summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-09-16 18:45:38 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2009-09-16 18:45:38 +0400
commita3eb51ecfa1d7be689f05c9f12cb0fcf862c516e (patch)
tree9995b3b9207c18a58ce99700f569b7bc2877e23c /mm
parentfdaa45e95d2ef59a140d2fb2e487141f83f5a07c (diff)
parent1ef7d9aa32a8ee054c4d4fdcd2ea537c04d61b2f (diff)
downloadlinux-a3eb51ecfa1d7be689f05c9f12cb0fcf862c516e.tar.xz
Merge branch 'writeback' of git://git.kernel.dk/linux-2.6-block
* 'writeback' of git://git.kernel.dk/linux-2.6-block: writeback: fix possible bdi writeback refcounting problem writeback: Fix bdi use after free in wb_work_complete() writeback: improve scalability of bdi writeback work queues writeback: remove smp_mb(), it's not needed with list_add_tail_rcu() writeback: use schedule_timeout_interruptible() writeback: add comments to bdi_work structure writeback: splice dirty inode entries to default bdi on bdi_destroy() writeback: separate starting of sync vs opportunistic writeback writeback: inline allocation failure handling in bdi_alloc_queue_work() writeback: use RCU to protect bdi_list writeback: only use bdi_writeback_all() for WB_SYNC_NONE writeout fs: Assign bdi in super_block writeback: make wb_writeback() take an argument structure writeback: merely wakeup flusher thread if work allocation fails for WB_SYNC_NONE writeback: get rid of wbc->for_writepages fs: remove bdev->bd_inode_backing_dev_info
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c90
-rw-r--r--mm/page-writeback.c22
2 files changed, 74 insertions, 38 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d3ca0dac1111..3d3accb1f800 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -26,6 +26,12 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
+
+/*
+ * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as
+ * reader side protection for bdi_pending_list. bdi_list has RCU reader side
+ * locking.
+ */
DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
LIST_HEAD(bdi_pending_list);
@@ -284,9 +290,9 @@ static int bdi_start_fn(void *ptr)
/*
* Add us to the active bdi_list
*/
- spin_lock(&bdi_lock);
- list_add(&bdi->bdi_list, &bdi_list);
- spin_unlock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
+ list_add_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
bdi_task_init(bdi, wb);
@@ -389,7 +395,7 @@ static int bdi_forker_task(void *ptr)
if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
wb_do_writeback(me, 0);
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
/*
* Check if any existing bdi's have dirty data without
@@ -410,7 +416,7 @@ static int bdi_forker_task(void *ptr)
if (list_empty(&bdi_pending_list)) {
unsigned long wait;
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
wait = msecs_to_jiffies(dirty_writeback_interval * 10);
schedule_timeout(wait);
try_to_freeze();
@@ -426,7 +432,7 @@ static int bdi_forker_task(void *ptr)
bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
bdi_list);
list_del_init(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
wb = &bdi->wb;
wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
@@ -445,9 +451,9 @@ static int bdi_forker_task(void *ptr)
* a chance to flush other bdi's to free
* memory.
*/
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
list_add_tail(&bdi->bdi_list, &bdi_pending_list);
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
bdi_flush_io(bdi);
}
@@ -456,6 +462,24 @@ static int bdi_forker_task(void *ptr)
return 0;
}
+static void bdi_add_to_pending(struct rcu_head *head)
+{
+ struct backing_dev_info *bdi;
+
+ bdi = container_of(head, struct backing_dev_info, rcu_head);
+ INIT_LIST_HEAD(&bdi->bdi_list);
+
+ spin_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ spin_unlock(&bdi_lock);
+
+ /*
+ * We are now on the pending list, wake up bdi_forker_task()
+ * to finish the job and add us back to the active bdi_list
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+}
+
/*
* Add the default flusher task that gets created for any bdi
* that has dirty data pending writeout
@@ -478,16 +502,29 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
* waiting for previous additions to finish.
*/
if (!test_and_set_bit(BDI_pending, &bdi->state)) {
- list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+ list_del_rcu(&bdi->bdi_list);
/*
- * We are now on the pending list, wake up bdi_forker_task()
- * to finish the job and add us back to the active bdi_list
+ * We must wait for the current RCU period to end before
+ * moving to the pending list. So schedule that operation
+ * from an RCU callback.
*/
- wake_up_process(default_backing_dev_info.wb.task);
+ call_rcu(&bdi->rcu_head, bdi_add_to_pending);
}
}
+/*
+ * Remove bdi from bdi_list, and ensure that it is no longer visible
+ */
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+ spin_lock_bh(&bdi_lock);
+ list_del_rcu(&bdi->bdi_list);
+ spin_unlock_bh(&bdi_lock);
+
+ synchronize_rcu();
+}
+
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
@@ -506,9 +543,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
- spin_lock(&bdi_lock);
- list_add_tail(&bdi->bdi_list, &bdi_list);
- spin_unlock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
+ list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
bdi->dev = dev;
@@ -526,9 +563,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
wb->task = NULL;
ret = -ENOMEM;
- spin_lock(&bdi_lock);
- list_del(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ bdi_remove_from_list(bdi);
goto exit;
}
}
@@ -565,9 +600,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
/*
* Make sure nobody finds us on the bdi_list anymore
*/
- spin_lock(&bdi_lock);
- list_del(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ bdi_remove_from_list(bdi);
/*
* Finally, kill the kernel threads. We don't need to be RCU
@@ -599,6 +632,7 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
spin_lock_init(&bdi->wb_lock);
+ INIT_RCU_HEAD(&bdi->rcu_head);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->wb_list);
INIT_LIST_HEAD(&bdi->work_list);
@@ -634,7 +668,19 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
- WARN_ON(bdi_has_dirty_io(bdi));
+ /*
+ * Splice our entries to the default_backing_dev_info, if this
+ * bdi disappears
+ */
+ if (bdi_has_dirty_io(bdi)) {
+ struct bdi_writeback *dst = &default_backing_dev_info.wb;
+
+ spin_lock(&inode_lock);
+ 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);
+ }
bdi_unregister(bdi);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index dd73d29c15a8..1eea4fa0d410 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -315,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -327,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
return ret;
}
@@ -339,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
if (max_ratio > 100)
return -EINVAL;
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
return ret;
}
@@ -582,16 +582,8 @@ static void balance_dirty_pages(struct address_space *mapping)
if ((laptop_mode && pages_written) ||
(!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS))
- > background_thresh))) {
- struct writeback_control wbc = {
- .bdi = bdi,
- .sync_mode = WB_SYNC_NONE,
- .nr_to_write = nr_writeback,
- };
-
-
- bdi_start_writeback(&wbc);
- }
+ > background_thresh)))
+ bdi_start_writeback(bdi, nr_writeback);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -1020,12 +1012,10 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
if (wbc->nr_to_write <= 0)
return 0;
- wbc->for_writepages = 1;
if (mapping->a_ops->writepages)
ret = mapping->a_ops->writepages(mapping, wbc);
else
ret = generic_writepages(mapping, wbc);
- wbc->for_writepages = 0;
return ret;
}