aboutsummaryrefslogtreecommitdiff
path: root/mm/backing-dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/backing-dev.c')
-rw-r--r--mm/backing-dev.c40
1 files changed, 25 insertions, 15 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 08b9aab631ab..8fe3ebd6ac00 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -115,6 +115,7 @@ static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
bdi, &bdi_debug_stats_fops);
if (!bdi->debug_stats) {
debugfs_remove(bdi->debug_dir);
+ bdi->debug_dir = NULL;
return -ENOMEM;
}
@@ -383,7 +384,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
* the barrier provided by test_and_clear_bit() above.
*/
smp_wmb();
- clear_bit(WB_shutting_down, &wb->state);
+ clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
@@ -411,6 +412,7 @@ static void wb_exit(struct bdi_writeback *wb)
* protected.
*/
static DEFINE_SPINLOCK(cgwb_lock);
+static struct workqueue_struct *cgwb_release_wq;
/**
* wb_congested_get_create - get or create a wb_congested
@@ -521,7 +523,7 @@ static void cgwb_release(struct percpu_ref *refcnt)
{
struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback,
refcnt);
- schedule_work(&wb->release_work);
+ queue_work(cgwb_release_wq, &wb->release_work);
}
static void cgwb_kill(struct bdi_writeback *wb)
@@ -783,6 +785,21 @@ static void cgwb_bdi_register(struct backing_dev_info *bdi)
spin_unlock_irq(&cgwb_lock);
}
+static int __init cgwb_init(void)
+{
+ /*
+ * There can be many concurrent release work items overwhelming
+ * system_wq. Put them in a separate wq and limit concurrency.
+ * There's no point in executing many of these in parallel.
+ */
+ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+ if (!cgwb_release_wq)
+ return -ENOMEM;
+
+ return 0;
+}
+subsys_initcall(cgwb_init);
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi)
@@ -1020,23 +1037,18 @@ EXPORT_SYMBOL(congestion_wait);
/**
* wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
- * @pgdat: A pgdat 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
- * @pgdat 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 pgdat congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the event of a congested backing_dev (any backing_dev) this waits
+ * for up to @timeout jiffies for either a BDI to exit congestion of the
+ * given @sync queue or a write to complete.
*
* 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 pglist_data *pgdat, int sync, long timeout)
+long wait_iff_congested(int sync, long timeout)
{
long ret;
unsigned long start = jiffies;
@@ -1044,12 +1056,10 @@ long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
wait_queue_head_t *wqh = &congestion_wqh[sync];
/*
- * If there is no congestion, or heavy congestion is not being
- * encountered in the current pgdat, yield if necessary instead
+ * If there is no congestion, yield if necessary instead
* of sleeping on the congestion queue
*/
- if (atomic_read(&nr_wb_congested[sync]) == 0 ||
- !test_bit(PGDAT_CONGESTED, &pgdat->flags)) {
+ if (atomic_read(&nr_wb_congested[sync]) == 0) {
cond_resched();
/* In case we scheduled, work out time remaining */