static void wb_min_max_ratio(struct bdi_writeback *wb,
unsigned long *minp, unsigned long *maxp)
{
- unsigned long this_bw = wb->avg_write_bandwidth;
+ unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
unsigned long long min = wb->bdi->min_ratio;
unsigned long long max = wb->bdi->max_ratio;
static void wb_position_ratio(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
- unsigned long write_bw = wb->avg_write_bandwidth;
+ unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
unsigned long wb_thresh = dtc->wb_thresh;
&wb->bdi->tot_write_bandwidth) <= 0);
}
wb->write_bandwidth = bw;
- wb->avg_write_bandwidth = avg;
+ WRITE_ONCE(wb->avg_write_bandwidth, avg);
}
static void update_dirty_limit(struct dirty_throttle_control *dtc)
dom->dirty_limit = limit;
}
-static void domain_update_bandwidth(struct dirty_throttle_control *dtc,
- unsigned long now)
+static void domain_update_dirty_limit(struct dirty_throttle_control *dtc,
+ unsigned long now)
{
struct wb_domain *dom = dtc_dom(dtc);
else
dirty_ratelimit -= step;
- wb->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+ WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL));
wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit);
{
struct bdi_writeback *wb = gdtc->wb;
unsigned long now = jiffies;
- unsigned long elapsed = now - wb->bw_time_stamp;
+ unsigned long elapsed;
unsigned long dirtied;
unsigned long written;
- lockdep_assert_held(&wb->list_lock);
+ spin_lock(&wb->list_lock);
/*
- * rate-limit, only update once every 200ms.
+ * Lockless checks for elapsed time are racy and delayed update after
+ * IO completion doesn't do it at all (to make sure written pages are
+ * accounted reasonably quickly). Make sure elapsed >= 1 to avoid
+ * division errors.
*/
- if (elapsed < BANDWIDTH_INTERVAL)
- return;
-
+ elapsed = max(now - wb->bw_time_stamp, 1UL);
dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
if (update_ratelimit) {
- domain_update_bandwidth(gdtc, now);
+ domain_update_dirty_limit(gdtc, now);
wb_update_dirty_ratelimit(gdtc, dirtied, elapsed);
/*
* compiler has no way to figure that out. Help it.
*/
if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {
- domain_update_bandwidth(mdtc, now);
+ domain_update_dirty_limit(mdtc, now);
wb_update_dirty_ratelimit(mdtc, dirtied, elapsed);
}
}
wb->dirtied_stamp = dirtied;
wb->written_stamp = written;
- wb->bw_time_stamp = now;
+ WRITE_ONCE(wb->bw_time_stamp, now);
+ spin_unlock(&wb->list_lock);
}
-static void wb_update_bandwidth(struct bdi_writeback *wb)
+void wb_update_bandwidth(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
- spin_lock(&wb->list_lock);
__wb_update_bandwidth(&gdtc, NULL, false);
- spin_unlock(&wb->list_lock);
}
/* Interval after which we consider wb idle and don't estimate bandwidth */
spin_lock(&wb->list_lock);
wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED);
wb->written_stamp = wb_stat(wb, WB_WRITTEN);
- wb->bw_time_stamp = now;
+ WRITE_ONCE(wb->bw_time_stamp, now);
spin_unlock(&wb->list_lock);
}
}
static unsigned long wb_max_pause(struct bdi_writeback *wb,
unsigned long wb_dirty)
{
- unsigned long bw = wb->avg_write_bandwidth;
+ unsigned long bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long t;
/*
unsigned long dirty_ratelimit,
int *nr_dirtied_pause)
{
- long hi = ilog2(wb->avg_write_bandwidth);
- long lo = ilog2(wb->dirty_ratelimit);
+ long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth));
+ long lo = ilog2(READ_ONCE(wb->dirty_ratelimit));
long t; /* target pause */
long pause; /* estimated next pause */
int pages; /* target nr_dirtied_pause */
if (dirty_exceeded && !wb->dirty_exceeded)
wb->dirty_exceeded = 1;
- if (time_is_before_jiffies(wb->bw_time_stamp +
- BANDWIDTH_INTERVAL)) {
- spin_lock(&wb->list_lock);
+ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+ BANDWIDTH_INTERVAL))
__wb_update_bandwidth(gdtc, mdtc, true);
- spin_unlock(&wb->list_lock);
- }
/* throttle according to the chosen dtc */
- dirty_ratelimit = wb->dirty_ratelimit;
+ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit);
task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >>
RATELIMIT_CALC_SHIFT;
max_pause = wb_max_pause(wb, sdtc->wb_dirty);
return ret;
}
-#ifdef CONFIG_BLOCK
void laptop_mode_timer_fn(struct timer_list *t)
{
struct backing_dev_info *backing_dev_info =
rcu_read_unlock();
}
-#endif
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
cond_resched();
congestion_wait(BLK_RW_ASYNC, HZ/50);
}
- wb_update_bandwidth(wb);
+ /*
+ * Usually few pages are written by now from those we've just submitted
+ * but if there's constant writeback being submitted, this makes sure
+ * writeback bandwidth is updated once in a while.
+ */
+ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+ BANDWIDTH_INTERVAL))
+ wb_update_bandwidth(wb);
return ret;
}
static void wb_inode_writeback_end(struct bdi_writeback *wb)
{
atomic_dec(&wb->writeback_inodes);
+ /*
+ * Make sure estimate of writeback throughput gets updated after
+ * writeback completed. We delay the update by BANDWIDTH_INTERVAL
+ * (which is the interval other bandwidth updates use for batching) so
+ * that if multiple inodes end writeback at a similar time, they get
+ * batched into one bandwidth update.
+ */
+ queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
}
int test_clear_page_writeback(struct page *page)