static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
struct backing_dev_info default_backing_dev_info = {
.name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
- .unplug_io_fn = default_unplug_io_fn,
};
EXPORT_SYMBOL_GPL(default_backing_dev_info);
struct backing_dev_info noop_backing_dev_info = {
.name = "noop",
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static int bdi_sync_supers(void *);
static void sync_supers_timer_fn(unsigned long);
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+ if (wb1 < wb2) {
+ spin_lock(&wb1->list_lock);
+ spin_lock_nested(&wb2->list_lock, 1);
+ } else {
+ spin_lock(&wb2->list_lock);
+ spin_lock_nested(&wb1->list_lock, 1);
+ }
+}
+
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
- unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+ unsigned long nr_dirty, nr_io, nr_more_io;
struct inode *inode;
- nr_wb = nr_dirty = nr_io = nr_more_io = 0;
- spin_lock(&inode_lock);
- list_for_each_entry(inode, &wb->b_dirty, i_list)
+ nr_dirty = nr_io = nr_more_io = 0;
+ spin_lock(&wb->list_lock);
+ list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
nr_dirty++;
- list_for_each_entry(inode, &wb->b_io, i_list)
+ list_for_each_entry(inode, &wb->b_io, i_wb_list)
nr_io++;
- list_for_each_entry(inode, &wb->b_more_io, i_list)
+ list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
nr_more_io++;
- spin_unlock(&inode_lock);
+ spin_unlock(&wb->list_lock);
- get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
+ bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
#define K(x) ((x) << (PAGE_SHIFT - 10))
seq_printf(m,
- "BdiWriteback: %8lu kB\n"
- "BdiReclaimable: %8lu kB\n"
- "BdiDirtyThresh: %8lu kB\n"
- "DirtyThresh: %8lu kB\n"
- "BackgroundThresh: %8lu kB\n"
- "b_dirty: %8lu\n"
- "b_io: %8lu\n"
- "b_more_io: %8lu\n"
- "bdi_list: %8u\n"
- "state: %8lx\n",
+ "BdiWriteback: %10lu kB\n"
+ "BdiReclaimable: %10lu kB\n"
+ "BdiDirtyThresh: %10lu kB\n"
+ "DirtyThresh: %10lu kB\n"
+ "BackgroundThresh: %10lu kB\n"
+ "BdiWritten: %10lu kB\n"
+ "BdiWriteBandwidth: %10lu kBps\n"
+ "b_dirty: %10lu\n"
+ "b_io: %10lu\n"
+ "b_more_io: %10lu\n"
+ "bdi_list: %10u\n"
+ "state: %10lx\n",
(unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
(unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
- K(bdi_thresh), K(dirty_thresh),
- K(background_thresh), nr_dirty, nr_io, nr_more_io,
+ K(bdi_thresh),
+ K(dirty_thresh),
+ K(background_thresh),
+ (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+ (unsigned long) K(bdi->write_bandwidth),
+ nr_dirty,
+ nr_io,
+ nr_more_io,
!list_empty(&bdi->bdi_list), bdi->state);
#undef K
sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
BUG_ON(IS_ERR(sync_supers_tsk));
- init_timer(&sync_supers_timer);
setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
bdi_arm_supers_timer();
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
+ err = bdi_init(&noop_backing_dev_info);
return err;
}
subsys_initcall(default_bdi_init);
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
-{
- memset(wb, 0, sizeof(*wb));
-
- wb->bdi = bdi;
- wb->last_old_flush = jiffies;
- INIT_LIST_HEAD(&wb->b_dirty);
- INIT_LIST_HEAD(&wb->b_io);
- INIT_LIST_HEAD(&wb->b_more_io);
-}
-
int bdi_has_dirty_io(struct backing_dev_info *bdi)
{
return wb_has_dirty_io(&bdi->wb);
}
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .range_cyclic = 1,
- .nr_to_write = 1024,
- };
-
- writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
/*
* kupdated() used to do this. We cannot do it from the bdi_forker_thread()
* or we risk deadlocking on ->s_umount. The longer term solution would be
bdi_arm_supers_timer();
}
+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 {
+ /*
+ * 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
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+ 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_FLUSHER | PF_SWAPWRITE;
+ current->flags |= PF_SWAPWRITE;
set_freezable();
/*
set_user_nice(current, 0);
for (;;) {
- bool fork = false;
- struct task_struct *task;
+ 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))
+ 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);
- set_current_state(TASK_INTERRUPTIBLE);
-
/*
- * Check if any existing bdi's have dirty data without
- * a thread registered. If so, set that up.
+ * 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. So we have to set task
+ * state already here so that we don't miss wakeups coming
+ * after we verify some condition.
*/
+ set_current_state(TASK_INTERRUPTIBLE);
+
list_for_each_entry(bdi, &bdi_list, bdi_list) {
- if (!bdi_cap_writeback_dirty(bdi))
- continue;
- if (bdi->wb.task)
- continue;
- if (list_empty(&bdi->work_list) &&
- !bdi_has_dirty_io(bdi))
+ 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);
- fork = true;
+ have_dirty_io = !list_empty(&bdi->work_list) ||
+ wb_has_dirty_io(&bdi->wb);
/*
- * Set the pending bit - if someone will try to
- * unregister this bdi - it'll wait on this bit.
+ * If the bdi has work to do, but the thread does not
+ * exist - create it.
