*
- * Finally, kill the kernel thread. We don't need to be RCU
- * safe anymore, since the bdi is gone from visibility.
+ * This shouldn't be necessary unless @bdi for some reason has
+ * unflushed dirty IO after work_list is drained. Do it anyway
+ * just in case.
*/
- spin_lock_bh(&bdi->wb_lock);
- task = bdi->wb.task;
- bdi->wb.task = NULL;
- spin_unlock_bh(&bdi->wb_lock);
-
- if (task)
- kthread_stop(task);
+ cancel_delayed_work_sync(&bdi->wb.dwork);
}
/*
bdi_set_min_ratio(bdi, 0);
trace_writeback_bdi_unregister(bdi);
bdi_prune_sb(bdi);
- del_timer_sync(&bdi->wb.wakeup_timer);
- if (!bdi_cap_flush_forker(bdi))
- bdi_wb_shutdown(bdi);
+ bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
spin_lock_bh(&bdi->wb_lock);
INIT_LIST_HEAD(&wb->b_io);
INIT_LIST_HEAD(&wb->b_more_io);
spin_lock_init(&wb->list_lock);
- setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+ INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
}
/*
bdi_unregister(bdi);
/*
- * If bdi_unregister() had already been called earlier, the
- * wakeup_timer could still be armed because bdi_prune_sb()
- * can race with the bdi_wakeup_thread_delayed() calls from
- * __mark_inode_dirty().
+ * If bdi_unregister() had already been called earlier, the dwork
+ * could still be pending because bdi_prune_sb() can race with the
+ * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
*/
- del_timer_sync(&bdi->wb.wakeup_timer);
+ cancel_delayed_work_sync(&bdi->wb.dwork);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
projects / platform / kernel / linux-arm64.git / commitdiff