*/
- set_bit(BDI_pending, &bdi->state);
- break;
+ 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);
if (!list_empty(&me->bdi->work_list))
__set_current_state(TASK_RUNNING);
- if (!fork) {
- unsigned long wait;
+ 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);
+ } 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;
- wait = msecs_to_jiffies(dirty_writeback_interval * 10);
- if (wait)
- schedule_timeout(wait);
+ 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();
+ schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
try_to_freeze();
- continue;
+ break;
}
-
- __set_current_state(TASK_RUNNING);
-
- task = kthread_run(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.
- */
- bdi_flush_io(bdi);
- } else
- bdi->wb.task = task;
}
return 0;
list_del_rcu(&bdi->bdi_list);
spin_unlock_bh(&bdi_lock);
- synchronize_rcu();
+ synchronize_rcu_expedited();
}
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
va_list args;
- int ret = 0;
struct device *dev;
if (bdi->dev) /* The driver needs to use separate queues per device */
- goto exit;
+ return 0;
va_start(args, fmt);
dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
va_end(args);
- if (IS_ERR(dev)) {
- ret = PTR_ERR(dev);
- goto exit;
- }
-
- spin_lock_bh(&bdi_lock);
- list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
- spin_unlock_bh(&bdi_lock);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
bdi->dev = dev;
wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
dev_name(dev));
- if (IS_ERR(wb->task)) {
- wb->task = NULL;
- ret = -ENOMEM;
-
- bdi_remove_from_list(bdi);
- goto exit;
- }
+ if (IS_ERR(wb->task))
+ return PTR_ERR(wb->task);
}
bdi_debug_register(bdi, dev_name(dev));
set_bit(BDI_registered, &bdi->state);
+
+ spin_lock_bh(&bdi_lock);
+ list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
+
trace_writeback_bdi_register(bdi);
-exit:
- return ret;
+ return 0;
}
EXPORT_SYMBOL(bdi_register);
return;
/*
- * If setup is pending, wait for that to complete first
+ * Make sure nobody finds us on the bdi_list anymore
*/
- wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
- TASK_UNINTERRUPTIBLE);
+ bdi_remove_from_list(bdi);
/*
- * Make sure nobody finds us on the bdi_list anymore
+ * If setup is pending, wait for that to complete first
*/
- bdi_remove_from_list(bdi);
+ wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
/*
* Finally, kill the kernel thread. We don't need to be RCU
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (sb->s_bdi == bdi)
- sb->s_bdi = NULL;
+ sb->s_bdi = &default_backing_dev_info;
}
spin_unlock(&sb_lock);
}
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
+ 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);
}
EXPORT_SYMBOL(bdi_unregister);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ wb->last_old_flush = jiffies;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ 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);
+}
+
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW (100 << (20 - PAGE_SHIFT))
+
int bdi_init(struct backing_dev_info *bdi)
{
int i, err;
}
bdi->dirty_exceeded = 0;
+
+ bdi->bw_time_stamp = jiffies;
+ bdi->written_stamp = 0;
+
+ bdi->write_bandwidth = INIT_BW;
+ bdi->avg_write_bandwidth = INIT_BW;
+
err = prop_local_init_percpu(&bdi->completions);
if (err) {
if (bdi_has_dirty_io(bdi)) {
struct bdi_writeback *dst = &default_backing_dev_info.wb;
- spin_lock(&inode_lock);
+ bdi_lock_two(&bdi->wb, dst);
list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
list_splice(&bdi->wb.b_io, &dst->b_io);
list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
- spin_unlock(&inode_lock);
+ spin_unlock(&bdi->wb.list_lock);
+ spin_unlock(&dst->list_lock);
}
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().
+ */
+ del_timer_sync(&bdi->wb.wakeup_timer);
+
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
+static atomic_t nr_bdi_congested[2];
void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
{
wait_queue_head_t *wqh = &congestion_wqh[sync];
bit = sync ? BDI_sync_congested : BDI_async_congested;
- clear_bit(bit, &bdi->state);
+ if (test_and_clear_bit(bit, &bdi->state))
+ atomic_dec(&nr_bdi_congested[sync]);
smp_mb__after_clear_bit();
if (waitqueue_active(wqh))
wake_up(wqh);
enum bdi_state bit;
bit = sync ? BDI_sync_congested : BDI_async_congested;
- set_bit(bit, &bdi->state);
+ if (!test_and_set_bit(bit, &bdi->state))
+ atomic_inc(&nr_bdi_congested[sync]);
}
EXPORT_SYMBOL(set_bdi_congested);
long congestion_wait(int sync, long timeout)
{
long ret;
+ unsigned long start = jiffies;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[sync];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
+
+ trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
+ jiffies_to_usecs(jiffies - start));
+
return ret;
}
EXPORT_SYMBOL(congestion_wait);
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absence of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+ long ret;
+ unsigned long start = jiffies;
+ DEFINE_WAIT(wait);
+ wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+ /*
+ * If there is no congestion, or heavy congestion is not being
+ * encountered in the current zone, yield if necessary instead
+ * of sleeping on the congestion queue
+ */
+ if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+ !zone_is_reclaim_congested(zone)) {
+ cond_resched();
+
+ /* In case we scheduled, work out time remaining */
+ ret = timeout - (jiffies - start);
+ if (ret < 0)
+ ret = 0;
+
+ goto out;
+ }
+
+ /* Sleep until uncongested or a write happens */
+ prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+ ret = io_schedule_timeout(timeout);
+ finish_wait(wqh, &wait);
+
+out:
+ trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+ jiffies_to_usecs(jiffies - start));
+
+ return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);